WO2021051601A1 - Procédé et appareil de sélection d'une boîte de détection à l'aide d'un masque r-cnn, et dispositif électronique et support de stockage - Google Patents

Procédé et appareil de sélection d'une boîte de détection à l'aide d'un masque r-cnn, et dispositif électronique et support de stockage Download PDF

Info

Publication number
WO2021051601A1
WO2021051601A1 PCT/CN2019/118279 CN2019118279W WO2021051601A1 WO 2021051601 A1 WO2021051601 A1 WO 2021051601A1 CN 2019118279 W CN2019118279 W CN 2019118279W WO 2021051601 A1 WO2021051601 A1 WO 2021051601A1
Authority
WO
WIPO (PCT)
Prior art keywords
iou
detection frame
mask
polygon
cnn
Prior art date
Application number
PCT/CN2019/118279
Other languages
English (en)
Chinese (zh)
Inventor
陈欣
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 WO2021051601A1 publication Critical patent/WO2021051601A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • 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
    • G06V10/20—Image preprocessing
    • G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
    • 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
    • G06V10/267—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 by performing operations on regions, e.g. growing, shrinking or watersheds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • 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
    • G06V2201/07—Target detection

Definitions

  • the neural network is continuously convolved and pooled, and the key features of the image are extracted and processed by the neural network algorithm, and the detection results and categories are obtained (that is, the rectangular frame of the object in the image is obtained); the obtained rectangular frame is compared with the real target Preliminary screening of the IOU value is performed on the overlapping part between the two; then, the polygon point set obtained by Mask (ie, the polygon outline obtained by the instance segmentation) is further used to perform the secondary screening of the IOU value of the polygon between the polygon point set and the real target, and finally accord with Set the border of the threshold as the detection frame.
  • the beneficial effects are as follows:
  • FIG. 3 is a schematic diagram of a preferred embodiment of the two-dimensional array mapping coding method of this application.
  • FIG. 5 is a schematic structural diagram of a preferred embodiment of the electronic device of this application.
  • the first matching between the candidate detection frame and the predicted target is performed first, and the first matching result is screened, that is, the screening is performed when the IOU value of the candidate detection frame is greater than IOU 1 .
  • Mask R-CNN finally expands the output dimension of RoIAlign and predicts a Mask; that is, the result obtained by Mask branch is the point set of the polygon outline.
  • the network interface 54 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface), and is generally used to establish a communication connection between the electronic device 5 and other electronic devices.
  • a standard wired interface and a wireless interface such as a WI-FI interface

Abstract

La présente invention concerne un procédé et un système permettant de sélectionner une boîte de détection à l'aide d'un masque R-CNN, et un dispositif électronique et un support de stockage, se rapportant au domaine technique de la reconnaissance d'image. Le procédé consiste : à effectuer une segmentation d'instance sur une image cible à l'aide d'un masque R-CNN, et à obtenir une boîte de détection candidate rectangulaire et un contour polygonal correspondant à la boîte de détection candidate (S110) ; à calculer respectivement des valeurs d'indice de Jaccard de la boîte de détection candidate et du contour polygonal, et lorsque la valeur d'indice de Jaccard de la boîte de détection candidate est supérieure à un premier seuil prédéfini d'indice de Jaccard1 et que la valeur d'indice de Jaccard du contour polygonal est supérieure à un second seuil prédéfini d'indice de Jaccard2, à cribler la boîte de détection candidate en tant que boîte de détection cible, le second seuil prédéfini d'indice de Jaccard2 étant supérieur au premier seuil prédéfini d'indice de Jaccard1 (S120). Au moyen du criblage secondaire d'indice de Jaccard du contour polygonal, la précision de détection de la boîte de détection est améliorée.
PCT/CN2019/118279 2019-09-19 2019-11-14 Procédé et appareil de sélection d'une boîte de détection à l'aide d'un masque r-cnn, et dispositif électronique et support de stockage WO2021051601A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910885674.7 2019-09-19
CN201910885674.7A CN110738125B (zh) 2019-09-19 2019-09-19 利用Mask R-CNN选择检测框的方法、装置及存储介质

Publications (1)

Publication Number Publication Date
WO2021051601A1 true WO2021051601A1 (fr) 2021-03-25

