Detection method and system targets in video

Abstract

The invention discloses a detection method and system targets in a video. The method includes executing the following steps on each frame of image of the video until final detection results of the targets in all frames of images of the video are obtained, wherein the steps include: detecting targets in the current frame of image, and acquiring targets, of which confidence degrees are greater thana first threshold value, to use the same as an intermediate detection result of the current frame of image; and utilizing a final detection result of a previous frame of image to carry out fusion matching, which is based on corresponding of the same target in the previous video frame of image and the later video frame of image, on the intermediate detection result of the current frame of image, and obtaining a final detection result of the current frame of image. The method avoids missed detection of the targets of multiple video frames through fusion matching which is on previous frames and later frames of the video and is based on target detection results of the images.

Description

technical field [0001] The present invention relates to the field of object detection in video, and more specifically, the present invention relates to a method and system for object detection in video. Background technique [0002] With the development of science and technology, the performance of target detection algorithms is constantly improving, and the scope of application is also expanding. For example, the combination of image-based target detection algorithms and target tracking algorithms is applied to video to complete the detection of targets in the video. The detection of targets in video has a wide range of applications in intelligent monitoring, such as: detection and early warning of criminal suspects, tracking of illegal vehicles, early warning of vicious parades, etc. Therefore, the research of this technology has also achieved remarkable results. [0003] At present, image-based video target detection algorithms are divided into two categories according to...

AI Technical Summary

Problems solved by technology

These two types of methods first detect the target based on the picture, and then use the tracking algorithm to track the target to complete the detection and reporting of the target in the video. The detection results directly affect the tracking results, but there are the following disadvantages: 1) Algorithm The target detection in each frame of the picture is not related to each other, resulting in the waste of relevant information between video frames; 2) The size and position of the target moving in the video are gradual, and the detection algorithm based on the picture will show the gradual change process. The periodic fluctuation of confidence, such as a target with a constant size, its confidence will change periodically as the target moves in the image

In this case, if a fixed threshold is used to filter the detection results, many objects in the video frames will be missed.

Images