CN111339923A - Vehicle bottom inspection method and system - Google Patents
Vehicle bottom inspection method and system Download PDFInfo
- Publication number
- CN111339923A CN111339923A CN202010114171.2A CN202010114171A CN111339923A CN 111339923 A CN111339923 A CN 111339923A CN 202010114171 A CN202010114171 A CN 202010114171A CN 111339923 A CN111339923 A CN 111339923A
- Authority
- CN
- China
- Prior art keywords
- vehicle bottom
- vehicle
- image
- processing system
- ground
- 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 37
- 238000007689 inspection Methods 0.000 title claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 51
- 238000012544 monitoring process Methods 0.000 claims abstract description 35
- 238000001514 detection method Methods 0.000 claims abstract description 31
- 238000013135 deep learning Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 16
- 230000001502 supplementing effect Effects 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 16
- 230000035807 sensation Effects 0.000 claims description 14
- 239000013589 supplement Substances 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000005286 illumination Methods 0.000 description 8
- 239000000243 solution Substances 0.000 description 6
- 239000011521 glass Substances 0.000 description 5
- 230000001939 inductive effect Effects 0.000 description 5
- 238000002834 transmittance Methods 0.000 description 5
- 230000006698 induction Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000002347 injection Methods 0.000 description 2
- 239000007924 injection Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a vehicle bottom inspection method and a vehicle bottom inspection system. The method comprises the following steps: detecting a vehicle through a ground sensing detection assembly; when a vehicle passes through, acquiring a vehicle bottom image through the vehicle bottom image acquisition assembly; and monitoring and analyzing the acquired image through a processing system, and judging whether the image has a suspected person collection event or not. The embodiment of the invention collects the vehicle bottom image, analyzes the image, detects whether suspected hidden people and/or hidden object events occur, is suitable for places such as customs and frontier inspection, and improves the safety inspection efficiency.
Description
Technical Field
The invention relates to the technical field of vehicle monitoring, in particular to a vehicle bottom inspection method and a vehicle bottom inspection system.
Background
Most of the inspection work of the existing vehicle bottom analysis scanning system adopts a mode of manual visual inspection or a mode of display interface inspection by using a video monitoring camera, and even a part of the inspection work adopts a large-scale X-ray machine technology for scanning.
The manual checking mode and the mode of adopting the video monitoring camera occupy human resources, and the vehicle is required to stop, so that the vehicle passing time is increased, the detection time is too long, the efficiency is low, and the later-stage follow-up is inconvenient.
The X-ray machine investigation technology has certain harm to personnel in the vehicle, occupies a large area, and only can see a side view and cannot see a bottom view.
Disclosure of Invention
The embodiment of the invention aims to provide a vehicle bottom inspection method and a vehicle bottom inspection system, which are used for dynamically scanning the vehicle bottom in real time, identifying and analyzing the scanned image and judging whether hidden people or hidden objects exist at the vehicle bottom.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows.
In a first aspect, a vehicle bottom inspection method is provided, which includes:
s11: detecting a vehicle through a ground sensing detection assembly;
s12: when a vehicle passes through, acquiring a vehicle bottom image through the vehicle bottom image acquisition assembly;
s13: monitoring and analyzing the acquired image through a processing system, and judging whether the image has a suspected collection event;
the processing system comprises a vehicle bottom monitoring and analyzing terminal, and the vehicle bottom monitoring and analyzing terminal is communicated with the vehicle bottom image acquisition assembly and the ground sensation detection assembly.
Further, the ground feeling detection assembly includes a first ground feeling and a second ground feeling provided at different positions in a vehicle advancing direction; the method further comprises the following steps:
detecting whether the vehicle reaches the first position through the first ground sense and detecting whether the vehicle reaches the second position through the second ground sense;
the processing system calculates the speed of the vehicle by recording the time when the vehicle respectively reaches the first position and the second position;
when the vehicle reaches the second position, the vehicle bottom light supplementing device is started to supplement light, and the vehicle bottom image acquisition assembly is started to acquire images;
when the vehicle leaves the second position, the vehicle bottom light supplementing device finishes light supplementing, and the vehicle bottom image acquisition assembly finishes image acquisition.
