CN113701642A - Method and system for calculating appearance size of vehicle body - Google Patents
Method and system for calculating appearance size of vehicle body Download PDFInfo
- Publication number
- CN113701642A CN113701642A CN202110876165.5A CN202110876165A CN113701642A CN 113701642 A CN113701642 A CN 113701642A CN 202110876165 A CN202110876165 A CN 202110876165A CN 113701642 A CN113701642 A CN 113701642A
- Authority
- CN
- China
- Prior art keywords
- vehicle body
- vehicle
- size
- information
- calculating
- 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
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000001514 detection method Methods 0.000 claims abstract description 34
- 238000004364 calculation method Methods 0.000 claims description 20
- 230000037237 body shape Effects 0.000 claims description 8
- 230000003068 static effect Effects 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 2
- 239000000203 mixture Substances 0.000 claims 1
- 239000002994 raw material Substances 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 7
- 230000008859 change Effects 0.000 abstract description 3
- 238000013527 convolutional neural network Methods 0.000 description 20
- 238000012545 processing Methods 0.000 description 20
- 238000005259 measurement Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 7
- 230000004913 activation Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/165—Anti-collision systems for passive traffic, e.g. including static obstacles, trees
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a method and a system for calculating the appearance size of a vehicle body, wherein the shape of the vehicle body is detected, and a vehicle body appearance calculating system detects the size information of the vehicle body and sends the size information to a vehicle appearance early warning system; detecting a lane scene, and acquiring image information of a lane in front of an automobile through a lane remote detection system to acquire road obstacle position information; the vehicle appearance early warning system compares the size information with the road obstacle information, if the collision risk exists, a prompt is sent, the size change of the appearance of the vehicle body and the obstacle information on the road can be detected in the driving process, the size of the collision risk of the vehicle is judged by calculating the size of the vehicle body and the remaining traffic space of the lane under the obstruction of the obstacle, and warning information is sent to provide a driver and passengers.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a method and a system for calculating the appearance of a vehicle body.
Background
Vehicles are developed to the present from the vehicles which originally replace carriage vehicles, become an indispensable life auxiliary product for each family, and bring more living space and living experience for each family.
Urban roads, for some reasons, limit the width or height of vehicles on the road. For example, there can be limit for height sign before the culvert, avoid too high vehicle top to run into with the culvert bottom and cause personnel's loss of property.
In some cases, although there is no width or height limit mark on the lane, there is a case where avoidance is actually required. For example, a poured pier is added in the middle of the road, or a hanging rope is added above the road. Both cases require calculations of width and height to account for passability.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
Therefore, the technical problem to be solved by the present invention is to provide a method and a system for calculating the external dimension of a vehicle body, which overcome the defect that the driver cannot accurately evaluate whether the external dimension of the vehicle body can pass through an obstacle in the prior art.
In order to solve the technical problems, the invention provides the following technical scheme: a method for calculating the appearance size of a vehicle body comprises the following steps: the method is characterized in that: the method comprises the steps of detecting the shape of a vehicle body, detecting size information of the vehicle body by a vehicle body shape calculation system, and sending the size information to a vehicle shape early warning system; detecting a lane scene, and acquiring image information of a lane in front of an automobile through a lane remote detection system to acquire road obstacle position information; and calculating collision risk, comparing the size information with the road obstacle information by the vehicle appearance early warning system, and sending a prompt if the collision risk exists.
As a preferable aspect of the method for calculating the apparent size of the vehicle body according to the present invention, wherein: and the size information of the vehicle body is acquired by a size acquisition module in the vehicle body appearance calculation system.
As a preferable aspect of the method for calculating the apparent size of the vehicle body according to the present invention, wherein: the size acquisition module sends the acquired vehicle body image information to the vehicle appearance early warning module, and the vehicle appearance early warning system compares the vehicle body image information with a preset vehicle body image to judge whether the vehicle body appearance changes.
As a preferable aspect of the method for calculating the apparent size of the vehicle body according to the present invention, wherein: the dimension acquisition module acquires a length dimension, a width dimension, and a height dimension of the vehicle, and takes an outermost edge of the acquired image as the dimension boundary.
