CN107976319B - Intelligent detection system and method for car additionally provided with pedal - Google Patents
Intelligent detection system and method for car additionally provided with pedal Download PDFInfo
- Publication number
- CN107976319B CN107976319B CN201710949537.6A CN201710949537A CN107976319B CN 107976319 B CN107976319 B CN 107976319B CN 201710949537 A CN201710949537 A CN 201710949537A CN 107976319 B CN107976319 B CN 107976319B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- pedal
- mark
- detection
- picture
- 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.)
- Expired - Fee Related
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 115
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000008569 process Effects 0.000 claims abstract description 17
- 238000013135 deep learning Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 12
- 238000007619 statistical method Methods 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 2
- 238000007689 inspection Methods 0.000 abstract description 5
- 238000012795 verification Methods 0.000 description 12
- 238000012550 audit Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011895 specific detection Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011076 safety test Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent detection system and method for adding a pedal to a car, and the intelligent detection system comprises a target detection module and a judgment module, wherein the target detection module comprises a vehicle target detection unit, a pedal target detection unit and a pedal detection mark judgment unit; the vehicle target detection unit acquires a vehicle region image, the pedal plate target detection unit detects the vehicle region image and identifies a pedal plate, the pedal plate detection mark judgment unit compares the file image with the pedal plate detection mark of the image to be detected, and the judgment module comprehensively judges the result of the whole detection process. The invention is mainly applied to the detection of the additional pedal of the car in the annual inspection of the motor vehicle, realizes the automatic check in the whole process in the detection process, and can transmit the failed detection image and reasons back to the server for storage and later evidence collection, thereby not only saving the labor, but also ensuring the justice and the openness of the check work.
Description
Technical Field
The invention relates to the technical field of artificial intelligence judgment of annual inspection of motor vehicles, in particular to an intelligent detection system and method for adding a pedal to a car.
Background
With the continuous development of social economy and the continuous improvement of the living standard of people, the quantity of motor vehicles in cities is rapidly increased. As an important traffic participant, a motor vehicle must have good safety and reliability. However, some motor vehicles have safety awareness and are illegally modified. The illegally modified vehicles are not subjected to safety tests, and the probability and the severity of traffic accidents can be increased. Therefore, it is very important to strictly detect whether a vehicle is refitted for maintaining traffic safety.
The traditional vehicle is mainly detected by adding the pedal through manual work, the method is high in labor cost and low in efficiency, long-time repeated verification operation is prone to generating fatigue, negligence and other adverse conditions, and verification accuracy is affected.
How to accurately and quickly check whether the pedal is additionally arranged on the vehicle, and simultaneously avoiding the defects of high manual check cost, easy fatigue, easy negligence and the like, is a technical problem to be continuously solved.
Disclosure of Invention
The purpose of the invention is: the intelligent detection system and method for the additional installation of the pedal plate on the car are provided, and whether the pedal plate is additionally installed on the car or not is automatically detected so as to meet the current requirements on the annual inspection work efficiency and accuracy of the car.
The technical scheme adopted by the invention for solving the technical problems is as follows:
the intelligent detection system for the additional installation of the pedal of the car comprises a target detection module and a judgment module, wherein the target detection module comprises a vehicle target detection unit, a pedal target detection unit and a pedal detection mark judgment unit; the vehicle target detection unit detects a vehicle image through a vehicle target detection model to obtain a vehicle region image, the pedal plate target detection unit detects the vehicle region image by using the pedal plate target detection model and identifies a pedal plate, the pedal plate detection mark judgment unit compares a file picture with a pedal plate detection mark of a picture to be detected, and the judgment module comprehensively judges the result of the whole detection process and feeds back the reasons and pictures of failure.
