Method and system for detecting pedestrians in video stream

Abstract

The invention provides a method and a system for detecting pedestrians in video streams. The method comprises the steps of obtaining multiple paths of video streams; performing moving target detection on each path of video stream; segmenting out a moving target region of each picture; splicing all pictures into a single large picture through a divide-and-conquer-based combination algorithm; obtaining a spliced image; and performing neural network prediction on the spliced image through a convolutional neural network to obtain a detection result. In the whole process, a moving target detection algorithm and a convolutional neural network pedestrian detection algorithm are efficiently combined together through the divide-and-conquer region combination algorithm, so that the pedestrians in the video streams can be efficiently and accurately detected.

Description

technical field

[0001] The invention relates to the technical field of image tracking, in particular to a method and system for pedestrian detection in video streams. Background technique

[0002] Pedestrian detection technology in video streams is currently widely used in the fields of smart home and industrial security. The pedestrian detection technology obtains the pedestrian area by analyzing the video stream collected by the front-end camera frame by frame, and uses this as a trigger condition to report the detected pedestrian objects to the user.

[0003] Pedestrian detection technologies in video streams are roughly divided into two categories: 1. Detection based on moving objects. This type of technology uses still images of no one as foreground images, and analyzes the difference between each frame image and the foreground image in real time. The probability of the pixels belonging to the stationary target or the moving target is established, and the positions bel...

Images