WO2017084204A1 - Procédé et système de suivi d'un point du squelette humain dans un flux vidéo en deux dimensions - Google Patents
Procédé et système de suivi d'un point du squelette humain dans un flux vidéo en deux dimensionsDownload PDFInfo
- Publication number
- WO2017084204A1 WO2017084204A1PCT/CN2016/070898CN2016070898WWO2017084204A1WO 2017084204 A1WO2017084204 A1WO 2017084204A1CN 2016070898 WCN2016070898 WCN 2016070898WWO 2017084204 A1WO2017084204 A1WO 2017084204A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- point
- image
- coordinates
- roi
- face
- 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.)
- Ceased
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/285—Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 inventionrelates to the research field of image processing, and in particular to a human bone point tracking method and system in a two-dimensional video stream.
- Human-computer interaction technologyrefers to the technology of realizing the effective communication between humans and computers through the input and output devices of computers to facilitate the way people use them.
- Human skeleton point tracking technologyis an important technology in the field of human-computer interaction. It can identify the movement of the human body by means of infrared rays, and can track multiple parts of the human body in real time without any external equipment for action capture. It has a wide application prospect in the machine interaction environment.
- the prior art human bone tracking technologyis generally a framework of Kinect and a PC host system. Kinect is mainly responsible for acquiring images, deep data streams and bone information, and the host is responsible for acquiring image and depth data through the database for bone trajectory tracking and three-dimensional data.
- the inventionprovides a human skeleton point tracking method in a two-dimensional video stream, the method comprising the following steps:
- each regionuses different scanning mode return points to realize elbow point detection, and obtain left elbow point and right elbow point coordinates;
- the specific method for outputting the foreground imageis:
- LD(a,b)represents shifting the image a as a whole to the right by b pixels
- the IMAGE and the BACKGROUNDare subtracted and denoised to obtain the foreground mask foreground_mask, and the foreground_mask is binarized to obtain the MASK;
- the IMAGE and MASKare processed and processed to output the foreground image FOREGROUND.
- the Haar classifieris used for face detection, and the specific method is:
- the Haar classifieris used to detect the positive face, and when the positive face is detected, the coordinates of the center point of the face and the length and width of the face rectangle are returned;
- the Haar classifierto detect the side face and return the coordinates of the face center point and The face is rectangular in length and width.
- the specific method for implementing the shoulder point detectionis:
- Image preprocessingto obtain the contour of the human body
- the coordinates of the left shoulder pointare obtained by the same identification method as described above.
- the specific method for implementing the hand point detectionis:
- Kreturns directly to the center point when the following conditions are met: the rectangle width is less than X times the rectangle height and the rectangle height is less than X times the rectangle width, where 1 ⁇ X ⁇ 2;
- the geometric position of p1 and p2is used to determine the general position of the hand, and the coordinates are assigned to p2.
- the valueis (0, 0), and the value of (0, 0) is not displayed;
- the coordinates of the right handare identified using the same method as described above.
- each regionuses different scanning mode return points to realize elbow point detection, and acquiring left elbow point and right elbow point coordinates, and implementing elbow point
- the specific method of detectionis:
- Image preprocessingto obtain the contour of the human body
- Forked waist movementWhen the difference between the shoulder coordinate of the shoulder point and the horizontal coordinate of the hand point is less than IMAGE_HEIGHT/50, the point is swept from left to right, and the coordinates of the point with the first pixel value greater than 50 are returned.
- the methodfurther comprises the steps of:
- the foot point detectionis implemented by using the near-end point of the minimum circumscribed rectangle of the foreground area of the lower body and returning.
- the specific method of the foot point detectionis:
- the human body lower body ROI of the foreground imageis taken out by half of the screen;
- Extracting the outer contourtraversing the outer contour and extracting the contour L corresponding to the largest area, creating a minimum circumscribed rectangle K of L;
- Kreturns directly to the center point when the following conditions are met: the rectangle width is less than Y times the rectangle height and the rectangle height is less than Y times the rectangle width, where 1 ⁇ Y ⁇ 2;
- Detect the left footfind the leftmost point, define it as ptfoot[0], determine the next left point, define it as ptfoot[1], define p1 as the midpoint of K, and define p2 as ptfoot[0] and ptfoot[ The midpoint of 1];
- the coordinates of the right foot pointare obtained by the same recognition method described above.