Further, the method further comprises:
the processing system superimposes date and/or time information on the acquired images;
and/or the processing system uploads the acquired image to a rear inspection system;
and/or the processing system carries out local or whole zooming processing on the acquired image;
and/or the processing system exports the captured image in a common file format.
Further, the processing system further includes a back-end server, a display terminal and a storage device, and the method further includes: and the vehicle bottom monitoring and analyzing terminal sends the processed image information to the display terminal, the rear-end server and/or the storage device.
Further, step S13 specifically includes: transmitting the images collected in real time into a deep learning network, and detecting and analyzing whether people hide or not; and if the suspected person collection event occurs, warning and sending a notice.
Further, the method further comprises: collecting a large number of images of the vehicle bottom collection object in advance, marking the images and making the images into a training set of a detection algorithm; training a network structure of a deep learning network by using the training set; determining a proper loss function and training network weight; and loading the network weight in the deep learning network.
Furthermore, the deep learning network takes MobileNet as a backbone network.
Further, the loss function combines the target category and the target location information, and the formula is as follows:
wherein x is a real category, c is a prediction confidence, L is a prediction box, g is a real box, N is a predicted target number, and LconfFor confidence loss, LlocTo locate the loss, α represents the weight.
The second aspect provides a vehicle bottom monitored control system, its characterized in that includes:
the system comprises a processing system and vehicle bottom hardware, wherein the vehicle bottom hardware comprises a vehicle bottom image acquisition assembly and a ground sensation detection assembly, and the processing system comprises a vehicle bottom monitoring and analyzing terminal;
the ground sense detection assembly is used for detecting a vehicle;
the vehicle bottom image acquisition assembly is used for acquiring a vehicle bottom image when a vehicle passes through and transmitting the acquired image to the processing system;
the processing system is used for monitoring and analyzing the acquired image and judging whether the suspected person collection event occurs in the image.
Furthermore, the processing system further comprises a rear-end server, a display terminal and a storage device, wherein the vehicle bottom monitoring and analyzing terminal is respectively connected with the rear-end server, the display terminal and the storage device.
According to the technical scheme, the embodiment of the invention has the following advantages:
by collecting the vehicle bottom image, the image is analyzed to detect whether a suspected hidden person and/or hidden object event occurs, and the method is suitable for places such as customs, frontier inspection and the like; compared with the modes of manually checking and looking up the display interface of the video monitoring camera and the like, the safety inspection efficiency is greatly improved, the labor is saved, the vehicle does not need to stop, and the passing efficiency is higher; compared with an X-ray machine mode, the vehicle bottom can be checked, the vehicle bottom checking device is safer, and the occupied area is reduced.
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 are 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 creative efforts.
FIG. 1 is a schematic structural diagram of a vehicle bottom monitoring system according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a MobileNet-SSD network architecture in an embodiment of the present invention;
fig. 3 is a schematic flow chart of a vehicle bottom inspection method according to an embodiment of the invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," "third," and the like in the description and in the claims, and in the above-described drawings, are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
The following are detailed descriptions of the respective embodiments.
Referring to fig. 1, an embodiment of the present invention provides a vehicle bottom monitoring system.
The system can comprise vehicle bottom hardware and a processing system, wherein the vehicle bottom hardware can comprise a vehicle bottom image acquisition assembly 11, a ground sensation detection assembly 12, a vehicle bottom light supplement device 13, and optionally a temperature and humidity detection device 14 and a glass transmittance detection device 15; the processing system can comprise a vehicle bottom monitoring and analyzing terminal 21 arranged at the front end, a rear end server 22 arranged at the rear end, a display terminal 23, a storage device 24 and the like.
