An Improved TLD Tracking Method Using Compressive Sensing
Qiang Li, Xueshi Ge, Geng Wang
Available Online January 2016.
- https://doi.org/10.2991/icaita-16.2016.64How to use a DOI?
- visual tracking; tracking-learning-detection (TLD); compressive tracking (CT); tracking speed; extent change
- Visual Tracking, as an important subject in computer vision, has been widely used in surveillance, space exploration, and human-computer interaction etc. Both tracking-learning-detection (TLD)  and compressive tracking (CT)  are successful algorithms among those proposed recently. However, TLD suffers from low efficiency and CT overlooks scale change during tracking. In this paper, we propose an improved TLD tracking algorithm by using compressive sensing. The improvements include enhancing the detection method in TLD with CT, employing Kalman filter in detector to estimate the tracking region for improving the detection speed. Besides, adaptive search radius is employed to deal with object disappearance and shielding issue. Lastly, the tracking results of TLD and CT are integrated to estimate the target status and update the classifier. The experiments show that, compared to the original algorithms, the improved algorithm combines the advantages of two algorithms, conducing to accurate tracking precision, faster tracking speed and handling the object extent change.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Qiang Li AU - Xueshi Ge AU - Geng Wang PY - 2016/01 DA - 2016/01 TI - An Improved TLD Tracking Method Using Compressive Sensing BT - Proceedings of the 2016 International Conference on Artificial Intelligence: Technologies and Applications PB - Atlantis Press SP - 259 EP - 262 SN - 1951-6851 UR - https://doi.org/10.2991/icaita-16.2016.64 DO - https://doi.org/10.2991/icaita-16.2016.64 ID - Li2016/01 ER -