- the knee point detectionis realized by scanning and returning the distance from the foot point to the set height.
- the specific method of the knee point detectionis:
- the background reconstruction moduleacquires the foreground of the human body, and in the whole body mode, removes the body ROI of the lower body;
- the coordinates of the right knee pointare obtained by the same recognition method described above.
- the foreground extraction moduleis configured to acquire a two-dimensional video stream, reconstruct a background, and extract a foreground mask by using a subtractive background method, and output a foreground image after denoising processing;
- a face detection moduleconfigured to detect a face of the output foreground image, and obtain a rectangle of the face, a head point, and a neck point coordinate;
- a judging moduleconfigured to determine whether the head point is in the screen; if not, proceeding to the face detecting module; if yes, dividing the human body into a left part ROI and a right part ROI to perform other key points respectively;
- a shoulder point detection modulefor performing shoulder point detection by scanning and returning a pixel value point using a specific position, and acquiring left shoulder point and right shoulder point coordinates
- the hand detection moduleis configured to perform the hand point detection by using the minimum circumscribed rectangle near the end point of the skin color region, and obtain the coordinates of the left hand point and the right hand point;
- the elbow detection moduleis configured to divide the hand ROI into three regions, and each region uses different scanning mode return points to realize elbow point detection, and obtain left elbow point and right elbow point coordinates;
- the statistics modulefinally counts the credibility of each point and displays the trusted points.
- the systemfurther comprises a foot point detection module and a knee point detection module;
- the foot point detecting moduleis configured to perform a foot point detection by using a minimum circumscribed rectangle near end point of the lower body foreground area and returning;
- the knee point detecting moduleis configured to scan and return by using a foot point to take a set height distance The method of returning implements knee point detection.
- the present inventionhas the following advantages and beneficial effects:
- the inventiondoes not need to use depth information, and can directly realize the human body skeleton point recognition by using an ordinary camera, and has universal applicability.
- the algorithm of the inventionis simple, occupies less computing resources, has low hardware requirements, and has strong real-time performance;
- the inventionis not limited by the development platform, and can be applied to mobile terminals (such as mobile phones, tablets, etc.) to meet cross-platform requirements and has strong portability.
- the inventioncan cope with the complicated background and uneven illumination in the general scene, and has strong robustness.
- Figure 6is a foreground view of the present invention.
- FIG. 7is a schematic diagram of a face detection area of the present invention.
- Figure 9is a schematic view of a region of a shoulder point of the present invention.
- Figure 10is a schematic view showing the area of the hand point of the present invention.
- Figure 11is a schematic view showing the division of the area of the present invention.
- Figure 12is a schematic view showing the area of the elbow point of the present invention.
- Figure 13is a diagram showing the recognition effect of the overall key points of the present invention.
- depth-based bone tracking technologycreates depth coordinates for each joint of the human body by processing depth data, and bone tracking can determine various parts of the body, such as the hand, head, and body, and determine where they are.
- the ordinary cameracan only obtain two-dimensional information in space. The goal of this algorithm is to realize the tracking of human skeleton points in the two-dimensional video stream.
- the present inventionprovides a method for tracking a human skeleton point in a two-dimensional video stream, the method comprising the following steps:
- Step S1The camera acquires a two-dimensional video stream, reconstructs a background, and extracts a foreground mask by using a subtractive background method, and outputs a foreground image after denoising processing;
- the IMAGE and the MASKare processed and processed to output a foreground image FOREGROUND.
- Step S4using a specific position scanning and returning a pixel value point method to achieve shoulder point detection, and acquiring left shoulder point and right shoulder point coordinates;
- the coordinates of the left shoulder pointare obtained by the same identification method as described above.
