CN113267755A - Millimeter wave signal processing method and device, electronic equipment and readable storage medium - Google Patents
Millimeter wave signal processing method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN113267755A CN113267755A CN202010096830.4A CN202010096830A CN113267755A CN 113267755 A CN113267755 A CN 113267755A CN 202010096830 A CN202010096830 A CN 202010096830A CN 113267755 A CN113267755 A CN 113267755A
- Authority
- CN
- China
- Prior art keywords
- signal
- millimeter wave
- characteristic
- wave response
- response signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 35
- 230000004044 response Effects 0.000 claims abstract description 242
- 238000007499 fusion processing Methods 0.000 claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims abstract description 13
- 230000004927 fusion Effects 0.000 claims description 55
- 238000012545 processing Methods 0.000 claims description 38
- 238000013145 classification model Methods 0.000 claims description 17
- 230000005540 biological transmission Effects 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 12
- 238000002372 labelling Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000007613 environmental effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000000704 physical effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The application provides a millimeter wave signal processing method and device, an electronic device and a readable storage medium. The method comprises the following steps: acquiring at least two times of first millimeter wave response signals; determining a first characteristic signal corresponding to the first millimeter wave response signal every time to obtain at least two first characteristic signals; performing fusion processing according to the first characteristic signal at least twice to obtain a target millimeter wave response signal; and inputting the target millimeter wave response signal into an object recognition model to obtain an object recognition result, wherein the object recognition model is obtained according to the millimeter wave response signal and corresponding object marking training. The method can reduce cost.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a millimeter wave signal processing method and apparatus, an electronic device, and a computer-readable storage medium.
Background
The current common millimeter wave identification mode is to transmit a millimeter wave signal to an object, receive a millimeter wave response signal returned by the object, and process the millimeter wave response signal to achieve the purpose of identifying the object. In order to improve the accuracy of object identification, the conventional method usually increases the transmitting power of the millimeter wave detector. The traditional millimeter wave signal processing method has the problem of high cost.
Disclosure of Invention
The embodiment of the application provides a millimeter wave signal processing method and device, electronic equipment and a computer readable storage medium, and the cost can be reduced.
A millimeter wave signal processing method applied to an electronic device including a millimeter wave transceiver for transmitting a millimeter wave transmission signal and receiving a millimeter wave response signal generated in response to the millimeter wave transmission signal, the method comprising:
acquiring at least two times of first millimeter wave response signals;
determining a first characteristic signal corresponding to the first millimeter wave response signal every time to obtain at least two first characteristic signals;
performing fusion processing according to the first characteristic signal at least twice to obtain a target millimeter wave response signal;
and inputting the target millimeter wave response signal into an object recognition model to obtain an object recognition result, wherein the object recognition model is obtained according to the millimeter wave response signal and corresponding object marking training.
A millimeter wave signal processing apparatus applied to an electronic device including a millimeter wave transceiver for transmitting a millimeter wave transmission signal and receiving a millimeter wave response signal generated in response to the millimeter wave transmission signal, comprising:
the acquisition module is used for acquiring the first millimeter wave response signals at least twice;
the determining module is used for determining a first characteristic signal corresponding to the first millimeter wave response signal each time to obtain at least two first characteristic signals;
the fusion module is used for carrying out fusion processing according to the first characteristic signal at least twice to obtain a target millimeter wave response signal;
and the identification module is used for inputting the target millimeter wave response signal into an object identification model to obtain an object identification result, wherein the object identification model is obtained according to the millimeter wave response signal and corresponding object marking training.
An electronic device comprising a memory and a processor, the memory having stored therein a computer program that, when executed by the processor, causes the processor to perform the steps of:
acquiring at least two times of first millimeter wave response signals;
determining a first characteristic signal corresponding to the first millimeter wave response signal every time to obtain at least two first characteristic signals;
performing fusion processing according to the first characteristic signal at least twice to obtain a target millimeter wave response signal;
and inputting the target millimeter wave response signal into an object recognition model to obtain an object recognition result, wherein the object recognition model is obtained according to the millimeter wave response signal and corresponding object marking training.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring at least two times of first millimeter wave response signals;
determining a first characteristic signal corresponding to the first millimeter wave response signal every time to obtain at least two first characteristic signals;
performing fusion processing according to the first characteristic signal at least twice to obtain a target millimeter wave response signal;
and inputting the target millimeter wave response signal into an object recognition model to obtain an object recognition result, wherein the object recognition model is obtained according to the millimeter wave response signal and corresponding object marking training.
In the millimeter wave signal processing method, the millimeter wave signal processing device, the electronic device, and the computer-readable storage medium in this embodiment, the first millimeter wave response signal is obtained at least twice, the first characteristic signal corresponding to the first millimeter wave response signal is determined each time, the characteristic signals are obtained at least twice, and then fusion processing is performed, that is, the millimeter wave response signal is obtained many times, the characteristic signal can be enhanced without increasing power, and cost can be reduced, so that the target millimeter wave response signal can be obtained, the signal-to-noise ratio of the target millimeter wave signal can be improved, the target millimeter wave response signal is input to the object recognition model, an object recognition result is obtained, and accuracy of object recognition based on millimeter waves is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow diagram of a millimeter wave signal processing method in one embodiment;
FIG. 2 is a schematic diagram of millimeter wave signals in one embodiment;
FIG. 3 is a flowchart of a millimeter wave signal processing method in another embodiment;
fig. 4 is a block diagram showing the configuration of a millimeter wave signal processing apparatus in one embodiment;
fig. 5 is a schematic diagram of an internal structure of the electronic device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It will be understood that the terms "first," "second," and the like as used herein may be used herein to describe various data, but the data is not limited by these terms. These terms are only used to distinguish one datum from another. For example, the first millimeter wave response signal may be referred to as a second millimeter wave response signal, and similarly, the second millimeter wave response signal may be referred to as a first millimeter wave response signal, without departing from the scope of the present application. Both the first millimeter wave response signal and the second millimeter wave response signal are millimeter wave response signals, but they are not the same millimeter wave response signal.
