Detection method of specific color pedestrians in static camera scene

Abstract

The invention provides a specific color pedestrian detecting method in a static video camera scene. The method utilizes a Gaussian mixture model to conduct modeling to a background of the scene, after a background model is obtained, a sketchy motion foreground is obtained by comparing with a disposed image at present, a foreground is obtained by enabling the motion foreground to be raised in a rectangular block mode after filtering processing and morphological processing are conducted. A ratio occupied by foreground point in each foreground block is calculated and combines with statistical property of the projection number that the foreground points are projected on a horizontal coordinates to distinguish a complex foreground from a simple foreground, and a horizontal coordinates of a pedestrian which possibly exits is estimated. For the complex foreground block, a pedestrian height estimation model and an Adaboost classifier based on the feature of a direction gradient histogram are used for conducting accurate detection to the pedestrian, after a pedestrian target location is obtained, a clothing color of the pedestrian is identified. The specific color pedestrian detecting method in the static video camera scene improves detection speed and accuracy of the pedestrian target and can be applied to real-time video monitoring and video retrieval.

Description

technical field [0001] The present invention relates to a method in the technical field of video image processing and pattern recognition, in particular to a specific color pedestrian detection method applied to a video surveillance system. Background technique [0002] The main task of pedestrian object detection is to mark the pedestrians in the video sequence for the purpose of retrieval. The detection of specific color pedestrians is to further identify pedestrian targets with specific colors on the basis of pedestrian target detection, for example, to detect pedestrians wearing blue shirts in a given video. The detection technology of specific color pedestrians can be applied to video surveillance, video retrieval and other fields, thereby reducing the burden on operators brought by massive surveillance video data. [0003] A typical pedestrian detection method is based on background modeling. According to the comparison between the current video picture information an...

AI Technical Summary

Problems solved by technology

But this method will consume a long time in the process of feature extraction and classification, making it difficult to be applied in the field of video surveillance alone

[0005] In the Chinese patent "Pedestrian Detection Method Based on Foreground Analysis and Pattern Recognition" (publication number CN102147869A), the patent combines background modeling and classifier detection to detect pedestrians, which is consistent with the framework of the pedestrian detection method of the present invention There are similarities in the above, foreground information and classifiers are used, but the height estimation of pedestrians in this method relies on the prior pedestrian height model, and manual height calibration is required before detection, and the finding described in the patent Estimating the position of pedestrians with the method of contour peak points may consume more time

Images