Fast pedestrian detection method with combination of static bottom characteristics and motion information

Abstract

The invention discloses a fast pedestrian detection method with the combination of static bottom characteristics and motion information. For a single image frame in a video sequence to be detected, amulti-scale sliding window method is used to extract a detection window of a specified size, a fast pyramid characteristic calculation method is used to calculate the static layer characteristics in each detection window, the static bottom layer characteristics comprise a direction gradient, a gradient amplitude and a color channel, the pre-classification of a pedestrians and no pedestrian is carried out on each detection window based on the static bottom characteristics of an image in each detection window. The specific motion speed characteristics of the pedestrians are used, through a detection window pixel-difference-averaging method, a detection window which is mistakenly detected to be a pedestrian in the pre-classification is removed, and finally the position of an image in a detection which is detected to be a pedestrian is the position of the pedestrian in the image frame. According to the method, the accuracy of detection is improved while the false detection rate is reduced.

Description

technical field [0001] The invention belongs to a pedestrian detection method based on the pedestrian's static bottom-level feature combined with the pedestrian's motion feature in intelligent video monitoring. Background technique [0002] Pedestrian detection and tracking technology is an important part of machine vision research, and it has played a role in many fields involving people's lives. Relying on advanced pedestrian detection technology, surveillance video has made great breakthroughs in intelligent storage, intelligent retrieval, behavior analysis, etc., thereby greatly reducing the construction cost of the surveillance system and saving a lot of security human resources. Real-time pedestrian detection enables the security monitoring system to promptly remind security personnel to pay attention to suspicious persons in the monitoring area, and help security personnel quickly locate and track criminal suspects. The intelligent video monitoring system can also ti...

AI Technical Summary

Problems solved by technology

When detecting pedestrians based on motion features, if background subtraction is used to detect moving objects, the background subtraction method is very sensitive to brightness changes and disordered scenes, and when the pedestrian’s clothing color is similar to the background color, the background subtraction method will cause a lot of errors. Segmentation, that is, a pedestrian movement area is divided into several unconnected areas, resulting in false detection and missed detection of pedestrians; if the optical flow feature is used, since the optical flow method uses an iterative method to calculate the optical flow field, it takes a long time and it is difficult to achieve real-time Pedestrian detection, and the optical flow method is sensitive to noise and light, so it is not suitable for pedestrian detection in low-quality images

Images