Fig. 1 is a flowchart of a millimeter wave signal processing method in one embodiment. The millimeter wave signal processing method in this embodiment is described by taking an example of the millimeter wave signal processing method being executed on an electronic device. The electronic equipment comprises a millimeter wave transceiver. The electronic device may be any terminal device including a mobile phone, a tablet computer, a PDA (Personal Digital Assistant), a Point of Sales (POS), a vehicle-mounted computer, a wearable device, and the like. The millimeter wave is an electromagnetic wave with a wavelength of 1-10 mm. The millimeter wave can measure a more accurate distance, and the specific distance measurement precision of the millimeter wave can reach 5 millimeters. The millimeter wave transceiver has the function of transceiving millimeter wave signals, and can be used for transmitting millimeter wave transmitting signals and receiving millimeter wave response signals generated by a target object to the millimeter wave transmitting signals. And object identification can be carried out according to the millimeter wave response signal received by the millimeter wave transceiver. Or the electronic device may construct a millimeter wave image according to the millimeter wave response signal and perform object recognition. For the identification technology based on millimeter waves, it is necessary to accurately extract the characteristic signal of the identified object from the reflected signal, so as to accurately identify the object. That is, in the process of processing the millimeter wave signal, a response signal of a high signal-to-noise ratio is a precondition for being able to accurately identify an object. Therefore, improving the signal-to-noise ratio of the response signal becomes an important technical direction for improving the millimeter wave identification accuracy.
As shown in fig. 1, the millimeter wave signal processing method includes steps 102 to 108.
And 102, acquiring the first millimeter wave response signal at least twice.
The first millimeter wave response signal refers to a millimeter wave response signal received by the millimeter wave transceiver in one time.
Specifically, the electronic device receives the first millimeter wave response signal through the millimeter wave transceiver each time, and receives the first millimeter wave response signal at least twice in total.
In this embodiment, when the electronic device photographs a moving object, the electronic device may receive the millimeter wave response signal at least twice consecutively. For example, the millimeter wave response signal is received once every 1/30 seconds, the electronic device receives the first millimeter wave response signal once at 1/30 seconds, and receives the second first millimeter wave response signal once at 2/30 seconds.
In this embodiment, the electronic device may receive the millimeter wave response signal at least twice, and perform filtering processing on the millimeter wave response signal each time to obtain the first millimeter wave response signal at least twice. Or the electronic device may receive the millimeter wave response signal at least twice, and perform filtering processing and signal enhancement processing on the millimeter wave response signal each time to obtain a first millimeter wave response signal at least twice.
And 104, determining a first characteristic signal corresponding to the first millimeter wave response signal every time to obtain at least two first characteristic signals.
The characteristic signal may be a signal corresponding to a characteristic region where the object identifier can be identified. For example, an image obtained after the millimeter wave transceiver receives the first millimeter wave response signal includes a scene and an object, and then the first millimeter wave signal corresponding to the object is the first characteristic signal.
Specifically, the electronic device may determine a characteristic region each time the first millimeter wave response signal is received, and take the first millimeter wave response signal corresponding to the characteristic region as the first characteristic signal. Wherein the feature regions are uniform in size each time. The feature region at a time may refer to the same millimetric-wave image region in a very short time. For example, if the feature region is an upper left corner region of the millimeter wave image, the electron takes the first millimeter wave response signal located in the upper left corner region for the first time as the feature region, and takes the first millimeter wave response signal located in the upper left corner region for the second time as the feature region. Or a certain region around the object is defined as a characteristic region according to the variation of the object.
And step 106, performing fusion processing according to the first characteristic signals at least twice to obtain target millimeter wave response signals.
Specifically, the electronic device may perform fusion processing on the first characteristic signal at least two times according to a preset ratio to obtain a target millimeter wave response signal. For example, the proportion of the first-time first millimeter wave response signal is 30%, the proportion of the second-time first millimeter wave response signal is 70%, and the like are not limited thereto. Or, the electronic device averages the first characteristic signals at least twice to obtain the target millimeter wave response signal. Or the electronic equipment performs superposition processing on the first characteristic signals at least twice to obtain target millimeter wave response signals.
In this embodiment, the electronic device may perform filtering processing on the first characteristic signal at least twice, and then perform fusion processing to obtain a target millimeter wave response signal. Or, the electronic device may perform filtering processing and signal enhancement processing on the first characteristic signal at least twice, and then perform fusion processing to obtain the target millimeter wave response signal. The filtering process is to filter the environmental noise inherent in the environment. The environmental noise is, for example, a millimeter wave response signal of the background and the background object in the characteristic region corresponding to the first characteristic signal. Due to the difference of some characteristics of the background and the distance, material and the like of the background object, the reflected signal is weak or has some frequency differences, so that the environmental noise can be filtered.
Or, the electronic device may perform fusion processing on the first characteristic signals at least two times, and then perform filtering processing to obtain the target millimeter wave response signal. Or, the electronic device may perform fusion processing on the first characteristic signal at least twice, and then perform filtering processing and signal enhancement processing to obtain a target millimeter wave response signal.
In this embodiment, as shown in fig. 2, a schematic diagram of millimeter wave signals in one embodiment is shown. Including first characteristic signal 202, first characteristic signal 204, and target millimeter wave signal 206. The signal includes characteristic signal points 1, 2, 3 and 4. The electronic device performs fusion enhancement processing on the first characteristic signal 202 and the first characteristic signal 204, and filters noise to obtain a target millimeter wave signal 206.
And 108, inputting the target millimeter wave response signal into an object recognition model to obtain an object recognition result, wherein the object recognition model is obtained according to the millimeter wave response signal and the corresponding object label training.
The object identification result may be an object identifier, and specifically may be composed of at least one of a number, a character, and a symbol. For example, the object recognition result may be a person, a vehicle, a flower, a grass, or the like, but is not limited thereto. The object label is a correct label corresponding to the millimeter wave response signal. Object labeling may be used to adjust parameter values of the initial object recognition model when training.
Specifically, the electronic device may obtain an initial object recognition result by inputting the millimeter wave response signal into the initial object recognition model. The initial object recognition model can be trained according to a convolutional neural network. And the electronic equipment compares the initial object recognition result with the corresponding object label and adjusts the parameters of the initial object recognition model until the matching degree between the object recognition result and the corresponding object label reaches the preset matching degree, so as to obtain the object recognition model. And the electronic equipment inputs the target millimeter wave response signal into the object recognition model to obtain an object recognition result.
In this embodiment, the electronic device may input the millimeter wave image generated by the millimeter wave response signal into the object recognition model to obtain the object recognition result.
The millimeter wave signal processing method in the embodiment obtains the first millimeter wave response signal at least twice, determines the first characteristic signal corresponding to the first millimeter wave response signal each time, obtains the characteristic signal at least twice, and performs fusion processing, that is, obtains the millimeter wave response signal many times, can enhance the characteristic signal without increasing power, can reduce cost, and overcomes the defect of signal restriction, thereby obtaining the target millimeter wave response signal, can improve the signal-to-noise ratio of the target millimeter wave signal, inputs the target millimeter wave response signal into the object recognition model, obtains the object recognition result, is applicable to a recognition scene with a complex environment, and further improves the accuracy of object recognition based on millimeter waves.
In one embodiment, determining the first characteristic signal corresponding to each time of the first millimeter wave response signal to obtain at least two first characteristic signals includes: determining a focusing area when the first millimeter wave response signal is received at least twice each time; and taking the first millimeter wave response signal corresponding to each focusing area as a first characteristic signal to obtain at least two first characteristic signals.
Specifically, each time the electronic device receives the first millimeter wave response signal through the millimeter wave transceiver, the focusing area is determined each time. The electronic device can acquire the input focusing area, or determine the focusing area each time through the subject recognition model, or acquire a preset object area. The electronic equipment takes the first millimeter wave response signal corresponding to the focusing area as a first characteristic signal to obtain at least two first characteristic signals.
In the millimeter wave signal processing method in this embodiment, the focusing region in each first millimeter wave response signal in at least two times is determined, and since the focusing region is often a region including an object, the first millimeter wave response signal corresponding to each focusing region is used as the first characteristic signal, so that the computation amount of the electronic device can be reduced, and the accuracy of object identification based on millimeter waves can be improved.
In one embodiment, determining the in-focus region each time the first millimeter wave response signal is received at least twice includes: and tracking the detected object by adopting a target tracking algorithm when receiving the first millimeter wave response signal every time to obtain at least two focusing areas.
The target tracking algorithm may be a TLD (tracking learning detection) algorithm, a minimum output sum of squared error MOSSE (minimum mean square error) filtering algorithm, a struck algorithm, or the like, but is not limited thereto.
In particular, since the moving range of the object is not too large whether the object is stationary or moving within a certain time, the electronic device may track the detected object using a target tracking algorithm. Then, when the electronic device detects a moving object through the millimeter wave transceiver and continuously receives the first millimeter wave response signal, the electronic device tracks the detected object by using a target tracking algorithm to obtain at least two focusing areas.
In the millimeter wave signal processing method in this embodiment, when the first millimeter wave response signal is received each time, the target tracking algorithm is used to track the detected object, so as to obtain at least two focusing areas, which can reduce the time for obtaining the focusing areas and improve the efficiency of object identification.
In one embodiment, determining the first characteristic signal corresponding to each time of the first millimeter wave response signal to obtain at least two first characteristic signals includes: and respectively inputting the at least two first millimeter wave response signals into a millimeter wave signal classification model to obtain corresponding at least two first characteristic signals, wherein the millimeter wave signal classification model is formed by labeling and training the millimeter wave response signals and the corresponding characteristic signals.
Wherein the millimeter wave signal classification model may be used to determine the characteristic signal. The electronic device may obtain the initial characteristic signal by inputting the millimeter wave response signal into the initial millimeter wave signal classification model. The initial millimeter wave signal classification model can be trained according to a convolutional neural network. And the electronic equipment compares the millimeter wave signal classification result with the corresponding characteristic signal, adjusts the parameters of the initial millimeter wave signal classification model, and obtains the millimeter wave signal classification model until the matching degree between the initial characteristic signal and the corresponding characteristic signal label reaches a matching degree threshold value. The electronic equipment inputs the first millimeter wave response signal into the millimeter wave signal classification model every time to obtain a corresponding first characteristic signal.
In the millimeter wave signal processing method in this embodiment, because the physical properties of the objects are different, the obtained characteristic signals may be used to represent a certain class of objects, the at least two times of first millimeter wave response signals are respectively input into the millimeter wave signal classification model to obtain the corresponding at least two times of first characteristic signals, and the millimeter wave signal classification model is trained according to the millimeter wave response signals and the corresponding characteristic signals, so that the characteristic signals can be more accurately obtained, and the accuracy of object identification based on millimeter waves is improved.
In one embodiment, each target pixel point corresponds to a first characteristic signal. Performing fusion processing according to the first characteristic signal at least twice to obtain a target millimeter wave response signal, including: acquiring signal intensity corresponding to each target pixel point in at least two times, wherein the signal intensity corresponds to the first characteristic signal; and for each target pixel point, performing fusion processing on the first characteristic signals of which the signal intensity is smaller than the signal intensity threshold value every time to obtain target millimeter wave response signals.
The signal strength threshold refers to an upper limit value of the signal strength. A signal strength threshold value below which the first characteristic signal is less pronounced is an indication that the first characteristic signal is not pronounced. The fusion processing may refer to fusing the first feature signals smaller than the signal intensity threshold of the same target pixel point, so as to achieve the effect of enhancing the signal. Or, overlapping the first characteristic signals smaller than the signal intensity threshold of the same target pixel point.
Specifically, each pixel point corresponds to one first millimeter wave response signal. And the pixel points capable of receiving the first characteristic signal are called target pixel points. That is, each target pixel point corresponds to one first characteristic signal. After the first characteristic signal is determined at each time in at least two times, the electronic equipment acquires the signal intensity of the first characteristic signal of each target pixel point at each time. For each target pixel point, the electronic equipment superposes the first characteristic signals of which the signal intensity is smaller than the signal intensity threshold value each time; the electronic equipment splices the first characteristic signal with the signal intensity being greater than or equal to the maximum signal intensity in the signal intensity threshold value at a certain time to obtain a target millimeter wave response signal.
