Abstract

Motion blur is a quite tricky issue in object tracking community. In recent years, many trackers have been explored to address this issue without sensational performance. This paper proposes a novel correlation tracking framework with Recurrent Neural Network (RNN) deblurnet and proposal detection to handle motion blur and heavy occlusion in object tracking tasks. We take advantage of high efficient Kernelized Correlation Filter (KCF) tracker, a typical method that exploits the circulant structure and the kernel trick to enhance the performance, and furthermore incorporate two regression methods in it. We employ RNN as our baseline of deblurnet, and introduce residual block and ConvLSTM in our deblur network to improve the result of deblurring. In addition, we suggest an edge information based rectification system to overcome the challenge of target occlusion. Finally, we update the model adaptively in term of the feedback from high-confidence tracking results to avoid the model degradation. Extensive experimental results demonstrate our tracker outperforms several state-of-the-art trackers on the OTB-2015 and VOT-2016 datasets.

Highlights

  • Visual tracking, referring to generating the trajectories of moving objects in a sequence of images, is an important and integral part of computer vision

  • We mainly focus on the performance of the most common challenge factors, namely Motion Blur (MB), Rotation (OPR or IPR), Occlusion (OCC), Background Clutter (BC), Scale Variation (SV) and Deformation (DEF)

  • It is obvious that Recurrent Neural Network (RNN) deblurnet can significantly enhance the performance of overcoming motion blur, and leads to 10.6% and 11.1%

Read more

Summary

Introduction

Visual tracking, referring to generating the trajectories of moving objects in a sequence of images, is an important and integral part of computer vision. It is useful in various real life applications such as robotics, video surveillance system, human computer interaction, traffic management system, missile tracking and automated car driven system [1]–[4]. If our tracker can not accommodate the size of the target, the box will contain too much background information or lack of target information, which will lead to inaccurate tracking results.

Methods
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.