Video behavior recognition method based on weighted fusion of multiple image tasks
A technology of weighted fusion and recognition method, which is applied in the direction of character and pattern recognition, instruments, computer parts, etc., can solve the problems of time-consuming and labor-intensive, and achieve the effect of expanding and reducing the distance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0051] Example
[0052] Step 1, collect the human activity video data set, divide according to the human body behavior category in the video, and give the category tag, the video data is subjected to normalization, divided into training set and test set, the specific method is:
[0053] Step 1.1. The collection of video data includes the self-built video data set or use the existing public data set: first download the relevant data set file from the official website, the specific data set is: HMDB51 is a video behavior identification with 51 action tags. There are 6849 videos, and each action contains at least 51 videos. The action mainly includes: facial action such as smiling, chewing, talking, facial and goods interacting, eating, drinking; body movements such as clapping, climbing, jumping, Run, interact with the item, such as combing, driver, playing golf, people with interaction between people, like hug, kiss; each type of action is doing action by 25 people, 1,3320 videos I...
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