In the processing system, the vehicle bottom monitoring and analyzing terminal 21 can be respectively connected with the rear-end server 22, the display terminal 23 and the storage device 24; the processing system can be in direct communication connection with the vehicle bottom image acquisition assembly 11, and can be in communication connection with the ground sensation detection assembly 12, the vehicle bottom light supplementing device 13, the temperature and humidity detection device 14 and the glass transmittance detection device 15 through the vehicle bottom hardware control device 10.
Wherein, the vehicle bottom image acquisition assembly 11 can comprise a vehicle bottom dynamic camera for acquiring images. The ground feel detecting assembly 12 may include a first ground feel and a second ground feel disposed at different positions in the vehicle forward direction. The vehicle bottom light supplement device 13 may include a light source for illumination. The temperature and humidity sensing device 14 may include a temperature and humidity meter. The glass transmittance detection device 15 may include a transmittance meter. The vehicle bottom hardware control device 10 may include, for example, an inductive lighting control component for controlling a vehicle bottom light supplement device, a switch for controlling a light source to be turned on or off, and the like.
Wherein, the processing system can be connected with the limit inspection system, the customs system and the like through a network.
Optionally, the system of the present invention further includes a dehumidifying and dehumidifying device, and the temperature and humidity detecting device may be configured to start the dehumidifying and dehumidifying device when detecting that the humidity or the temperature is too high.
Optionally, the system of the present invention further comprises an air injection device, and the glass transmittance detection device may be configured to start the air injection device to clean the surface when the outer surface of the glass has soil or accumulated water.
As described above, the vehicle bottom monitoring system according to the embodiment of the present invention can provide the following functions.
(1) Automatic scanning
When a vehicle passes at the speed of (1-25) km/h, the vehicle bottom image acquisition assembly of the system can automatically scan and acquire the vehicle chassis image (vehicle bottom image for short) and can display a clear and complete vehicle bottom image through the display device. The vehicle bottom image can be a video image or a static image.
(2) Multi-angle snapshot function
The system can provide a multi-angle high-definition dynamic snapshot function, and image information can be accessed to a one-stop public information platform (background simulation systems such as a side inspection system and a customs system) to provide visual and reliable information for the inspection and the release of vehicles.
(3) Inductive lighting control
The system can be provided with an inductive illumination control assembly, and when a vehicle passes through, the inductive illumination control assembly can automatically induce and control the vehicle bottom light supplementing device to start the light source for illumination; when the vehicle leaves, the induction illumination control assembly can automatically induce and control the vehicle bottom light supplementing device to close the light source for illumination.
(4) Image overlay
The system can superpose date and time on the acquired vehicle bottom image; its image overlay function should be turned on or off.
(5) Automatic storage of images
The system can automatically store the acquired vehicle bottom images.
(6) Image scaling
The system software can carry out local or whole zooming processing on the acquired vehicle bottom image.
(7) Image derivation
The system can export the acquired vehicle bottom image in a universal file format.
(8) Angle of field of view
The vehicle bottom image acquisition assembly can adopt a wide-angle camera to acquire images so that the view field angle of the vehicle bottom images is larger.
(9) Vehicle bottom hidden person event alarm
When the system monitors that the suspected hidden object event of the hidden person occurs in the vehicle bottom image, the system gives an alarm and informs background personnel to process the corresponding event. Herein, the human hiding event refers to a human hiding event and/or a object hiding event, namely, a human hiding event, or an object hiding event, or an event of both human hiding and object hiding.
(10) License plate recognition
The system can have the license plate recognition function and automatically store the collected license plates.
The vehicle bottom monitoring system of the embodiment of the invention has the working process that: detecting a vehicle through a ground sensing detection assembly; when a vehicle passes through, acquiring a vehicle bottom image through the vehicle bottom image acquisition assembly, and transmitting the acquired image to a processing system, wherein the processing system comprises a vehicle bottom monitoring and analyzing terminal; the processing system monitors and analyzes the collected images, judges whether the images have suspected hidden events, and can give an alarm and send out a notice if the images have the suspected hidden events. The vehicle bottom monitoring and analyzing terminal can send the processed image information to the display terminal, the rear-end server and/or the storage device.
Optionally, in some embodiments, the vehicle bottom monitoring system of the present invention may acquire an image, for example, in the following manner: when a vehicle passes through, a plurality of images are collected through a vehicle bottom image collecting assembly, and the images respectively correspond to different areas of the bottom of the vehicle; the acquired images are spliced by the processing system to obtain a complete vehicle bottom image, and whether license plate information and/or driver information are/is superposed on the vehicle bottom image can be selected.
In an embodiment of a specific application scenario of the present invention, the ground sensation detection assembly may include two ground sensation detectors, i.e., a ground sensation 1 and a ground sensation 2, which are respectively disposed at different first positions and second positions in the forward direction of the vehicle. The ground sense detection assembly has the functions of: and triggering the speed measuring function, finishing the speed measuring function, starting the light supplement and closing the light supplement. The system workflow may specifically include the following.
[ first stage ] image scanning
When the vehicle passes through the ground sensor 1, the system starts a speed measuring system and starts to time t 1;
when the vehicle passes through the ground sensor 2, the system ends the speed measuring system, and the timing is t 2; meanwhile, a vehicle bottom light supplementing device is started; meanwhile, the vehicle bottom image acquisition assembly is started to scan images of the vehicle bottom;
at which point the passage of the vehicle can be calculatedAverage velocityWherein, S1 is the distance between the ground feel 1 and the ground feel 2, which is fixed during construction;
when the vehicle passes through the departure sense 2, the time is t 3;
the calculation of t4 is carried out,wherein, S2 is the distance between the ground sense 2 and the vehicle bottom image acquisition assembly, which is fixed during construction;
closing the vehicle bottom image acquisition assembly and the vehicle bottom image acquisition assembly at t4, and finishing the vehicle bottom image scanning;
meanwhile, license plate information and/or driver information can be acquired through external equipment such as license plate recognition equipment and face recognition equipment;
and carrying out subsequent work.
[ second stage ] image analysis
The processing system may run a detection algorithm to perform image analysis, and the algorithm flow may include:
collecting a large number of images of the vehicle bottom collection object in advance, marking the images and making the images into a training set of a detection algorithm;
training a network structure of a deep learning network by using the training set;
determining a proper loss function and training network weight;
loading network weights in the deep learning network;
and (4) transmitting the images acquired in real time into a deep learning network, and detecting and analyzing whether the human deposits are hidden or not.
In the detection algorithm, the deep learning network can take the MobileNet as a backbone network and then the SSD outputs the target type and position information in consideration of the performance of the embedded device. The MobileNet-SSD network structure is shown in fig. 2.
Wherein the loss function combines the target class and the target location information, and the formula is as follows:
wherein x is a real category, c is a prediction confidence, L is a prediction box, g is a real box, N is a predicted target number, and LconfFor confidence loss, LlocTo locate the loss, α represents the weight.
Referring to fig. 3, an embodiment of the present invention further provides a vehicle bottom inspection method, which is implemented by the vehicle bottom monitoring system. The method may comprise the steps of:
s11: detecting a vehicle through a ground sensing detection assembly;
s12: when a vehicle passes through, light is supplemented through the vehicle bottom light supplementing device, a vehicle bottom image is collected through the vehicle bottom image collecting assembly, and the collected image is transmitted to the processing system;
s13: monitoring and analyzing the collected image through a processing system, judging whether the image has a suspected person collection event, and if so, alarming and sending a notice;
the processing system comprises a vehicle bottom monitoring and analyzing terminal, and the vehicle bottom monitoring and analyzing terminal is communicated with the vehicle bottom image acquisition assembly, the ground sensation detection assembly and the vehicle bottom light supplementing device.
In some embodiments, further, the ground sensation detecting assembly includes a first ground sensation and a second ground sensation disposed at different positions in a vehicle forward direction; the method further comprises the following steps:
detecting whether the vehicle reaches the first position through the first ground sense and detecting whether the vehicle reaches the second position through the second ground sense;
the processing system calculates the speed of the vehicle by recording the time when the vehicle respectively reaches the first position and the second position;
when the vehicle reaches the second position, the vehicle bottom light supplementing device is started to supplement light, and the vehicle bottom image acquisition assembly is started to acquire images;
when the vehicle leaves the second position, the vehicle bottom light supplementing device finishes light supplementing, and the vehicle bottom image acquisition assembly finishes image acquisition.
In some embodiments, the vehicle bottom monitoring and analyzing terminal is connected to the ground sensing detection assembly and the vehicle bottom light supplement device through a vehicle bottom hardware control device, the vehicle bottom hardware control device includes an inductive lighting control assembly, and the method further includes:
when the vehicle passes through, the induction illumination control assembly automatically induces and controls the vehicle bottom light supplement device to start the light source for illumination;
when the vehicle leaves, the induction lighting control assembly automatically induces and controls the vehicle bottom light supplementing device to close the light source for lighting.
In some embodiments, further, the method further comprises:
the processing system stores the acquired images;
and/or, the processing system superimposes date and/or time information for the acquired images;
and/or the processing system uploads the acquired image to a rear inspection system;
and/or the processing system carries out local or whole zooming processing on the acquired image;
and/or the processing system exports the captured image in a common file format.
In some embodiments, the processing system further comprises a back-end server, a display terminal, and a storage device, and the method further comprises: and the vehicle bottom monitoring and analyzing terminal sends the processed image information to the display terminal, the rear-end server and/or the storage device.
In some embodiments, step S13 specifically includes: transmitting the images collected in real time into a deep learning network, and detecting and analyzing whether people hide or not; and if the suspected person collection event occurs, warning and sending a notice.
In some embodiments, further, the method further comprises: collecting a large number of images of the vehicle bottom collection object in advance, marking the images and making the images into a training set of a detection algorithm; training a network structure of a deep learning network by using the training set; determining a proper loss function and training network weight; and loading the network weight in the deep learning network.
In some embodiments, further, the deep learning network uses MobileNet as a backbone network.
In some embodiments, further, the loss function combines the object class and the object location information, and the formula is as follows:
where x is the true category, c is the prediction confidence, l is the prediction box, g is the true box, N is the predicted target number, Lconf is the confidence loss, Lloc is the positioning loss, α represents the weight.
In summary, the embodiment of the invention discloses a vehicle bottom inspection method and a vehicle bottom inspection system, which are used for analyzing images by acquiring vehicle bottom images and detecting whether suspected hidden people and/or hidden object events occur or not, and are suitable for customs, frontier inspection and other places; compared with the modes of manually checking and looking up the display interface of the video monitoring camera and the like, the safety inspection efficiency is greatly improved, the labor is saved, the vehicle does not need to stop, and the passing efficiency is higher; compared with an X-ray machine mode, the vehicle bottom can be checked, the vehicle bottom checking device is safer, and the occupied area is reduced.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to the related descriptions of other embodiments.
The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; those of ordinary skill in the art will understand that: the technical solutions described in the above embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A vehicle bottom inspection method is characterized by comprising the following steps:
s11: detecting a vehicle through a ground sensing detection assembly;
s12: when a vehicle passes through, acquiring a vehicle bottom image through the vehicle bottom image acquisition assembly;
s13: monitoring and analyzing the acquired image through a processing system, and judging whether the image has a suspected collection event;
the processing system comprises a vehicle bottom monitoring and analyzing terminal, and the vehicle bottom monitoring and analyzing terminal is communicated with the vehicle bottom image acquisition assembly and the ground sensation detection assembly.
2. The method of claim 1, wherein the ground-feel detecting assembly includes a first ground feel and a second ground feel disposed at different locations in a vehicle forward direction;
the method further comprises the following steps:
detecting whether the vehicle reaches the first position through the first ground sense and detecting whether the vehicle reaches the second position through the second ground sense;
the processing system calculates the speed of the vehicle by recording the time when the vehicle respectively reaches the first position and the second position;
when the vehicle reaches the second position, the vehicle bottom light supplementing device is started to supplement light, and the vehicle bottom image acquisition assembly is started to acquire images;
when the vehicle leaves the second position, the vehicle bottom light supplementing device finishes light supplementing, and the vehicle bottom image acquisition assembly finishes image acquisition.