As a preferable aspect of the method for calculating the apparent size of the vehicle body according to the present invention, wherein: an environment acquisition module in the lane remote detection system acquires environment image information of a lane in front of a vehicle and sends the environment information of the lane to the vehicle appearance early warning system.
As a preferable aspect of the method for calculating the apparent size of the vehicle body according to the present invention, wherein: and according to the acquired environment image information of the lane, carrying out obstacle recognition through an image recognition technology, and storing the recognized obstacle shape information into a database.
As a preferable aspect of the method for calculating the apparent size of the vehicle body according to the present invention, wherein: the obstacles are divided into static obstacles and moving obstacles, and the static obstacles and the moving obstacles are classified and identified respectively to form corresponding classifiers.
As a preferable aspect of the method for calculating the apparent size of the vehicle body according to the present invention, wherein: the step of recognizing the obstacle image and the lane image according to the acquired vehicle image information comprises the following steps:
extracting the obstacle image and the lane image by a target detection algorithm;
and classifying and identifying the extracted obstacle image and the classifier of the lane to obtain the category and size information of the obstacle.
The invention also provides a system for calculating the appearance size of the car body, which comprises
The vehicle body appearance calculation system comprises a size acquisition module arranged outside a vehicle body and used for acquiring the actual size information of the vehicle;
the lane remote detection system comprises an environment acquisition module arranged on a vehicle and used for acquiring environment information on a road where the vehicle is located;
and the vehicle appearance early warning system compares the received vehicle body appearance size information with the obstacle information in the environment information, judges the collision risk of the vehicle and sends out an alarm.
As a preferable aspect of the system for calculating the apparent size of a vehicle body according to the present invention, wherein: the size acquisition module comprises a width detection camera, a height detection camera and a length detection camera which are arranged outside the vehicle, and the width detection camera, the height detection camera and the length detection camera are respectively arranged outside a wheel frame, on the roof and on the front windshield and the rear windshield of the vehicle.
The invention has the beneficial effects that: the method and the system for calculating the appearance size of the vehicle body can detect the size change of the appearance of the vehicle body and the information of the obstacles on the road in the driving process, accurately judge the collision risk of the vehicle by calculating the size of the vehicle body and the residual traffic space of the lane under the obstruction of the obstacles, and send out the alarm information to provide a driver and passengers.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
FIG. 1 is a schematic diagram of a method of calculating the apparent dimensions of a vehicle body;
FIG. 2 is a block diagram of a system for calculating the apparent dimensions of a vehicle body;
fig. 3 is a flowchart for calculating the apparent dimension of the vehicle body.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Example 1
The embodiment provides a method for calculating the appearance size of a vehicle body, which comprises the following steps:
and detecting the shape of the vehicle body, detecting the size information of the vehicle body by the vehicle body shape calculating system, and sending the size information to the vehicle shape early warning system. And detecting a lane scene, and acquiring image information of a lane in front of the automobile through a lane remote detection system to acquire road obstacle position information. And calculating collision risk, comparing the size information with the road obstacle information by the vehicle appearance early warning system, and sending a prompt if the collision risk exists.
In the embodiment, the size information of the vehicle body is acquired by a size acquisition module in a vehicle body appearance calculation system; the size acquisition module sends the acquired vehicle body image information to the vehicle appearance early warning module, and the vehicle appearance early warning system compares the vehicle body image information with a preset vehicle body image and judges whether the vehicle body appearance changes.
The dimension acquisition module acquires a length dimension, a width dimension, and a height dimension of the vehicle, and takes an outermost edge of the acquired image as a dimension boundary.
Specifically, the size acquisition module in the vehicle body contour calculation system in this embodiment takes pictures of each part of the vehicle body, the pictures are processed into a contour image by the image processing module 202 and the image recognition module 203, the contour image is calculated and compared with a preset vehicle body original image, and whether the appearance of the vehicle body changes is judged by using an image algorithm; for example, when a passenger protrudes an arm through a window or a trunk is attached to a roof, it is recognized that the size of the vehicle body is changed, and the size of the vehicle body at this time is used as a reference value for determining the collision risk.