- p1as the midpoint of K and define p2 as the midpoint of ptt[0] and ptt[1];
- the YCbCr formatcan be obtained by linearly changing from the RGB format.
- the conversion formulais as follows:
- the skin color clusteris in a small range in the chromaticity space, and the following calculation formula determines whether it belongs to the skin area:
- the method for achieving elbow point detectionis:
- the hand ROIis divided into three regions, and the three regions are as shown in FIG. 11, and each region uses different scanning manner return points to realize elbow point recognition;
- HAND.y-SHOULDER.y>IMAGE_HEIGHT/5sweep the point from right to left (swipe horizontally with the ROI down to 8 pixels), and sweep back to the point where the pixel value is greater than return
- Forklift action(Zone 3): When the difference between the abscissa of the shoulder point and the abscissa of the hand point is less than IMAGE_HEIGHT/50:
- the identification of the right shoulder pointis the same as the left shoulder.
- step S7the credibility of each point is finally counted and the trusted point is displayed.
- the human skeleton point chase in the two-dimensional video stream in this embodiment Tracking methodfurther comprises the following steps:
- Detect the left footfind the leftmost point, define it as ptfoot[0], determine the next left point, define it as ptfoot[1], define p1 as the midpoint of K, and define p2 as ptfoot[0] and ptfoot[ The midpoint of 1];
- the GI filtering algorithminputs the color map I and the initial mask P, and the output is an optimized mask for complementing the edge information of the color map.
- the processis as follows:
- the Gaussian filter preset parametersare: processing window size is 15x15, sigma is 20.
- the inventionalso discloses a human skeleton point tracking system in a two-dimensional video stream, the system comprising:
- the foreground extraction moduleis configured to acquire a two-dimensional video stream, reconstruct a background, and extract a foreground mask by using a subtractive background method, and output a foreground image after denoising processing;
- a face detection moduleconfigured to detect a face of the output foreground image, and obtain a rectangle of the face, a head point, and a neck point coordinate;
- a judging moduleconfigured to determine whether the head point is in the screen, and if not, proceeding to the face detecting module; if yes, dividing the human body into a left part ROI and a right part ROI for performing other key points respectively Detection
- a shoulder point detection modulefor performing shoulder point detection by scanning and returning a pixel value point using a specific position, and acquiring left shoulder point and right shoulder point coordinates