3. The method of claim 1, further comprising:
the processing system superimposes date and/or time information on the acquired images;
and/or the processing system uploads the acquired image to a rear inspection system;
and/or the processing system carries out local or whole zooming processing on the acquired image;
and/or the processing system exports the captured image in a common file format.
4. The method of claim 1, wherein the processing system further comprises a backend server, a display terminal, and a storage device, the method further comprising:
and the vehicle bottom monitoring and analyzing terminal sends the processed image information to the display terminal, the rear-end server and/or the storage device.
5. The method according to any one of claims 1 to 4, wherein step S13 specifically comprises:
transmitting the images collected in real time into a deep learning network, and detecting and analyzing whether people hide or not;
and if the suspected person collection event occurs, warning and sending a notice.
6. The method of claim 5, further comprising:
collecting a large number of images of the vehicle bottom collection object in advance, marking the images and making the images into a training set of a detection algorithm;
training a network structure of a deep learning network by using the training set;
determining a proper loss function and training network weight;
and loading the network weight in the deep learning network.
7. The method of claim 6,
the deep learning network takes MobileNet as a backbone network.
8. The method of claim 6,
the loss function combines the target class and target location information, and the formula is as follows:
wherein x is a real category, c is a prediction confidence, L is a prediction box, g is a real box, N is a predicted target number, and LconfTo be arranged atLoss of signal, LlocTo locate the loss, α represents the weight.
9. The utility model provides a vehicle bottom monitored control system which characterized in that includes:
the system comprises a processing system and vehicle bottom hardware, wherein the vehicle bottom hardware comprises a vehicle bottom image acquisition assembly and a ground sensation detection assembly, and the processing system comprises a vehicle bottom monitoring and analyzing terminal;
the ground sense detection assembly is used for detecting a vehicle;
the vehicle bottom image acquisition assembly is used for acquiring a vehicle bottom image when a vehicle passes through and transmitting the acquired image to the processing system;
the processing system is used for monitoring and analyzing the acquired image and judging whether the suspected person collection event occurs in the image.
10. The system of claim 9,
the processing system further comprises a rear-end server, a display terminal and a storage device, and the vehicle bottom monitoring and analyzing terminal is connected with the rear-end server, the display terminal and the storage device respectively.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010114171.2A CN111339923A (en) | 2020-02-25 | 2020-02-25 | Vehicle bottom inspection method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010114171.2A CN111339923A (en) | 2020-02-25 | 2020-02-25 | Vehicle bottom inspection method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111339923A true CN111339923A (en) | 2020-06-26 |
Family
ID=71185496
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010114171.2A Pending CN111339923A (en) | 2020-02-25 | 2020-02-25 | Vehicle bottom inspection method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111339923A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112070006A (en) * | 2020-09-08 | 2020-12-11 | 哈尔滨市科佳通用机电股份有限公司 | Side inspection system and side inspection method for road vehicles |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102637033A (en) * | 2012-04-28 | 2012-08-15 | 成都西物信安智能系统有限公司 | Control system for safety inspection of vehicle bottom |
CN202548640U (en) * | 2012-04-28 | 2012-11-21 | 成都西物信安智能系统有限公司 | Control system for safety inspection on underbody of track traffic vehicle |
CN202632095U (en) * | 2012-04-28 | 2012-12-26 | 成都西物信安智能系统有限公司 | Control system for safety inspection of vehicle bottom |
CN202631757U (en) * | 2012-04-28 | 2012-12-26 | 成都西物信安智能系统有限公司 | Control system for multiple-lane safety inspection of vehicle chassis |
