CN110794462A - Building site safety monitoring system and monitoring method and device thereof - Google Patents
Building site safety monitoring system and monitoring method and device thereof Download PDFInfo
- Publication number
- CN110794462A CN110794462A CN201911078294.9A CN201911078294A CN110794462A CN 110794462 A CN110794462 A CN 110794462A CN 201911078294 A CN201911078294 A CN 201911078294A CN 110794462 A CN110794462 A CN 110794462A
- Authority
- CN
- China
- Prior art keywords
- electromagnetic wave
- wave signal
- safety monitoring
- neural network
- waveform
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V3/00—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation
- G01V3/12—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation operating with electromagnetic waves
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Electromagnetism (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Geophysics (AREA)
- Alarm Systems (AREA)
Abstract
The application provides a building site safety monitoring system, a monitoring method and a monitoring device thereof, computer equipment and a storage medium, wherein the building site safety monitoring system comprises an electromagnetic wave signal transmitting device, an electromagnetic wave signal receiving device and a monitoring platform; each electromagnetic wave signal transmitting device and at least one electromagnetic wave signal receiving device form the electromagnetic wave sensor array; the electromagnetic wave signal transmitting device transmits an electromagnetic wave signal to a monitoring area, and the electromagnetic wave signal receiving device receives the electromagnetic wave signal and transmits the electromagnetic wave signal to the monitoring platform; the monitoring platform acquires a target electromagnetic wave signal sent by the electromagnetic wave sensor array; extracting a current characteristic waveform of a target electromagnetic wave signal; and inputting the current characteristic waveform into a safety monitoring neural network model trained in advance for recognition, and determining the position information and/or the structural characteristics of the invading object. According to the technical scheme, the influence of the environment on the safety of the construction site can be reduced, and the accuracy and the recognition rate of the safety monitoring of the construction site are improved.
Description
Technical Field
The application relates to the field of building site safety monitoring, in particular to a basic building site safety monitoring system, a monitoring method and a monitoring device thereof, and further relates to computer equipment and a storage medium.
Background
In order to ensure the safety of the construction site, the construction site needs to be monitored, for example, the characteristics of the construction site with safety risks are identified, and especially, the identification and monitoring of an illegal intrusion object in a monitoring area are carried out.
The existing construction site safety monitoring system is mainly based on optical monitoring, however, sensors used for optical monitoring such as a visual sensor and a laser sensor are greatly influenced by the environment, especially under the condition that illumination is unstable in rainy days, at night and the like, or a non-penetrable shelter is arranged, and the accuracy and the efficiency of monitoring are affected.
Disclosure of Invention
The object of the present application is to solve at least one of the above technical drawbacks, in particular the problems of low monitoring accuracy and efficiency.
In a first aspect, an embodiment of the present application provides a building site safety monitoring system, which includes an electromagnetic wave signal transmitting device, an electromagnetic wave signal receiving device, and a monitoring platform; the electromagnetic wave signal receiving device is connected with the monitoring platform;
the electromagnetic wave signal transmitting device and the electromagnetic wave signal receiving device are distributed at the appointed positions of the construction site; each electromagnetic wave signal transmitting device and at least one electromagnetic wave signal receiving device form the electromagnetic wave sensor array;
the electromagnetic wave signal transmitting device transmits an electromagnetic wave signal to a monitoring area, and the electromagnetic wave signal receiving device receives the electromagnetic wave signal and transmits the electromagnetic wave signal to the monitoring platform;
and the monitoring platform extracts the waveform characteristics of the electromagnetic wave signals, and judges that illegal invasion occurs when the waveform characteristics change relative to a constant state.
In some embodiments, the monitoring area is divided into four quadrants by planar area; wherein, at least one electromagnetic wave signal transmitting device and three electromagnetic wave signal receiving devices are arranged in the single quadrant.
In some embodiments, the monitoring platform performs signal modulation on the electromagnetic wave signal to output waveform characteristics, and outputs a constant characteristic waveform when no invading object exists in a corresponding quadrant, and outputs a varying characteristic waveform when the invading object exists.
In some embodiments, the monitoring platform is further configured to input the changed characteristic waveform into a safety monitoring neural network model trained in advance for recognition, and obtain position information and structural characteristics of the invading object.
In a second aspect, an embodiment of the present application further provides a building site safety monitoring method, which is applied to the monitoring platform according to any embodiment of the first aspect, and includes the following steps:
acquiring a target electromagnetic wave signal sent by an electromagnetic wave sensor array;
extracting a current characteristic waveform of the target electromagnetic wave signal;
and inputting the current characteristic waveform into a safety monitoring neural network model trained in advance for recognition, and determining the position information and/or the structural characteristics of the invading object.
In some embodiments, the security monitoring neural network model includes a security monitoring static neural network and a security monitoring dynamic neural network.
In some embodiments, the safety monitoring static neural network is trained by:
acquiring a characteristic waveform training set, wherein the characteristic waveform training set comprises a training characteristic waveform array output by an electromagnetic wave sensor array when a training object is static at different positions of a monitoring area of the electromagnetic wave sensor array;
and inputting the training characteristic waveform array into a static neural network for training to obtain a safety monitoring static neural network model.
In some embodiments, the safety monitoring static neural network is trained by:
extracting an intermediate layer parameter array and a static function in the safety monitoring static neural network model, taking the intermediate layer parameter array as an initial parameter of dynamic training, and taking the static function as a reference comparison function of the dynamic training;
acquiring a time sequence waveform training set;
inputting the time sequence waveforms in the time sequence waveform training set into a static neural network for training based on the initial parameters and the reference comparison function to obtain a time sequence dynamic function;
and superposing the safety monitoring static neural network model on the time sequence dynamic function to generate a safety monitoring dynamic neural network model.
In some embodiments, the current signature is a waveform peak;
inputting the current characteristic waveform into a safety monitoring neural network model trained in advance for recognition, and determining the position information and/or the structural characteristics of the invading object, wherein the steps comprise:
and inputting the waveform peak value into a safety monitoring static neural network model trained in advance for identification, and determining the position point coordinates and/or the structural characteristics of the invading object.
