Visual multi-target tracking method and device based on deep learning

Abstract

The embodiment of the invention provides a visual multi-target tracking method and a device based on deep learning, and the method comprises the steps: sequentially obtaining the candidate detection frames of a tracking target in a current video frame through a target detection network model, recording the coordinate position information, and obtaining a corresponding template image; acquiring each frame of image in the video except the first frame as a to-be-searched area image; and inputting each template image and the to-be-searched region image into a target tracking network model constructed by a twin convolutional neural network, thereby obtaining a tracking result of a tracking target. According to the visual multi-target tracking method and the device based on deep learning, the template image corresponding to each tracking target and the to-be-searched area image which are acquired by using the target detection network model are respectively input into the target tracking network model constructed by the twin convolutional neural network, so that the tracking result of the tracking target corresponding to the template image is acquired, the calculation amount is low, and multi-target real-time and accurate tracking is realized.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a deep learning-based visual multi-target tracking method and device. Background technique [0002] Visual object tracking is a hot issue in the field of computer vision research. With the rapid development of computer technology, object tracking technology has also made great progress. With the rapid rise of artificial intelligence in recent years, the research of object tracking technology has received more and more attention. [0003] Deep learning technology has powerful feature representation capabilities, and has achieved better results than traditional methods in applications such as image classification, object recognition, and natural language processing, so it has gradually become the mainstream technology for image and video research. The tracking method based on deep learning is an important branch of the target tracking method. It takes advantage of the end-...

AI Technical Summary

Problems solved by technology

However, the multi-target tracking methods disclosed in the prior art generally have a large amount of calculation and cannot realize real-time tracking, resulting in poor tracking effect

Images