Human Pose Estimation Method with Adaptive Configuration of Multi-model

Abstract

The invention discloses a multi-model self-adaptive configuration method for human pose estimation. Obtain the minimum configuration value required for the current processing video segment; step 2, according to the minimum configuration parameters, the sampled frames obtained by sampling are divided into sub-regions and processing levels in a fine-grained manner, and the human body posture that best matches the processing level of each sub-region is used. The estimation model performs estimation processing, and then obtains the final estimation result through coordinate transformation; Step 3, judge whether the current minimum configuration parameters match the next video, if it matches, follow steps 2 to 3, if it does not match, follow steps 1 to 3, until Process the entire pending video. The method is based on the adaptive configuration of the multi-person pose estimation model, which can improve the execution efficiency of multi-person human pose estimation under the condition of limited computing resources and without reducing its accuracy.

Description

technical field [0001] The invention relates to the field of video analysis, in particular to a method for estimating human body posture with adaptive configuration of multiple models. Background technique [0002] At present, a large number of cameras are widely used in practice, such as in security scenarios, various work scenarios, and traffic scenarios. With the popularization of camera applications, the work of video analysis is becoming more and more important. In particular, human pose estimation is a very important part of the function. [0003] At present, there are very mature human pose estimation methods, which can accurately detect the human pose in the case of a single person. However, when there are many people, the existing human pose estimation methods have at least the following limitations: frameworks with relatively accurate detection results (such as Openpose) require a lot of computational overhead, and the frame rate that can be processed per second c...

AI Technical Summary

Problems solved by technology

[0004] In view of the problems existing in the existing methods, the purpose of the present invention is to provide a human body pose estimation method with adaptive configuration of multiple models, which can solve the problems of the existing human body pose estimation methods, such as high computational overhead, slow processing speed or inaccurate results. The problem that the balance between processing speed and result accuracy cannot be achieved

Images