A pedestrian detection method based on multi-feature fusion of hiksvm classifier

Abstract

The invention relates to a pedestrian detection method based on multi-feature fusion of a HIKSVM classifier, which specifically includes the following steps: determining the behavior area in the pedestrian image sequence; extracting multiple features in the behavior area to form a fusion feature; using the trained The HIKSVM classifier of the above fused features is used for pedestrian detection. The present invention improves the feature extraction method. After extracting the HOG feature, by analogy, the gradient field is changed to the optical flow field, and the HOF feature is extracted, the shape information and motion information of the object are retained, and at the same time, the use of the optical flow field to describe the entire image is avoided. The computational complexity of moving objects is strong; through the improvement of the LBP algorithm, the LQC algorithm is used to extract texture features, and the computational complexity is reduced without loss of texture information; the histogram cross kernel is used to drop the cross coordinates The method of classifying and training the SVM classifier has low computational complexity and high detection accuracy.

Description

technical field [0001] The invention relates to the technical fields of computer vision and pattern recognition, in particular to a pedestrian detection method based on multi-feature fusion of a HIKSVM classifier. Background technique [0002] Pedestrian detection is a challenging task due to their high variability in appearance and wide variety of poses. A robust feature set is crucial for correctly distinguishing pedestrians if one wants to correctly detect humans in cluttered backgrounds or under difficult lighting conditions. [0003] For the problem of pedestrian detection, many descriptors for feature extraction have been proposed. Among them, the Histogram of Oriented Gradients (HOG) descriptor provides superior performance relative to other feature sets, including wavelets. However, the gradient direction histogram represents the edge information of the image, and retains the shape information of the target. It is aimed at a single image, but pedestrian detection i...

AI Technical Summary

Problems solved by technology

[0006] In view of the above analysis, the present invention aims to provide a pedestrian detection method based on the multi-feature fusion of the HIKSVM classifier to solve the problems of low detection accuracy and poor real-time detection of existing pedestrian detection methods

Images