In some embodiments, the current signature is a time-series waveform;
inputting the current characteristic waveform into a safety monitoring neural network model trained in advance for recognition, and determining the position information and/or the structural characteristics of the invading object, wherein the steps comprise:
and inputting the time sequence waveform into a pre-trained safety monitoring dynamic neural network model for identification, and determining the time sequence track coordinate and/or the structural characteristic of the invading object.
In some embodiments, the step of inputting the training characteristic waveform array into a static neural network for training to obtain a safety monitoring neural network model includes:
inputting the training characteristic waveform array into a static neural network to generate a training position characteristic array corresponding to the training characteristic waveform array;
comparing each actual position feature in the training position feature array with a standard position feature to obtain a modification weight;
and continuously optimizing the parameters of the static neural network according to the modified weight value to obtain a safety monitoring static neural network model.
In some embodiments, before the step of acquiring the target electromagnetic wave signal sent by the electromagnetic wave sensor array, the method further includes:
acquiring a first electromagnetic wave signal output by the electromagnetic wave sensor array when no invading object exists in a monitoring area of the electromagnetic wave sensor array;
the step of acquiring the target electromagnetic wave signal sent by the electromagnetic wave sensor array comprises the following steps:
acquiring a second electromagnetic wave signal output by the electromagnetic wave sensor array when an invading object exists in a monitoring area of the electromagnetic wave sensor array;
and comparing the second electromagnetic wave signal with the first electromagnetic wave signal to obtain a target electromagnetic wave signal sent by the electromagnetic wave sensor array.
In a third aspect, an embodiment of the present application further provides a construction site safety monitoring device applied to the monitoring platform according to any one of the embodiments of the first aspect, including:
the acquisition module is used for acquiring a target electromagnetic wave signal sent by the electromagnetic wave sensor array;
the extraction module is used for extracting the current characteristic waveform of the target electromagnetic wave signal;
and the determining module is used for inputting the current characteristic waveform into a safety monitoring neural network model trained in advance for recognition, and determining the position information and/or the structural characteristics of the invading object.
In a fourth aspect, the present application further provides a computer device, including a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the building site safety monitoring method according to any one of the embodiments of the second aspect.
In a fifth aspect, the present embodiments also provide a storage medium containing computer executable instructions for performing the steps of the construction site safety monitoring method according to any one of the second aspect when executed by a computer processor.
The construction site safety monitoring system, the monitoring method and device thereof, the computer equipment and the storage medium provided by the embodiment comprise an electromagnetic wave signal transmitting device, an electromagnetic wave signal receiving device and a monitoring platform; the electromagnetic wave signal receiving device is connected with the monitoring platform; the electromagnetic wave signal transmitting device and the electromagnetic wave signal receiving device are distributed at the designated positions of the construction site; each electromagnetic wave signal transmitting device and at least one electromagnetic wave signal receiving device form the electromagnetic wave sensor array; the electromagnetic wave signal transmitting device transmits an electromagnetic wave signal to a monitoring area, and the electromagnetic wave signal receiving device receives the electromagnetic wave signal and transmits the electromagnetic wave signal to the monitoring platform; the monitoring platform acquires a target electromagnetic wave signal sent by the electromagnetic wave sensor array; extracting a current characteristic waveform of a target electromagnetic wave signal; and inputting the current characteristic waveform into a safety monitoring neural network model trained in advance for recognition, and determining the position information and/or the structural characteristics of the invading object. According to the technical scheme, the influence of the environment on the safety of the construction site can be reduced, and the accuracy and the recognition rate of the safety monitoring of the construction site are improved.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic diagram of a construction site safety monitoring system according to an embodiment;
FIG. 2 is a schematic diagram of a construction site safety monitoring system based on an electromagnetic wave sensor array;
FIG. 3 is a schematic diagram of signal transmission in a two-dimensional planar area of an electromagnetic wave sensor array;
FIG. 4 is a schematic diagram of signal transmission in a three-dimensional area of an electromagnetic wave sensor array;
FIG. 5 is a flow diagram of a construction site safety monitoring method according to an embodiment;
FIG. 6 is a flow diagram of a method for training a safety monitoring static neural network model according to an embodiment;
FIG. 7 is a flow diagram of a method for training a safety monitoring dynamic neural network model provided by an embodiment;
FIG. 8 is a schematic structural diagram of a construction site safety monitoring device according to an embodiment.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled.
It will be understood by those within the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Fig. 1 is a schematic structural diagram of a construction site safety monitoring system provided by an embodiment, and as shown in fig. 1, a construction site safety monitoring system 10 may include an electromagnetic wave signal transmitting device 101, an electromagnetic wave signal receiving device 102 and a monitoring platform 103; the electromagnetic wave signal receiving device 102 is connected to the monitoring platform 103.
The electromagnetic wave signal transmitting device 101 and the electromagnetic wave signal receiving device 102 are distributed at designated positions of a construction site; wherein each electromagnetic wave signal transmitting device 101 and at least one electromagnetic wave signal receiving device 102 form the electromagnetic wave sensor array 104; the electromagnetic wave signal transmitting device 101 transmits an electromagnetic wave signal to a monitoring area, and the electromagnetic wave signal receiving device 102 receives the electromagnetic wave signal and transmits the electromagnetic wave signal to the monitoring platform 103; the monitoring platform 103 extracts the waveform characteristics of the electromagnetic wave signal, and judges that illegal intrusion occurs when the waveform characteristics change relative to a constant state.
In some embodiments, the electromagnetic wave signal emitting device 101 and the electromagnetic wave signal receiving device 102 are distributed at designated locations on a construction site. Fig. 2 is a schematic diagram of a building site safety monitoring system based on an electromagnetic wave sensor array, and as shown in fig. 2, the designated positions of the building site can comprise monitoring areas of the building site, such as a building tower crane body 105, a building climbing scaffold body 106, a building foundation pit body 107 and a construction building body 108. The designated location of a construction site has a sensitive requirement for a safe location, namely whether a foreign object is illegally invaded or not and the position tracking identification after the invasion are judged in a defined area.
For example, the electromagnetic wave sensor array 104 can be deployed on a key structure node on the building tower crane body 105, and by utilizing the high advantage of the electromagnetic wave sensor array on the building site, the electromagnetic wave signal can be sent and received, and the electromagnetic wave signal can cover most sensitive areas of the building site and can be identified and defined in position characteristics in a short time.