The size identification process in this embodiment is as follows:
and loading the image, namely loading the image information acquired by the size acquisition module into an image processing environment, such as an Open CV visual library.
Correcting the image, detecting whether the image is abnormal or not, and selecting a reference original image; the reference original drawings in this embodiment may be provided in plural, and the vehicle body appearance images acquired from different angles by the corresponding image acquisition modules are used as the reference original drawings.
Image processing, comprising:
1. graying the image, namely changing the color in the image into gray by adopting a weighted average method, wherein the gray in different areas is different;
2. image filtering, namely, suppressing noise in an image by using a median filtering method so as to improve the accuracy of a subsequent processing result;
3. performing image binarization, namely recording segmentation threshold values of an image I (x, y), a foreground (namely a target) and a background as T by using an OTSU algorithm, recording the proportion of the number of pixels belonging to the foreground in the whole image as omega 0, and recording the average gray level as mu 0; the proportion of the number of background pixels in the whole image is omega 1, and the average gray scale is mu 1; the average gray scale of the whole image is recorded as mu, and the inter-class variance is recorded as g.
Assuming that the image size is M × N, the number of pixels in the image with the gray scale value smaller than the threshold T is N0, and the number of pixels with the gray scale value larger than the threshold T is N1, then
ω0＝N0/M×N
ω1＝N1/M×N
N0+N1＝M×N
ω0+ω1＝1
μ＝ω0*μ0+ω1*μ1
g＝ω0(μ0-μ)^2+ω1(μ1-μ)^2
g＝ω0ω1(μ0-μ1)^2
A threshold value T which enables the inter-class variance g to be maximum is adopted by a traversal method; and changing the part of the image with the gray level smaller than T into a background, and taking the part of the image with the gray level larger than T as a foreground to obtain a binary image.
4. The image segmentation sequentially uses an image opening operation, an image closing operation and a binary inversion method, and the brightness of the environment is high in the daytime or low at night, so that the vehicle body and the environment are easily separated after the image is processed, and the vehicle body and the environment are easily identified.
And (4) processing a result: after obtaining the image processing result, the main control system 100 selects the inter-image pearson correlation coefficient, pixel and ratio to judge whether the three areas are different from the original reference image due to the object shielding; if so, the size of the vehicle body is judged to be changed, and the increased length is added to the preset size of the vehicle body by calculating the size information of the outermost contour of the difference part.
If there are multiple increased sizes in the same direction, taking the maximum value of the increased sizes; the size of the vehicle body in the three directions of length, width and height is detected to form a rectangular frame model, and the simplified rectangular frame model is compared with the detected remaining passing space of the obstacles on the lane, so that whether the vehicle has the risk of collision or not can be evaluated.
An environment acquisition module in the lane remote detection system in this embodiment acquires environment image information of a lane in front of a vehicle, and sends the environment information of the lane to the vehicle appearance early warning system.
The lane remote detection system in this embodiment performs obstacle recognition using a convolutional neural network, specifically, performs obstacle recognition by using an image recognition technique according to the collected environmental image information of the lane, and stores the recognized obstacle shape information in a database.
The obstacles are divided into static obstacles and moving obstacles, and the static obstacles and the moving obstacles are classified and recognized respectively to form corresponding classifiers.
The invention designs a convolutional neural network CNN-MC comprising a plurality of classifiers by improving the structure of the convolutional neural network; preferably, in the embodiment, an additional linear classifier is added to the convolutional layer, and an activation module is used to monitor the output of each classifier when performing an image classification task, wherein the activation module of the embodiment mainly comprises a confidence value, and determines whether the classification is finished in advance through an activation function, so as to achieve the purpose of shortening the classification time.
The invention adopts a convolutional neural network rapid classification method based on a plurality of classifiers to improve the structure of the convolutional neural network; the convolutional neural network comprises an input layer, a plurality of convolutional layers, a full-link layer and a classification output layer, wherein the convolutional layers are respectively provided with a pooling layer. The invention comprises a network training method and a network classification method, wherein the network training method of the embodiment needs to determine the number of additional classifiers and train all the classifiers.