For example, the target pixel points corresponding to the first characteristic signal for the first time are a to Z, and the target pixel points corresponding to the first characteristic signal for the second time are also a to Z, so that the electronic device obtains the signal intensity of the first characteristic signal of each target pixel point in a to Z corresponding to the first time, and the signal intensity of the first characteristic of each target pixel point in a to Z corresponding to the second time. The signal intensity of the point A at the first time and the signal intensity of the point Z at the second time are both smaller than the signal intensity threshold value, and the signal intensity of the point Z at the first time and the signal intensity of the point Z at the second time are both smaller than the signal intensity threshold value, then the first characteristic signals of the point A at the first time and the second time are subjected to superposition processing, and the first characteristic signals of the point Z at the first time and the second time are subjected to superposition processing; and the remaining points B to Y are not satisfied with the condition that the signal intensity is smaller than the signal intensity threshold value every time, and then the first characteristic signal corresponding to the maximum signal intensity in every time is taken, so that the target millimeter wave response signal is obtained.
In the millimeter wave signal processing method in this embodiment, the signal intensity corresponding to each target pixel point in each of at least two times is obtained, and the signal intensity is the signal intensity corresponding to the first characteristic signal; for each target pixel point, the first characteristic signals with signal strength smaller than the signal strength threshold value at each time are subjected to fusion enhancement processing to obtain target millimeter wave response signals, the characteristic signals with weak signal strength can be enhanced without increasing power, the signal-to-noise ratio of the characteristic signals is improved, and therefore accuracy of object identification based on millimeter waves is improved.
In one embodiment, the millimeter wave signal processing method further includes: determining the signal-to-noise ratio of the target millimeter wave response signal; and when the signal-to-noise ratio of the target millimeter wave response signal reaches a preset signal-to-noise ratio, executing the step of inputting the target millimeter wave response signal into the object recognition model.
Where signal-to-noise ratio refers to the ratio of signal to noise. The larger the signal-to-noise ratio, the better the quality of the signal; the smaller the signal-to-noise ratio, the worse the quality of the signal. The predetermined signal-to-noise ratio is a signal-to-noise ratio threshold stored in the electronic device.
Specifically, the electronic device determines a signal-to-noise ratio of the target millimeter wave response signal. When the signal-to-noise ratio of the target millimeter wave reaches the preset signal-to-noise ratio, the quality of the target millimeter wave signal meets the requirement, and the electronic equipment inputs the target millimeter wave response signal into the object recognition model to obtain an object recognition result.
In the millimeter wave signal processing method in this embodiment, the signal-to-noise ratio of the target millimeter wave response signal is determined, and when the signal-to-noise ratio of the target millimeter wave response signal reaches the preset signal-to-noise ratio, the step of inputting the target millimeter wave response signal into the object recognition model is performed, that is, the millimeter wave signal with better signal quality is input into the object recognition model, so that the accuracy of object recognition based on millimeter waves is improved.
In one embodiment, the millimeter wave signal processing method further includes: when the signal-to-noise ratio of the target millimeter wave response signal does not reach a preset signal-to-noise ratio, acquiring a second millimeter wave response signal; determining a second characteristic signal corresponding to the second millimeter wave response signal; fusing the target millimeter wave response signal and the second characteristic signal to obtain a millimeter wave fusion signal; and when the signal-to-noise ratio of the millimeter wave fusion signal meets the preset signal-to-noise ratio, inputting the millimeter wave fusion signal into the object recognition model to obtain an object recognition result.
And acquiring the second millimeter wave response signal after acquiring the first millimeter wave response signal. The frequency corresponding to the second millimeter wave response signal may not be the same as the frequency of the first millimeter wave signal. The second characteristic signal refers to a characteristic signal in the second millimeter wave response signal.
Specifically, after the signal-to-noise ratio of the target millimeter wave response signal is determined, when the signal-to-noise ratio of the target millimeter wave response signal is smaller than a preset signal-to-noise ratio, a second millimeter wave response signal is acquired. The electronic device can determine a focusing area when the second millimeter wave response signal is acquired, and take the second millimeter wave response signal corresponding to the focusing area as the second characteristic signal. The electronic device may track the detected object to determine a focus area. Or the electronic device may input the second millimeter wave response signal into the millimeter wave signal classification model to obtain the second characteristic signal. And the electronic equipment performs fusion processing on the target millimeter wave response signal and the second characteristic signal to obtain a millimeter wave fusion signal. And inputting the millimeter wave fusion signal into the object recognition model until the signal-to-noise ratio of the millimeter wave fusion signal meets the preset signal-to-noise ratio, and obtaining an object recognition result.
In the millimeter wave signal processing method in this embodiment, when the signal-to-noise ratio of the target millimeter wave response signal is smaller than the preset signal-to-noise ratio, the second millimeter wave response signal is obtained, that is, when the quality of the target millimeter wave signal does not meet the requirement, the millimeter wave response signal is obtained again and fusion processing is performed, so that the number of times of signal fusion can be dynamically adjusted according to the result of fusion, multiple times of fusion may be performed on a reflection signal with a complex environment to obtain a high signal-to-noise ratio fused millimeter wave signal, and until the millimeter wave fusion signal meets the preset signal-to-noise ratio, the millimeter wave fusion signal is input into the object recognition model to obtain the object recognition result, which can improve the accuracy of object recognition based.
In one embodiment, as shown in fig. 3, a schematic flow chart of a millimeter wave signal processing method in another embodiment includes:
And step 304, transmitting the millimeter wave transmission signal at least twice.
And 310, performing fusion processing according to the first characteristic signals at least twice to obtain target millimeter wave response signals.
And step 314, inputting the millimeter wave fusion signal into the object recognition model when the preset signal-to-noise ratio is reached, and obtaining an object recognition result.
And step 316, acquiring a second millimeter wave response signal when the preset signal-to-noise ratio is not satisfied.
And 318, fusing the target millimeter wave response signal and the second characteristic signal to obtain a millimeter wave fusion signal.
And 322, inputting the millimeter wave fusion signal into the object recognition model to obtain an object recognition result when the signal-to-noise ratio of the millimeter wave fusion signal meets a preset signal-to-noise ratio. And when the signal-to-noise ratio of the millimeter wave fusion signal does not meet the preset signal-to-noise ratio, re-executing the step 316.
In the millimeter wave signal processing method in this embodiment, when the signal-to-noise ratio of the target millimeter wave response signal is greater than the preset signal-to-noise ratio, an object recognition result is obtained by inputting the millimeter wave response signal into the object recognition model, and when the signal-to-noise ratio of the target millimeter wave response signal is less than the preset signal-to-noise ratio, a second millimeter wave response signal is obtained, that is, when the quality of the target millimeter wave signal does not meet the requirement, the millimeter wave response signal is obtained again and fusion processing is performed, until the millimeter wave fusion signal meets the preset signal-to-noise ratio, the millimeter wave fusion signal is input into the object recognition model, so that the object recognition result is obtained, and the accuracy of object recognition based on millimeter waves can be improved.
In one embodiment, the fusing the target millimeter wave response signal and the second characteristic signal to obtain a millimeter wave fused signal includes: determining at least two millimeter wave characteristic signals from the second characteristic signal and the first characteristic signal for at least two times according to the signal-to-noise ratio from large to small; and fusing the determined at least two millimeter wave characteristic signals to obtain a millimeter wave fusion signal.
Specifically, the electronic device determines at least two millimeter wave characteristic signals from the second characteristic signal and the first characteristic signal at least twice according to the signal-to-noise ratio from large to small. And the electronic equipment fuses the determined at least two millimeter wave characteristic signals to obtain millimeter wave fusion signals. For example, the first characteristic signal is a and b, the second characteristic signal is c, and the signal-to-noise ratio is c > b > a, then the electronic device may select c and b to perform fusion to obtain the millimeter wave fusion signal.
According to the millimeter wave signal processing method in the embodiment, at least two millimeter wave characteristic signals are determined according to the signal-to-noise ratio from large to small, and then the millimeter wave characteristic signals are fused to obtain a millimeter wave fusion signal, so that object recognition can be performed according to the millimeter wave signal with higher quality, and the accuracy of object recognition based on millimeter waves can be improved.
In one embodiment, a millimeter wave signal processing method is applied to an electronic device, the electronic device including a millimeter wave transceiver for transmitting a millimeter wave transmission signal and receiving a millimeter wave response signal generated from the millimeter wave transmission signal, and the method includes:
and (a1) acquiring the first millimeter wave response signal at least twice.
And (a2) tracking the detected object by adopting a target tracking algorithm to obtain at least two focusing areas when receiving the first millimeter wave response signal every time.
And (a3) taking the first millimeter wave response signal corresponding to each focusing area as a first characteristic signal to obtain at least two first characteristic signals.
And (a4) acquiring a signal intensity corresponding to each target pixel point in each of at least two times, wherein the signal intensity corresponds to the first characteristic signal.
And (a5) for each target pixel point, performing fusion enhancement processing on the first characteristic signals of which the signal intensity is smaller than the signal intensity threshold value every time to obtain target millimeter wave response signals.
And (a6) inputting the target millimeter wave response signal into an object recognition model to obtain an object recognition result, wherein the object recognition model is obtained by training according to the millimeter wave response signal and a corresponding object label.
Step (a7), determine the signal-to-noise ratio of the target millimeter wave response signal.
And (a8) when the signal-to-noise ratio of the target millimeter wave response signal reaches a preset signal-to-noise ratio, performing the step of inputting the target millimeter wave response signal into the object recognition model.
And (a9) acquiring a second millimeter wave response signal when the signal-to-noise ratio of the target millimeter wave response signal does not reach a preset signal-to-noise ratio.
And (a10) determining a second characteristic signal corresponding to the second millimeter wave response signal.
And (a11) determining at least two millimeter wave characteristic signals from the second characteristic signal and the first characteristic signal at least twice according to the signal-to-noise ratio from large to small.
And (a12) fusing the determined at least two millimeter wave characteristic signals to obtain a millimeter wave fusion signal.
And (a13) when the signal-to-noise ratio of the millimeter wave fusion signal meets the preset signal-to-noise ratio, inputting the millimeter wave fusion signal into the object recognition model to obtain an object recognition result.
In the millimeter wave signal processing method in the embodiment, the first millimeter wave response signal is obtained at least twice, the first characteristic signal corresponding to the first millimeter wave response signal is determined each time, the characteristic signal is obtained at least twice, and then fusion processing is performed, that is, the millimeter wave response signal is obtained many times, the characteristic signal can be enhanced without increasing power, and the defect of signal restriction can be overcome, so that the target millimeter wave response signal is obtained, the signal-to-noise ratio of the target millimeter wave signal can be improved, the target millimeter wave response signal is input into the object recognition model, the object recognition result is obtained, and the method is applicable to recognition scenes with complex environments; when the signal-to-noise ratio of the target millimeter wave response signal is greater than the preset signal-to-noise ratio, the target millimeter wave response signal is input into the object recognition model to obtain an object recognition result, when the signal-to-noise ratio of the target millimeter wave response signal is less than the preset signal-to-noise ratio, a second millimeter wave response signal is obtained, namely when the quality of the target millimeter wave signal cannot meet the requirement, the millimeter wave response signal is obtained again and fusion processing is carried out, and the millimeter wave fusion signal is input into the object recognition model until the millimeter wave fusion signal meets the preset signal-to-noise ratio to obtain the object recognition result, so that the accuracy of object recognition based on millimeter waves can be improved.
It should be understood that although the various steps in the flowcharts of fig. 1 and 3 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1 and 3 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.
