Single target tracking method based on convolution neural network

Abstract

The invention discloses a single target tracking method based on a convolution neural network. The method comprises the steps that training data are used to preliminarily train a six-layer convolution neural network classification model; when tracking test is carried out, Ground-Truth information given by the first frame of a video is used to extract some sample data; through parameter fine-tuning of the network model, the network model can better adapt to the currently tracked video sequence; a Bounding Box regression model is trained for a currently tracked target to optimize a tracking result; and for a correct tracking result, the Bounding Box regression model is used to optimize the tracking result to acquire the accurate position of the target object. When tracking is carried out, network model parameters are timely and appropriately updated, so that the model can better adapt to the currently tracked video sequence. According to the invention, a pooling layer in the network structure is improved; a detection module is added, which makes the performance of a tracker more robust; and the tracking precision is improved.

Description

technical field [0001] The invention relates to technologies such as deep learning, target tracking, target detection, image preprocessing, and feature expression, and belongs to the technical field of computer vision tracking. Background technique [0002] Visual tracking task is a very basic and important problem in the field of computer vision, which has attracted more and more attention of researchers. The requirement of the visual tracking task is that for a given video clip, the position coordinates of the object to be tracked in the first frame of the video are given, and then the target object to be tracked can be automatically identified in the subsequent video sequence, and the Its location in the video is marked (with a box around the target). Since the appearance of the target object to be tracked is affected by factors such as sudden motion, deformation, occlusion, and illumination changes, the visual tracking task is still a very challenging problem. Some pre...

AI Technical Summary

Problems solved by technology

The features usually used in these two methods are some manually extracted features. These low-level manual features are often not very robust to dynamic scenarios such as illumination changes, occlusion, and deformation.

Images