An intelligent detection method for adding a pedal to a car comprises the following steps:
s1, downloading the picture of the vehicle to be detected and the corresponding archive picture from the server;
s2, detecting the vehicle by adopting a vehicle target detection model based on the deep learning network, judging whether the vehicle target exists in the picture of the vehicle to be detected, recording the mark as 0 if the vehicle target exists, and extracting a vehicle region image; if the mark does not exist, recording the mark as 1, storing the related picture, and entering a statistical analysis process;
s3, detecting the vehicle by adopting a vehicle target detection model based on the deep learning network, judging whether the vehicle target exists in the archive picture, recording the mark as 0 if the vehicle target exists, and extracting a vehicle region image; if the mark does not exist, recording the mark as 1, storing the related picture, and entering a statistical analysis process;
s4, detecting a vehicle region image extracted from a vehicle picture to be detected by adopting a pedal target detection model based on a deep learning network, judging whether a pedal exists, recording the mark as 0 if the pedal exists, and extracting the pedal region image; if not, recording the mark as 1;
s5, detecting a vehicle region image extracted from the archive picture by adopting a pedal target detection model based on a deep learning network, judging whether a pedal exists, recording the mark as 0 if the pedal exists, and extracting the pedal region image; if not, recording the mark as 1;
s6, judging whether the pedal detection sign of the vehicle picture to be detected is consistent with the pedal detection sign of the file picture, and if so, recording the sign as 0; if not, judging whether the pedal detection mark of the file picture is 0 or not, if so, recording the mark as 0, and if not, recording the mark as 1;
s7, performing statistical analysis on the action result of the whole process, and if the input module mark is 0, passing the detection; if the mark input into the module has a mark 1, the detection is not passed, and meanwhile, the reason for the failure of the detection and a problem picture can be obtained according to the position where the mark is 1;
further, the vehicle target detection model is obtained by the following steps:
s21, acquiring vehicle images shot by different vehicle types under different illumination conditions and at different angles;
s22, marking the position of the vehicle area image by adopting a rectangular frame;
and S23, training a target detection depth neural network model by using the vehicle area image to obtain a vehicle target detection model.
Further, the step of obtaining the pedal target detection model is as follows:
s31, obtaining vehicle images of different vehicle types with pedals, wherein the pedal area of the vehicle body needs to be complete;
s32, intercepting a vehicle area image;
s33, marking the position of the pedal plate area image by adopting a rectangular frame;
and S34, training a target detection depth neural network model by using the pedal plate area image to obtain a pedal plate target detection model.
The invention has the beneficial effects that: the invention is mainly applied to the detection of the additional pedal of the car in the annual inspection of the motor vehicle, realizes the automatic check in the whole process in the detection process, and can transmit the failed detection image and reasons back to the server for storage and later evidence collection, thereby not only saving the labor, but also ensuring the justice and the openness of the check work.
Drawings
Fig. 1 is a schematic structural diagram of the intelligent detection system of the present invention.
FIG. 2 is a flow chart illustrating the steps of the present invention for detecting and determining an additional foot pedal.
Fig. 3 is a schematic structural view of a vehicle object detecting unit of the present invention.
Fig. 4 is a schematic structural view of the pedal target detection unit of the present invention.
Detailed Description
The following is combined with the attached drawings. The present invention is further explained.
The structure of the intelligent detection system of the invention is shown in fig. 1, and comprises an object detection module and a judgment module.
Wherein, the target detection module includes: a vehicle target detection unit, a pedal target detection unit and a pedal detection flag judgment unit;
the vehicle target detection unit applies a vehicle target detection model to the vehicle image to acquire a vehicle area image. Then, the vehicle area image is transmitted into a pedal target detection unit, and a pedal target detection model is applied to the vehicle area image to identify the pedal. The target detection module detects the vehicle target firstly and then detects the pedal target in the vehicle target image, and the distributed detection means can effectively avoid false detection caused by factors such as complex image background, other vehicle pedals contained in the background and the like, and improve the accuracy of pedal detection.
The pedal detection mark judging unit compares the file picture with the pedal detection mark of the picture to be detected, the judging module comprehensively judges the result of the whole detection process and feeds back the reason and the picture of failure.
The specific detection method of the vehicle target detection unit comprises the following steps: as shown in fig. 3, the detection module firstly inputs the image of the vehicle to be detected into the vehicle target detection model, and firstly obtains N one-dimensional arrays [ class, x, y, width, height ], the first element of the array represents the object class, the vehicle class is 1, the vehicle class is 0, the vehicle class is not 0, the four elements after the array represent the rectangular area where the target object is located, x and y represent the coordinates of the upper left corner point of the rectangle, width represents the width of the rectangle, and height represents the height of the rectangle. Each array corresponds to a vehicle target, vehicle distance information is constructed by using the area size of a rectangular frame of a vehicle area, the array with the largest area of the rectangular frame is used as a detection module to be output, and then a vehicle area image is extracted from an image through position information of the rectangular frame. The method can effectively pick out other non-annual inspection target vehicles in the background.
The vehicle target detection model obtaining method comprises the following steps:
s1, training data preparation: obtaining vehicle images of different vehicle types (such as cars, sports cars, off-road vehicles, minivans, commercial vehicles and the like), different brands and appointed shooting angle ranges (the images of areas where pedals are arranged on the top of the vehicle body need to be complete);
s2, data annotation: marking the vehicle target in the image by adopting a rectangular frame, wherein each image corresponds to one rectangular frame, and the frame contains the vehicle target;
s3, model training: training a vehicle target detection model based on a deep learning network by using the marked training data (common knowledge, which is not repeated);
the specific detection method of the pedal target detection unit comprises the following steps: as shown in fig. 4, the obtained vehicle region image is input into the pedal target detection model, and a one-dimensional array [ class, x, y, width, height ] is obtained, the first element of the array represents the object type, the pedal is 1, the pedal is not 0, the four elements after the array represent the rectangular region where the target object is located, x and y represent the coordinates of the upper left corner point of the rectangle, width represents the width of the rectangle, height represents the height of the rectangle, and the pedal region image is extracted from the vehicle region image through the position information of the rectangular frame.
The pedal target detection model acquisition method comprises the following steps:
s1, training data preparation: acquiring images of different vehicle types, different brands and a specified shooting angle range (the images of areas where pedals are arranged on the top of a vehicle body need to be complete), and processing the images in batch by adopting a vehicle area target detection model to obtain vehicle area images;
s2, data annotation: marking the pedal plates in the vehicle area images by adopting rectangular frames, wherein each vehicle area image corresponds to one rectangular frame, and the frame contains a pedal plate target;
s3, model training: training a pedal target detection model based on a deep learning network by using the marked training data (common knowledge, which is not repeated);
the detection standard of the additional pedal plate is as follows: whether a vehicle target exists in the chart to be detected or not; whether a vehicle target exists in the archive picture; whether a pedal exists in the picture vehicle region image to be detected or not; whether a pedal exists in the archive picture vehicle region image or not; comparing the result of the pedal detection mark of the file picture and the picture to be detected; the invention adopts a one-dimensional array [ x1, x2, x3, x4, x5] to represent the check state, and the initial value is [0, 0, 0, 0, 0 ]. A flag x1 represents whether a vehicle object exists in the map to be detected, if so, x1 is 0, and if not, x1 is 1; the flag x2 represents whether the pedal object exists in the file picture, if yes, x2 is 0, and if not, x2 is 1; the flag x3 represents whether a pedal exists in the picture vehicle region image to be detected, if so, x3 is 0, and if not, x3 is 1; the flag x4 represents whether the pedal exists in the archival picture vehicle region image, if so, x4 is 0, and if not, x4 is 1; the mark position x5 represents the comparison result of the pedal detection mark of the file picture and the picture