Method for representing and recognizing gait characteristics based on frequency domain analysis
A technology of gait characteristics and frequency domain analysis, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as large amount of calculation, many parameters, difficult model modeling gait, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0044] The present invention adopts the binarized side view of gait features, and performs gait feature representation and recognition based on frequency domain analysis, such as figure 1 , and its specific implementation is as follows:
[0045] 1) Binarized side view sequence preprocessing, such as figure 2 :
[0046] 11) Gait cycle detection. The gait cycle is determined by analyzing the number of moving foreground pixels in the binarized side view. A complete gait cycle of a person contains five key postures, which are the left and right feet together, and the left foot forward. and landing, left and right feet together, right foot forward and landing, left and right feet together, they respectively correspond to the local minimum value, local maximum value, local minimum value, local maximum value, and local minimum value of the number of moving foreground pixels. Value a subsequence of the sequence of side views that is considered to be a cycle of the gait if it contai...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 