CN109165552A - A kind of gesture recognition method based on human body key point, system and memory - Google Patents
A kind of gesture recognition method based on human body key point, system and memory Download PDFInfo
- Publication number
- CN109165552A CN109165552A CN201810772931.1A CN201810772931A CN109165552A CN 109165552 A CN109165552 A CN 109165552A CN 201810772931 A CN201810772931 A CN 201810772931A CN 109165552 A CN109165552 A CN 109165552A
- Authority
- CN
- China
- Prior art keywords
- key point
- window
- gesture recognition
- body key
- human body
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of gesture recognition method based on human body key point, system and memories, this method comprises: judging the region moved in video pictures by mobile detection first, then do target detection in these effective coverages.The key point for obtaining body and face by gesture recognition again, carries out machine learning for key point, then identifies the posture of people, such as stands, and is seated, turns round, laughs.The key point of human body and face is trained in this way, then gesture recognition is carried out to target, the accuracy of gesture recognition can be greatly promoted, improves gesture recognition in the feasibility of practical application scene.
Description
Technical field
The present invention relates to gesture recognition technical fields, and in particular to a kind of gesture recognition method based on human body key point,
System and memory.
Background technique
Human body attitude identification and deep learning are the research hotspots in intelligent video analysis field, have obtained academia in recent years
And the extensive attention of engineering circles, it is the theoretical base of the numerous areas such as intelligent video analysis and understanding, video monitoring, human-computer interaction
Plinth.In recent years, by the deep learning algorithm of extensive concern by Successful utilization in each necks such as speech recognition, figure identifications
Domain.Deep learning theory achieves distinguished achievement in still image feature extraction, and gradually extends to time series
In video behavior Study of recognition.
In education sector, video flowing, identification and record captured by the method analytic instruction scene by deep learning
The behavior of student, to assess quality of instruction, the classroom performance of student provides direct guidance for subsequent teaching optimization.
In order to analyze classroom instruction appearance behavior, need by recognition of face go out be which student, it is also necessary to tracking and
The behavior for analyzing student, for example raises one's hand to make a speech on classroom, stands up and answers a question, the movement such as sit down.Currently, popular does
Method, by identifying and marking the position of physical feature, to understand the posture performance under different angle, then judge to be likely to occur
Behavior.
But under scene of imparting knowledge to students, it will usually there are tens students while occurring in picture, the lower part of the body of student usually quilt
What desk blocked；And front and back also will appear the case where blocking.Using above-mentioned under the environment complicated and changeable in face of teacher
Posture detection analyzes the posture of student, it is easy to lead to not the concrete behavior of correct cognometrics, can frequently result in erroneous judgement
Situation occurs.
Summary of the invention
The present invention for the technical problems in the prior art, provides a kind of gesture recognition side based on human body key point
Method, system and memory grab effective region by mobile detection, and human testing finally carries out behavioural analysis and note
Record has reached behavioural analysis that can accurately under real-time analytic instruction scene.
The technical scheme to solve the above technical problems is that
On the one hand, the present invention provides a kind of gesture recognition method based on human body key point, comprising the following steps:
Obtain RTSP video flowing；
Moving target detection is carried out to image in video flowing, obtains mobile target region；
People's face and body critical point detection and information extraction are carried out to image in region；
To carry out in the trained in advance SVM classifier of people's face and body key point information input of extraction Classification and Identification and
Attitude prediction.
Further, described that Moving target detection is carried out to image in video flowing, obtain mobile target region, packet
It includes:
Comparison front and back video frame, carries out movable object tracking and target detection, obtains window where mobile target；
Filtering threshold is set, filters the size detected and is less than window where the mobile target of filtering threshold；
Window where remaining mobile target is spliced, mobile target region is obtained.
Further, described to splice window where remaining mobile target, obtain moving object region, comprising:
According to the window's position where the remaining mobile target, a rectangle frame, as moving object region are generated, it is described
Rectangle frame be can frame select the minimum rectangle frames of windows where all remaining mobile targets in video frame.
