A Target Tracking Method Based on Attention Recurrent Network

Abstract

The present invention is a target tracking method based on the attention loop network. By introducing the local position attention mechanism and the appearance attention mechanism in the target tracking framework, three depth models are set up, and the loop convolution neural network is used for timing prediction. Adding technical means such as uncertainty evaluation mechanism to the tracking framework has greatly improved the efficiency and accuracy of visual target tracking based on computer algorithms, and has high reliability and generalizable value. Compared with other time series prediction methods, the parameters Small amount, fast speed, and high accuracy; the uncertainty evaluation mechanism is used in the tracking process, which can ensure the quality of the tracking results, and initialize the tracker or stop tracking in time when the quality drops, so as to avoid giving too many wrong results As a result, there is higher reliability.

Description

technical field [0001] The invention relates to the technical field of visual target tracking algorithms, in particular to a target tracking method based on an attention loop network. Background technique [0002] Target tracking is one of the important problems in computer vision. The main purpose is to track multiple targets in the video screen and give the target's trajectory; the typical scene of target tracking is: for continuous video sequences, artificially given one or more Target, find and distinguish multiple calibrated targets in subsequent video frames; [0003] The algorithm model of computer vision for target tracking is mainly divided into two types: generative model and discriminative model, among which: [0004] ①Generation model: learn the joint probability distribution of data, judge by finding the conditional probability distribution, and learn the way of data generation; [0005] ② Discriminant model: directly learn the conditional probability distribu...

AI Technical Summary

Problems solved by technology

[0009] Disadvantage 1: The timing feature of the target is an important feature in target tracking. At present, most methods only consider the appearance feature of the target, and assume that the appearance feature of the tracking target does not change with time, which loses important priors in the target tracking problem;

[0011] Disadvantage 2: Some target tracking methods that introduce time information use long-short-term memory neural network (LSTM) for timing prediction, which has a large amount of parameters, slow speed and cannot predict image information;

[0013] Disadvantage 3: Most target tracking methods do not have a tracking result evaluation mechanism, and cannot give the model's confidence in the prediction results, so it is difficult to apply in occasions that require high reliability;

Images