Recoverable Recommended Keypoint-aware Visual Tracking Using Coupled-layer Appearance Modelling

TY - GEN

T1 - Recoverable Recommended Keypoint-aware Visual Tracking Using Coupled-layer Appearance Modelling

AU - Duan, Ran

AU - Fu, Changhong

AU - Kayacan, Erdal

PY - 2016/11/28

Y1 - 2016/11/28

N2 - Object tracking over image sequences plays an remarkably crucial role in several computer vision applications, interalia, automated video surveillance, unmanned aerial vehicles and 3D reconstruction. In this paper, a novel, accurate, robust and recoverable real-time feature-based tracking framework is presented. The appearance modelling consists of a local and global layer. We propose a recommended keypointaware (RKA) tracker, which is fast and accurate, for the former, while the latter employs support vector machine (SVM) to determine the object and background, so that the RKA tracker can be recovered under possible target losing circumstances. Furthermore, the RKA tracker converts the tracking problem into the ranking of samples which provides a score of tracking confidence. Therefore, the priority switching between the local layer and global layer dependent upon the score becomes valid. Extensive experiments have been done by strictly following the visual tracking benchmark v1.0 protocol. The results demonstrate that the proposed novel method outperforms the stateofthe-art trackers in terms of robustness, speed and accuracy.

AB - Object tracking over image sequences plays an remarkably crucial role in several computer vision applications, interalia, automated video surveillance, unmanned aerial vehicles and 3D reconstruction. In this paper, a novel, accurate, robust and recoverable real-time feature-based tracking framework is presented. The appearance modelling consists of a local and global layer. We propose a recommended keypointaware (RKA) tracker, which is fast and accurate, for the former, while the latter employs support vector machine (SVM) to determine the object and background, so that the RKA tracker can be recovered under possible target losing circumstances. Furthermore, the RKA tracker converts the tracking problem into the ranking of samples which provides a score of tracking confidence. Therefore, the priority switching between the local layer and global layer dependent upon the score becomes valid. Extensive experiments have been done by strictly following the visual tracking benchmark v1.0 protocol. The results demonstrate that the proposed novel method outperforms the stateofthe-art trackers in terms of robustness, speed and accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85006339925&partnerID=8YFLogxK

U2 - 10.1109/IROS.2016.7759601

DO - 10.1109/IROS.2016.7759601

M3 - Article in proceedings

SN - 978-1-5090-3762-9

SP - 4085

EP - 4091

BT - IROS 2016 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems

PB - IEEE

T2 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems

Y2 - 9 October 2016 through 14 October 2016

ER -