Target tracking method based on deep learning and discriminant model training and memory

Abstract

The invention relates to the field of computer vision and pattern recognition, in particular to a target tracking method based on deep learning and discriminant model training and a memory, and aims to improve the positioning precision of target tracking. The tracking method comprises the following steps of: in an offline training stage, extracting sample frame features from a training image and atest image by using a depth feature extraction network, and calculating a sample frame label of the training image and a sample frame first label of the test image; utilizing a discriminant model solver to train to obtain a discriminant model according to the sample frame feature and the label of the training image; according to the sample frame feature of the test image, using the discriminant model to perform prediction to obtain a second label; calculating network prediction loss according to the second label and the first label so as to drive optimization learning of the deep feature extraction network; in an online tracking stage, using the trained depth feature extraction network in a target tracking algorithm based on online discriminant model training. According to the method of the invention, the positioning precision of target tracking is effectively improved.

Description

technical field [0001] The invention relates to the fields of computer vision and pattern recognition, in particular to a target tracking method and memory based on deep learning and discriminant model training. Background technique [0002] Visual object tracking is one of the hot research topics in computer vision, and it is also an important research direction in the application of pattern recognition based on computer vision. In a video sequence, given the state (position and size) of the target object of interest in the first frame, the target tracking algorithm needs to estimate the state of the target object in the entire video sequence. [0003] At present, the target tracking algorithm based on online discriminant model training has achieved a good balance of accuracy and speed on multiple public databases, so it has attracted extensive attention from researchers. Most of the existing target tracking algorithms of this type use deep convolutional neural networks (s...

AI Technical Summary

Problems solved by technology

This essential difference in feature requirements seriously hinders the accuracy improvement of target tracking algorithms based on online discriminative model training that currently uses deep convolutional neural networks trained in target classification tasks for feature extraction.

Images