CN105447456A - Intelligent visual vehicle identification method - Google Patents
Intelligent visual vehicle identification method Download PDFInfo
- Publication number
- CN105447456A CN105447456A CN201510789061.5A CN201510789061A CN105447456A CN 105447456 A CN105447456 A CN 105447456A CN 201510789061 A CN201510789061 A CN 201510789061A CN 105447456 A CN105447456 A CN 105447456A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- image information
- brand
- tailstock
- headstock
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- 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
Abstract
The invention provides an intelligent visual vehicle identification method. The method comprises the following steps of step 1, establishing a vehicle information database; step 2, through a PC, setting a detection mode and then reading in all the photographs to be identified or videos to be identified which are acquired through a monitoring camera in a time period; step 3, if the photographs in the time period is read in, directly starting identification; if the videos in the time period is read in, firstly assigning one area to be detected and then starting the identification; step 4, using the PC to form a polling list about identified license plate numbers, vehicle brands and vehicle models of all the vehicles and displaying the polling list on the PC so that a user can check. The invention provides a vehicle automation identification method. A workload of police officers is greatly mitigated and simultaneously an error probability is reduced.
Description
Technical field
The present invention relates to a kind of method of Intelligent Recognition vehicle model and car plate.
Background technology
Checking monitoring video to obtain the important ring that useful information is criminal investigation work, especially when suspect uses vehicle, need to check a large amount of monitor video with obtain suspect use the information of vehicle.At present, the work of checking monitoring video is often undertaken by naked eyes, so not only need the time of at substantial, and human eye stares at screen for a long time and sees and be very easy to cause visual fatigue, and target vehicle dodges often in video and wink namely to die, therefore, often cause erroneous judgement, thus delay criminal investigation work.
Summary of the invention
The object of this invention is to provide a kind of method of video or photo being carried out to Intelligent Recognition.
In order to achieve the above object, technical scheme of the present invention there is provided a kind of intelligent vision and knows car method, it is characterized in that, comprises the steps:
The first step, set up vehicle information database, in this database, store headstock image information and the tailstock image information of each vehicle models under different brands, vehicle brand, vehicle model, headstock image information and tailstock image information define relation one to one;
Second step, set detecting pattern by PC, detecting pattern comprises headstock recognition mode, tailstock recognition mode and headstock tailstock mixing recognition mode, reset the overall width of detection, read in the photo all to be identified or video to be identified that are obtained by monitoring camera in a period of time subsequently;
The photo that what if the 3rd step was read in is in a period of time, the license plate number of vehicle on picture is then automatically identified by PC, simultaneously, the brand of vehicle is identified by PC, headstock image information and/or the tailstock image information of all vehicles in vehicle information database under this brand is read again according to the brand recognized, the headstock of the headstock image information in vehicle information database and/or tailstock image information and vehicle on picture and/or the tailstock are mated, if the match is successful, then obtain vehicle on photo current: license plate number, vehicle brand and vehicle model;
If what read in is video in a period of time, then on any one video, first specify a region to be detected, then allly all not identified by the vehicle in this region to be detected in video, recognition methods is specially: automatically identify the license plate number through vehicle in video by PC, simultaneously, the brand of this vehicle is identified by PC, headstock image information and/or the tailstock image information of all vehicles in vehicle information database under this vehicle brand is read again according to the brand recognized, headstock image information in vehicle information database and/or tailstock image information are mated through the headstock of the vehicle in region to be detected and/or the tailstock with video, if the match is successful, then to obtain Current vehicle: license plate number, vehicle brand and vehicle model,
4th step, by PC, the license plate number of all vehicles recognized, vehicle brand and vehicle model are formed a question blank, and show on PC and check for user.
The invention provides a kind of automatic identifying method to vehicle, significantly reduce the workload of criminal detective, meanwhile, reduce error probability.
Embodiment
For making the present invention become apparent, be hereby described in detail below with preferred embodiment.