US20190084481A1 (en) * | 2017-09-21 | 2019-03-21 | Ford Global Technologies, Llc | Adjustment of vehicle rearview mirror displays |
CN109858486A (en) * | 2019-01-27 | 2019-06-07 | 中国人民解放军国防科技大学 | Deep learning-based data center cloud target identification method |
CN110472503A (en) * | 2019-07-11 | 2019-11-19 | 桂林电子科技大学 | A kind of road target detection method, device and storage medium |
CN110832596A (en) * | 2017-10-16 | 2020-02-21 | 因美纳有限公司 | Deep convolutional neural network training method based on deep learning |
-
2020
- 2020-02-25 CN CN202010114171.2A patent/CN111339923A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102637033A (en) * | 2012-04-28 | 2012-08-15 | 成都西物信安智能系统有限公司 | Control system for safety inspection of vehicle bottom |
CN202548640U (en) * | 2012-04-28 | 2012-11-21 | 成都西物信安智能系统有限公司 | Control system for safety inspection on underbody of track traffic vehicle |
CN202632095U (en) * | 2012-04-28 | 2012-12-26 | 成都西物信安智能系统有限公司 | Control system for safety inspection of vehicle bottom |
CN202631757U (en) * | 2012-04-28 | 2012-12-26 | 成都西物信安智能系统有限公司 | Control system for multiple-lane safety inspection of vehicle chassis |
US20190084481A1 (en) * | 2017-09-21 | 2019-03-21 | Ford Global Technologies, Llc | Adjustment of vehicle rearview mirror displays |
CN110832596A (en) * | 2017-10-16 | 2020-02-21 | 因美纳有限公司 | Deep convolutional neural network training method based on deep learning |
CN109858486A (en) * | 2019-01-27 | 2019-06-07 | 中国人民解放军国防科技大学 | Deep learning-based data center cloud target identification method |
CN110472503A (en) * | 2019-07-11 | 2019-11-19 | 桂林电子科技大学 | A kind of road target detection method, device and storage medium |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112070006A (en) * | 2020-09-08 | 2020-12-11 | 哈尔滨市科佳通用机电股份有限公司 | Side inspection system and side inspection method for road vehicles |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105390021B (en) | The detection method and device of parking space state | |
US11361556B2 (en) | Deterioration diagnosis device, deterioration diagnosis system, deterioration diagnosis method, and storage medium for storing program | |
US6999004B2 (en) | System and method for vehicle detection and tracking | |
CN102521578B (en) | Method for detecting and identifying intrusion | |
CN103366565B (en) | Method and system of detecting pedestrian running red light based on Kinect | |
CN210899299U (en) | Tunnel monitoring system | |
CN109410497B (en) | Bridge opening space safety monitoring and alarming system based on deep learning | |
JP2005086626A (en) | Wide area monitoring device | |
CN102034357A (en) | Vehicle monitoring device as well as device, system and method for detecting regulation-violating vehicles | |
CN110008804B (en) | Elevator monitoring key frame obtaining and detecting method based on deep learning | |
JP2019079303A (en) | Road facility inspection system, road facility inspection method, and server used therefor | |
CN103456168A (en) | System and method for monitoring behaviors of pedestrians at traffic intersection | |
CN111339923A (en) | Vehicle bottom inspection method and system | |
CN211904213U (en) | Vehicle bottom checking system | |
CN212724329U (en) | Illegal whistle and illegal refitted vehicle snapshot system covering bidirectional lane | |
CN116665419B (en) | Intelligent fault early warning system and method based on AI analysis in power production operation | |
JPH08180276A (en) | Method and device for obstacle detection | |
CN101814134A (en) | Intelligent flame detection method based on computer vision monitoring technology | |
JP2000137842A (en) | Method and device for prevention escape from parking lot without payment | |
CN108122414A (en) | The detection method and device of car on-board and off-board on highway | |
CN110346767A (en) | A kind of test method and device for automobile lane change miscellaneous function | |
CN111127280A (en) | Intelligent community management system | |
CN108664695B (en) | System for simulating vehicle accident and application thereof | |
JPH1131296A (en) | Parking lot managing method/device | |
CN114359839A (en) | Method and system for identifying entrance of electric vehicle into elevator |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200626 |
|
RJ01 | Rejection of invention patent application after publication |