Human body behavior identification method based on depth sequence
A recognition method and sequence technology, applied in the field of pattern recognition and computer vision, can solve problems such as unsatisfactory effects, achieve the effect of filtering the background, strong robustness, and reduce the amount of data
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0042] According to the description of the method above, the experimental verification was carried out. The experimental data chooses MSRAction3D database and MSRGesture3D database. The MSRAction3D database is a public database collected using the Microsoft Kinect depth sensor. The database consists of 10 performers completing 20 depth sequences of actions. Each action of each performer is collected 2-3 times, although the background of this database has been processed. , but because many of the 20 actions are very similar, it is still very challenging to recognize this data set; MSRGesture3D is a gesture database that acquires depth sequences through depth cameras, and is also a very popular human gesture test evaluation database . The database contains 12 dynamic gestures defined by AmericanSignLanguage (ASL). Each gesture was performed 2-3 times by 10 people. This database is quite challenging due to the self-occlusion problem.
[0043] The experimental results of the m...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com