Incremental learning of 3D-DCT compact representations for robust visual tracking

CORC > 厦门大学 > 萨本栋－已发表论文

	Incremental learning of 3D-DCT compact representations for robust visual tracking
	Li, Xi ; Dick, Anthony ; Shen, Chunhua ; Van Den Hengel, Anton ; Wang, Han ; Li X(李鑫) ; Wang HZ(王菡子)
刊名	http://dx.doi.org/10.1109/TPAMI.2012.166
	2013
关键词	Discrete cosine transforms Signal analysis Signal reconstruction Template matching Tracking (position) Video recording
英文摘要	Visual tracking usually requires an object appearance model that is robust to changing illumination, pose, and other factors encountered in video. Many recent trackers utilize appearance samples in previous frames to form the bases upon which the object appearance model is built. This approach has the following limitations: 1) The bases are data driven, so they can be easily corrupted, and 2) it is difficult to robustly update the bases in challenging situations. In this paper, we construct an appearance model using the 3D discrete cosine transform (3D-DCT). The 3D-DCT is based on a set of cosine basis functions which are determined by the dimensions of the 3D signal and thus independent of the input video data. In addition, the 3D-DCT can generate a compact energy spectrum whose high-frequency coefficients are sparse if the appearance samples are similar. By discarding these high-frequency coefficients, we simultaneously obtain a compact 3D-DCT-based object representation and a signal reconstruction-based similarity measure (reflecting the information loss from signal reconstruction). To efficiently update the object representation, we propose an incremental 3D-DCT algorithm which decomposes the 3D-DCT into successive operations of the 2D discrete cosine transform (2D-DCT) and 1D discrete cosine transform (1D-DCT) on the input video data. As a result, the incremental 3D-DCT algorithm only needs to compute the 2D-DCT for newly added frames as well as the 1D-DCT along the third dimension, which significantly reduces the computational complexity. Based on this incremental 3D-DCT algorithm, we design a discriminative criterion to evaluate the likelihood of a test sample belonging to the foreground object. We then embed the discriminative criterion into a particle filtering framework for object state inference over time. Experimental results demonstrate the effectiveness and robustness of the proposed tracker. ? 1979-2012 IEEE.
语种	英语
出版者	IEEE Computer Society
内容类型	期刊论文
源URL	[http://dspace.xmu.edu.cn/handle/2288/90429]
专题	萨本栋－已发表论文
推荐引用方式 GB/T 7714	Li, Xi,Dick, Anthony,Shen, Chunhua,et al. Incremental learning of 3D-DCT compact representations for robust visual tracking[J]. http://dx.doi.org/10.1109/TPAMI.2012.166,2013.
APA	Li, Xi.,Dick, Anthony.,Shen, Chunhua.,Van Den Hengel, Anton.,Wang, Han.,...&王菡子.(2013).Incremental learning of 3D-DCT compact representations for robust visual tracking.http://dx.doi.org/10.1109/TPAMI.2012.166.
MLA	Li, Xi,et al."Incremental learning of 3D-DCT compact representations for robust visual tracking".http://dx.doi.org/10.1109/TPAMI.2012.166 (2013).