The electromagnetic wave sensor array 104 can be deployed on key structure nodes of the building climbing scaffold body 106, and can transmit and receive electromagnetic wave signals by utilizing the coverage advantages of the electromagnetic wave sensor array per se on a building body, so that accurate signal delivery as required in the building body can be realized, and accurate signal coverage of characteristic areas in the building body can be realized.
The electromagnetic wave sensor array 104 can be deployed at a key structure node on the building foundation pit body 107, and can realize reference signal setting and model accumulation on a building body by utilizing the prior advantages of the electromagnetic wave sensor array in building construction, namely, the foundation pit is used as the foundation and the reference of the initial construction of the building.
The electromagnetic wave sensor array 104 is deployed on a key structure node of the construction building body 108, and comparison and area division of electromagnetic wave signals are performed by using model characteristics of the building after construction, so that long-term monitoring in a safety sensitive area of the construction building can be realized.
Further, after receiving the electromagnetic wave signal sent by the electromagnetic wave signal receiving device 102, the monitoring platform 103 extracts waveform characteristics of the electromagnetic wave signal, such as a peak and a variation frequency of the waveform. When no illegal invasive object appears in the monitoring area, the electromagnetic wave signal is stable and is in a relatively constant state; when an illegal intrusion object appears in the monitoring area, the existence of the intrusion object influences the receiving of the electromagnetic wave signal by the electromagnetic wave signal receiving device 102, so that when the waveform characteristics of the electromagnetic wave signal extracted by the monitoring platform 103 changes relative to a constant state, the illegal intrusion is judged to appear.
The building site safety monitoring system provided by the embodiment comprises an electromagnetic wave signal transmitting device, an electromagnetic wave signal receiving device and a monitoring platform, wherein an electromagnetic wave signal is transmitted to a monitoring area through the electromagnetic wave signal transmitting device, the electromagnetic wave signal receiving device receives the electromagnetic wave signal and transmits the electromagnetic wave signal to the monitoring platform, the monitoring platform extracts the waveform characteristics of the electromagnetic wave signal, and whether an object is illegally invaded is judged according to whether the waveform characteristics change relative to a constant state. Because the electromagnetic wave signal is little influenced by the environment, whether there is the invasion object with electromagnetic wave signal monitoring for the safety monitoring of building site is more accurate reliable. The deployment of the electromagnetic wave sensor array is to carry out long-term dynamic monitoring on a building site, and the complex scenes can be identified by matching a corresponding monitoring system algorithm, so that dynamic monitoring in a complex area is realized.
Further, in some embodiments, the monitoring area may be divided into four quadrants according to a plane area; wherein, at least one electromagnetic wave signal transmitting device and three electromagnetic wave signal receiving devices are arranged in the single quadrant.
In an embodiment, in a plane, an electromagnetic wave sensor array formed by an electromagnetic wave signal transmitting device and an electromagnetic wave signal receiving device can divide a plane area into four quadrants, such as A, B, C and D four quadrants. Fig. 3 is a schematic diagram of signal transmission in a two-dimensional plane area of an electromagnetic wave sensor array, as shown in fig. 3, at least one electromagnetic wave signal transmitting device 101 and three electromagnetic wave signal receiving devices 102 are arranged in a single quadrant, so as to analyze the three electromagnetic wave signals according to different electromagnetic wave signals received by the three electromagnetic wave signal receiving devices 102, and to more accurately determine whether an illegal intrusion occurs and characteristics, such as size and position, of an intruding object.
Fig. 4 is a schematic diagram of signal transmission in a three-dimensional region of an electromagnetic wave sensor array, as shown in fig. 4, in a space, the electromagnetic wave sensor array can divide the space into a plurality of specific monitoring regions, and a single specific monitoring region can be provided with at least four electromagnetic wave signal transmitting devices and four electromagnetic wave signal receiving devices, the electromagnetic wave signal transmitting devices transmit electromagnetic wave signals, and the electromagnetic wave signal receiving devices receive the electromagnetic wave signals and form a spatial electromagnetic wave signal field after signal modulation.
Further, in an embodiment, the monitoring platform performs signal modulation on the electromagnetic wave signal to output a waveform characteristic, and outputs a constant characteristic waveform when no intruding object exists in a corresponding quadrant, and outputs a varying characteristic waveform when an intruding object exists.
The monitoring platform performs signal modulation on the received electromagnetic wave signals sent by one or more electromagnetic wave signal receiving devices and outputs corresponding waveform characteristics, such as wave crest, frequency and the like. In the quadrant of the monitoring area corresponding to the electromagnetic wave sensor array, if no intrusion object disturbs the electromagnetic wave signal, the electromagnetic wave signal received by the monitoring platform from the electromagnetic wave signal receiving device is stable, and the waveform characteristic of the electromagnetic wave signal after signal modulation is also constant. If an intruding object exists, the intruding object can block the transmission of electromagnetic waves, so that the electromagnetic wave signals are changed, the electromagnetic wave signals received by the monitoring platform from the electromagnetic wave signal receiving device are changed, and the waveform characteristics of the electromagnetic wave signals after signal modulation are changed accordingly.
In an embodiment, the monitoring platform is further configured to input the changed characteristic waveform into a safety monitoring neural network model trained in advance for recognition, and obtain position information and structural characteristics of the invading object.
The pre-trained safety monitoring neural network model is obtained by training according to the difference between the electromagnetic wave signal received by the electromagnetic wave signal receiving device and the output characteristic waveform when a large number of training samples are static at different positions of a monitoring area. When the changed characteristic waveform is input into the safety monitoring neural network model trained in advance, the safety monitoring neural network model can input position information of an intruding object, such as current position coordinates and the like. Because the interference degree of different invading objects on the electromagnetic wave signals at the same position is different, the structural physical signs of the invading objects, such as the size and the like, can be obtained by inputting different characteristic waveforms in the safety monitoring neural network model.
In order to illustrate the technical scheme more clearly, the process of building site safety monitoring through the safety monitoring neural network model is illustrated below.
Fig. 5 is a flow chart of a construction site safety monitoring method provided by an embodiment, which is applied to the monitoring platform in any one of the above embodiments.