Preferably, the multi-classifier convolutional neural network (CNN-MC) of the present invention is improved over the standard Convolutional Neural Network (CNN); when constructing the CNN-MC, a standard convolutional neural network is first constructed, the convolutional neural network includes an input layer, a plurality of convolutional layers and a fully-connected layer, a pooling layer is arranged behind each convolutional layer, and a classifier is arranged behind the fully-connected layer.
After a CNN (convolutional neural network) is trained, a classifier and an activation module for judging a classification result are added behind a first convolutional layer; then, training the classifier by using Dtrain, and collecting the average time required by a single sample to pass through the classifier and an activation module; and finally, adjusting parameters of the activation module to enable the overall classification accuracy of the network to reach the highest.
The invention relates to an environment image acquisition module, which is used for identifying roads and non-road objects in an environment image acquired by the environment acquisition module, calculating the positions of the non-road objects on the roads in a processing environment such as OPENGL and the like of the image, obtaining the distance between the non-road objects and the boundaries of the roads and taking the distance as a value for comparing the distance with the size of a vehicle body.
The vehicle appearance early warning system judges whether the vehicle has collision risk in the driving process according to the obtained comparison result information of the sizes in the three directions and the distance value of the remaining space of the obstacle, if so, the vehicle appearance early warning system reminds a driver and passengers in the vehicle, and the reminding mode can be reminded by a vehicle-mounted human-computer interaction interface or voice.
The technical effects adopted in the method are verified and explained, and the method selects an anti-collision early warning method based on machine vision, an ultrasonic automobile anti-collision early warning method and the method to carry out comparison test, compares test results by means of scientific demonstration, and verifies the real effect of the method.
The anti-collision early warning method based on machine vision is restricted by software and hardware conditions, the imaging speed is slow, and the detection is unstable in severe weather; the application of the ultrasonic automobile anti-collision early warning method to automobiles running at high speed has certain limitation, is easily influenced by weather, and has long measuring time; neither method can determine whether the vehicle body shape has changed.
In order to verify that the method has higher measurement precision and prediction accuracy compared with the machine vision-based anti-collision early warning method and the ultrasonic automobile anti-collision early warning method, the machine vision-based anti-collision early warning method, the ultrasonic automobile anti-collision early warning method and the method are adopted to respectively perform real-time measurement comparison on three same vehicles.
And (3) testing environment: a cuboid obstacle with the size of 100cm x 70cm x 80cm is placed on a test road, three test vehicles run on the test road at the running speed of 20km/h, the anti-collision early warning method based on machine vision, the ultrasonic vehicle anti-collision early warning method and the method are respectively adopted for measurement in the daytime and at night, corresponding measurement results are recorded, and the results are shown in the following table.
Table 1: and (5) comparing collision avoidance measurement results.
As can be seen from the table 1, the detection effect of the method is superior to that of a machine vision-based anti-collision early warning method and an ultrasonic automobile anti-collision early warning method, the vehicle distance monitoring value in the table is the horizontal distance between a test vehicle and a cuboid obstacle, the monitoring value of the method and the machine vision-based anti-collision early warning method meet the requirements for the daytime measurement result by referring to the dynamic standard value (20m) of the safe vehicle distance, only the method meets the requirements for the night measurement result, and the time for finding the cuboid obstacle is short.
In order to verify that the method has a better classification effect compared with the existing CNN classification method, in this embodiment, the existing CNN classifier and the method are adopted to perform classification, identification and comparison on 25 stationary obstacles and 25 moving obstacles respectively.
And (3) operating environment: a CPU: 2.3 GHz; memory: 8 GB; and OS: win 1064 bit; program compiling is carried out in Python3.5, and the training parameters of the method are executed in a Keras framework; the classification results are shown in the following table.