Further, it is described people's face and body critical point detection and information extraction are carried out to image in window after, also wrap
It includes:
People's face and body key point information of extraction is normalized.
Further, the training process of the SVM classifier includes:
Obtain RTSP video flowing；
Movable object tracking and target detection are carried out to image in video flowing, obtain mobile target region；
People's face and body critical point detection and information extraction are carried out to image in region；
People's face and body key point information of extraction is normalized；
Mark classification processing is carried out to the data after normalized, and is trained by SVM, SVM classifier is obtained；
Wherein, the types of models of the SVM selects C_SVC, and the Selection of kernel function LINEAR of the SVM, training sample is not
Less than 10000.
On the other hand, the present invention also provides a kind of gesture recognition system based on human body key point, which includes:
Video flowing obtains module, for obtaining RTSP video flowing；
Moving target detection module is obtained and is moved for carrying out movable object tracking and target detection to image in video flowing
Moving-target region；
Key point information extraction module, for being mentioned to image progress people's face and body critical point detection and information in region
It takes；
Identification module, in people's face and body key point information input for that will extract SVM classifier trained in advance into
Row Classification and Identification and attitude prediction.
Further, the Moving target detection module, comprising:
Window obtains module, for comparing front and back video frame, carries out movable object tracking and target detection, obtains mobile mesh
Window where mark；
Threshold value setting and filtering module filter the shifting that the size detected is less than filtering threshold for filtering threshold to be arranged
Window where moving-target；
Window splicing module obtains mobile target location for splicing window where remaining mobile target
Domain.
Further, the window splicing module, is specifically used for: according to the window's position where the remaining mobile target,
Generate a rectangle frame, as moving object region, the rectangle frame for can frame select all remaining mobile target institutes in video frame
In the minimum rectangle frame of window.
Further, which further includes normalized module, for extracting in the key point information extraction module
After face and body key point information, key point information is normalized.
Further, it the present invention also provides a kind of memory, is stored in the memory and is based on for realizing above-mentioned one kind
The computer software programs of the gesture recognition method of human body key point.
The beneficial effects of the present invention are:
1. the present invention proposes that the result based on mobile detection goes the key point for carrying out human body and face to extract, substantially increase
The speed of feature extraction.
2. proposing to carry out data mark after mixing based on characteristics of human body and facial characteristics, keep the operability of data big
It is big to improve.
3. proposing to carry out gesture recognition into mixing using characteristics of human body and facial characteristics, the standard of gesture recognition is substantially increased
True property.
Detailed description of the invention
Fig. 1 is the method for the present invention flow chart；
Fig. 2 is present system structure chart.
Specific embodiment
The principle and features of the present invention will be described below with reference to the accompanying drawings, and the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the invention.
Gesture recognition technology plays in various fields such as intelligent monitoring, human-computer interaction, video sequence understanding, medical treatment & healths
More and more important role, and video gesture recognition technology is in visible angle, obtained under the factors such as scene is complicated, and number is excessive compared with
High accuracy rate has very big challenge.
In education sector, in order to analyze the teaching behavior of student and teacher, the feedback and guidance of quality of instruction are obtained, this
It can be realized by analyzing the video flowing of camera in real time based on deep learning network.
In order to realize that student's posture analysis under scene of imparting knowledge to students, this patent propose such solution:
The region moved in video pictures is judged by mobile detection first, then does target inspection in these effective coverages
It surveys.The key point for obtaining body and face by gesture recognition again, carries out machine learning for key point, then identifies the posture of people,
Such as stand, it is seated, turns round, laugh.The key point of human body and face is trained in this way, then posture knowledge is carried out to target
Not, the accuracy of gesture recognition can be greatly promoted, improves gesture recognition in the feasibility of practical application scene.
On the one hand, the present invention provides a kind of gesture recognition method based on human body key point, as shown in Figure 1, including following
Step:
S100 obtains RTSP video flowing；
S200 carries out Moving target detection to image in video flowing, obtains mobile target region；
Either target detection or posture analysis all compare consuming software and hardware resources.In order to improve efficiency, target is being done
Before detection, mobile detection is done first, finds the window where mobile target.This window is usually larger, but still compares whole picture
Image is much smaller.Lesser window is mostly wrong report, can be according to threshold filtering.Specifically,
Comparison front and back video frame first, carries out movable object tracking and target detection, obtains window where mobile target；
Filtering threshold is set, filters the size detected and is less than window where the mobile target of filtering threshold；
According to the window's position where the remaining mobile target, a rectangle frame, as moving object region are generated, it is described
Rectangle frame be can frame select the minimum rectangle frames of windows where all remaining mobile targets in video frame.
Multiple moving windows detected are spliced together, so that target identification is only used in the partial region of mobile target
Target detection is inside done, the speed of target detection can be greatly improved in this way.
S300 carries out people's face and body critical point detection and information extraction to image in region；Body critical point detection, mesh
Before have many schemes, more fiery has such as OpenPose and the AlphaPose to increase income recently etc., uses these to carry out crucial
The extraction of point.There are also many schemes for the extraction of face key point, and that more famous is dlib landmark, and based on deep
Spend the deep landmark etc. of study.
S400, in order to improve the validity of data training and the accuracy rate of result, to people's face and body key point of extraction
Information is normalized；
Normalize formula are as follows:
Wherein, xiIndicate that i-th of the face extracted or body key point information, i value are integer.
Mark is carried out to people's face and body key point information after normalization, i.e., is according to the actual situation closed people's face and body
Key point information labeling is to raise one's hand to make a speech, stand up and the movement such as answer a question, sit down；
People's face and body key point information after mark is input in SVM and is trained by S500, the model of the SVM
Type selects C_SVC, the Selection of kernel function LINEAR of the SVM, and training sample is not less than 10000；
People's face and body key point information is extracted, instruction is then input to using above-mentioned SVM training method in cognitive phase
Classification and Identification and attitude prediction are carried out in the SVM classifier perfected.
On the other hand, the present invention also provides a kind of gesture recognition systems based on human body key point, as shown in Fig. 2, this is
System includes:
Video flowing obtains module, for obtaining RTSP video flowing；
Moving target detection module is obtained and is moved for carrying out movable object tracking and target detection to image in video flowing
Moving-target region；
Key point information extraction module, for being mentioned to image progress people's face and body critical point detection and information in region
It takes；
Identification module, in people's face and body key point information input for that will extract SVM classifier trained in advance into
Row Classification and Identification and attitude prediction.
Further, the Moving target detection module, comprising:
Window obtains module, for comparing front and back video frame, carries out movable object tracking and target detection, obtains mobile mesh
Window where mark；
Threshold value setting and filtering module filter the shifting that the size detected is less than filtering threshold for filtering threshold to be arranged
Window where moving-target；
Window splicing module obtains mobile target location for splicing window where remaining mobile target
Domain.
Further, the window splicing module, is specifically used for: according to the window's position where the remaining mobile target,
Generate a rectangle frame, as moving object region, the rectangle frame for can frame select all remaining mobile target institutes in video frame
In the minimum rectangle frame of window.
Further, which further includes normalized module, for extracting in the key point information extraction module
After face and body key point information, key point information is normalized.
Further, it the present invention also provides a kind of memory, is stored in the memory and is based on for realizing above-mentioned one kind
The computer software programs of the gesture recognition method of human body key point.
The present invention proposes that the result based on mobile detection goes the key point for carrying out human body and face to extract, and substantially increases spy
Levy the speed extracted；It proposes to carry out data mark after mixing based on characteristics of human body and facial characteristics, makes operating for data
Property greatly improves；It proposes to carry out gesture recognition into mixing using characteristics of human body and facial characteristics, substantially increases gesture recognition
Accuracy.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of gesture recognition method based on human body key point, which comprises the following steps:
Obtain RTSP video flowing；
Moving target detection is carried out to image in video flowing, obtains mobile target region；
People's face and body critical point detection and information extraction are carried out to image in region；
Classification and Identification and posture will be carried out in people's face and body key point information input of extraction SVM classifier trained in advance
Prediction.
2. a kind of gesture recognition method based on human body key point according to claim 1, which is characterized in that described to view
Image carries out Moving target detection in frequency stream, obtains mobile target region, comprising:
Comparison front and back video frame, carries out movable object tracking and target detection, obtains window where mobile target；
Filtering threshold is set, filters the size detected and is less than window where the mobile target of filtering threshold；
Window where remaining mobile target is spliced, mobile target region is obtained.
3. a kind of gesture recognition method based on human body key point according to claim 2, which is characterized in that described will remain
Window where remaining mobile target is spliced, and moving object region is obtained, comprising:
According to the window's position where the remaining mobile target, a rectangle frame, as moving object region, the rectangle are generated
Frame be can frame select the minimum rectangle frames of windows where all remaining mobile targets in video frame.
4. a kind of gesture recognition method based on human body key point according to claim 1, which is characterized in that described to window
After image carries out people's face and body critical point detection and information extraction in mouthful, further includes:
People's face and body key point information of extraction is normalized.
5. a kind of gesture recognition method based on human body key point according to claim 4, which is characterized in that the SVM points
The training process of class device includes:
Obtain RTSP video flowing；
Movable object tracking and target detection are carried out to image in video flowing, obtain mobile target region；
People's face and body critical point detection and information extraction are carried out to image in region；
People's face and body key point information of extraction is normalized；
Mark classification processing is carried out to the data after normalized, and is trained by SVM, SVM classifier is obtained；
Wherein, the types of models of the SVM selects C_SVC, the Selection of kernel function L I NEAR of the SVM, and training sample is small
In 10000.
6. a kind of gesture recognition system based on human body key point, which is characterized in that the system includes:
Video flowing obtains module, for obtaining RTSP video flowing；
Moving target detection module obtains mobile mesh for carrying out movable object tracking and target detection to image in video flowing
Mark region；
Key point information extraction module, for carrying out people's face and body critical point detection and information extraction to image in region；
Identification module divides for inputting people's face and body key point information of extraction in SVM classifier trained in advance
Class identification and attitude prediction.
7. a kind of gesture recognition system based on human body key point according to claim 6, which is characterized in that the mobile mesh
Mark detection module, comprising:
Window obtains module, for comparing front and back video frame, carries out movable object tracking and target detection, obtains mobile target institute
In window；
Threshold value setting and filtering module filter the mobile mesh that the size detected is less than filtering threshold for filtering threshold to be arranged
Window where mark；
Window splicing module obtains mobile target region for splicing window where remaining mobile target.
8. a kind of gesture recognition system based on human body key point according to claim 7, which is characterized in that the window is spelled
Connection module is specifically used for: according to the window's position where the remaining mobile target, generating a rectangle frame, as moves target
Region, the rectangle frame be can frame select the minimum rectangle frames of windows where all remaining mobile targets in video frame.
9. a kind of gesture recognition system based on human body key point according to claim 6, which is characterized in that further include normalizing
Change processing module, for after the key point information extraction module extracts face and body key point information, to key
Point information is normalized.
10. a kind of memory, which is characterized in that be stored in the memory described in any item for realizing claim 1-5
A kind of computer software programs of the gesture recognition method based on human body key point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810772931.1A CN109165552B (en) | 2018-07-14 | 2018-07-14 | Gesture recognition method and system based on human body key points and memory |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810772931.1A CN109165552B (en) | 2018-07-14 | 2018-07-14 | Gesture recognition method and system based on human body key points and memory |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109165552A true CN109165552A (en) | 2019-01-08 |
| CN109165552B CN109165552B (en) | 2021-02-26 |
Family
ID=64897918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810772931.1A Active CN109165552B (en) | 2018-07-14 | 2018-07-14 | Gesture recognition method and system based on human body key points and memory |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109165552B (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109815921A (en) * | 2019-01-29 | 2019-05-28 | 北京融链科技有限公司 | The prediction technique and device of the class of activity in hydrogenation stations |
| CN109858444A (en) * | 2019-01-31 | 2019-06-07 | 北京字节跳动网络技术有限公司 | The training method and device of human body critical point detection model |
| CN109871804A (en) * | 2019-02-19 | 2019-06-11 | 上海宝尊电子商务有限公司 | A kind of method and system of shop stream of people discriminance analysis |
| CN110147712A (en) * | 2019-03-27 | 2019-08-20 | 苏州书客贝塔软件科技有限公司 | A kind of intelligent cloud platform of pedestrian's analysis |
| CN110222608A (en) * | 2019-05-24 | 2019-09-10 | 山东海博科技信息系统股份有限公司 | A kind of self-service examination machine eyesight detection intelligent processing method |
| CN110298237A (en) * | 2019-05-20 | 2019-10-01 | 平安科技（深圳）有限公司 | Head pose recognition methods, device, computer equipment and storage medium |
| CN110399822A (en) * | 2019-07-17 | 2019-11-01 | 思百达物联网科技(北京)有限公司 | Action identification method of raising one's hand, device and storage medium based on deep learning |
| CN110457999A (en) * | 2019-06-27 | 2019-11-15 | 广东工业大学 | A kind of animal posture behavior estimation based on deep learning and SVM and mood recognition methods |
| CN110674785A (en) * | 2019-10-08 | 2020-01-10 | 中兴飞流信息科技有限公司 | Multi-person posture analysis method based on human body key point tracking |
| CN110826401A (en) * | 2019-09-26 | 2020-02-21 | 广州视觉风科技有限公司 | Human body limb language identification method and system |
| CN110837795A (en) * | 2019-11-04 | 2020-02-25 | 防灾科技学院 | Teaching condition intelligent monitoring method, device and equipment based on classroom monitoring video |
| CN111046825A (en) * | 2019-12-19 | 2020-04-21 | 杭州晨鹰军泰科技有限公司 | Human body posture recognition method, device and system and computer readable storage medium |
| CN111513745A (en) * | 2020-04-21 | 2020-08-11 | 南通大学 | Intelligent non-contact CT body position recognition device used in high-risk environment |
| CN111582208A (en) * | 2020-05-13 | 2020-08-25 | 北京字节跳动网络技术有限公司 | Method and device for generating organism posture key point information |
| CN111652076A (en) * | 2020-05-11 | 2020-09-11 | 重庆大学 | Automatic gesture recognition system for AD (analog-digital) scale comprehension capability test |
| CN111680562A (en) * | 2020-05-09 | 2020-09-18 | 北京中广上洋科技股份有限公司 | Human body posture identification method and device based on skeleton key points, storage medium and terminal |
| CN111907520A (en) * | 2020-07-31 | 2020-11-10 | 东软睿驰汽车技术（沈阳）有限公司 | Pedestrian posture recognition method and device and unmanned automobile |
| CN112836667A (en) * | 2021-02-20 | 2021-05-25 | 上海吉盛网络技术有限公司 | Method for judging falling and retrograde of passenger on ascending escalator |
| CN113065482A (en) * | 2021-04-09 | 2021-07-02 | 上海云从企业发展有限公司 | Behavior detection method, system, computer device and medium based on image recognition |
| CN113158756A (en) * | 2021-02-09 | 2021-07-23 | 上海领本智能科技有限公司 | Posture and behavior analysis module and method based on HRNet deep learning |
| CN114663910A (en) * | 2022-01-11 | 2022-06-24 | 重庆工程学院 | Multi-mode learning state analysis system |
| WO2023185034A1 (en) * | 2022-03-31 | 2023-10-05 | 上海商汤智能科技有限公司 | Action detection method and apparatus, electronic device and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5990824A (en) * | 1998-06-19 | 1999-11-23 | Northrop Grumman Corporation | Ground based pulse radar system and method providing high clutter rejection and reliable moving target indication with extended range for airport traffic control and other applications |
| US6697010B1 (en) * | 2002-04-23 | 2004-02-24 | Lockheed Martin Corporation | System and method for moving target detection |
| US20150138078A1 (en) * | 2013-11-18 | 2015-05-21 | Eyal Krupka | Hand pose recognition using boosted look up tables |
| CN105389549A (en) * | 2015-10-28 | 2016-03-09 | 北京旷视科技有限公司 | Object recognition method and device based on human body action characteristic |
| CN105469065A (en) * | 2015-12-07 | 2016-04-06 | 中国科学院自动化研究所 | Recurrent neural network-based discrete emotion recognition method |
| CN106228293A (en) * | 2016-07-18 | 2016-12-14 | 重庆中科云丛科技有限公司 | teaching evaluation method and system |
| CN106778585A (en) * | 2016-12-08 | 2017-05-31 | 腾讯科技（上海）有限公司 | A kind of face key point-tracking method and device |
| CN106845338A (en) * | 2016-12-13 | 2017-06-13 | 深圳市智美达科技股份有限公司 | Pedestrian detection method and system in video flowing |
| CN107330914A (en) * | 2017-06-02 | 2017-11-07 | 广州视源电子科技股份有限公司 | Human face part motion detection method and device and living body identification method and system |
| CN107697069A (en) * | 2017-10-31 | 2018-02-16 | 上海汽车集团股份有限公司 | Fatigue of automobile driver driving intelligent control method |
| CN108197589A (en) * | 2018-01-19 | 2018-06-22 | 北京智能管家科技有限公司 | Semantic understanding method, apparatus, equipment and the storage medium of dynamic human body posture |
| CN108198208A (en) * | 2017-12-27 | 2018-06-22 | 浩云科技股份有限公司 | A kind of mobile detection method based on target following |
-
2018
- 2018-07-14 CN CN201810772931.1A patent/CN109165552B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5990824A (en) * | 1998-06-19 | 1999-11-23 | Northrop Grumman Corporation | Ground based pulse radar system and method providing high clutter rejection and reliable moving target indication with extended range for airport traffic control and other applications |
| US6697010B1 (en) * | 2002-04-23 | 2004-02-24 | Lockheed Martin Corporation | System and method for moving target detection |
| US20150138078A1 (en) * | 2013-11-18 | 2015-05-21 | Eyal Krupka | Hand pose recognition using boosted look up tables |
| CN105389549A (en) * | 2015-10-28 | 2016-03-09 | 北京旷视科技有限公司 | Object recognition method and device based on human body action characteristic |
| CN105469065A (en) * | 2015-12-07 | 2016-04-06 | 中国科学院自动化研究所 | Recurrent neural network-based discrete emotion recognition method |
| CN106228293A (en) * | 2016-07-18 | 2016-12-14 | 重庆中科云丛科技有限公司 | teaching evaluation method and system |
| CN106778585A (en) * | 2016-12-08 | 2017-05-31 | 腾讯科技（上海）有限公司 | A kind of face key point-tracking method and device |
| CN106845338A (en) * | 2016-12-13 | 2017-06-13 | 深圳市智美达科技股份有限公司 | Pedestrian detection method and system in video flowing |
| CN107330914A (en) * | 2017-06-02 | 2017-11-07 | 广州视源电子科技股份有限公司 | Human face part motion detection method and device and living body identification method and system |
| CN107697069A (en) * | 2017-10-31 | 2018-02-16 | 上海汽车集团股份有限公司 | Fatigue of automobile driver driving intelligent control method |
| CN108198208A (en) * | 2017-12-27 | 2018-06-22 | 浩云科技股份有限公司 | A kind of mobile detection method based on target following |
| CN108197589A (en) * | 2018-01-19 | 2018-06-22 | 北京智能管家科技有限公司 | Semantic understanding method, apparatus, equipment and the storage medium of dynamic human body posture |
Non-Patent Citations (6)
| Title |
|---|
| JERRYZHANG__: "OpenPose 安装配置与测试", 《HTTPS:https://BLOG.CSDN.NET/JERRYZHANG__/ARTICLE/DETAILS/76208871》 * |
| YUTIAN CAO等: "Two Algorithms for the Detection and Tracking of Moving Vehicle Targets in Aerial Infrared Image Sequences", 《REMOTE SENSING》 * |
| ZHE CAO等: "Realtime Multi-person 2D Pose Estimation using Part Affinity Fields", 《2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)》 * |
| 张鸿宇: "课堂学习行为测量系统的设计与实现", 《中国优秀硕士学位论文全文数据库 社会科学II辑》 * |
| 李搏轩: "基于图像处理的移动目标测量方法的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 邵恒等: "智慧国土视频监控运动目标提取新方法研究", 《现代测绘》 * |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109815921A (en) * | 2019-01-29 | 2019-05-28 | 北京融链科技有限公司 | The prediction technique and device of the class of activity in hydrogenation stations |
| CN109858444A (en) * | 2019-01-31 | 2019-06-07 | 北京字节跳动网络技术有限公司 | The training method and device of human body critical point detection model |
| CN109871804A (en) * | 2019-02-19 | 2019-06-11 | 上海宝尊电子商务有限公司 | A kind of method and system of shop stream of people discriminance analysis |
| CN110147712A (en) * | 2019-03-27 | 2019-08-20 | 苏州书客贝塔软件科技有限公司 | A kind of intelligent cloud platform of pedestrian's analysis |
| CN110298237A (en) * | 2019-05-20 | 2019-10-01 | 平安科技（深圳）有限公司 | Head pose recognition methods, device, computer equipment and storage medium |
| CN110222608A (en) * | 2019-05-24 | 2019-09-10 | 山东海博科技信息系统股份有限公司 | A kind of self-service examination machine eyesight detection intelligent processing method |
| CN110457999B (en) * | 2019-06-27 | 2022-11-04 | 广东工业大学 | Animal posture behavior estimation and mood recognition method based on deep learning and SVM |
| CN110457999A (en) * | 2019-06-27 | 2019-11-15 | 广东工业大学 | A kind of animal posture behavior estimation based on deep learning and SVM and mood recognition methods |
| CN110399822A (en) * | 2019-07-17 | 2019-11-01 | 思百达物联网科技(北京)有限公司 | Action identification method of raising one's hand, device and storage medium based on deep learning |
| CN110826401A (en) * | 2019-09-26 | 2020-02-21 | 广州视觉风科技有限公司 | Human body limb language identification method and system |
| CN110826401B (en) * | 2019-09-26 | 2023-12-26 | 广州视觉风科技有限公司 | Human body limb language identification method and system |
| CN110674785A (en) * | 2019-10-08 | 2020-01-10 | 中兴飞流信息科技有限公司 | Multi-person posture analysis method based on human body key point tracking |
| CN110837795A (en) * | 2019-11-04 | 2020-02-25 | 防灾科技学院 | Teaching condition intelligent monitoring method, device and equipment based on classroom monitoring video |
| CN111046825A (en) * | 2019-12-19 | 2020-04-21 | 杭州晨鹰军泰科技有限公司 | Human body posture recognition method, device and system and computer readable storage medium |
| CN111513745A (en) * | 2020-04-21 | 2020-08-11 | 南通大学 | Intelligent non-contact CT body position recognition device used in high-risk environment |
| CN111513745B (en) * | 2020-04-21 | 2021-10-26 | 南通大学 | Intelligent non-contact CT body position recognition device used in high-risk environment |
| CN111680562A (en) * | 2020-05-09 | 2020-09-18 | 北京中广上洋科技股份有限公司 | Human body posture identification method and device based on skeleton key points, storage medium and terminal |
| CN111652076A (en) * | 2020-05-11 | 2020-09-11 | 重庆大学 | Automatic gesture recognition system for AD (analog-digital) scale comprehension capability test |
| CN111652076B (en) * | 2020-05-11 | 2024-05-31 | 重庆知熠行科技发展有限公司 | Automatic gesture recognition system for AD (analog-to-digital) meter understanding capability test |
| CN111582208A (en) * | 2020-05-13 | 2020-08-25 | 北京字节跳动网络技术有限公司 | Method and device for generating organism posture key point information |
| CN111907520A (en) * | 2020-07-31 | 2020-11-10 | 东软睿驰汽车技术（沈阳）有限公司 | Pedestrian posture recognition method and device and unmanned automobile |
| CN113158756A (en) * | 2021-02-09 | 2021-07-23 | 上海领本智能科技有限公司 | Posture and behavior analysis module and method based on HRNet deep learning |
| CN112836667A (en) * | 2021-02-20 | 2021-05-25 | 上海吉盛网络技术有限公司 | Method for judging falling and retrograde of passenger on ascending escalator |
| CN112836667B (en) * | 2021-02-20 | 2022-11-15 | 上海吉盛网络技术有限公司 | Method for judging falling and reverse running of passengers going upstairs escalator |
| CN113065482A (en) * | 2021-04-09 | 2021-07-02 | 上海云从企业发展有限公司 | Behavior detection method, system, computer device and medium based on image recognition |
| CN114663910A (en) * | 2022-01-11 | 2022-06-24 | 重庆工程学院 | Multi-mode learning state analysis system |
| WO2023185034A1 (en) * | 2022-03-31 | 2023-10-05 | 上海商汤智能科技有限公司 | Action detection method and apparatus, electronic device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109165552B (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109165552A (en) | A kind of gesture recognition method based on human body key point, system and memory | |
| Sincan et al. | Autsl: A large scale multi-modal turkish sign language dataset and baseline methods | |
| CN108090857B (en) | Multi-mode student classroom behavior analysis system and method | |
| CN113762133B (en) | Dead weight body-building auxiliary training system, method and terminal based on human body gesture recognition | |
| WO2021077382A1 (en) | Method and apparatus for determining learning state, and intelligent robot | |
| CN104111733B (en) | A kind of gesture recognition system and method | |
| CN109034099A (en) | A kind of expression recognition method and device | |
| CN104517097A (en) | Kinect-based moving human body posture recognition method | |
| CN110085068A (en) | Learning tutoring method and device based on image recognition | |
| CN108846853A (en) | A kind of teaching behavior analysis method and device based on target following and attitude detection | |
| CN109377429A (en) | A kind of recognition of face quality-oriented education wisdom evaluation system | |
| WO2020007097A1 (en) | Data processing method, storage medium and electronic device | |
| Gao et al. | Application of posture recognition service system based on information fusion smart sensor in dance training | |
| CN111950486A (en) | Teaching video processing method based on cloud computing | |
| CN113705510A (en) | Target identification tracking method, device, equipment and storage medium | |
| Hrúz et al. | Local Binary Pattern based features for sign language recognition | |
| Yi et al. | Real time learning evaluation based on gaze tracking | |
| Zhang et al. | Intelligent classroom teaching assessment system based on deep learning model face recognition technology | |
| Seneviratne et al. | Student and lecturer performance enhancement system using artificial intelligence | |
| CN115132027A (en) | Intelligent programming learning system and method based on multi-mode deep learning | |
| CN110689066B (en) | Training method combining face recognition data equalization and enhancement | |
| Ferrie et al. | Cell tracking: A modeling and minimization approach | |
| Huang et al. | Research on learning state based on students’ attitude and emotion in class learning | |
| Méndez-Ortega et al. | Supervision and control of students during online assessments applying computer vision techniques: a systematic literature review | |
| CN117992344A (en) | UI (user interface) automation test assertion statement generation method, device and equipment |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220406 Address after: 518000 A1201, block ABCD, building 3, phase I, Tianan Yungu Industrial Park, Gangtou community, Bantian street, Longgang District, Shenzhen, Guangdong Patentee after: Shenzhen Zhongwei Shenmu Technology Co.,Ltd. Address before: 518000 Room 401, building 7, Jinxiu Dadi, 117 hudipai, songyuanxia community, Guanhu street, Longhua District, Shenzhen City, Guangdong Province Patentee before: SHENZHEN SHENMU INFORMATION TECHNOLOGY Co.,Ltd. |