Specifically, as shown in fig. 5, the construction site safety monitoring method may include the steps of:
and S110, acquiring a target electromagnetic wave signal sent by the electromagnetic wave sensor array.
In the present embodiment, the electromagnetic wave sensor array may include an electromagnetic wave signal transmitting device and an electromagnetic wave signal receiving device. The electromagnetic wave signal transmitting device transmits electromagnetic waves to the electromagnetic wave signal receiving device, and the electromagnetic wave signal receiving device transmits target electromagnetic wave signals to the monitoring platform after receiving the electromagnetic waves. Generally speaking, when no foreign invading object appears in the monitoring area of the electromagnetic wave sensor array, the target electromagnetic wave signal is constant, and when the foreign invading object appears, the foreign invading object can interfere the electromagnetic wave signal receiving device to receive the electromagnetic wave signal, so that the target electromagnetic wave signal sent to the monitoring platform is changed.
Further, in some embodiments, before acquiring the target electromagnetic wave signal, it is first required to acquire a first electromagnetic wave signal output by the electromagnetic wave sensor array when no intrusion object exists in the monitoring area of the electromagnetic wave sensor array, and the waveform characteristic of the first electromagnetic wave signal is relatively stable because there is no interference from a foreign intrusion object. And acquiring a second electromagnetic wave signal output by the electromagnetic wave sensor array when an invading object exists in a monitoring area of the electromagnetic wave sensor array, wherein the waveform characteristic of the second electromagnetic wave signal is changed due to the interference of the external invading object. The second electromagnetic wave signal is compared with the first electromagnetic wave signal, for example, the first electromagnetic wave signal can be subtracted from the first electromagnetic wave signal to obtain the target electromagnetic wave signal.
And S120, extracting the current characteristic waveform of the target electromagnetic wave signal.
Furthermore, the current characteristic waveform of the target electromagnetic wave signal is extracted, the waveform characteristics of the target electromagnetic wave signal, such as the amplitude, the frequency and the like of the waveform, are identified, and further, the waveform characteristics can be arranged according to a time sequence to obtain a time sequence waveform.
S130, inputting the current characteristic waveform into a safety monitoring neural network model trained in advance for recognition, and determining the position information and/or the structural characteristics of the invading object.
In this embodiment, the monitoring platform may store a safety monitoring neural network model trained in advance. After the current characteristic waveform is obtained, the current characteristic waveform may be input to a safety monitoring neural network model trained in advance for identification, so as to obtain position information corresponding to the current characteristic waveform, and in some other embodiments, structural characteristics of the invading object, such as size and shape, or position information and structural characteristics of the invading object may also be obtained.
According to the building site safety monitoring method provided by the embodiment, a target electromagnetic wave signal sent by an electromagnetic wave sensor array is obtained; extracting a current characteristic waveform of a target electromagnetic wave signal; and inputting the current characteristic waveform into a safety monitoring neural network model trained in advance for identification, determining the position information and the structural characteristics of the invading object, and improving the identification accuracy of the invading object.
Further, the safety monitoring neural network model may include a safety monitoring static neural network and a safety monitoring dynamic neural network. The position point coordinates of the invading object when the invading object is static can be obtained by utilizing the static safety monitoring neural network, and the dynamic motion track of the invading object when the invading object moves can be obtained by utilizing the dynamic safety monitoring neural network.
The following describes the training process of the safety monitoring static neural network and the safety monitoring dynamic neural network.
Fig. 6 is a flowchart of a training method of a safety monitoring static neural network model, which may be executed by a computer device according to an embodiment, as shown in fig. 6, where the safety monitoring static neural network model may be trained by:
s210, obtaining a characteristic waveform training set, wherein the characteristic waveform training set comprises a training characteristic waveform array output by the electromagnetic wave sensor array when a training object is static at different positions of a monitoring area of the electromagnetic wave sensor array.
In an embodiment, the training object may be an object used for training and serving as a foreign invasion object, and the size, the size and the placement position of the object are preset. And (4) a set of characteristic waveforms corresponding to the training object forms a characteristic waveform training set. In some embodiments, training objects are placed at different target positions in the monitoring area, the monitoring area is kept still for a certain time, the characteristic waveform change conditions of the electromagnetic wave signals before and after the training objects are placed at the target positions are compared, the same training object and the training characteristic waveforms output by the electromagnetic wave sensor array are matched, and training characteristic waveform arrays of the same training object at different target positions are generated.
In other embodiments, different training objects may be placed at the same target position in the monitoring area, and the training objects may be kept still for a certain period of time, and the structural features, such as dimensions, of the different training objects and the training signatures output by the battery wave sensor arrays may be correlated to compare the change of the signatures of the electromagnetic wave signals before and after the different training objects are placed at the same target position, so as to generate training signature arrays of the different training objects at the same target position.
In other embodiments, training characteristic waveform arrays of the same training object at different target positions and training characteristic waveform arrays of different training objects at the same target position may be combined to obtain training characteristic waveform arrays of different training objects at different target positions.
And S220, inputting the training characteristic waveform array into a static neural network for training to obtain a safety monitoring neural network model.
In the embodiment, the training characteristic waveform array is used as the input of the static neural network, and the position characteristic corresponding to each characteristic waveform in the training characteristic waveform array is used as the expected output of the static neural network. And comparing the actual output and the expected output of the static neural network, and continuously training and optimizing the parameters of the static neural network to obtain a safety monitoring neural network model for monitoring the safety of the construction site.
Further, step S220 may include the steps of:
and S221, inputting the training characteristic waveform array into a static neural network, and generating a training position characteristic array corresponding to the training characteristic waveform array.
In this embodiment, the training characteristic waveform array may be a waveform peak and a frequency corresponding to a training object. For convenience of explanation, the following embodiments are described taking the peak of the waveform as an example.