to be detected, if the values of x3 and x4 are the same, x5 is 0, if the values of x3 and x4 are different, and x4 is 0, x5 is 0, which corresponds to the existence of a pedal in the file picture, but the pedal is not in the picture to be detected, which does not belong to the additional detection range; if the values of x3 and x4 are different and x4 is 1, then x5 is 1, which corresponds to the existence of a pedal target in the file picture to be detected and the absence of a pedal in the file picture, belonging to the additional installation of a pedal; finally, the states of the flags [ x1, x2, x5] are counted, if the flags are all 0, the check is passed, and if 1 exists, the check is not passed. The reason for the failed verification can be derived from the position where state 1 occurs. If x1 is 1, the vehicle object is not detected in the image to be detected, and possible reasons are: an error occurs in the stage of acquiring the image to be detected, the vehicle shooting angle does not meet the requirements, the vehicle body is not completely contained, or the image quality is not good, and overexposure or over-darkness occurs, so that the audit is not passed; if x2 is 1, the vehicle object is not detected in the archive image, which may be caused by an error in the archive data acquisition stage, or an error in the classification stage when the server stores the archive image, which may cause another image category to be stored by mistake, thereby resulting in a failure of the audit. If x3 is 1, it indicates that the vehicle is illegally equipped with a pedal, and the audit is not passed.
The judgment module judges whether the pedal passes the verification according to the verification standard, if the pedal passes the verification, the judgment module directly returns a verification success identifier, and if the pedal does not pass the verification, the judgment module returns a verification failure reason and a corresponding picture according to the position with the flag bit of 1, and the verification is reserved for later verification and verification.
The specific process of the present invention is shown in fig. 2, and comprises the following steps:
s1, downloading the picture of the vehicle to be detected and the corresponding archive picture from the server;
s2, detecting the vehicle by adopting a vehicle target detection model based on the deep learning network, judging whether the vehicle target exists in the picture of the vehicle to be detected, recording the mark as 0 if the vehicle target exists, and extracting a vehicle region image; if the mark does not exist, recording the mark as 1, storing the related picture, and entering a statistical analysis process;
s3, detecting the vehicle by adopting a vehicle target detection model based on the deep learning network, judging whether the vehicle target exists in the archive picture, recording the mark as 0 if the vehicle target exists, and extracting a vehicle region image; if the mark does not exist, recording the mark as 1, storing the related picture, and entering a statistical analysis process;
s4, detecting a vehicle region image extracted from a vehicle picture to be detected by adopting a pedal target detection model based on a deep learning network, judging whether a pedal exists, recording the mark as 0 if the pedal exists, and extracting the pedal region image; if not, recording the mark as 1;
s5, detecting a vehicle region image extracted from the archive picture by adopting a pedal target detection model based on a deep learning network, judging whether a pedal exists, recording the mark as 0 if the pedal exists, and extracting the pedal region image; if not, recording the mark as 1;
s6, judging whether the pedal detection sign of the vehicle picture to be detected is consistent with the pedal detection sign of the file picture, and if so, recording the sign as 0; if not, judging whether the pedal detection mark of the file picture is 0 or not, if so, recording the mark as 0, and if not, recording the mark as 1;
s7, performing statistical analysis on the action result of the whole process, and if the input module mark is 0, passing the detection; if the mark input into the module has a mark 1, the detection is not passed, and the reason for the failure detection and the problem picture can be obtained according to the position where the mark is 1.
The basic principles and the main features of the solution and the advantages of the solution have been shown and described above. It will be understood by those skilled in the art that the present solution is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principles of the solution, but that various changes and modifications may be made to the solution without departing from the spirit and scope of the solution, and these changes and modifications are intended to be within the scope of the claimed solution. The scope of the present solution is defined by the appended claims and equivalents thereof.
