Target tracking method and system based on multi-resolution neural network

Abstract

The invention provides a target tracking method based on a multi-resolution neural network. The method is suitable for use in video target tracking, and includes: receiving a to-be-detected current video frame, and extracting a detection block on the current video frame, extracting multiple layers of depth features which have different resolution and are of the detection block; utilizing a kernel correlation filtering model to calculate target displacement response graphs of all the layers of depth features; utilizing the multi-resolution neural network to carry out displacement estimation according to the target displacement response graphs of all the layers to obtain estimated target displacement, and updating the kernel correlation filtering model; and utilizing a scale estimation model to carry out scale estimation according to the estimated target displacement to obtain estimated values, and updating the scale estimation model. Through the embodiment, situations of tracking drift and tracking loss can be substantially reduced, and the robustness and the stability in complex environments of motion mutation, illumination variation and the like or long-sequence video tracking are substantially improved.

Description

technical field [0001] The invention belongs to the field of video technology, and in particular relates to a method and system for tracking a target based on a multi-resolution neural network. Background technique [0002] Visual target tracking is an important research topic of computer vision. Its main task is to continuously, real-time and accurately locate the target object being tracked in the video sequence. widely used. [0003] The target tracking method based on correlation filter has become a research hotspot because of its superior performance. Using a deep neural network pre-trained on a large-scale classification data set to extract the deep features of the tracking target not only avoids the dilemma of insufficient samples for direct training of the deep neural network during tracking, but also makes full use of the powerful representation ability of deep features. The method of applying deep features to the correlation filter tracking model combines the adv...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a target tracking method and system based on a multi-resolution neural network, which aims to solve the problems in complex environments such as sudden motion changes and illumination changes in the prior art that the target model does not support adaptive update. The problem of insufficient robustness

Images