Target tracking method and device, storage medium and electronic equipment

Abstract

The invention discloses a target tracking method and device, a storage medium and electronic equipment, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring a video stream acquired by a camera, and decoding the video stream to obtain multiple frames of images; for a to-be-processed current frame image, when the current frame image is afirst type image, performing target detection on the current frame image to obtain position information of a detected target in the current frame image; and when the current frame of image is a secondtype of image, predicting the position information of the detected target in the previous frame of image in the current frame of image based on the motion vector of the previous frame of image. According to the target tracking method provided by the invention, the information of all the decoded images is utilized, the problem of relatively low speed caused by performing target detection on the frame-by-frame images is avoided, the real-time tracking speed is ensured, and the accuracy of the obtained tracking result is also ensured.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular to a target tracking method, device, storage medium and electronic equipment. Background technique [0002] As the core of artificial intelligence, computer vision technology has been applied in many fields. For example, as an important research direction of computer vision technology, target tracking has a very wide range of applications at present, and can be applied in scenarios such as video surveillance, human-computer interaction, and unmanned driving. [0003] Taking multi-target tracking with a single camera as an example, when performing target tracking in related technologies, firstly, the video stream collected by the camera is decoded into multiple frames of images; after that, target detection is performed on each frame of decoded images based on the target detection algorithm. Furthermore, target tracking is realized according to the targ...

AI Technical Summary

Problems solved by technology

[0004] Since target detection needs to be performed on each frame of image, it is time-consuming, especially in the face of high-resolution images, the larger the image used for target detection, the slower the detection speed, which will seriously affect the accuracy of target tracking. performance, it is difficult to track in real time

In order to achieve the effect of real-time tracking, the relevant technology adopts a method of extracting a small number of decoded frame images for target detection and leaving the remaining images without any processing. Since the information of all frame images is not utilized, the tracking will be severely restricted. accuracy of results

Images