Abstract
In this paper, we present a robust object tracking system capable of handling pose and scale variations. The system is based on adaptive sparse representation and dictionary learning. We focus on the problem of automatic tracking with no prior knowledge other than the location of the region to be tracked in the first frame, which could be located by a detector. The detected region, i.e., a bounding box, and some samples near the bounding box are extracted as positive samples. In addition, we select regions outside the bounding box as negative samples. Both, positive and negative samples are used to build the dictionary and we use K-SVD method for dictionary learning in order to decrease the number of atoms and improve the processing speed. One of the main drawbacks in tracking systems is false tracking when the object is not in the frame any more. We overcome this problem by comparing the newly tracked region with previously tracked regions to find out if the object is still in the frame or not. If the object is not in the frame, the algorithm stops tracking and starts searching for the object using the sparse detector in the following frames. Experiments on video sequences demonstrate the effectiveness and robustness of the proposed system for tracking.
| Original language | English (US) |
|---|---|
| Title of host publication | 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 1160-1164 |
| Number of pages | 5 |
| ISBN (Print) | 9781479975914 |
| DOIs | |
| State | Published - Feb 23 2016 |
| Event | IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015 - Orlando, United States Duration: Dec 13 2015 → Dec 16 2015 |
Other
| Other | IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015 |
|---|---|
| Country | United States |
| City | Orlando |
| Period | 12/13/15 → 12/16/15 |
Fingerprint
Keywords
- Dictionary Learning
- Object Detection
- Sparse Representation
- Tracking
ASJC Scopus subject areas
- Information Systems
- Signal Processing
Cite this
Robust object tracking via adaptive sparse representation. / Khorsandi, Rahman; Abdel-Mottaleb, Mohamed.
2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1160-1164 7418380.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Robust object tracking via adaptive sparse representation
AU - Khorsandi, Rahman
AU - Abdel-Mottaleb, Mohamed
PY - 2016/2/23
Y1 - 2016/2/23
N2 - In this paper, we present a robust object tracking system capable of handling pose and scale variations. The system is based on adaptive sparse representation and dictionary learning. We focus on the problem of automatic tracking with no prior knowledge other than the location of the region to be tracked in the first frame, which could be located by a detector. The detected region, i.e., a bounding box, and some samples near the bounding box are extracted as positive samples. In addition, we select regions outside the bounding box as negative samples. Both, positive and negative samples are used to build the dictionary and we use K-SVD method for dictionary learning in order to decrease the number of atoms and improve the processing speed. One of the main drawbacks in tracking systems is false tracking when the object is not in the frame any more. We overcome this problem by comparing the newly tracked region with previously tracked regions to find out if the object is still in the frame or not. If the object is not in the frame, the algorithm stops tracking and starts searching for the object using the sparse detector in the following frames. Experiments on video sequences demonstrate the effectiveness and robustness of the proposed system for tracking.
AB - In this paper, we present a robust object tracking system capable of handling pose and scale variations. The system is based on adaptive sparse representation and dictionary learning. We focus on the problem of automatic tracking with no prior knowledge other than the location of the region to be tracked in the first frame, which could be located by a detector. The detected region, i.e., a bounding box, and some samples near the bounding box are extracted as positive samples. In addition, we select regions outside the bounding box as negative samples. Both, positive and negative samples are used to build the dictionary and we use K-SVD method for dictionary learning in order to decrease the number of atoms and improve the processing speed. One of the main drawbacks in tracking systems is false tracking when the object is not in the frame any more. We overcome this problem by comparing the newly tracked region with previously tracked regions to find out if the object is still in the frame or not. If the object is not in the frame, the algorithm stops tracking and starts searching for the object using the sparse detector in the following frames. Experiments on video sequences demonstrate the effectiveness and robustness of the proposed system for tracking.
KW - Dictionary Learning
KW - Object Detection
KW - Sparse Representation
KW - Tracking
UR - http://www.scopus.com/inward/record.url?scp=84964766331&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84964766331&partnerID=8YFLogxK
U2 - 10.1109/GlobalSIP.2015.7418380
DO - 10.1109/GlobalSIP.2015.7418380
M3 - Conference contribution
AN - SCOPUS:84964766331
SN - 9781479975914
SP - 1160
EP - 1164
BT - 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015
PB - Institute of Electrical and Electronics Engineers Inc.
ER -