The waveform peak value of the target electromagnetic wave signalForm an input array x[m]The waveform peak is used as the input layer (m) of the static neural networki1,mi2,mi3… …). Inputting the waveform peak value into the middle layer of the static neural network, wherein the middle layer is a deep learning algorithm based on a multi-layer neural network, and the middle parameters of each layer can form a transition array a1[m]，a2[m]……an[m]. Taking the structural characteristics and the position information of a training object as an output layer (m) of a static neural networko1,mo2,mo3… …), constituting an output matrix y[m]The calculation function of the output layer, the intermediate layer and the output layer can be obtained as y[m]＝f(x[m]·a1[m]·a2[m]·…·an[m]). Because each training characteristic waveform in the training characteristic waveform array corresponds to a unique actual output position characteristic, the training characteristic waveform is mapped to the corresponding actual output position characteristic to generate a training position characteristic array.
S222, comparing each actual output position feature in the training position feature array with a standard output position feature to obtain a modification weight.
Illustratively, a training characteristic waveform array in the characteristic waveform training set is input into the static neural network, and a training position characteristic array is output by the output layer, wherein the training position characteristic array comprises one or more actual output position characteristics. And comparing the actual output position characteristic with the standard output position characteristic, and calculating the difference degree of the actual output position characteristic and the standard output position characteristic. Wherein the standard output position feature is a position feature expected to be output by the static neural network. And determining a modification weight value of the parameters of the middle layer of the static neural network according to the difference degree. If the difference degree is larger, the modification weight value is larger, and if the difference degree is smaller, the modification weight value is smaller.
And S223, continuously optimizing the parameters of the static neural network according to the modified weight value to obtain a safety monitoring static neural network model.
And continuously optimizing a parameter array of the middle layer of the static neural network according to the modified weight value so as to enable the actual output position characteristics to be as close to the standard output position characteristics as possible, training the whole deep learning algorithm of the static neural network, realizing the mapping relation between input parameters of an input layer, such as characteristic waveforms, and parameters of an output layer, such as position characteristics, and obtaining a safety monitoring neural network model.
According to the building site safety monitoring method provided by the embodiment, a training characteristic waveform array output by an electromagnetic wave sensor array is obtained when a training object is static at different positions of a monitoring area of the electromagnetic wave sensor array; and inputting the training characteristic waveform array into a static neural network for training to obtain a safety monitoring neural network model so as to realize dynamic autonomous learning of the monitoring platform on the environment of the construction site and improve the robustness of safety monitoring of the construction site.
Fig. 7 is a flowchart of a training method of a safety monitoring dynamic neural network model, which may be executed by a computer device according to an embodiment, as shown in fig. 7, where the safety monitoring dynamic neural network model may be trained by:
s310, extracting an intermediate layer parameter array and a static function in the safety monitoring static neural network model, taking the intermediate layer parameter array as an initial parameter of dynamic training, and taking the static function as a reference comparison function of the dynamic training.
In this embodiment, an intermediate layer parameter array in the safety monitoring static neural network is obtained, the intermediate layer parameter array is used as an initial parameter for dynamic training, and a static function of the safety monitoring static neural network is used as a reference comparison function for dynamic parameter training.
And S320, acquiring a time sequence waveform training set.
In the present embodiment, a plurality of preset time-series waveforms are grouped into a time-series waveform training set.
S330, inputting the time sequence waveforms in the time sequence waveform training set into a static neural network for training based on the initial parameters and the reference comparison function to obtain a time sequence dynamic function.
Using time sequence waveform as input of static neural networkLayer (g (t)i1，g(t)i2，g(t)i2… …) constitute an input array x'[m]Taking the object size and/or time sequence track coordinate as the output layer of the static neural network (g (t))o1，g(t)o2，g(t)o3… …) to form an output array y' [ m ]]。
Wherein, the intermediate layer of the static neural network is a deep learning algorithm based on a multilayer neural network, and the intermediate parameters of each layer can form a transition array a1’[m]，a2’[m]……an’[m]。
It can be derived that the calculated functions of the output, intermediate and output layers are y'[m]＝f(t)(x’[m]·a1’[m]·a2’[m]·…·an’[m])。
Through the continuous change of the values of the time sequence waveform input layer, the object size and/or the time sequence track coordinate output layer, the whole static neural network can be trained, and the mapping relation between the input layer parameters and the output layer parameters is realized. And after dynamic training, obtaining an intermediate layer parameter array and a time sequence dynamic function.
And S340, superposing the safety monitoring static neural network model on the time sequence dynamic function to generate a safety monitoring dynamic neural network model.
And superposing a time sequence dynamic function on an algorithm corresponding to the safety monitoring static neural network model to obtain a dynamic neural network, continuously carrying out deep learning training, mapping an input parameter of a time sequence waveform with an output parameter of a time sequence track coordinate, and optimizing the time sequence dynamic function and a parameter array of an intermediate layer of the dynamic neural network to obtain the safety monitoring dynamic neural network model.
The safety monitoring neural network model provided by the technical scheme can accurately identify the position information of the invaded object when the invaded object is static, and also can accurately identify the dynamic motion track of the invaded object.
In some embodiments, when the intrusion object is monitored to be stationary, a waveform peak value of the target electromagnetic wave signal is extracted, and the waveform peak value is taken as a current characteristic waveform. The waveform peak value is input into a safety monitoring static neural network model trained in advance for identification, the safety monitoring static neural network model determines the position point coordinates of the invading object according to the waveform peak value, and in some embodiments, the structural characteristics, such as size and the like, of the invading object can also be determined according to the waveform peak value.
In some embodiments, when the motion of the invading object is monitored, the time sequence waveform of the target electromagnetic wave signal is extracted, and the time sequence waveform is taken as the current characteristic waveform. The time sequence waveform is input into a safety monitoring dynamic neural network model trained in advance for recognition, the safety monitoring dynamic neural network model outputs time sequence track coordinates of an invading object according to the time sequence waveform, and the dynamic motion track of the invading object is determined.
The relevant embodiments of the construction site safety monitoring device are explained in detail below.
Fig. 8 is a schematic structural diagram of a construction site safety monitoring device applied to a computer device, such as a monitoring platform, and further, a server according to an embodiment. As shown in fig. 8, the construction site safety monitoring apparatus 10 may include: an acquisition module 110, an extraction module 120, and a determination module 130.
The acquiring module 110 is configured to acquire a target electromagnetic wave signal sent by an electromagnetic wave sensor array; an extracting module 120, configured to extract a current characteristic waveform of the target electromagnetic wave signal; and the determining module 130 is configured to input the current characteristic waveform into a pre-trained safety monitoring neural network model for recognition, and determine the position information and/or the structural characteristics of the invading object.