Fig. 4 is a block diagram of a millimeter wave signal processing apparatus according to an embodiment. A millimeter wave signal processing apparatus comprising an obtaining module 402, a determining module 404, a fusing module 406, and an identifying module 408, wherein:
an obtaining module 402, configured to obtain at least two first millimeter wave response signals;
a determining module 404, configured to determine a first characteristic signal corresponding to the first millimeter wave response signal each time, so as to obtain at least two first characteristic signals;
the fusion module 406 is configured to perform fusion processing according to the first characteristic signal at least two times to obtain a target millimeter wave response signal;
the recognition module 408 is configured to input the target millimeter wave response signal into an object recognition model to obtain an object recognition result, where the object recognition model is obtained according to the millimeter wave response signal and a corresponding object label training.
The millimeter wave signal processing device in this embodiment determines the first characteristic signal corresponding to the first millimeter wave response signal each time by obtaining the first millimeter wave response signal at least twice, obtains the characteristic signal at least twice, and performs fusion processing, that is, obtains the millimeter wave response signal many times, can enhance the characteristic signal without increasing power, can reduce cost, and overcomes the disadvantage of signal restriction, thereby obtaining the target millimeter wave response signal, and can improve the signal-to-noise ratio of the target millimeter wave signal.
In one embodiment, the determining module 404 is configured to determine a focusing area each time the first millimeter wave response signal is received at least twice; and taking the first millimeter wave response signal corresponding to each focusing area as a first characteristic signal to obtain at least two first characteristic signals.
In the millimeter wave signal processing apparatus in this embodiment, the focusing region in each time of the first millimeter wave response signal in at least two times is determined, and since the focusing region is often a region including an object, the first millimeter wave response signal corresponding to each focusing region is used as the first characteristic signal, so that the computation amount of the electronic device can be reduced, and the accuracy of object identification based on millimeter waves can also be improved.
In one embodiment, the determining module 404 is configured to track the detected object by using a target tracking algorithm to obtain at least two focusing areas each time the first millimeter wave response signal is received.
In the millimeter wave signal processing device in this embodiment, when receiving the first millimeter wave response signal each time, the target tracking algorithm is used to track the detected object, so as to obtain at least two focusing areas, which can reduce the time for obtaining the focusing areas and improve the efficiency of object identification.
In an embodiment, the determining module 404 is configured to input the at least two first millimeter wave response signals into a millimeter wave signal classification model respectively to obtain corresponding at least two first feature signals, where the millimeter wave signal classification model is trained according to the millimeter wave response signals and corresponding feature signal labels.
In the millimeter wave signal processing device in this embodiment, because the physical properties of the objects are different, the obtained characteristic signals may be used to represent a certain class of objects, the at least two times of first millimeter wave response signals are respectively input into the millimeter wave signal classification model to obtain the corresponding at least two times of first characteristic signals, and the millimeter wave signal classification model is trained according to the millimeter wave response signals and the corresponding characteristic signals, so that the characteristic signals can be obtained more accurately, and the accuracy of object identification based on millimeter waves is improved.
In one embodiment, each target pixel point corresponds to a first characteristic signal. The fusion module 406 is configured to obtain a signal intensity corresponding to each target pixel point in at least two times, where the signal intensity corresponds to the first feature signal; and for each target pixel point, performing fusion enhancement processing on the first characteristic signals of which the signal intensity is smaller than the signal intensity threshold value every time to obtain target millimeter wave response signals.
The millimeter wave signal processing device in this embodiment obtains a signal intensity corresponding to each target pixel point in at least two times, where the signal intensity is a signal intensity corresponding to the first characteristic signal; for each target pixel point, the first characteristic signals with signal strength smaller than the signal strength threshold value at each time are subjected to fusion enhancement processing to obtain target millimeter wave response signals, the characteristic signals with weak signal strength can be enhanced without increasing power, the signal-to-noise ratio of the characteristic signals is improved, and therefore accuracy of object identification based on millimeter waves is improved.
In one embodiment, the determining module 404 is further configured to determine a signal-to-noise ratio of the target millimeter wave response signal; when the signal-to-noise ratio of the target millimeter wave response signal reaches the preset signal-to-noise ratio, the recognition module 408 is configured to input the target millimeter wave response signal into the object recognition model.
The millimeter wave signal processing device in this embodiment determines the signal-to-noise ratio of the target millimeter wave response signal, and when the signal-to-noise ratio of the target millimeter wave response signal reaches a preset signal-to-noise ratio, executes the step of inputting the target millimeter wave response signal into the object recognition model, that is, the millimeter wave signal with better signal quality is input into the object recognition model, so that the accuracy of object recognition based on millimeter waves is improved.
In an embodiment, the obtaining module 402 is further configured to obtain a second millimeter wave response signal when the signal-to-noise ratio of the target millimeter wave response signal does not reach the preset signal-to-noise ratio. The determining module 404 is further configured to determine a second characteristic signal corresponding to the second millimeter wave response signal. The fusion module 406 is further configured to perform fusion processing on the target millimeter wave response signal and the second characteristic signal to obtain a millimeter wave fusion signal. The recognition module 408 is further configured to input the millimeter wave fusion signal into the object recognition model when the signal-to-noise ratio of the millimeter wave fusion signal satisfies the preset signal-to-noise ratio, so as to obtain an object recognition result.
In the millimeter wave signal processing apparatus in this embodiment, when the signal-to-noise ratio of the target millimeter wave response signal is smaller than the preset signal-to-noise ratio, the second millimeter wave response signal is obtained, that is, when the quality of the target millimeter wave signal does not meet the requirement, the millimeter wave response signal is obtained again and fusion processing is performed, so that the number of times of signal fusion can be dynamically adjusted according to the result of fusion, multiple times of fusion may be performed on a reflection signal with a complex environment to obtain a fused millimeter wave signal with a high signal-to-noise ratio, and until the millimeter wave fusion signal meets the preset signal-to-noise ratio, the millimeter wave fusion signal is input into the object recognition model to obtain the object recognition result, which can improve the accuracy of object recognition based on millimeter waves.
