A Pedestrian Detection Method Based on Hierarchical Kernel Sparse Representation

Abstract

The invention discloses a pedestrian detection method based on layered kernel sparse representation, which is characterized by the following steps: preprocessing the collected traffic video, obtaining the required positive and negative samples, and obtaining the required positive and negative samples through layered sub-block division. Multi-scale feature vectors, and construct two types of dictionary matrices; preprocess the pedestrian images to be tested to obtain test samples, extract pedestrian features in the same way as the dictionary construction process, and form feature vectors of test samples; use histogram cross-kernel Function, the kernel sparse decomposition is performed on the feature vector of the test sample, and the Gaussian function is used for weighting in the iterative solution process, and then the pedestrian detection is realized through the reconstruction error. The invention can obtain better detection performance, effectively improves the accuracy of pedestrian detection in the case of partial occlusion, and enhances the robustness of the pedestrian detection system for appearance changes.

Description

technical field [0001] The invention belongs to the field of intelligent transportation, and in particular relates to a pedestrian detection method based on hierarchical kernel sparse representation. Background technique [0002] Pedestrian detection is to separate the pedestrians appearing in the video or image from the background and precisely locate them. It has broad application prospects in video surveillance, intelligent driving and other fields. However, due to the large changes in the size, clothing, posture, or angle of view and illumination of pedestrian targets, coupled with complex background scenes and the movement and shaking of the camera itself, pedestrian detection requires high precision and real-time performance. , making pedestrian detection one of the most difficult topics in the field of intelligent transportation. [0003] At present, the pedestrian detection system is generally divided into two parts: appearance feature extraction and classification ...

AI Technical Summary

Problems solved by technology

[0004] In applications such as driving assistance systems, there are high requirements for the accuracy of pedestrian detection, but the existing methods generally use a fixed algorithm process to extract the global features of the target. For example, the implementation method of the direction gradient histogram is to first divide the image into small squares The unit connected area; then collect the gradient direction or edge direction histogram of each pixel in the grid unit; finally, these histograms can be combined to form a feature descriptor. The global features extracted by this inherent process cannot adapt to scenes and pedestrians. quick change of appearance

At the same time, due to the partial occlusion formed by street appendages, vehicles, trees, etc., it is also difficult for the classification model trained by the classifier to accurately distinguish pedestrians. It is difficult for existing methods to stably deal with complex situations such as partial occlusion and viewing angle change.

Images