
For FullText PDF, please login, if you are a member of IEICE,
or go to Pay Per View on menu list, if you are a nonmember of IEICE.

Adaptive MultiScale Tracking Target Algorithm through Drone
Qiusheng HE Xiuyan SHAO Wei CHEN Xiaoyun LI Xiao YANG Tongfeng SUN
Publication
IEICE TRANSACTIONS on Communications
Vol.E102B
No.10
pp.19982005 Publication Date: 2019/10/01
Online ISSN: 17451345
DOI: 10.1587/transcom.2018DRP0040
Type of Manuscript: Special Section PAPER (Special Section on Exploring Drone for Mobile Sensing, Coverage and Communications: Theory and Applications) Category: Keyword: target tracking, color feature, principal component analysis, scale adaptation,
Full Text: PDF(4.3MB)>>
Summary:
In order to solve the influence of scale change on target tracking using the drone, a multiscale target tracking algorithm is proposed which based on the color feature tracking algorithm. The algorithm realized adaptive scale tracking by training position and scale correlation filters. It can first obtain the target center position of next frame by computing the maximum of the response, where the position correlation filter is learned by the least squares classifier and the dimensionality reduction for color features is analyzed by principal component analysis. The scale correlation filter is obtained by color characteristics at 33 rectangular areas which is set by the scale factor around the central location and is reduced dimensions by orthogonal triangle decomposition. Finally, the location and size of the target are updated by the maximum of the response. By testing 13 challenging video sequences taken by the drone, the results show that the algorithm has adaptability to the changes in the target scale and its robustness along with many other performance indicators are both better than the most stateoftheart methods in illumination Variation, fast motion, motion blur and other complex situations.