In one embodiment, the fusion module 406 is further configured to determine at least two millimeter wave characteristic signals from the second characteristic signal and the at least two first characteristic signals according to the signal-to-noise ratio from large to small; and fusing the determined at least two millimeter wave characteristic signals to obtain a millimeter wave fusion signal.
The millimeter wave signal processing device in the embodiment determines at least two millimeter wave characteristic signals according to the signal-to-noise ratio from large to small, and then performs fusion to obtain a millimeter wave fusion signal, so that object recognition can be performed according to a millimeter wave signal with higher quality, and the accuracy of object recognition based on millimeter waves can be improved.
The division of each module in the millimeter wave signal processing apparatus is only for illustration, and in other embodiments, the millimeter wave signal processing apparatus may be divided into different modules as needed to complete all or part of the functions of the millimeter wave signal processing apparatus.
For the specific definition of the millimeter wave signal processing device, reference may be made to the above definition of the millimeter wave signal processing method, which is not described herein again. All or part of each module in the millimeter wave signal processing device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Fig. 5 is a schematic diagram of an internal structure of the electronic device in one embodiment. As shown in fig. 5, the electronic device includes a processor and a memory connected by a system bus. Wherein, the processor is used for providing calculation and control capability and supporting the operation of the whole electronic equipment. The memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The computer program may be executed by a processor to implement a millimeter wave signal processing method provided in each of the following embodiments. The internal memory provides a cached execution environment for the operating system computer programs in the non-volatile storage medium. The electronic device may be a mobile phone, a tablet computer, or a personal digital assistant or a wearable device, etc. In an embodiment of the present application, the electronic device includes a processor that implements the steps of the millimeter wave signal processing method when executing a computer program stored on a memory.
The implementation of each module in the millimeter wave signal processing apparatus provided in the embodiment of the present application may be in the form of a computer program. The computer program may be run on a terminal or a server. The program modules constituted by the computer program may be stored on the memory of the terminal or the server. Which when executed by a processor, performs the steps of the method described in the embodiments of the present application.
The embodiment of the application also provides a computer readable storage medium. One or more non-transitory computer-readable storage media containing computer-executable instructions that, when executed by one or more processors, cause the processors to perform the steps of the millimeter wave signal processing method.
A computer program product containing instructions which, when run on a computer, cause the computer to perform a millimeter wave signal processing method.
Any reference to memory, storage, database, or other medium used herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM), which acts as external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (11)
1. A millimeter wave signal processing method applied to an electronic device including a millimeter wave transceiver for transmitting a millimeter wave transmission signal and receiving a millimeter wave response signal generated in response to the millimeter wave transmission signal, the method comprising:
acquiring at least two times of first millimeter wave response signals;
determining a first characteristic signal corresponding to the first millimeter wave response signal every time to obtain at least two first characteristic signals;
performing fusion processing according to the first characteristic signal at least twice to obtain a target millimeter wave response signal;
and inputting the target millimeter wave response signal into an object recognition model to obtain an object recognition result, wherein the object recognition model is obtained according to the millimeter wave response signal and corresponding object marking training.
2. The method of claim 1, wherein said determining the first characteristic signal corresponding to each time of the first millimeter wave response signal to obtain at least two first characteristic signals comprises:
determining a focusing area for each time of receiving the first millimeter wave response signal in the at least two times;
and taking the first millimeter wave response signal corresponding to each focusing area as a first characteristic signal to obtain at least two first characteristic signals.
3. The method of claim 2, wherein said determining the in-focus region for each of said at least two times said first millimeter wave response signal is received comprises:
and tracking the detected object by adopting a target tracking algorithm when receiving the first millimeter wave response signal every time to obtain at least two focusing areas.
4. The method of claim 1, wherein said determining the first characteristic signal corresponding to each time of the first millimeter wave response signal to obtain at least two first characteristic signals comprises:
and respectively inputting the first millimeter wave response signals at least twice into a millimeter wave signal classification model to obtain corresponding first characteristic signals at least twice, wherein the millimeter wave signal classification model is formed by labeling and training the millimeter wave response signals and the corresponding characteristic signals.
5. The method according to any one of claims 1 to 4, wherein each target pixel point corresponds to a first characteristic signal;
the obtaining of the target millimeter wave response signal by performing fusion processing according to the first characteristic signal at least twice includes:
acquiring the signal intensity corresponding to each target pixel point in each of the at least two times, wherein the signal intensity corresponds to the first characteristic signal;
and for each target pixel point, performing fusion processing on the first characteristic signals of which the signal intensity is smaller than the signal intensity threshold value every time to obtain target millimeter wave response signals.
6. The method according to any one of claims 1 to 4, further comprising:
determining the signal-to-noise ratio of the target millimeter wave response signal;
and when the signal-to-noise ratio of the target millimeter wave response signal reaches a preset signal-to-noise ratio, executing the step of inputting the target millimeter wave response signal into an object recognition model.
7. The method of claim 6, further comprising:
when the signal-to-noise ratio of the target millimeter wave response signal does not reach the preset signal-to-noise ratio, acquiring a second millimeter wave response signal;
determining a second characteristic signal corresponding to the second millimeter wave response signal;
fusing the target millimeter wave response signal and the second characteristic signal to obtain a millimeter wave fusion signal;
and when the signal-to-noise ratio of the millimeter wave fusion signal meets the preset signal-to-noise ratio, inputting the millimeter wave fusion signal into the object recognition model to obtain an object recognition result.
8. The method according to claim 7, wherein the fusing the target millimeter wave response signal and the second characteristic signal to obtain a millimeter wave fused signal comprises:
determining at least two millimeter wave characteristic signals from the second characteristic signal and the first characteristic signal at least twice according to the signal-to-noise ratio from large to small;
and fusing the determined at least two millimeter wave characteristic signals to obtain a millimeter wave fusion signal.
9. A millimeter wave signal processing apparatus, applied to an electronic device including a millimeter wave transceiver for transmitting a millimeter wave transmission signal and receiving a millimeter wave response signal generated in response to the millimeter wave transmission signal, comprising:
the acquisition module is used for acquiring the first millimeter wave response signals at least twice;
the determining module is used for determining a first characteristic signal corresponding to the first millimeter wave response signal each time to obtain at least two first characteristic signals;
the fusion module is used for carrying out fusion processing according to the first characteristic signal at least twice to obtain a target millimeter wave response signal;
and the identification module is used for inputting the target millimeter wave response signal into an object identification model to obtain an object identification result, wherein the object identification model is obtained according to the millimeter wave response signal and corresponding object marking training.
10. An electronic device comprising a memory and a processor, the memory having stored therein a computer program that, when executed by the processor, causes the processor to perform the steps of the millimeter wave signal processing method according to any one of claims 1 to 8.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010096830.4A CN113267755A (en) | 2020-02-14 | 2020-02-14 | Millimeter wave signal processing method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010096830.4A CN113267755A (en) | 2020-02-14 | 2020-02-14 | Millimeter wave signal processing method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113267755A true CN113267755A (en) | 2021-08-17 |
Family
ID=77227455
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010096830.4A Pending CN113267755A (en) | 2020-02-14 | 2020-02-14 | Millimeter wave signal processing method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113267755A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012220377A (en) * | 2011-04-11 | 2012-11-12 | Denso Corp | Object identification apparatus and object identification program |
| CN105574542A (en) * | 2015-12-15 | 2016-05-11 | 中国北方车辆研究所 | Multi-vision feature vehicle detection method based on multi-sensor fusion |
| CN106295684A (en) * | 2016-08-02 | 2017-01-04 | 清华大学 | A kind of the most continuous based on micro-Doppler feature/discontinuous gesture recognition methods |
| CN109212499A (en) * | 2017-07-07 | 2019-01-15 | 英飞凌科技股份有限公司 | Use the system and method for radar sensor identification target |
| CN109492714A (en) * | 2018-12-29 | 2019-03-19 | 同方威视技术股份有限公司 | Image processing apparatus and its method |
| CN109581312A (en) * | 2018-11-22 | 2019-04-05 | 西安电子科技大学昆山创新研究院 | A kind of high-resolution millimetre-wave radar multi-object clustering method |
| US20200025877A1 (en) * | 2018-07-18 | 2020-01-23 | Qualcomm Incorporated | Object verification using radar images |
| US20200025911A1 (en) * | 2018-05-24 | 2020-01-23 | New York University | System, method and computer-accessible medium for real time imaging using a portable device |
-
2020
- 2020-02-14 CN CN202010096830.4A patent/CN113267755A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012220377A (en) * | 2011-04-11 | 2012-11-12 | Denso Corp | Object identification apparatus and object identification program |
| CN105574542A (en) * | 2015-12-15 | 2016-05-11 | 中国北方车辆研究所 | Multi-vision feature vehicle detection method based on multi-sensor fusion |
| CN106295684A (en) * | 2016-08-02 | 2017-01-04 | 清华大学 | A kind of the most continuous based on micro-Doppler feature/discontinuous gesture recognition methods |
| CN109212499A (en) * | 2017-07-07 | 2019-01-15 | 英飞凌科技股份有限公司 | Use the system and method for radar sensor identification target |
| US20200025911A1 (en) * | 2018-05-24 | 2020-01-23 | New York University | System, method and computer-accessible medium for real time imaging using a portable device |
| US20200025877A1 (en) * | 2018-07-18 | 2020-01-23 | Qualcomm Incorporated | Object verification using radar images |
| CN109581312A (en) * | 2018-11-22 | 2019-04-05 | 西安电子科技大学昆山创新研究院 | A kind of high-resolution millimetre-wave radar multi-object clustering method |
| CN109492714A (en) * | 2018-12-29 | 2019-03-19 | 同方威视技术股份有限公司 | Image processing apparatus and its method |
Non-Patent Citations (1)
| Title |
|---|
| 黄骏等: ""提高毫米波近程探测雷达距离跟踪精度新算法"", 《电子与信息学报》, vol. 32, no. 12, pages 2854 - 2860 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210326624A1 (en) | Method, system and device for difference automatic calibration in cross modal target detection | |
| Mayer et al. | Accurate and efficient image forgery detection using lateral chromatic aberration | |
| CN109799544B (en) | Intelligent detection method and device applied to millimeter wave security check instrument and storage device | |
| CN109063604A (en) | A kind of face identification method and terminal device | |
| CN111476099B (en) | Target detection method, target detection device and terminal equipment | |
| CN113807350A (en) | Target detection method, device, equipment and storage medium | |
| CN111612834A (en) | Method, device and equipment for generating target image | |
| CN110555400A (en) | icing detection method and system based on unmanned aerial vehicle inspection overhead transmission line | |
| CN110599479A (en) | Monitoring area change detection method and device and storage medium | |
| CN111401321A (en) | Object recognition model training method and device, electronic equipment and readable storage medium | |
| CN113466839B (en) | Side-scan sonar sea bottom line detection method and device | |
| CN112949785B (en) | Object detection method, device, equipment and computer storage medium | |
| CN110689556A (en) | Tracking method and device and intelligent equipment | |
| CN109978855A (en) | A kind of method for detecting change of remote sensing image and device | |
| CN107392948B (en) | Image registration method of amplitude-division real-time polarization imaging system | |
| CN113267755A (en) | Millimeter wave signal processing method and device, electronic equipment and readable storage medium | |
| CN113327209A (en) | Depth image generation method and device, electronic equipment and storage medium | |
| CN116740145A (en) | Multi-target tracking method, device, vehicle and storage medium | |
| CN111353526A (en) | Image matching method and device and related equipment | |
| CN116645612A (en) | Forest resource asset determination method and system | |
| CN116258873A (en) | Position information determining method, training method and device of object recognition model | |
| CN113009467B (en) | Radar blind area target detection tracking method and device and terminal equipment | |
| CN115343774A (en) | Method and device for detecting metal object, terminal equipment and storage medium | |
| CN110766005B (en) | Target feature extraction method and device and terminal equipment | |
| CN117593194B (en) | Gas feature map generation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| AD01 | Patent right deemed abandoned | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20241008 |