Table 2: and respectively adopting the existing CNN classifier and the method to compare the identification results of the obstacles.
| Recognition rate (static obstacle) | Recognition rate (moving obstacle) | Total time of identification | |
| Existing CNN classifier | 92％ | 80％ | 51.7s |
| Method for producing a |
100％ | 96％ | 35.6s |
As can be seen from the above table, the classification effect of the CNN-based improved multi-classifier convolutional neural network (CNN-MC) is superior to that of the existing CNN classifier.
Example 2
The embodiment provides a system for calculating the appearance dimension of a vehicle body.A vehicle body appearance calculating system 100 comprises a dimension collecting module 101 arranged outside the vehicle body and used for collecting the actual dimension information of the vehicle. The lane remote detection system 200 includes an environment collection module 201 disposed on the vehicle for collecting environment information on a road where the vehicle is located. The vehicle contour early warning system 300 compares the received vehicle contour dimension information with the obstacle information in the environmental information, determines the collision risk of the vehicle, and gives an alarm.
Specifically, the vehicle body outline calculation system 100 in this embodiment includes a size acquisition module 101, a size processing module 102, and a size recognition module 103, where the size acquisition module 101 includes cameras disposed at multiple positions of a vehicle body, and acquires image information of each part of the vehicle body in real time during driving, and the size processing module 102 processes the acquired image information into an image easy to recognize, and then calculates by the size recognition module 103 to obtain an actual size of the vehicle body
The size acquisition module 101 in this embodiment is a CCD camera disposed outside the vehicle, and sends the shooting result to the size processing module 102 in a data manner for processing. The size processing module 102 and the size recognition module 103 are integrated on the same single chip, and the same processor is responsible for executing operation. The size acquisition device can comprise a plurality of CCD cameras for acquiring environment pictures in different directions. The cameras in this embodiment are located outside the wheel frame, on the roof and on the front and rear windshields.
The lane remote detection system 200 in this embodiment includes an environment acquisition module 201, an environment processing module 202, and an environment recognition module 203, where the environment acquisition module 201 includes a camera disposed in front of or behind the vehicle body, and acquires image information of a certain distance in front of the vehicle in real time during driving, and the environment processing module 202 processes the acquired image information into an image easy to recognize, and then the environment recognition module 203 performs calculation to obtain obstacle information on the road in front of or behind the vehicle body.
The vehicle appearance early warning system 300 comprises a central processing unit 301, a receiving end, a transmitting end and a storage, wherein the receiving end and the transmitting end are connected with the vehicle appearance calculation system 100 and the lane remote detection system 200. The receiving end and the sending end can be PCI-E, SATA, I/O, AUX and other types. The judgment results obtained after the information sent by the vehicle body shape calculation system 100 and the lane remote detection system 200 is processed by the central processor 301 are used for judging the collision risk. The main control module is specifically positioned on the traveling computer ECU and is powered by the vehicle-mounted power supply. The memory is a vehicle-mounted hard disk and a random access memory and is used for storing the driving control system data and the temporary data respectively.
In order to simplify the system of the present embodiment, the vehicle body shape calculating system 100 of the present embodiment is integrated on the central processing unit 301 of the main control system and is located on the vehicle computer ECU, except for the size collecting module 101 and the environment collecting module 201 of the lane remote detecting system 200.
Alternatively, in order to achieve faster processing speed of the body contour calculation system 100 and the lane remote detection system 200 in this embodiment, the image processing module and the image recognition module in this embodiment may be implemented by graphic processing, and the graphic processor and the central processing unit 301 are located in the vehicle computer ECU.
Example 3
Based on the calculation method and system of the external dimensions of the vehicle body proposed in the embodiment 1 and the embodiment 2, as shown in fig. 3, the following workflow is given:
step 1: the vehicle body shape calculation module identifies the change of the vehicle body shape through vision. If yes, step 2 is executed, otherwise, step 1 is continuously executed.
Step 2: and the body outline calculation module updates the outline dimension. Step 3 is performed.
And step 3: and the vehicle body appearance calculation module sends the newly calculated vehicle body dimension to the vehicle appearance early warning module, and step 7 is executed. The body contour calculation module continues to jump back to step 1.