Claims (3)
1. An intelligent detection method for adding a pedal to a car is characterized by comprising the following steps:
s1, downloading the picture of the vehicle to be detected and the corresponding archive picture from the server;
s2, detecting the vehicle by adopting a vehicle target detection model based on the deep learning network, judging whether the vehicle target exists in the picture of the vehicle to be detected, recording the mark as 0 if the vehicle target exists, and extracting a vehicle region image; if the mark does not exist, recording the mark as 1, storing the related picture, and entering a statistical analysis process;
s3, detecting the vehicle by adopting a vehicle target detection model based on the deep learning network, judging whether the vehicle target exists in the archive picture, recording the mark as 0 if the vehicle target exists, and extracting a vehicle region image; if the mark does not exist, recording the mark as 1, storing the related picture, and entering a statistical analysis process;
s4, detecting a vehicle region image extracted from a vehicle picture to be detected by adopting a pedal target detection model based on a deep learning network, judging whether a pedal exists, recording the mark as 0 if the pedal exists, and extracting the pedal region image; if not, recording the mark as 1;
s5, detecting a vehicle region image extracted from the archive picture by adopting a pedal target detection model based on a deep learning network, judging whether a pedal exists, recording the mark as 0 if the pedal exists, and extracting the pedal region image; if not, recording the mark as 1;
s6, judging whether the pedal detection sign of the vehicle picture to be detected is consistent with the pedal detection sign of the file picture, and if so, recording the sign as 0; if not, judging whether the pedal detection mark of the file picture is 0 or not, if so, recording the mark as 0, and if not, recording the mark as 1;
s7, performing statistical analysis on the action result of the whole process, and if the input module mark is 0, passing the detection; if the mark input into the module has a mark 1, the detection is not passed, and the reason for the failure detection and the problem picture can be obtained according to the position where the mark is 1.
2. The intelligent detection method according to claim 1, wherein the vehicle object detection model is obtained by:
s21, acquiring vehicle images shot by different vehicle types under different illumination conditions and at different angles;
s22, marking the position of the vehicle area image by adopting a rectangular frame;
and S23, training a target detection depth neural network model by using the vehicle area image to obtain a vehicle target detection model.
3. The intelligent detection method as claimed in claim 1, wherein the step of obtaining the pedal target detection model is as follows:
s31, obtaining vehicle images of different vehicle types with pedals, wherein the pedal area at the top of the vehicle body needs to be complete;
s32, intercepting a vehicle area image;
s33, marking the position of the pedal plate area image by adopting a rectangular frame;
and S34, training a target detection depth neural network model by using the pedal plate area image to obtain a pedal plate target detection model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710949537.6A CN107976319B (en) | 2017-10-13 | 2017-10-13 | Intelligent detection system and method for car additionally provided with pedal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710949537.6A CN107976319B (en) | 2017-10-13 | 2017-10-13 | Intelligent detection system and method for car additionally provided with pedal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107976319A CN107976319A (en) | 2018-05-01 |
| CN107976319B true CN107976319B (en) | 2020-06-16 |
Family
ID=62012406
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710949537.6A Expired - Fee Related CN107976319B (en) | 2017-10-13 | 2017-10-13 | Intelligent detection system and method for car additionally provided with pedal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107976319B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629349B (en) * | 2018-05-11 | 2020-10-23 | 北京环境特性研究所 | Pedal detection method and system based on image processing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007310572A (en) * | 2006-05-17 | 2007-11-29 | Toyota Motor Corp | Recognition device and recognition method |
| CN105184271A (en) * | 2015-09-18 | 2015-12-23 | 苏州派瑞雷尔智能科技有限公司 | Automatic vehicle detection method based on deep learning |
