Method for detecting human body parts by performing parallel statistical learning based on three-dimensional depth image information

Abstract

The invention discloses a method for detecting human body parts by performing parallel statistical learning based on three-dimensional depth image information. Specific to the problems of complex deformation, difficulty to describe, and the like, of human body parts (head, hands and feet), a novel feature, namely universal feature, for reflecting diversity of the human body parts, is constructed. A parallel statistical learning method is utilized to select effective and sufficient novel features and form a parallel cascaded classifier, so as to perform real-time efficient detection on the human body parts.

Description

Technical field [0001] The invention relates to the fields of image processing, pattern recognition, human-computer interaction, visual monitoring and the like, in particular to a method for detecting human body parts based on parallel statistical learning of three-dimensional depth image information. Background technique [0002] With the gradual improvement of computer performance and the continuous use of computers in various fields, the interaction technology between humans and computers has increasingly become a research hotspot in the computer field. Target recognition based on dynamic sequence images has become a research content in the field of computer vision in recent years. It mainly conducts research on detection, recognition, tracking and the understanding and description of biological characteristics from image sequences. [0003] Target detection is the most critical step in target recognition. It is to study how to make a computer find out the area of ​​the target o...

AI Technical Summary

Problems solved by technology

However, most of the algorithms only use the original pixels of the image as features, most of them are very sensitive to illumination changes and noise

Images