- the hand detection moduleis configured to perform the hand point detection by using the minimum circumscribed rectangle near the end point of the skin color region, and obtain the coordinates of the left hand point and the right hand point;
- the statistics modulefinally counts the credibility of each point and displays the trusted points.
- systemfurther includes a foot point detection module and a knee point detection module;
- the foot point detecting moduleis configured to perform a foot point detection by using a minimum circumscribed rectangle near end point of the lower body foreground area and returning;
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510808527.1 | 2015-11-19 | ||
| CN201510808527.1ACN105469113B (zh) | 2015-11-19 | 2015-11-19 | 一种二维视频流中的人体骨骼点追踪方法及系统 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2017084204A1true WO2017084204A1 (fr) | 2017-05-26 |
Family
ID=55606784
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2016/070898CeasedWO2017084204A1 (fr) | 2015-11-19 | 2016-01-14 | Procédé et système de suivi d'un point du squelette humain dans un flux vidéo en deux dimensions |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105469113B (fr) |
| WO (1) | WO2017084204A1 (fr) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107865753A (zh)* | 2017-11-30 | 2018-04-03 | 湖南妙手机器人有限公司 | 康复机器人及其控制方法 |
| CN110288520A (zh)* | 2019-06-29 | 2019-09-27 | 北京字节跳动网络技术有限公司 | 图像美化方法、装置及电子设备 |
| CN110310351A (zh)* | 2019-07-04 | 2019-10-08 | 北京信息科技大学 | 一种基于草图的三维人体骨骼动画自动生成方法 |
| CN111435421A (zh)* | 2019-01-11 | 2020-07-21 | 北京邮电大学 | 一种面向交通目标的车辆重识别方法和装置 |
| CN111461020A (zh)* | 2020-04-01 | 2020-07-28 | 浙江大华技术股份有限公司 | 不安全使用手机行为的识别方法、设备及相关存储介质 |
| CN111652076A (zh)* | 2020-05-11 | 2020-09-11 | 重庆大学 | 一种面向ad量表理解能力测试的姿态自动识别系统 |
| CN111709360A (zh)* | 2020-06-16 | 2020-09-25 | 上海大学 | 一种安全绳佩戴识别方法及系统 |
| TWI719409B (zh)* | 2019-02-23 | 2021-02-21 | 和碩聯合科技股份有限公司 | 追蹤系統及其方法 |
| CN112612434A (zh)* | 2020-12-16 | 2021-04-06 | 杭州当虹科技股份有限公司 | 一种基于ai技术视频竖屏解决方法 |
| CN113392738A (zh)* | 2021-06-01 | 2021-09-14 | 浙江大华技术股份有限公司 | 行为规范性检测方法、装置、电子设备和存储介质 |
| CN114187368A (zh)* | 2022-02-17 | 2022-03-15 | 深圳艾灵网络有限公司 | 建筑板材的暗纹检测方法、装置、电子设备及存储介质 |
| CN114252018A (zh)* | 2021-12-29 | 2022-03-29 | 西安奕斯伟材料科技有限公司 | 晶体直径检测方法、系统及计算机程序产品 |
| CN114577122A (zh)* | 2022-02-28 | 2022-06-03 | 长三角先进材料研究院 | 一种基于图像处理的自冲铆接剖面几何参数自动测量方法 |
| CN115396576A (zh)* | 2022-08-24 | 2022-11-25 | 南京农业大学 | 从侧视、俯视双视角图像自动测量羊体尺的装置和方法 |
| CN115620117A (zh)* | 2022-12-20 | 2023-01-17 | 吉林省信息技术研究所 | 一种用于网络访问权限认证的人脸信息加密方法及系统 |
| US12175684B2 (en) | 2020-12-04 | 2024-12-24 | Boe Technology Group Co., Ltd. | Pedestrian tracking method, computing device, pedestrian tracking system and storage medium |
| CN120183002A (zh)* | 2025-05-22 | 2025-06-20 | 泰山体育产业集团有限公司 | 一种单目彩色视频的三维人体关节点定位方法 |
| US12418713B2 (en) | 2022-02-25 | 2025-09-16 | Canon Kabushiki Kaisha | Main object determination apparatus, imaging apparatus, and control method for controlling main object determination apparatus |
Families Citing this family (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106446958B (zh)* | 2016-10-09 | 2019-04-12 | 湖南穗富眼电子科技有限公司 | 一种人体离开可靠检测方法 |
| WO2019014812A1 (fr)* | 2017-07-17 | 2019-01-24 | 深圳和而泰智能控制股份有限公司 | Procédé de détection d'un bouton sur un visage humain, et terminal intelligent |
| CN107392146A (zh)* | 2017-07-20 | 2017-11-24 | 湖南科乐坊教育科技股份有限公司 | 一种儿童坐姿检测方法及装置 |
| CN107767419A (zh)* | 2017-11-07 | 2018-03-06 | 广州深域信息科技有限公司 | 一种人体骨骼关键点检测方法及装置 |
| CN108829233B (zh)* | 2018-04-26 | 2021-06-15 | 深圳市同维通信技术有限公司 | 一种交互方法及装置 |
| CN108648229B (zh)* | 2018-05-18 | 2020-07-28 | 四川效率未来科技有限公司 | 基于Kinect相机的人体背部特征点提取方法 |
| CN109325995B (zh)* | 2018-09-13 | 2022-11-25 | 叠境数字科技（上海）有限公司 | 基于人手参数模型的低分辨率多视角手部重建方法 |
| US11715308B2 (en)* | 2018-10-10 | 2023-08-01 | Delaval Holding Ab | Animal identification using vision techniques |
| CN109697446B (zh)* | 2018-12-04 | 2021-12-07 | 北京字节跳动网络技术有限公司 | 图像关键点提取方法、装置、可读存储介质及电子设备 |
| CN109685797B (zh)* | 2018-12-25 | 2021-08-10 | 北京旷视科技有限公司 | 骨骼点检测方法、装置、处理设备及存储介质 |
| CN109947247B (zh)* | 2019-03-14 | 2022-07-05 | 海南师范大学 | 一种体感交互展示系统及方法 |
| CN109948560B (zh)* | 2019-03-25 | 2023-04-07 | 南开大学 | 融合骨骼识别和IFace-TLD的移动机器人目标跟踪系统 |
| CN111062239A (zh)* | 2019-10-15 | 2020-04-24 | 平安科技（深圳）有限公司 | 人体目标检测方法、装置、计算机设备及存储介质 |
| CN111368746A (zh)* | 2020-03-06 | 2020-07-03 | 杭州宇泛智能科技有限公司 | 视频中人员安全帽佩戴状态的检测方法、装置及电子设备 |
| US20240161316A1 (en)* | 2021-04-26 | 2024-05-16 | Intel Corporation | Method and system of image processing with multi-skeleton tracking |
| CN113609917B (zh)* | 2021-07-12 | 2022-09-27 | 深圳市鸿合创新信息技术有限责任公司 | 人手位置信息确定方法及相关设备 |
| CN113610868B (zh)* | 2021-08-06 | 2024-11-22 | 云南白药集团上海健康产品有限公司 | 一种皱纹区域的确定方法、电子设备及可读存储介质 |
| CN113807915A (zh)* | 2021-08-31 | 2021-12-17 | 恩梯梯数据(中国)信息技术有限公司 | 一种基于深度学习构建的无人超市人货匹配方法及其系统 |
| CN116188530B (zh)* | 2023-02-07 | 2025-08-01 | 南开大学 | 一种多目标斑马鱼三维运动轨迹追踪方法 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100034457A1 (en)* | 2006-05-11 | 2010-02-11 | Tamir Berliner | Modeling of humanoid forms from depth maps |
| US20120087539A1 (en)* | 2010-10-08 | 2012-04-12 | Po-Lung Chen | Method of detecting feature points of an object in a system for motion detection |
| CN102609683A (zh)* | 2012-01-13 | 2012-07-25 | 北京邮电大学 | 一种基于单目视频的人体关节自动标注方法 |
| CN103559491A (zh)* | 2013-10-11 | 2014-02-05 | 北京邮电大学 | 人体动作捕获及姿态分析系统 |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110317871A1 (en)* | 2010-06-29 | 2011-12-29 | Microsoft Corporation | Skeletal joint recognition and tracking system |
| US9355305B2 (en)* | 2010-10-08 | 2016-05-31 | Panasonic Corporation | Posture estimation device and posture estimation method |
| KR101908284B1 (ko)* | 2012-01-13 | 2018-10-16 | 삼성전자주식회사 | 신체 연결 관계 분석 장치 및 방법 |
| CN104680127A (zh)* | 2014-12-18 | 2015-06-03 | 闻泰通讯股份有限公司 | 手势识别方法及系统 |
- 2015
- 2015-11-19CNCN201510808527.1Apatent/CN105469113B/zhactiveActive
- 2016
- 2016-01-14WOPCT/CN2016/070898patent/WO2017084204A1/frnot_activeCeased
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100034457A1 (en)* | 2006-05-11 | 2010-02-11 | Tamir Berliner | Modeling of humanoid forms from depth maps |
| US20120087539A1 (en)* | 2010-10-08 | 2012-04-12 | Po-Lung Chen | Method of detecting feature points of an object in a system for motion detection |
| CN102609683A (zh)* | 2012-01-13 | 2012-07-25 | 北京邮电大学 | 一种基于单目视频的人体关节自动标注方法 |
| CN103559491A (zh)* | 2013-10-11 | 2014-02-05 | 北京邮电大学 | 人体动作捕获及姿态分析系统 |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107865753B (zh)* | 2017-11-30 | 2023-05-09 | 湖南妙手机器人有限公司 | 康复机器人 |
| CN107865753A (zh)* | 2017-11-30 | 2018-04-03 | 湖南妙手机器人有限公司 | 康复机器人及其控制方法 |
| CN111435421B (zh)* | 2019-01-11 | 2023-12-19 | 北京邮电大学 | 一种面向交通目标的车辆重识别方法和装置 |
| CN111435421A (zh)* | 2019-01-11 | 2020-07-21 | 北京邮电大学 | 一种面向交通目标的车辆重识别方法和装置 |
| TWI719409B (zh)* | 2019-02-23 | 2021-02-21 | 和碩聯合科技股份有限公司 | 追蹤系統及其方法 |
| CN110288520A (zh)* | 2019-06-29 | 2019-09-27 | 北京字节跳动网络技术有限公司 | 图像美化方法、装置及电子设备 |
| CN110288520B (zh)* | 2019-06-29 | 2023-03-31 | 北京字节跳动网络技术有限公司 | 图像美化方法、装置及电子设备 |
| CN110310351A (zh)* | 2019-07-04 | 2019-10-08 | 北京信息科技大学 | 一种基于草图的三维人体骨骼动画自动生成方法 |
| CN110310351B (zh)* | 2019-07-04 | 2023-07-21 | 北京信息科技大学 | 一种基于草图的三维人体骨骼动画自动生成方法 |
| CN111461020B (zh)* | 2020-04-01 | 2024-01-19 | 浙江大华技术股份有限公司 | 不安全使用手机行为的识别方法、设备及相关存储介质 |
| CN111461020A (zh)* | 2020-04-01 | 2020-07-28 | 浙江大华技术股份有限公司 | 不安全使用手机行为的识别方法、设备及相关存储介质 |
| CN111652076B (zh)* | 2020-05-11 | 2024-05-31 | 重庆知熠行科技发展有限公司 | 一种面向ad量表理解能力测试的姿态自动识别系统 |
| CN111652076A (zh)* | 2020-05-11 | 2020-09-11 | 重庆大学 | 一种面向ad量表理解能力测试的姿态自动识别系统 |
| CN111709360A (zh)* | 2020-06-16 | 2020-09-25 | 上海大学 | 一种安全绳佩戴识别方法及系统 |
| CN111709360B (zh)* | 2020-06-16 | 2023-04-07 | 上海大学 | 一种安全绳佩戴识别方法及系统 |
| US12175684B2 (en) | 2020-12-04 | 2024-12-24 | Boe Technology Group Co., Ltd. | Pedestrian tracking method, computing device, pedestrian tracking system and storage medium |
| CN112612434A (zh)* | 2020-12-16 | 2021-04-06 | 杭州当虹科技股份有限公司 | 一种基于ai技术视频竖屏解决方法 |
| CN113392738A (zh)* | 2021-06-01 | 2021-09-14 | 浙江大华技术股份有限公司 | 行为规范性检测方法、装置、电子设备和存储介质 |
| CN113392738B (zh)* | 2021-06-01 | 2023-12-26 | 浙江大华技术股份有限公司 | 行为规范性检测方法、装置、电子设备和存储介质 |
| CN114252018B (zh)* | 2021-12-29 | 2024-04-30 | 西安奕斯伟材料科技股份有限公司 | 晶体直径检测方法、系统及计算机程序产品 |