The invention provides a kind of intelligent vision and know car method:
The first step, set up vehicle information database, in this database, store headstock image information and the tailstock image information of each vehicle models under different brands, vehicle brand, vehicle model, headstock image information and tailstock image information define relation one to one;
Second step, on PC, create account and the secret of vehicle detecting system for different users, each user logins the vehicle detecting system on PC by oneself account and secret, Detection task is created subsequently on vehicle detecting system, need to set on interface: the overall width of detecting pattern and detection while establishment Detection task, wherein, detecting pattern comprises headstock recognition mode, tailstock recognition mode and headstock tailstock mixing recognition mode.For headstock recognition mode, the overall width minimum value of detection is 250mm, and for tailstock recognition mode and headstock tailstock mixing recognition mode, the minimum value of the overall width of detection is 200mm.The photo all to be identified obtained by monitoring camera in a period of time can be read in subsequently, also can read in the video to be identified obtained by monitoring camera in a period of time.
3rd step, if what read in second step is photo in a period of time, automatically identified the license plate number of vehicle on picture by vehicle detecting system after then starting task, simultaneously, the brand of vehicle is identified by PC, headstock image information and/or the tailstock image information of all vehicles in vehicle information database under this brand is read again according to the brand recognized, the headstock of the headstock image information in vehicle information database and/or tailstock image information and vehicle on picture and/or the tailstock are mated, if the match is successful, then obtain vehicle on photo current: license plate number, vehicle brand and vehicle model.
If what read in second step is video in a period of time, then must first specify a region to be detected on any one video before task starts, then task starts rear allly all not identified by the vehicle in this region to be detected in video, recognition methods is specially: automatically identify the license plate number through vehicle in video by PC, simultaneously, the brand of this vehicle is identified by PC, headstock image information and/or the tailstock image information of all vehicles in vehicle information database under this vehicle brand is read again according to the brand recognized, headstock image information in vehicle information database and/or tailstock image information are mated through the headstock of the vehicle in region to be detected and/or the tailstock with video, if the match is successful, then to obtain Current vehicle: license plate number, vehicle brand and vehicle model.
In the process that task is carried out, can end task, also can restart mission.
4th step, by PC, the license plate number of all vehicles recognized, vehicle brand and vehicle model are formed a question blank, and show on PC and check for user.
Claims (1)
1. intelligent vision knows a car method, it is characterized in that, comprises the steps:
The first step, set up vehicle information database, in this database, store headstock image information and the tailstock image information of each vehicle models under different brands, vehicle brand, vehicle model, headstock image information and tailstock image information define relation one to one;
Second step, set detecting pattern by PC, detecting pattern comprises headstock recognition mode, tailstock recognition mode and headstock tailstock mixing recognition mode, reset the overall width of detection, read in the photo all to be identified or video to be identified that are obtained by monitoring camera in a period of time subsequently;
The photo that what if the 3rd step was read in is in a period of time, the license plate number of vehicle on picture is then automatically identified by PC, simultaneously, the brand of vehicle is identified by PC, headstock image information and/or the tailstock image information of all vehicles in vehicle information database under this brand is read again according to the brand recognized, the headstock of the headstock image information in vehicle information database and/or tailstock image information and vehicle on picture and/or the tailstock are mated, if the match is successful, then obtain vehicle on photo current: license plate number, vehicle brand and vehicle model;
If what read in is video in a period of time, then on any one video, first specify a region to be detected, then allly all not identified by the vehicle in this region to be detected in video, recognition methods is specially: automatically identify the license plate number through vehicle in video by PC, simultaneously, the brand of this vehicle is identified by PC, headstock image information and/or the tailstock image information of all vehicles in vehicle information database under this vehicle brand is read again according to the brand recognized, headstock image information in vehicle information database and/or tailstock image information are mated through the headstock of the vehicle in region to be detected and/or the tailstock with video, if the match is successful, then to obtain Current vehicle: license plate number, vehicle brand and vehicle model,
