Visual Object Tracking based on Adaptive Siamese and Motion Estimation Network

TL;DR

This paper introduces an advanced visual object tracking method combining adaptive Siamese networks, motion estimation, and appearance weighting CNNs to improve accuracy and robustness in dynamic scenarios.

Contribution

It proposes a novel tracking framework integrating motion estimation and adaptive weighting CNNs with Siamese networks, enhancing tracking performance over existing methods.

Findings

Outperforms state-of-the-art trackers on benchmark datasets

Effectively handles target appearance changes

Improves motion and observation modeling in tracking

Abstract

Recently, convolutional neural network (CNN) has attracted much attention in different areas of computer vision, due to its powerful abstract feature representation. Visual object tracking is one of the interesting and important areas in computer vision that achieves remarkable improvements in recent years. In this work, we aim to improve both the motion and observation models in visual object tracking by leveraging representation power of CNNs. To this end, a motion estimation network (named MEN) is utilized to seek the most likely locations of the target and prepare a further clue in addition to the previous target position. Hence the motion estimation would be enhanced by generating a small number of candidates near two plausible positions. The generated candidates are then fed into a trained Siamese network to detect the most probable candidate. Each candidate is compared to an adaptable buffer, which is updated under a predefined condition. To take into account the target appearance changes, a weighting CNN (called WCNN) adaptively assigns weights to the final similarity scores of the Siamese network using sequence-specific information. Evaluation results on well-known benchmark datasets (OTB100, OTB50 and OTB2013) prove that the proposed tracker outperforms the state-of-the-art competitors.