According to the building site safety monitoring device provided by the embodiment, a target electromagnetic wave signal sent by an electromagnetic wave sensor array is obtained through an obtaining module; the extraction module extracts the current characteristic waveform of the target electromagnetic wave signal; the current characteristic waveform is input into a safety monitoring neural network model which is trained in advance for recognition, and the determining module determines the position information and the structural characteristics of the invading object, so that the recognition accuracy of the invading object is improved. In an embodiment, the safety monitoring neural network model includes a safety monitoring static neural network and a safety monitoring dynamic neural network.
In one embodiment, the construction site safety monitoring device 10 includes a static training module comprising: a training set acquisition unit and a static model training unit;
the first training set acquisition unit is used for acquiring a characteristic waveform training set; the characteristic waveform training set comprises a training characteristic waveform array output by the electromagnetic wave sensor array when a training object is static at different positions of a monitoring area of the electromagnetic wave sensor array; and the static model training unit is used for inputting the training characteristic waveform array into a static neural network for training to obtain a safety monitoring static neural network model.
In one embodiment, the construction site safety monitoring device 10 includes a dynamic training module, which includes a parameter extraction unit, a second training set acquisition unit, a time sequence dynamic function obtaining unit, and a dynamic model generation unit;
the parameter extraction unit is used for extracting an intermediate layer parameter array and a static function in the safety monitoring static neural network model, taking the intermediate layer parameter array as an initial parameter of dynamic training, and taking the static function as a reference comparison function of the dynamic training; the second training set acquisition unit is used for acquiring a time sequence waveform training set; a time sequence dynamic function obtaining unit, configured to input the time sequence waveforms in the time sequence waveform training set to a static neural network for training based on the initial parameters and the reference comparison function, so as to obtain a time sequence dynamic function; and the dynamic model generating unit is used for superposing the safety monitoring static neural network model on the book order dynamic function to generate a safety monitoring dynamic neural network model.
In one embodiment, the current signature is a waveform peak; the determining module 130 is configured to input the waveform peak into a safety monitoring static neural network model trained in advance for identification, and determine a position point coordinate and/or a structural feature of the intruding object.
In one embodiment, the current signature is a time-series waveform; the determining module 130 is configured to input the time sequence waveform into a pre-trained safety monitoring dynamic neural network model for identification, and determine a time sequence track coordinate and/or a structural feature of the invading object.
In one embodiment, the static model training unit comprises a waveform array input subunit, a weight correction obtaining subunit and a static model optimization subunit;
the waveform array input subunit is used for inputting the training characteristic waveform array into a static neural network to generate a training position characteristic array corresponding to the training characteristic waveform array; a weight correction obtaining subunit, configured to compare each actual position feature in the training position feature array with a standard position feature to obtain a correction weight; and the static model optimization subunit is used for continuously optimizing the parameters of the static neural network according to the modification weight to obtain a safety monitoring static neural network model.
In one embodiment, the construction site safety monitoring device further comprises:
the first electromagnetic wave signal acquisition module is used for acquiring a first electromagnetic wave signal output by the electromagnetic wave sensor array when no invading object exists in a monitoring area of the electromagnetic wave sensor array;
further, the obtaining module 110 includes a second electromagnetic wave signal obtaining unit and a target electromagnetic wave signal obtaining unit;
the second electromagnetic wave signal acquisition unit is used for acquiring a second electromagnetic wave signal output by the electromagnetic wave sensor array when an invading object exists in the monitoring area of the electromagnetic wave sensor array; and the target electromagnetic wave signal obtaining unit is used for comparing the second electromagnetic wave signal with the first electromagnetic wave signal to obtain a target electromagnetic wave signal sent by the electromagnetic wave sensor array.
The building site safety monitoring device provided by the embodiment can be used for executing the building site safety monitoring method provided by any embodiment, and has corresponding functions and beneficial effects.
The embodiment of the present application further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and when the processor executes the program, the method for monitoring the safety of the construction site as in any one of the above embodiments is implemented.
Optionally, the computer device may be a mobile terminal, a tablet computer, a server, or the like. The computer equipment provided by the above has corresponding functions and advantages when executing the building site safety monitoring method provided by any one of the above embodiments.
Embodiments of the present application also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method for building site safety monitoring, comprising:
acquiring a target electromagnetic wave signal sent by an electromagnetic wave sensor array;
extracting a current characteristic waveform of the target electromagnetic wave signal;
and inputting the current characteristic waveform into a safety monitoring neural network model trained in advance for recognition, and determining the position information and/or the structural characteristics of the invading object.
Of course, the storage medium provided by the embodiments of the present application includes computer-executable instructions, and the computer-executable instructions are not limited to the operations of the processing method of image segmentation information as described above, and may also perform related operations in the method for monitoring safety of a construction site provided by any embodiment of the present application, and have corresponding functions and advantages.
From the above description of the embodiments, it is obvious for those skilled in the art that the present application can be implemented by software and necessary general hardware, and certainly can be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk, or an optical disk of a computer, and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) to execute the building site security monitoring method according to any embodiment of the present application.
It should be understood that, although the steps in the flowcharts of the figures 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 may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The foregoing is only a partial embodiment of the present application, and it should be noted that, for those skilled in the art, several modifications and decorations can be made without departing from the principle of the present application, and these modifications and decorations should also be regarded as the protection scope of the present application.
Claims (15)
1. A building site safety monitoring system is characterized by comprising an electromagnetic wave signal transmitting device, an electromagnetic wave signal receiving device and a monitoring platform; the electromagnetic wave signal receiving device is connected with the monitoring platform;
the electromagnetic wave signal transmitting device and the electromagnetic wave signal receiving device are distributed at the appointed positions of the construction site; each electromagnetic wave signal transmitting device and at least one electromagnetic wave signal receiving device form the electromagnetic wave sensor array;
the electromagnetic wave signal transmitting device transmits an electromagnetic wave signal to a monitoring area, and the electromagnetic wave signal receiving device receives the electromagnetic wave signal and transmits the electromagnetic wave signal to the monitoring platform;
and the monitoring platform extracts the waveform characteristics of the electromagnetic wave signals, and judges that illegal invasion occurs when the waveform characteristics change relative to a constant state.