And 4, step 4: and the lane remote detection module is used for judging whether a high-risk collision object exists in front of the road, if so, executing the step 5, and if not, continuing to execute the step 4.
And 5: the size of the collision and the distance of the collided object to the vehicle are calculated. Step 6 is performed.
Step 6: and sending a message to the vehicle appearance early warning module, and executing the step 9. The vehicle remote detection module continues to jump back to step 4.
And 7: the vehicle appearance early warning module judges whether the information of the vehicle body appearance calculation module is received. If yes, go to step 8. Otherwise, go to step 9.
And 8: and updating the overall dimension of the vehicle body, and setting a recalculation mark position for recalculating the collision risk later. Execution continues with step 9.
And step 9: the vehicle appearance early warning module judges whether the message of the vehicle remote detection module is received. If yes, step 10 is performed. Otherwise, go to step 11.
Step 10: and updating the size and the distance of the collision object and setting a recalculation flag bit. Execution continues at step 11.
Step 11: whether to recalculate the collision risk. Yes, step 12 is performed. Otherwise, go back to step 7.
Step 12: and judging whether collision happens or not through calculation. Step 13 is performed. And not, jumping back to step 7.
Step 13: reminding to notice collision. Jump back to step 7.
It is important to note that the construction and arrangement of the present application as shown in the various exemplary embodiments is illustrative only. Although only a few embodiments have been described in detail in this disclosure, those skilled in the art who review this disclosure will readily appreciate that many modifications are possible (e.g., variations in sizes, dimensions, structures, shapes and proportions of the various elements, values of parameters (e.g., temperatures, pressures, etc.), mounting arrangements, use of materials, colors, orientations, etc.) without materially departing from the novel teachings and advantages of the subject matter recited in this application. For example, elements shown as integrally formed may be constructed of multiple parts or elements, the position of elements may be reversed or otherwise varied, and the nature or number of discrete elements or positions may be altered or varied. Accordingly, all such modifications are intended to be included within the scope of this invention. The order or sequence of any process or method steps may be varied or re-sequenced according to alternative embodiments. In the claims, any means-plus-function clause is intended to cover the structures described herein as performing the recited function and not only structural equivalents but also equivalent structures. Other substitutions, modifications, changes and omissions may be made in the design, operating conditions and arrangement of the exemplary embodiments without departing from the scope of the present inventions. Therefore, the present invention is not limited to a particular embodiment, but extends to various modifications that nevertheless fall within the scope of the appended claims.
Moreover, in an effort to provide a concise description of the exemplary embodiments, all features of an actual implementation may not be described (i.e., those unrelated to the presently contemplated best mode of carrying out the invention, or those unrelated to enabling the invention).
It should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort might be complex and time consuming, but would nevertheless be a routine undertaking of design, fabrication, and manufacture for those of ordinary skill having the benefit of this disclosure, without undue experimentation.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (10)
1. A method for calculating the appearance size of a vehicle body is characterized by comprising the following steps: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
detecting the shape of a vehicle body, detecting size information of the vehicle body by a vehicle body shape calculating system (100), and sending the size information to a vehicle shape early warning system (300);
detecting a lane scene, and acquiring image information of a lane in front of an automobile through a lane remote detection system (200) to acquire position information of a road obstacle;
and calculating the collision risk, comparing the size information with the road obstacle information by the vehicle appearance early warning system (300), and sending a prompt if the collision risk exists.
2. The method of calculating the apparent size of a vehicle body according to claim 1, characterized in that: the size information of the vehicle body is acquired by a size acquisition module (101) in the vehicle body outline calculation system (100).
3. The method of calculating the apparent size of a vehicle body according to claim 2, characterized in that: the vehicle appearance early warning system is characterized in that the size acquisition module (101) sends acquired vehicle body image information to the vehicle appearance early warning module, and the vehicle appearance early warning system (300) compares the vehicle body image information with a preset vehicle body image to judge whether the vehicle body appearance changes.
