Target tracking method based on long short-term memory network

Abstract

The present invention provides a target tracking method based on a long short-term memory network, and relates to the computer vision technology. The method comprises the steps of: performing pre-estimation of a candidate target state by employing a fast matching method based on similarity learning, screening out high-quality candidate target states, and performing classification of the high-quality candidate target states by employing a long short-term memory network. The long short-term memory network comprises a convolutional layer used for feature extraction and a long short-term memory layer used for classification. The convolutional layer is obtained through offline training on a large-scale image data set ILSVRC15 to avoid a risk of overfitting of the target tracking data set. The long short-term memory layer is obtained through online learning and fully employs the time correlation included by an input video sequence so as to have good capacities on adaption of target forms andmotion change. The speed is observably improved, the long short-term memory network capable of adapting target change is utilized to target tracking.

Description

technical field [0001] The invention relates to computer vision technology, in particular to a target tracking method based on a long-short-term memory network. Background technique [0002] Visual object tracking is a very challenging research hotspot in the field of computer vision, which has a wide range of applications in video surveillance, human-computer interaction, and unmanned driving. The definition of target tracking is that given the target position in the initial frame of the video sequence, the position of the target is automatically given in the following video sequence. Object tracking is in the middle level of video content analysis research. It obtains the position and motion information of objects in the video, and provides the basis for further semantic layer analysis (action recognition, scene recognition). The difficulty of the target tracking task lies in processing various visual information and motion information in the video, including the informat...

AI Technical Summary

Problems solved by technology

However, due to the wide variety of targets contained in the videos used for offline training, it is difficult for this method to learn a general model to describe the changes of all target shapes and actions.

Therefore, the tracking accuracy of Re3 is not ideal

Images