2. The construction site safety monitoring system according to claim 1, wherein the monitoring area is divided into four quadrants by a planar area; wherein, at least one electromagnetic wave signal transmitting device and three electromagnetic wave signal receiving devices are arranged in the single quadrant.
3. The system for monitoring the safety of the construction site according to claim 2, wherein the monitoring platform performs signal modulation on the electromagnetic wave signal to output a waveform characteristic, when no invading object exists in a corresponding quadrant, a constant characteristic waveform is output, the invading object exists, and a variable characteristic waveform is output.
4. The construction site safety monitoring system according to claim 3, wherein the monitoring platform is further configured to input the changed characteristic waveform into a safety monitoring neural network model trained in advance for recognition, and obtain position information and structural characteristics of an intruding object.
5. A construction site safety monitoring method, applied to the monitoring platform of any one of claims 1 to 4, comprising the steps of:
acquiring a target electromagnetic wave signal sent by an electromagnetic wave sensor array;
extracting a current characteristic waveform of the target electromagnetic wave signal;
and inputting the current characteristic waveform into a safety monitoring neural network model trained in advance for recognition, and determining the position information and/or the structural characteristics of the invading object.
6. The construction site safety monitoring method according to claim 5, wherein the safety monitoring neural network model includes a safety monitoring static neural network and a safety monitoring dynamic neural network.
7. The construction site safety monitoring method according to claim 6, wherein the safety monitoring static neural network is trained by the following steps:
acquiring a characteristic waveform training set, wherein the characteristic waveform training set comprises a training characteristic waveform array output by an electromagnetic wave sensor array when a training object is static at different positions of a monitoring area of the electromagnetic wave sensor array;
and inputting the training characteristic waveform array into a static neural network for training to obtain a safety monitoring static neural network model.
8. The construction site safety monitoring method according to claim 7, wherein the safety monitoring static neural network is trained by the steps of:
extracting an intermediate layer parameter array and a static function in the safety monitoring static neural network model, taking the intermediate layer parameter array as an initial parameter of dynamic training, and taking the static function as a reference comparison function of the dynamic training;
acquiring a time sequence waveform training set;
inputting the time sequence waveforms in the time sequence waveform training set into a static neural network for training based on the initial parameters and the reference comparison function to obtain a time sequence dynamic function;
and superposing the safety monitoring static neural network model on the book order dynamic function to generate a safety monitoring dynamic neural network model.
9. The construction site safety monitoring method according to claim 6, wherein the current characteristic waveform is a waveform peak;
inputting the current characteristic waveform into a safety monitoring neural network model trained in advance for recognition, and determining the position information and/or the structural characteristics of the invading object, wherein the steps comprise:
and inputting the waveform peak value into a safety monitoring static neural network model trained in advance for identification, and determining the position point coordinates and/or the structural characteristics of the invading object.
10. The construction site safety monitoring method according to claim 7, wherein the current signature is a time-series waveform;
inputting the current characteristic waveform into a safety monitoring neural network model trained in advance for recognition, and determining the position information and/or the structural characteristics of the invading object, wherein the steps comprise:
and inputting the time sequence waveform into a pre-trained safety monitoring dynamic neural network model for identification, and determining the time sequence track coordinate and/or the structural characteristic of the invading object.
11. The construction site safety monitoring method according to claim 6, wherein the step of inputting the training characteristic waveform array into a static neural network for training to obtain a safety monitoring static neural network model comprises the following steps:
inputting the training characteristic waveform array into a static neural network to generate a training position characteristic array corresponding to the training characteristic waveform array;
comparing each actual position feature in the training position feature array with a standard position feature to obtain a modification weight;
and continuously optimizing the parameters of the static neural network according to the modified weight value to generate a safety monitoring static neural network model.
12. The construction site safety monitoring method according to claim 5, wherein the step of acquiring the target electromagnetic wave signal transmitted by the electromagnetic wave sensor array is preceded by the steps of:
acquiring a first electromagnetic wave signal output by the electromagnetic wave sensor array when no invading object exists in a monitoring area of the electromagnetic wave sensor array;
the step of acquiring the target electromagnetic wave signal sent by the electromagnetic wave sensor array comprises the following steps:
acquiring a second electromagnetic wave signal output by the electromagnetic wave sensor array when an invading object exists in a monitoring area of the electromagnetic wave sensor array;
and comparing the second electromagnetic wave signal with the first electromagnetic wave signal to obtain a target electromagnetic wave signal sent by the electromagnetic wave sensor array.
13. A construction site safety monitoring device applied to the monitoring platform of any one of claims 1 to 4, comprising:
the acquisition module is used for acquiring a target electromagnetic wave signal sent by the electromagnetic wave sensor array;
the extraction module is used for extracting the current characteristic waveform of the target electromagnetic wave signal;
and the determining module is used for inputting the current characteristic waveform into a safety monitoring neural network model trained in advance for recognition, and determining the position information and/or the structural characteristics of the invading object.
14. Computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the program, carries out the steps of the construction site safety monitoring method according to any of claims 5-12.