| CN105740855A (en) * | 2016-03-24 | 2016-07-06 | 博康智能信息技术有限公司 | Front and rear license plate detection and recognition method based on deep learning |
| CN106203385A (en) * | 2016-07-20 | 2016-12-07 | 东方网力科技股份有限公司 | A kind of driver's hand-held phone behavioral value method and device |
| CN106600581A (en) * | 2016-12-02 | 2017-04-26 | 北京航空航天大学 | Train operation fault automatic detection system and method based on binocular stereoscopic vision |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9945652B2 (en) * | 2011-10-03 | 2018-04-17 | International Electronic Machines Corporation | Brake component monitoring |
| US20150009010A1 (en) * | 2013-07-03 | 2015-01-08 | Magna Electronics Inc. | Vehicle vision system with driver detection |
-
2017
- 2017-10-13 CN CN201710949537.6A patent/CN107976319B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007310572A (en) * | 2006-05-17 | 2007-11-29 | Toyota Motor Corp | Recognition device and recognition method |
| CN105184271A (en) * | 2015-09-18 | 2015-12-23 | 苏州派瑞雷尔智能科技有限公司 | Automatic vehicle detection method based on deep learning |
| CN105740855A (en) * | 2016-03-24 | 2016-07-06 | 博康智能信息技术有限公司 | Front and rear license plate detection and recognition method based on deep learning |
| CN106203385A (en) * | 2016-07-20 | 2016-12-07 | 东方网力科技股份有限公司 | A kind of driver's hand-held phone behavioral value method and device |
| CN106600581A (en) * | 2016-12-02 | 2017-04-26 | 北京航空航天大学 | Train operation fault automatic detection system and method based on binocular stereoscopic vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107976319A (en) | 2018-05-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107818322A (en) | A kind of vehicle VIN code tampering detection system and methods for vehicle annual test | |
| WO2019105342A1 (en) | Method and apparatus for detecting fake license plates of vehicles, readable storage medium, and electronic device | |
| WO2017190574A1 (en) | Fast pedestrian detection method based on aggregation channel features | |
| WO2020038138A1 (en) | Sample labeling method and device, and damage category identification method and device | |
| CN110956169A (en) | License plate recognition method and device and electronic equipment | |
| US11113582B2 (en) | Method and system for facilitating detection and identification of vehicle parts | |
| CN110378258B (en) | Image-based vehicle seat information detection method and device | |
| CN109344886B (en) | Occlusion number plate distinguishing method based on convolutional neural network | |
| CN106951898B (en) | Vehicle candidate area recommendation method and system and electronic equipment | |
| CN110348360A (en) | A kind of examining report recognition methods and equipment | |
| CN107958200A (en) | A kind of intelligent checking system and method for car repacking exhaust fan | |
| CN107967445A (en) | A kind of car installs the intelligent checking system and method for skylight additional | |
| CN105551261A (en) | False-license-plate vehicle detection method and system | |
| CN107798301A (en) | A kind of signature detection system and method for vehicle annual test | |
| CN111723656A (en) | Smoke detection method and device based on YOLO v3 and self-optimization | |
| CN107798302A (en) | A kind of intelligent checking system and method for car mounting luggage frame | |
| CN103473925B (en) | A kind of verification method of road vehicle detection system | |
| CN107976319B (en) | Intelligent detection system and method for car additionally provided with pedal | |
| CN109376738A (en) | Altering detecting method based on vehicle VIN code start-stop symbol type | |
| CN109344829A (en) | A kind of Train number recognition method and device of High Speed Railway Trains | |
| CN111460198B (en) | Picture timestamp auditing method and device | |
| CN116228756B (en) | Method and system for detecting bad points of camera in automatic driving | |
| CN110659534B (en) | Shared bicycle detection method and device | |
| CN111126286A (en) | Vehicle dynamic detection method and device, computer equipment and storage medium | |
| CN112633163B (en) | Detection method for realizing illegal operation vehicle detection based on machine learning algorithm |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An intelligent detection system and method for adding pedal to car Effective date of registration: 20220211 Granted publication date: 20200616 Pledgee: Shanghai Bianwei Network Technology Co.,Ltd. Pledgor: SHANGHAI EYE CONTROL TECHNOLOGY Co.,Ltd. Registration number: Y2022310000023 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200616 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |