Adaptive action recognition method based on multi-view and multi-mode characteristics
An action recognition and multi-view technology, applied in the field of computer vision and pattern recognition, can solve the problems of not being able to fully capture the historical change process of target movement, performance degradation, and unstable recognition performance, so as to improve performance, performance and stability , the effect of improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0032] Example 1
[0033] Such as figure 1 Shown is the operation flowchart of the adaptive action recognition method based on multi-view and multi-modal features of the present invention. The operation steps of the method include:
[0034] Step 01 video preprocessing
[0035] Filter and denoise the input depth image and RGB image sequence. At the same time, through the infrared device of the Kinect device, the approximate distance between the target and the camera can be measured. According to the distance value, add 0.5 meters to obtain a large threshold, and subtract 1 meter to obtain The small threshold, for example, in this embodiment, the distance between the target and the camera is about 2 meters, the large threshold is 2.5 meters, and the small threshold is 1 meter. When the depth value of a pixel is greater than the large threshold or less than the small threshold, the pixel is marked as 0, otherwise it is marked as 1, so that the interference of the background to the t...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap