Distribution fields for tracking
Top Cited Papers
- 1 June 2012
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2012 IEEE Conference on Computer Vision and Pattern Recognition
- p. 1910-1917
- https://doi.org/10.1109/cvpr.2012.6247891
Abstract
Visual tracking of general objects often relies on the assumption that gradient descent of the alignment function will reach the global optimum. A common technique to smooth the objective function is to blur the image. However, blurring the image destroys image information, which can cause the target to be lost. To address this problem we introduce a method for building an image descriptor using distribution fields (DFs), a representation that allows smoothing the objective function without destroying information about pixel values. We present experimental evidence on the superiority of the width of the basin of attraction around the global optimum of DFs over other descriptors. DFs also allow the representation of uncertainty about the tracked object. This helps in disregarding outliers during tracking (like occlusions or small misalignments) without modeling them explicitly. Finally, this provides a convenient way to aggregate the observations of the object through time and maintain an updated model. We present a simple tracking algorithm that uses DFs and obtains state-of-the-art results on standard benchmarks.Keywords
This publication has 20 references indexed in Scilit:
- Seeing through the blurPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- PROST: Parallel robust online simple trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Mean-Shift Tracking with Random SamplingPublished by British Machine Vision Association and Society for Pattern Recognition ,2006
- Data driven image models through continuous joint alignmentIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Robust online appearance models for visual trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Multiple Collaborative Kernel TrackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Multiple kernel tracking with SSDPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- The Template Update ProblemPublished by British Machine Vision Association and Society for Pattern Recognition ,2003
- Learning patterns of activity using real-time trackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000