Human detection method based on multi-feature and depth information

Abstract

The invention provides a human detection method based on multiple features and depth information, which mainly solves the problem of high detection false alarm of the existing method. The human detection method is implemented by the following process of: calculating a kernel function of the directed gradient histogram feature and a kernel function of the uniform local binary pattern feature of a training sample image in a CVC-02 database; executing classification training on the kernel function of the directed gradient histogram feature and the kernel function of the uniform local binary pattern feature through an MKL (multi-kernel learning) algorithm to obtain a multi-kernel classifier; inputting the kernel function of the directed gradient histogram feature and the kernel function of the uniform local binary pattern feature of a to-be-detected image into the multi-kernel classifier to get the classifier score of each scanning window; by the depth of field information, removing the background window of which the classifier score is more than 0; and combining the final human windows to get the final human detection result. The human detection method has the advantages of high detection accuracy and low false alarm, and can be used for pedestrian detection in a video.

Description

technical field [0001] The invention belongs to the technical field of computer vision and pattern recognition, relates to a human body detection method, and can be used to detect human bodies and other complex objects in images. Background technique [0002] Human detection has many important applications in computer vision, such as video surveillance, smart cars and smart transportation, robotics and advanced human-computer interaction, etc. However, the appearance of the human body varies greatly due to factors such as changes in the human body's own posture, diversity of clothing, and illumination, making human body detection a very difficult problem. [0003] At present, the methods of human body detection in images mainly include methods based on human body models, methods based on template matching and methods based on statistical classification. [0004] Human body model-based methods have explicit models that can handle occlusion and can infer the pose of the human...

AI Technical Summary

Problems solved by technology

The advantage of this statistical classification method is that it is relatively robust. The disadvantage is that the extracted single feature can only describe a certain characteristic of the object, and the representation ability is limited, which affects the performance of the classifier, and there are problems of missed detection or virtual scenes.

Images