Video-based multi-target continuous behavior analysis method, system and device
A behavioral analysis and multi-objective technology, applied to instruments, character and pattern recognition, computer components, etc., can solve problems such as excessive dependence on the environment and background, excessive data volume requirements, low recognition accuracy, etc., to achieve robustness performance, strong anti-interference, and the effect of improving accuracy
Pending Publication Date: 2020-04-28
夸氪思维(南京)智能技术有限公司
View PDF5 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem that the existing target behavior recognition method has low recognition accuracy due to excessive data volume requirements in the training process, excessive dependence on the environment and background, etc., the first method of the present invention Aspects, a video-based multi-target continuous behavior analysis method is proposed, which includes:
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0043] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than Full examples. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0044] The application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, rather than to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention belongs to the field of behavior recognition, and particularly relates to a video-based multi-target continuous behavior analysis method, system and device. The objective of the invention is to solve the problem of low accuracy of existing target behavior identification. The method of the system comprises the following steps: acquiring a target and a target area in each video frame of an input video; performing key point extraction on each target area, building a motion model, and taking the model as a global feature; respectively extracting local features of each target area ineach video frame by adopting a feature heat map based on an attention mechanism; fusing the global features and the local features by adopting a staging ensemble learning method to obtain fused features; performing action sequence classification on each video frame and the fusion features of the input video through a classifier to obtain a plurality of groups of action classification results; andgenerating a descriptive statement corresponding to the action of each target through a descriptor based on a result of the plurality of groups of action classifications. According to the invention, the accuracy of target behavior recognition is improved.
Description
technical field [0001] The invention belongs to the field of behavior recognition, and in particular relates to a video-based multi-target continuous behavior analysis method, system and device. Background technique [0002] Target action recognition is an important topic in the field of computer vision. It has a wide range of application values in behavior detection, video surveillance and other fields. Different from pure image recognition, target behavior recognition will be interfered by many factors, such as lighting, background and so on. The current target recognition methods are generally divided into traditional template matching methods based on artificial features, and data-driven end-to-end training and learning methods. [0003] The traditional template matching method based on artificial features creates an original standard template by collecting image information in advance, and then when detecting, the system will match the relevant values of the targe...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & AuthorityApplications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/41G06V20/46G06F18/241Y02D10/00
Inventor吴伟马超王威关飞庆左丹婷
Owner夸氪思维(南京)智能技术有限公司