4th step, by PC, the license plate number of all vehicles recognized, vehicle brand and vehicle model are formed a question blank, and show on PC and check for user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510789061.5A CN105447456A (en) | 2015-11-17 | 2015-11-17 | Intelligent visual vehicle identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510789061.5A CN105447456A (en) | 2015-11-17 | 2015-11-17 | Intelligent visual vehicle identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105447456A true CN105447456A (en) | 2016-03-30 |
Family
ID=55557616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510789061.5A Pending CN105447456A (en) | 2015-11-17 | 2015-11-17 | Intelligent visual vehicle identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105447456A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1987007057A1 (en) * | 1986-05-05 | 1987-11-19 | Perceptics Corporation | Apparatus for reading a license plate |
| CN102426786A (en) * | 2011-11-15 | 2012-04-25 | 无锡港湾网络科技有限公司 | Intelligent video analyzing system and method for automatically identifying fake plate vehicle |
| CN102521986A (en) * | 2011-12-05 | 2012-06-27 | 沈阳聚德视频技术有限公司 | Automatic detection system for fake plate vehicle and control method for automatic detection system |
| CN103646548A (en) * | 2013-12-06 | 2014-03-19 | 镇江市星禾物联科技有限公司 | Image identification technology-based license plate identification method |
| CN104282154A (en) * | 2014-10-29 | 2015-01-14 | 合肥指南针电子科技有限责任公司 | Vehicle overload monitoring system and method |
| CN104408431A (en) * | 2014-11-28 | 2015-03-11 | 江苏物联网研究发展中心 | Vehicle model identification method under traffic monitoring |
| CN104680795A (en) * | 2015-02-28 | 2015-06-03 | 武汉烽火众智数字技术有限责任公司 | Vehicle type recognition method and device based on partial area characteristic |
-
2015
- 2015-11-17 CN CN201510789061.5A patent/CN105447456A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1987007057A1 (en) * | 1986-05-05 | 1987-11-19 | Perceptics Corporation | Apparatus for reading a license plate |
| CN102426786A (en) * | 2011-11-15 | 2012-04-25 | 无锡港湾网络科技有限公司 | Intelligent video analyzing system and method for automatically identifying fake plate vehicle |
| CN102521986A (en) * | 2011-12-05 | 2012-06-27 | 沈阳聚德视频技术有限公司 | Automatic detection system for fake plate vehicle and control method for automatic detection system |
| CN103646548A (en) * | 2013-12-06 | 2014-03-19 | 镇江市星禾物联科技有限公司 | Image identification technology-based license plate identification method |
| CN104282154A (en) * | 2014-10-29 | 2015-01-14 | 合肥指南针电子科技有限责任公司 | Vehicle overload monitoring system and method |
| CN104408431A (en) * | 2014-11-28 | 2015-03-11 | 江苏物联网研究发展中心 | Vehicle model identification method under traffic monitoring |
| CN104680795A (en) * | 2015-02-28 | 2015-06-03 | 武汉烽火众智数字技术有限责任公司 | Vehicle type recognition method and device based on partial area characteristic |
Non-Patent Citations (1)
| Title |
|---|
| 赵池航等: "《交通信息感知理论与方法》", 30 September 2014 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104506857B (en) | A kind of camera position deviation detection method and apparatus | |
| US20130250108A1 (en) | Access Control System by Face Recognition in An Automobile | |
| WO2019126908A1 (en) | Image data processing method, device and equipment | |
| US20190205622A1 (en) | Method and device of detecting picture type | |
| US9864908B2 (en) | Slow change detection system | |
| CN109409172B (en) | Driver sight line detection method, system, medium, and apparatus | |
| WO2017000494A1 (en) | Iris identification method, iris identification system, and terminal | |
| JP2020169680A (en) | Device, method and program for detecting bolt fastening condition | |
| WO2014126735A1 (en) | Real time object scanning using a mobile phone and cloud-based visual search engine | |
| CN111783640A (en) | Detection method, device, equipment and storage medium | |
| CN108805184B (en) | Image recognition method and system for fixed space and vehicle | |
| KR102203687B1 (en) | Stereo camera apparatus and rectification method of the same | |
| US20200293760A1 (en) | Multi-modal identity recognition | |
| CN105844282A (en) | Method for detecting defects of fuel injection nozzle O-Ring through line scanning camera | |
| CN108876824B (en) | Target tracking method, device and system and dome camera | |
| CN104512334A (en) | Filtering device | |
| CN106803937B (en) | Double-camera video monitoring method, system and monitoring device with text log | |
| CN105447456A (en) | Intelligent visual vehicle identification method | |
| CN109460077B (en) | Automatic tracking method, automatic tracking equipment and automatic tracking system | |
| US20230156161A1 (en) | Failure identification and handling method, and system | |
| WO2013144906A4 (en) | System and method for face detection and recognition using locally evaluated zernike and similar moments | |
| CN111695445A (en) | Face recognition method, device, equipment and computer readable storage medium | |
| CN104133175B (en) | Key testing method | |
| WO2019208020A1 (en) | Identification system, method, and program | |
| CN106598468B (en) | Starting method and device of photographing search application |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160330 |