location: Current position: Home >> Scientific Research >> Paper Publications

Robust Tracking Based on Pixel-Wise Spatial Pyramid and Biased Fusion

Hits:

Indexed by:会议论文

Date of Publication:2010-11-08

Included Journals:EI、CPCI-S、Scopus

Volume:6495

Issue:PART 4

Page Number:165-176

Abstract:We propose a novel tracking algorithm for the balance between stability and adaptivity as well as a. new online appearance model. Since the update error is inevitable, we present three tracking modules, i.e., reference model, soft reference model and adaptive model, and fuse them using biased multiplicative formula. These three contributors are built through the same appearance model with different update rate. The appearance model, Pixel-wise Spatial Pyramid, employs pixel feature vectors instead of SIFT vectors, to combine several pixel characteristics. In particular, the reserved pixel feature vectors are used to create a new codebook together with the earlier codebook. A hybrid feature map consisting of the reserved pixel vectors and anti-part of previous hybrid feature map is built to represent the new target map. Experimental results show that our approach tracks the object with drastic appearance change, accurately and robustly.

Pre One:On Feature Combination and Multiple Kernel Learning for Object Tracking

Next One:ROBUST TRACKING BASED ON BOOSTED COLOR SOFT SEGMENTATION AND ICA-R