20 February 2018 A visual tracking method based on deep learning without online model updating
Author Affiliations +
Abstract
The paper proposes a visual tracking method based on deep learning without online model updating. In consideration of the advantages of deep learning in feature representation, deep model SSD (Single Shot Multibox Detector) is used as the object extractor in the tracking model. Simultaneously, the color histogram feature and HOG (Histogram of Oriented Gradient) feature are combined to select the tracking object. In the process of tracking, multi-scale object searching map is built to improve the detection performance of deep detection model and the tracking efficiency. In the experiment of eight respective tracking video sequences in the baseline dataset, compared with six state-of-the-art methods, the method in the paper has better robustness in the tracking challenging factors, such as deformation, scale variation, rotation variation, illumination variation, and background clutters, moreover, its general performance is better than other six tracking methods.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Cong Tang, Yicheng Wang, Yunsong Feng, Chao Zheng, Wei Jin, "A visual tracking method based on deep learning without online model updating ", Proc. SPIE 10697, Fourth Seminar on Novel Optoelectronic Detection Technology and Application, 1069726 (20 February 2018); doi: 10.1117/12.2315389; https://doi.org/10.1117/12.2315389
PROCEEDINGS
9 PAGES


SHARE
RELATED CONTENT

An improved TLD with Harris corner and color moment
Proceedings of SPIE (February 08 2017)
Siamese convolutional networks for tracking the spine motion
Proceedings of SPIE (September 19 2017)
Object Recognition by a Hopfield Neural Network
Proceedings of SPIE (March 01 1990)
Relevance feedback-based building recognition
Proceedings of SPIE (July 14 2010)

Back to Top