WO2020140611A1 - Procédé d'identification de code vin basé sur un traitement d'image, dispositif et support - Google Patents

Procédé d'identification de code vin basé sur un traitement d'image, dispositif et support Download PDF

Info

Publication number
WO2020140611A1
WO2020140611A1 PCT/CN2019/117069 CN2019117069W WO2020140611A1 WO 2020140611 A1 WO2020140611 A1 WO 2020140611A1 CN 2019117069 W CN2019117069 W CN 2019117069W WO 2020140611 A1 WO2020140611 A1 WO 2020140611A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
shooting
target
target vehicle
vin code
Prior art date
Application number
PCT/CN2019/117069
Other languages
English (en)
Chinese (zh)
Inventor
林春伟
马进
王健宗
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2020140611A1 publication Critical patent/WO2020140611A1/fr

Links

Images

Classifications

    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion

Definitions

  • vehicle environment information of the target vehicle within the shooting range of the shooting device includes the model of the target vehicle, the ambient light intensity of the target vehicle, and the distance between the target vehicle and the shooting device Any one or more of distance and system time;
  • an embodiment of the present application provides a computer non-volatile readable storage medium, where the computer non-volatile readable storage medium stores a computer program, the computer program includes program instructions, and the program instructions When executed by a processor, the processor is caused to perform the method of the first aspect described above.
  • the vin code image After acquiring the vin code image including the vin code area, the vin code image can be processed to extract the vin code area.
  • edge detection can be performed on the vin code image, for example, the edge detection can be performed using a Canny operator.
  • the characteristic of the Canny algorithm is to try to assemble candidate pixels of independent edges into an outline.
  • the specific algorithm steps of Canny operator to find edge points are as follows:
  • the N can be obtained based on the statistical relationship between the character pitch size of the vin code area and the vin code image size in the captured image. For example, the larger the ratio between the character pitch size and the vin code image size, the larger the value of N.
  • the correspondence relationship between N and the ratio of the character pitch size to the image size is preset.
  • the N can be obtained according to the image width setting, for example, the value of the N can be 5% of the image width.
  • the morphological closed calculation result is obtained to exclude small black holes (black areas).
  • FIG. 2 is a schematic flowchart of another vin code recognition method based on image processing provided by an embodiment of the present application.
  • the vin code recognition method based on image processing may include the following steps:
  • the vehicle environment information of the target vehicle may include the vehicle model of the target vehicle.
  • the image processing device determines the target shooting parameter, it may find the shooting parameter corresponding to the same vehicle model as the target vehicle model from the database according to the preset correspondence between the vehicle model and the shooting parameter, and find out The shooting parameter of is determined as the target shooting parameter for shooting the target vehicle.
  • a variety of vehicle models and shooting parameters corresponding to each vehicle model can be pre-stored in the database.
  • the shooting parameters corresponding to each vehicle model may be selected vin code images with better shooting effects under the vehicle model, such as shooting quality greater than the preset quality threshold and/or vin code area accounting for the image ratio greater than the preset ratio threshold, etc. Sample shooting parameters.
  • the vehicle environment information of the target vehicle includes the vehicle model of the target vehicle
  • the database stores multiple vehicle models and shooting parameters corresponding to each vehicle model.
  • the processing unit 302 may be specifically configured to determine a target distance interval in which the distance between the target vehicle and the shooting device is among the multiple distance intervals according to preset multiple distance intervals; according to the preset vehicle Correspondence between the vehicle model, the distance interval and the shooting parameters, the shooting parameters corresponding to the vehicle model of the target vehicle and the target distance interval are found from the database, and the found shooting parameters are determined Target shooting parameters for shooting the target vehicle;
  • the following steps may be specifically performed: performing edge detection on the vin code image after the tophat transformation to obtain an edge image after edge detection .
  • An embodiment of the present application also provides a computer-readable storage medium that stores a computer program, and when the computer program is executed by a processor, the computer program can be implemented as described in the embodiments corresponding to FIG. 1 to FIG. 2 Part or all of the steps in the vin code recognition method based on image processing may also realize the functions of the image processing device of the embodiment shown in FIG. 3 or FIG. 4 of the present application, and details are not described here.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

La présente invention, qui appartient au domaine technique du traitement d'images, concerne un procédé d'identification de code VIN basé sur un traitement d'image, un dispositif et un support. Le procédé comprend : l'obtention d'informations d'environnement de véhicule pour un véhicule cible (101) ; la détermination d'un paramètre de photographie cible selon les informations d'environnement du véhicule, et l'acquisition d'une image de code VIN du véhicule cible à l'aide d'un dispositif de photographie selon le paramètre de photographie cible (102) ; la réalisation d'une détection de bord sur l'image de code VIN pour obtenir une image de bord soumise à la détection de bord (103) ; la réalisation d'une opération de fermeture morphologique sur l'image de bord pour obtenir une image d'opération de fermeture (104) ; la réalisation d'une opération d'ouverture morphologique sur l'image d'opération de fermeture pour obtenir une image d'opération d'ouverture (105) ; la détermination d'un rectangle minimal de délimitation d'une région de code VIN dans l'image d'opération d'ouverture, et la détermination de la région déterminée par le rectangle minimal de délimitation en tant que région de code VIN du véhicule cible (106) ; et l'identification de la région de code VIN du véhicule cible pour identifier le code VIN (107). Le procédé permet d'améliorer l'efficacité d'identification du code VIN de l'image de véhicule.
PCT/CN2019/117069 2019-01-04 2019-11-11 Procédé d'identification de code vin basé sur un traitement d'image, dispositif et support WO2020140611A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910013905.5A CN109784322A (zh) 2019-01-04 2019-01-04 一种基于图像处理的vin码识别方法、设备及介质
CN201910013905.5 2019-01-04

Publications (1)

Publication Number Publication Date
WO2020140611A1 true WO2020140611A1 (fr) 2020-07-09

Family

ID=66500102

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/117069 WO2020140611A1 (fr) 2019-01-04 2019-11-11 Procédé d'identification de code vin basé sur un traitement d'image, dispositif et support

Country Status (2)

Country Link
CN (1) CN109784322A (fr)
WO (1) WO2020140611A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112818746A (zh) * 2020-12-30 2021-05-18 北京立禾物联科技有限公司 一种合格证的识别方法、装置及系统

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109784322A (zh) * 2019-01-04 2019-05-21 平安科技（深圳）有限公司 一种基于图像处理的vin码识别方法、设备及介质
CN110503102A (zh) * 2019-08-27 2019-11-26 上海眼控科技股份有限公司 车辆识别码检测方法、装置、计算机设备和存储介质
CN110796709A (zh) * 2019-10-29 2020-02-14 上海眼控科技股份有限公司 车架号尺寸获取方法、装置、计算机设备和存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101246551A (zh) * 2008-03-07 2008-08-20 北京航空航天大学 一种快速的车牌定位方法
CN102646195A (zh) * 2012-02-21 2012-08-22 北京工业大学 基于jpeg压缩图像的车牌定位方法
CN105426899A (zh) * 2014-09-19 2016-03-23 腾讯科技（北京）有限公司 车辆识别方法、装置和客户端
CN105913059A (zh) * 2016-04-11 2016-08-31 吉林大学 一种车辆vin码的自动识别系统及其控制方法
CN106558121A (zh) * 2015-09-30 2017-04-05 中兴通讯股份有限公司 摄像的方法及装置
CN109784322A (zh) * 2019-01-04 2019-05-21 平安科技（深圳）有限公司 一种基于图像处理的vin码识别方法、设备及介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101789080B (zh) * 2010-01-21 2012-07-04 上海交通大学 车辆车牌实时定位字符分割的检测方法
CN103148837B (zh) * 2012-11-16 2015-08-26 深圳Tcl工业研究院有限公司 一种车距测量方法、装置及汽车
CN103927526B (zh) * 2014-04-30 2017-02-15 长安大学 一种基于高斯差分多尺度边缘融合的车辆检测方法
CN104751097B (zh) * 2015-03-30 2018-05-11 深圳市道通科技股份有限公司 一种车辆识别码的检测处理方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101246551A (zh) * 2008-03-07 2008-08-20 北京航空航天大学 一种快速的车牌定位方法
CN102646195A (zh) * 2012-02-21 2012-08-22 北京工业大学 基于jpeg压缩图像的车牌定位方法
CN105426899A (zh) * 2014-09-19 2016-03-23 腾讯科技（北京）有限公司 车辆识别方法、装置和客户端
CN106558121A (zh) * 2015-09-30 2017-04-05 中兴通讯股份有限公司 摄像的方法及装置
CN105913059A (zh) * 2016-04-11 2016-08-31 吉林大学 一种车辆vin码的自动识别系统及其控制方法
CN109784322A (zh) * 2019-01-04 2019-05-21 平安科技（深圳）有限公司 一种基于图像处理的vin码识别方法、设备及介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112818746A (zh) * 2020-12-30 2021-05-18 北京立禾物联科技有限公司 一种合格证的识别方法、装置及系统

Also Published As

Publication number Publication date
CN109784322A (zh) 2019-05-21

Similar Documents

Publication Publication Date Title
WO2020140610A1 (fr) Procédé et dispositif de traitement d'image et support de stockage lisible par ordinateur
WO2020140611A1 (fr) Procédé d'identification de code vin basé sur un traitement d'image, dispositif et support
CN109740478B (zh) 车辆检测及识别方法、装置、计算机设备及可读存储介质
Zhang et al. Image segmentation based on 2D Otsu method with histogram analysis
Kasaei et al. New morphology-based method for robustiranian car plate detection and recognition
US20070281734A1 (en) Method, system and apparatus for handset screen analysis
US20080166018A1 (en) Method and apparatus for performing object recognition on a target detected using motion information
CN111325769B (zh) 一种目标对象检测方法及装置
CN110335216B (zh) 图像处理方法、图像处理装置、终端设备及可读存储介质
WO2009105812A1 (fr) Mode basé sur la spatio-activité correspondant au domaine de l'invention
US20180047271A1 (en) Fire detection method, fire detection apparatus and electronic equipment
CN111210399A (zh) 一种成像质量评价方法、装置及设备
CN111783524A (zh) 一种场景变换检测方法、装置、存储介质及终端设备
CN112507897A (zh) 跨模态人脸识别方法、装置、设备及存储介质
CN108769521B (zh) 一种拍照方法、移动终端及计算机可读存储介质
CN111178118B (zh) 图像采集处理方法、装置及计算机可读存储介质
CN111027564A (zh) 基于深度学习一体化的低照度成像车牌识别方法及装置
CN113158773B (zh) 一种活体检测模型的训练方法及训练装置
CN108805883B (zh) 一种图像分割方法、图像分割装置及电子设备
KR20220047749A (ko) 슬랩/핑거 전경(foreground) 마스크를 생성하기 위한 방법
CN108810407B (zh) 一种图像处理方法、移动终端及计算机可读存储介质
CN111402185B (zh) 一种图像检测方法及装置
CN111062272A (zh) 基于色彩恢复的图像处理、行人识别方法、装置与可读存储介质
CN112883762A (zh) 一种活体检测方法、装置、系统及存储介质
CN110610178A (zh) 图像识别方法、装置、终端及计算机可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19907388

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS (EPO FORM 1205A DATED 25.08.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19907388

Country of ref document: EP

Kind code of ref document: A1