15. A storage medium containing computer executable instructions for performing the steps of the construction site safety monitoring method according to any one of claims 5 to 12 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911078294.9A CN110794462B (en) | 2019-11-06 | 2019-11-06 | Building site safety monitoring system and monitoring method and device thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911078294.9A CN110794462B (en) | 2019-11-06 | 2019-11-06 | Building site safety monitoring system and monitoring method and device thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110794462A true CN110794462A (en) | 2020-02-14 |
| CN110794462B CN110794462B (en) | 2021-08-03 |
Family
ID=69442970
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911078294.9A Active CN110794462B (en) | 2019-11-06 | 2019-11-06 | Building site safety monitoring system and monitoring method and device thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110794462B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1979575A (en) * | 2005-11-30 | 2007-06-13 | 中国科学院声学研究所 | Supersonic invasion detection method and detection device |
| CN101436336A (en) * | 2007-11-15 | 2009-05-20 | 中国科学院自动化研究所 | Intrusion detection system and method |
| CN102289906A (en) * | 2011-06-09 | 2011-12-21 | 无锡国科微纳传感网科技有限公司 | Enclosure intrusion detection method, device and system |
| CN102289902A (en) * | 2010-10-18 | 2011-12-21 | 航天科工深圳（集团）有限公司 | Overhead power transmission line monitoring and early warning system and working method thereof |
| JP2015041332A (en) * | 2013-08-23 | 2015-03-02 | 株式会社東海理化電機製作所 | Intruder detection system |
| CN204315020U (en) * | 2014-09-15 | 2015-05-06 | 天津职业技术师范大学 | A kind of personnel's intrusion detection device |
| CN105809110A (en) * | 2016-02-24 | 2016-07-27 | 南京大学 | Behavior identification system and method based on wireless signal identity |
| CN106251536A (en) * | 2016-08-23 | 2016-12-21 | 高杰 | A kind of miniature intrusion detection power-supply system and detection method |
| CN106372576A (en) * | 2016-08-23 | 2017-02-01 | 南京邮电大学 | Deep learning-based intelligent indoor intrusion detection method and system |
| CN106408825A (en) * | 2016-12-03 | 2017-02-15 | 上海腾盛智能安全科技股份有限公司 | Home safety monitoring system and method |
| JP2018163036A (en) * | 2017-03-27 | 2018-10-18 | 中国計器工業株式会社 | Radio wave diffusion plate |
| CN109064696A (en) * | 2018-08-17 | 2018-12-21 | 成都九洲电子信息系统股份有限公司 | The optical fiber perimeter security system realized based on deep learning |
| CN109671238A (en) * | 2018-12-07 | 2019-04-23 | 浙江大学 | A kind of indoor intrusion detection method based on radio channel status information |
| CN110059631A (en) * | 2019-04-19 | 2019-07-26 | 中铁第一勘察设计院集团有限公司 | The contactless monitoring defect identification method of contact net |
-
2019
- 2019-11-06 CN CN201911078294.9A patent/CN110794462B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1979575A (en) * | 2005-11-30 | 2007-06-13 | 中国科学院声学研究所 | Supersonic invasion detection method and detection device |
| CN101436336A (en) * | 2007-11-15 | 2009-05-20 | 中国科学院自动化研究所 | Intrusion detection system and method |
| CN102289902A (en) * | 2010-10-18 | 2011-12-21 | 航天科工深圳（集团）有限公司 | Overhead power transmission line monitoring and early warning system and working method thereof |
| CN102289906A (en) * | 2011-06-09 | 2011-12-21 | 无锡国科微纳传感网科技有限公司 | Enclosure intrusion detection method, device and system |
| JP2015041332A (en) * | 2013-08-23 | 2015-03-02 | 株式会社東海理化電機製作所 | Intruder detection system |
| CN204315020U (en) * | 2014-09-15 | 2015-05-06 | 天津职业技术师范大学 | A kind of personnel's intrusion detection device |
| CN105809110A (en) * | 2016-02-24 | 2016-07-27 | 南京大学 | Behavior identification system and method based on wireless signal identity |
| CN106251536A (en) * | 2016-08-23 | 2016-12-21 | 高杰 | A kind of miniature intrusion detection power-supply system and detection method |
| CN106372576A (en) * | 2016-08-23 | 2017-02-01 | 南京邮电大学 | Deep learning-based intelligent indoor intrusion detection method and system |
| CN106408825A (en) * | 2016-12-03 | 2017-02-15 | 上海腾盛智能安全科技股份有限公司 | Home safety monitoring system and method |
| JP2018163036A (en) * | 2017-03-27 | 2018-10-18 | 中国計器工業株式会社 | Radio wave diffusion plate |
| CN109064696A (en) * | 2018-08-17 | 2018-12-21 | 成都九洲电子信息系统股份有限公司 | The optical fiber perimeter security system realized based on deep learning |
| CN109671238A (en) * | 2018-12-07 | 2019-04-23 | 浙江大学 | A kind of indoor intrusion detection method based on radio channel status information |
| CN110059631A (en) * | 2019-04-19 | 2019-07-26 | 中铁第一勘察设计院集团有限公司 | The contactless monitoring defect identification method of contact net |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110794462B (en) | 2021-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2464991B1 (en) | A method for human only activity detection based on radar signals | |
| CN110632849B (en) | Intelligent household appliance, control method and device thereof and storage medium | |
| CN110927712B (en) | Tracking method and device | |
| US11391817B2 (en) | Radio frequency (RF) object detection using radar and machine learning | |
| CN110456320B (en) | Ultra-wideband radar identity recognition method based on free space gait time sequence characteristics | |
| JP2020003489A (en) | Ego motion estimation device and method using motion recognition model, and motion recognition model training device and method | |
| KR102030340B1 (en) | Radar apparatus and method for detecting High Resolution Doppler using the same | |
| CN104287946A (en) | Device and method for prompting blind persons to avoid obstacles | |
| KR102170597B1 (en) | System for observing costal water surface | |
| Reichman et al. | On choosing training and testing data for supervised algorithms in ground-penetrating radar data for buried threat detection | |
| CN102043958A (en) | High-definition remote sensing image multi-class target detection and identification method | |
| CN106056034A (en) | Pressure sensor-based object identification method and object identification method | |
| CN110717496A (en) | Complex scene tree detection method based on neural network | |
| CN107340517A (en) | Tracking before a kind of multisensor multi frame detection | |
| Amin et al. | Radar classifications of consecutive and contiguous human gross‐motor activities | |
| CN110348434A (en) | Camera source discrimination method, system, storage medium and calculating equipment | |
| CN116577788A (en) | Power transmission line foreign matter intrusion monitoring method, device and computer equipment | |
| CN108109208A (en) | A kind of marine wind electric field augmented reality method | |
| CN110794462B (en) | Building site safety monitoring system and monitoring method and device thereof | |
| CN116520315A (en) | Target recognition system, target recognition method and target recognition device | |
| CN115311574A (en) | Building monitoring method, equipment and medium | |
| CN113688742A (en) | SAR image recognition method and device and storage medium | |
| TW202129595A (en) | Life form radar system, identification method, and database establishment method | |
| CN113945912B (en) | Target detection system of radar image for series corner reflector interference | |
| CN113435230A (en) | Abnormal area detection method, device, system and computer readable 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |