Pedestrian detection method based on HOG and D-S evidence theory multi-information fusion

Abstract

Provided is a pedestrian detection method based on HOG and D-S evidence theory multi-information fusion. The method is characterized by carrying out gray conversion on an original video frame image; then, carrying out detection on the converted image by utilizing a classifier based on HOG features to obtain a preliminary pedestrian detection result; based on the result, judging whether a region is supposed to have a pedestrian, but the region is not detected through an inter-frame relation matrix; then, detecting the region by utilizing a classifier based on LBP features to make up for the loss due to HOG features; and if the region is not detected under such condition, carrying out predication by utilizing historical data, that is, the data obtained through the inter-frame relation matrix, and by utilizing a Kalman filter to obtain the position of the pedestrian target, and enhancing accuracy of judgment by utilizing the D-S evidence theory and through fusion of multiple information of detection and tracking and the like. The method can detect the corresponding pedestrians accurately, and has a good effect under the condition of having partial shielding; and accuracy, robustness and anti-interference capability of pedestrian detection are enhanced.

Description

technical field [0001] The invention belongs to the field of image processing technology and pattern recognition technology, in particular to a pedestrian detection method based on multi-information fusion of HOG and D-S evidence theory. Background technique [0002] In recent years, with the rapid development of the information industry and the continuous improvement of computer performance, using computers to detect pedestrian information in images or videos has become the main task of the development of intelligent video surveillance systems. So how to identify pedestrians and how to effectively distinguish pedestrians from other objects is an important part of the intelligent video surveillance system, which is also the primary task of pedestrian detection. The current pedestrian detection methods can be roughly divided into two categories: one is a method based on background modeling, and the other is a method based on statistical learning. The method based on backgrou...

AI Technical Summary

Problems solved by technology

At present, the patents related to pedestrian detection mainly involve multi-feature fusion, and changes are made in the selection of features. However, purely using feature information is likely to cause detection failure due to occlusion, light changes, etc., and does not take into account the continuity of pedestrian movement. Handle detection failures caused by occlusion or lighting changes, and cannot accurately and continuously detect pedestrian targets

In addition, the current multi-feature fusion is mainly feature-level fusion, that is, various features are fused into a new feature through a certain method, but the flexibility of data processing is not high, and the anti-interference ability is not strong.

Images