| CN114252018A (zh)* | 2021-12-29 | 2022-03-29 | 西安奕斯伟材料科技有限公司 | 晶体直径检测方法、系统及计算机程序产品 |
| CN114187368A (zh)* | 2022-02-17 | 2022-03-15 | 深圳艾灵网络有限公司 | 建筑板材的暗纹检测方法、装置、电子设备及存储介质 |
| US12418713B2 (en) | 2022-02-25 | 2025-09-16 | Canon Kabushiki Kaisha | Main object determination apparatus, imaging apparatus, and control method for controlling main object determination apparatus |
| CN114577122B (zh)* | 2022-02-28 | 2023-08-18 | 长三角先进材料研究院 | 一种基于图像处理的自冲铆接剖面几何参数自动测量方法 |
| CN114577122A (zh)* | 2022-02-28 | 2022-06-03 | 长三角先进材料研究院 | 一种基于图像处理的自冲铆接剖面几何参数自动测量方法 |
| CN115396576B (zh)* | 2022-08-24 | 2023-08-08 | 南京农业大学 | 从侧视、俯视双视角图像自动测量羊体尺的装置和方法 |
| CN115396576A (zh)* | 2022-08-24 | 2022-11-25 | 南京农业大学 | 从侧视、俯视双视角图像自动测量羊体尺的装置和方法 |
| CN115620117B (zh)* | 2022-12-20 | 2023-03-14 | 吉林省信息技术研究所 | 一种用于网络访问权限认证的人脸信息加密方法及系统 |
| CN115620117A (zh)* | 2022-12-20 | 2023-01-17 | 吉林省信息技术研究所 | 一种用于网络访问权限认证的人脸信息加密方法及系统 |
| CN120183002A (zh)* | 2025-05-22 | 2025-06-20 | 泰山体育产业集团有限公司 | 一种单目彩色视频的三维人体关节点定位方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105469113B (zh) | 2019-03-22 |
| CN105469113A (zh) | 2016-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017084204A1 (fr) | Procédé et système de suivi d'un point du squelette humain dans un flux vidéo en deux dimensions | |
| CN103927016B (zh) | 一种基于双目视觉的实时三维双手手势识别方法及其系统 | |
| WO2021008019A1 (fr) | Procédé et appareil de suivi de position et support de stockage lisible par ordinateur | |
| CN107909081B (zh) | 一种深度学习中图像数据集的快速获取和快速标定方法 | |
| CN101854467B (zh) | 一种视频分割中阴影的自适应检测及消除方法 | |
| WO2018145470A1 (fr) | Procédé et dispositif de détection d'image | |
| US20110299774A1 (en) | Method and system for detecting and tracking hands in an image | |
| CN105160297B (zh) | 基于肤色特征的蒙面人事件自动检测方法 | |
| Ibraheem et al. | Comparative study of skin color based segmentation techniques | |
| CN103119625B (zh) | 一种视频人物分割的方法及装置 | |
| CN101593022A (zh) | 一种基于指端跟踪的快速人机交互方法 | |
| CN103218605A (zh) | 一种基于积分投影与边缘检测的快速人眼定位方法 | |
| Chen et al. | A novel color edge detection algorithm in RGB color space | |
| CN101483763A (zh) | 一种面向社会治安监控的数字影像处理方法及其装置 | |
| CN110032932B (zh) | 一种基于视频处理和决策树设定阈值的人体姿态识别方法 | |
| CN103440035A (zh) | 一种三维空间中的手势识别系统及其识别方法 | |
| CN104182976B (zh) | 一种野外运动目标精细化提取方法 | |
| CN115100226A (zh) | 一种基于单目数字图像的轮廓提取方法 | |
| CN102609728B (zh) | 特定类敏感图像检测方法 | |
| CN117133032A (zh) | 人脸遮挡条件下基于rgb-d图像的人员识别与定位方法 | |
| CN110287894A (zh) | 一种针对超广角视频的手势识别方法及系统 | |
| Dawod et al. | Adaptive skin color model for hand segmentation | |
| CN105930793A (zh) | 一种基于sae特征可视化学习的人体检测方法 | |
| CN102163277B (zh) | 一种基于区域的肤色分割方法 | |
| CN105844641B (zh) | 一种动态环境下的自适应阈值分割方法 |
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:16865387 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:16865387 Country of ref document:EP Kind code of ref document:A1 |