4. The method of calculating the apparent size of a vehicle body according to claim 2 or 3, characterized in that: the dimension acquisition module (101) acquires a length dimension, a width dimension, and a height dimension of the vehicle, and takes an outermost edge of the acquired image as the dimension boundary.
5. The method of calculating the apparent size of a vehicle body according to any one of claims 1, 2, and 3, wherein: an environment acquisition module (201) in the lane remote detection system (200) acquires environment image information of a lane in front of a vehicle and sends the environment information of the lane to the vehicle appearance early warning system (300).
6. The method of calculating the apparent size of a vehicle body according to claim 5, characterized in that: and according to the acquired environment image information of the lane, carrying out obstacle recognition through an image recognition technology, and storing the recognized obstacle shape information into a database.
7. The method of calculating the apparent size of a vehicle body according to claim 6, characterized in that: the obstacles are divided into static obstacles and moving obstacles, and the static obstacles and the moving obstacles are classified and identified respectively to form corresponding classifiers.
8. The method of calculating the apparent size of a vehicle body according to claim 7, characterized in that: the step of recognizing the obstacle image and the lane image according to the acquired vehicle image information comprises the following steps:
extracting the obstacle image and the lane image by a target detection algorithm;
and classifying and identifying the extracted obstacle image and the classifier of the lane to obtain the category and size information of the obstacle.
9. A system for calculating the apparent dimensions of a vehicle body, characterized by: comprises that
The vehicle body appearance calculation system (100) comprises a size acquisition module (101) arranged outside the vehicle body and used for acquiring the actual size information of the vehicle;
the lane remote detection system (200) comprises an environment acquisition module (201) arranged on a vehicle and used for acquiring environment information on a road where the vehicle is located;
and the vehicle appearance early warning system (300) compares the received vehicle body appearance size information with the obstacle information in the environment information, judges the collision risk of the vehicle and gives an alarm.
10. The system for calculating the apparent dimension of a vehicle body according to claim 9, wherein: the size acquisition module (101) comprises a width detection camera, a height detection camera and a length detection camera which are arranged outside the vehicle, and the width detection camera, the height detection camera and the length detection camera are respectively arranged outside a wheel frame, on the roof and on front and rear windshields of the vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110876165.5A CN113701642A (en) | 2021-07-30 | 2021-07-30 | Method and system for calculating appearance size of vehicle body |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110876165.5A CN113701642A (en) | 2021-07-30 | 2021-07-30 | Method and system for calculating appearance size of vehicle body |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113701642A true CN113701642A (en) | 2021-11-26 |
Family
ID=78651035
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110876165.5A Pending CN113701642A (en) | 2021-07-30 | 2021-07-30 | Method and system for calculating appearance size of vehicle body |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113701642A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114863083A (en) * | 2022-04-06 | 2022-08-05 | 包头钢铁（集团）有限责任公司 | Method and system for positioning vehicle and measuring size |
| CN117553695A (en) * | 2024-01-11 | 2024-02-13 | 摩斯智联科技有限公司 | Method, apparatus and computer storage medium for calculating vehicle height based on aspect ratio suppression noise |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008249517A (en) * | 2007-03-30 | 2008-10-16 | Honda Motor Co Ltd | Obstacle detector |
| CN102542843A (en) * | 2010-12-07 | 2012-07-04 | 比亚迪股份有限公司 | Early warning method for preventing vehicle collision and device |
| US20140347485A1 (en) * | 2013-05-23 | 2014-11-27 | GM Global Technology Operations LLC | Enhanced front curb viewing system |
| CN105869438A (en) * | 2016-04-12 | 2016-08-17 | 深圳市中天安驰有限责任公司 | Vehicular anti-collision early-warning system |
| CN106599832A (en) * | 2016-12-09 | 2017-04-26 | 重庆邮电大学 | Method for detecting and recognizing various types of obstacles based on convolution neural network |
| CN107914713A (en) * | 2016-10-05 | 2018-04-17 | Lg电子株式会社 | Display apparatus and the vehicle for including it |
| US20200241549A1 (en) * | 2017-10-12 | 2020-07-30 | Sony Corporation | Information processing apparatus, moving apparatus, and method, and program |
-
2021
- 2021-07-30 CN CN202110876165.5A patent/CN113701642A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008249517A (en) * | 2007-03-30 | 2008-10-16 | Honda Motor Co Ltd | Obstacle detector |
| CN102542843A (en) * | 2010-12-07 | 2012-07-04 | 比亚迪股份有限公司 | Early warning method for preventing vehicle collision and device |
| US20140347485A1 (en) * | 2013-05-23 | 2014-11-27 | GM Global Technology Operations LLC | Enhanced front curb viewing system |
| CN105869438A (en) * | 2016-04-12 | 2016-08-17 | 深圳市中天安驰有限责任公司 | Vehicular anti-collision early-warning system |
| CN107914713A (en) * | 2016-10-05 | 2018-04-17 | Lg电子株式会社 | Display apparatus and the vehicle for including it |
| CN106599832A (en) * | 2016-12-09 | 2017-04-26 | 重庆邮电大学 | Method for detecting and recognizing various types of obstacles based on convolution neural network |
| US20200241549A1 (en) * | 2017-10-12 | 2020-07-30 | Sony Corporation | Information processing apparatus, moving apparatus, and method, and program |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114863083A (en) * | 2022-04-06 | 2022-08-05 | 包头钢铁（集团）有限责任公司 | Method and system for positioning vehicle and measuring size |
| CN117553695A (en) * | 2024-01-11 | 2024-02-13 | 摩斯智联科技有限公司 | Method, apparatus and computer storage medium for calculating vehicle height based on aspect ratio suppression noise |
| CN117553695B (en) * | 2024-01-11 | 2024-05-03 | 摩斯智联科技有限公司 | Method and device for calculating vehicle height and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829403B (en) | Vehicle anti-collision early warning method and system based on deep learning | |
| JP7090105B2 (en) | Classification of rare cases | |
| CN111667512B (en) | Multi-target vehicle track prediction method based on improved Kalman filtering | |
| CN100440269C (en) | Intelligent detecting prewarning method for expressway automobile running and prewaring system thereof | |
| CN103984950B (en) | A kind of moving vehicle brake light status recognition methods for adapting to detection on daytime | |
| CN103914688A (en) | Urban road obstacle recognition system | |
| CN111242015A (en) | Method for predicting driving danger scene based on motion contour semantic graph | |
| CN113701642A (en) | Method and system for calculating appearance size of vehicle body | |
| CN111626170B (en) | Image recognition method for railway side slope falling stone intrusion detection | |
| CN107909012B (en) | Real-time vehicle tracking detection method and device based on disparity map | |
| CN111860274A (en) | Traffic police command gesture recognition method based on head orientation and upper half body skeleton characteristics | |
| CN109858456B (en) | Railway vehicle state fault analysis system | |
| CN112651441B (en) | Fine-grained non-motor vehicle feature detection method, storage medium and computer equipment | |
| CN106845458B (en) | Rapid traffic sign detection method based on nuclear overrun learning machine | |
| KR102619326B1 (en) | Apparatus and Method for Detecting Vehicle using Image Pyramid | |
| CN103927548A (en) | Novel vehicle collision avoiding brake behavior detection method | |
| CN112666573B (en) | Detection method for retaining wall and barrier behind mine unloading area vehicle | |
| CN103295003A (en) | Vehicle detection method based on multi-feature fusion | |
| Álvarez et al. | Perception advances in outdoor vehicle detection for automatic cruise control | |
| CN116587978A (en) | Collision early warning method and system based on vehicle-mounted display screen | |
| CN116110230A (en) | Vehicle lane crossing line identification method and system based on vehicle-mounted camera | |
| Ab Ghani et al. | Lane detection using deep learning for rainy conditions | |
| CN110414357B (en) | Front vehicle positioning method based on vehicle type identification | |
| CN114758326A (en) | Real-time traffic post working behavior state detection system | |
| CN112949595A (en) | Improved pedestrian and vehicle safety distance detection algorithm based on YOLOv5 |
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 |