TY - GEN
T1 - Target tracking algorithm with adaptive learning rate complementary filtering
AU - Pan, Yulei
AU - Bai, Yongqiang
N1 - Publisher Copyright:
© 2020 Technical Committee on Control Theory, Chinese Association of Automation.
PY - 2020/7
Y1 - 2020/7
N2 - The Correlation filtering algorithm is not effective for fast deformation and fast movement. It is easy to lose when encountering problems such as occlusion. However, it has a good advantage of dealing with situations such as motion blur and lighting changes. A tracking algorithm based on color statistical features has a good effect on the rotation and translation of objects. The Staple algorithm combines the two algorithms to track using complementary fusion, but it also does not handle the occlusion and other issues well. In this paper, based on the Staple algorithm, the average peak correlation energy (APCE) and the maximum response are introduced. The value is used as the tracking confidence, and a detector using a support vector machine (SVM) is added. When the tracking confidence is low, the target is blocked or moved violently. At this time, the detector works, and the search area is expanded around the original area for the target. At the same time, because the traditional tracking algorithm uses a fixed learning rate to update the template, this paper uses an adaptive tracking learning rate. When the tracking confidence is low, the update speed of the target model is reduced, which can effectively deal with the occlusion deformation in the tracking process. OTB100 benchmark experiments show that this method can solve the occlusion problem during target tracking. The degree of change is robust and stability.
AB - The Correlation filtering algorithm is not effective for fast deformation and fast movement. It is easy to lose when encountering problems such as occlusion. However, it has a good advantage of dealing with situations such as motion blur and lighting changes. A tracking algorithm based on color statistical features has a good effect on the rotation and translation of objects. The Staple algorithm combines the two algorithms to track using complementary fusion, but it also does not handle the occlusion and other issues well. In this paper, based on the Staple algorithm, the average peak correlation energy (APCE) and the maximum response are introduced. The value is used as the tracking confidence, and a detector using a support vector machine (SVM) is added. When the tracking confidence is low, the target is blocked or moved violently. At this time, the detector works, and the search area is expanded around the original area for the target. At the same time, because the traditional tracking algorithm uses a fixed learning rate to update the template, this paper uses an adaptive tracking learning rate. When the tracking confidence is low, the update speed of the target model is reduced, which can effectively deal with the occlusion deformation in the tracking process. OTB100 benchmark experiments show that this method can solve the occlusion problem during target tracking. The degree of change is robust and stability.
KW - Adaptive Learning Rate
KW - Complementary Filtering
KW - Re-detection
KW - Target Tracking
UR - http://www.scopus.com/inward/record.url?scp=85091399542&partnerID=8YFLogxK
U2 - 10.23919/CCC50068.2020.9188814
DO - 10.23919/CCC50068.2020.9188814
M3 - Conference contribution
AN - SCOPUS:85091399542
T3 - Chinese Control Conference, CCC
SP - 6618
EP - 6623
BT - Proceedings of the 39th Chinese Control Conference, CCC 2020
A2 - Fu, Jun
A2 - Sun, Jian
PB - IEEE Computer Society
T2 - 39th Chinese Control Conference, CCC 2020
Y2 - 27 July 2020 through 29 July 2020
ER -