Family

ID=69268320

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/118279 WO2021051601A1 (fr) 2019-09-19 2019-11-14 Procédé et appareil de sélection d'une boîte de détection à l'aide d'un masque r-cnn, et dispositif électronique et support de stockage

Country Status (2)

Country Link
CN (1) CN110738125B (fr)
WO (1) WO2021051601A1 (fr)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113409267A (zh) * 2021-06-17 2021-09-17 西安热工研究院有限公司 一种基于深度学习的路面裂缝检测与分割方法
CN113409255A (zh) * 2021-06-07 2021-09-17 同济大学 一种基于Mask R-CNN的斑马鱼形态学分类方法
CN113469302A (zh) * 2021-09-06 2021-10-01 南昌工学院 一种视频图像的多圆形目标识别方法和系统
CN113591734A (zh) * 2021-08-03 2021-11-02 中国科学院空天信息创新研究院 一种基于改进nms算法的目标检测方法
CN114526709A (zh) * 2022-02-21 2022-05-24 中国科学技术大学先进技术研究院 基于无人机的面积测量方法、设备及存储介质
CN116486265A (zh) * 2023-04-26 2023-07-25 北京卫星信息工程研究所 基于目标分割与图分类的飞机细粒度识别方法

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111507341B (zh) * 2020-04-20 2022-06-28 广州文远知行科技有限公司 一种目标边界框的调整方法、装置、设备及存储介质
CN111898411B (zh) * 2020-06-16 2021-08-31 华南理工大学 文本图像标注系统、方法、计算机设备和存储介质
CN112132832B (zh) * 2020-08-21 2021-09-28 苏州浪潮智能科技有限公司 一种增强图像实例分割的方法、系统、设备及介质
CN112861711A (zh) * 2021-02-05 2021-05-28 深圳市安软科技股份有限公司 区域入侵检测方法、装置、电子设备及存储介质
CN113343779B (zh) * 2021-05-14 2024-03-12 南方电网调峰调频发电有限公司 环境异常检测方法、装置、计算机设备和存储介质
CN113408531B (zh) * 2021-07-19 2023-07-14 北博（厦门）智能科技有限公司 一种基于图像识别的目标物形状框选方法及终端
CN113705643B (zh) * 2021-08-17 2022-10-28 荣耀终端有限公司 一种目标物检测方法、装置以及电子设备
CN114863265A (zh) * 2021-12-14 2022-08-05 青岛海尔电冰箱有限公司 冰箱内物品信息识别方法、冰箱和计算机存储介质
CN114882348A (zh) * 2022-03-29 2022-08-09 青岛海尔电冰箱有限公司 冰箱内物品信息识别方法、冰箱和计算机存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150071529A1 (en) * 2013-09-12 2015-03-12 Kabushiki Kaisha Toshiba Learning image collection apparatus, learning apparatus, and target object detection apparatus
CN106529565A (zh) * 2016-09-23 2017-03-22 北京市商汤科技开发有限公司 目标识别模型训练和目标识别方法及装置、计算设备
CN108009554A (zh) * 2017-12-01 2018-05-08 国信优易数据有限公司 一种图像处理方法以及装置
CN109389640A (zh) * 2018-09-29 2019-02-26 北京字节跳动网络技术有限公司 图像处理方法和装置
CN109903310A (zh) * 2019-01-23 2019-06-18 平安科技（深圳）有限公司 目标跟踪方法、装置、计算机装置及计算机存储介质
CN110047095A (zh) * 2019-03-06 2019-07-23 平安科技（深圳）有限公司 基于目标检测的跟踪方法、装置及终端设备

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9972092B2 (en) * 2016-03-31 2018-05-15 Adobe Systems Incorporated Utilizing deep learning for boundary-aware image segmentation
US11475351B2 (en) * 2017-11-15 2022-10-18 Uatc, Llc Systems and methods for object detection, tracking, and motion prediction
CN108875577A (zh) * 2018-05-11 2018-11-23 深圳市易成自动驾驶技术有限公司 目标检测方法、装置及计算机可读存储介质
CN109977943B (zh) * 2019-02-14 2024-05-07 平安科技（深圳）有限公司 一种基于yolo的图像目标识别方法、系统和存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150071529A1 (en) * 2013-09-12 2015-03-12 Kabushiki Kaisha Toshiba Learning image collection apparatus, learning apparatus, and target object detection apparatus
CN106529565A (zh) * 2016-09-23 2017-03-22 北京市商汤科技开发有限公司 目标识别模型训练和目标识别方法及装置、计算设备
CN108009554A (zh) * 2017-12-01 2018-05-08 国信优易数据有限公司 一种图像处理方法以及装置
CN109389640A (zh) * 2018-09-29 2019-02-26 北京字节跳动网络技术有限公司 图像处理方法和装置
CN109903310A (zh) * 2019-01-23 2019-06-18 平安科技（深圳）有限公司 目标跟踪方法、装置、计算机装置及计算机存储介质
CN110047095A (zh) * 2019-03-06 2019-07-23 平安科技（深圳）有限公司 基于目标检测的跟踪方法、装置及终端设备

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113409255A (zh) * 2021-06-07 2021-09-17 同济大学 一种基于Mask R-CNN的斑马鱼形态学分类方法
CN113409267A (zh) * 2021-06-17 2021-09-17 西安热工研究院有限公司 一种基于深度学习的路面裂缝检测与分割方法
CN113591734A (zh) * 2021-08-03 2021-11-02 中国科学院空天信息创新研究院 一种基于改进nms算法的目标检测方法
CN113591734B (zh) * 2021-08-03 2024-02-20 中国科学院空天信息创新研究院 一种基于改进nms算法的目标检测方法
CN113469302A (zh) * 2021-09-06 2021-10-01 南昌工学院 一种视频图像的多圆形目标识别方法和系统
CN114526709A (zh) * 2022-02-21 2022-05-24 中国科学技术大学先进技术研究院 基于无人机的面积测量方法、设备及存储介质
CN116486265A (zh) * 2023-04-26 2023-07-25 北京卫星信息工程研究所 基于目标分割与图分类的飞机细粒度识别方法
CN116486265B (zh) * 2023-04-26 2023-12-19 北京卫星信息工程研究所 基于目标分割与图分类的飞机细粒度识别方法

Also Published As

Publication number Publication date
CN110738125A (zh) 2020-01-31
CN110738125B (zh) 2023-08-01

Similar Documents

Publication Publication Date Title
WO2021051601A1 (fr) Procédé et appareil de sélection d'une boîte de détection à l'aide d'un masque r-cnn, et dispositif électronique et support de stockage
CN108009543B (zh) 一种车牌识别方法及装置
CN110738101B (zh) 行为识别方法、装置及计算机可读存储介质
CN109657533B (zh) 行人重识别方法及相关产品
CN112560999B (zh) 一种目标检测模型训练方法、装置、电子设备及存储介质
WO2019218824A1 (fr) Procédé d'acquisition de piste de mouvement et dispositif associé, support de stockage et terminal
US11455805B2 (en) Method and apparatus for detecting parking space usage condition, electronic device, and storage medium
CN108268867B (zh) 一种车牌定位方法及装置
CN108805016B (zh) 一种头肩区域检测方法及装置
CN110781836A (zh) 人体识别方法、装置、计算机设备及存储介质
WO2020258077A1 (fr) Procédé et dispositif de détection de piéton
CN111274926B (zh) 图像数据筛选方法、装置、计算机设备和存储介质
CN115170792B (zh) 红外图像处理方法、装置及设备、存储介质
CN113642474A (zh) 一种基于yolov5的危险区域人员监控方法
CN112800978A (zh) 属性识别方法、部位属性提取网络的训练方法和装置
Jiang et al. A fast and high-performance object proposal method for vision sensors: Application to object detection
US20220300774A1 (en) Methods, apparatuses, devices and storage media for detecting correlated objects involved in image
Bisht et al. Integration of hough transform and inter-frame clustering for road lane detection and tracking
CN113591758A (zh) 一种人体行为识别模型训练方法、装置及计算机设备
CN110689556A (zh) 跟踪方法、装置及智能设备
Lashkov et al. Edge-computing-facilitated nighttime vehicle detection investigations with CLAHE-enhanced images
CN111723614A (zh) 交通信号灯识别方法及装置
CN112784691B (zh) 一种目标检测模型训练方法、目标检测方法和装置
CN112069357B (zh) 视频资源处理方法、装置、电子设备及存储介质
Ojala et al. Motion detection and classification: ultra-fast road user detection

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: 19946046

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19946046

Country of ref document: EP

Kind code of ref document: A1