Target classification method and system based on target edge direction

Abstract

The invention relates to the field of video image processing and discloses a target classification method and system based on a target edge direction. In the invention, target characteristics are extracted directly through background; edge detection is performed by using an edge detection operator and the system is more sensitive to image noise; movement targets are classified according to a multiple-Gaussian model quick algorithm by directly using gradient orientation histogram characteristics. By the adoption of the method and the system provided by the invention, effective computation is achieved, operation cost is reduced, detection accuracy is improved, and the effects of higher adaptability and less computation quantity are achieved.

Description

technical field [0001] The invention relates to the field of video image processing, in particular to a technology for automatically classifying objects in surveillance videos. Background technique [0002] At present, traffic accidents are one of the main factors leading to the death of pedestrians. Because cyclists and pedestrians are often in a weak position in traffic accidents, once they have a traffic accident with a motor vehicle, they are easily injured. Therefore, pedestrian detection technology has become a research direction that has attracted much attention in the field of intelligent analysis in recent years, especially in the field of intelligent traffic video analysis, where the classification and detection of objects plays a vital role in road management and traffic safety. [0003] The inventors of the present invention have found that the current main methods of object classification have the following corresponding deficiencies: [0004] 1. The method of ...

AI Technical Summary

Problems solved by technology

However, in practical applications, according to different scenes and different actual situations, the assumed height and angle of the camera are not the same, so the robustness of the classifier is not high, and it is often necessary to train the corresponding trainer for different scenes; in the actual monitoring The video sequence needs to be processed in real time, and the target needs to be tracked. The use of classifiers cannot meet the real-time requirements very well, and different video scenes are different, so it is impossible to determine a unified detection area, which brings inconvenience in use.

Images