Distribution fields for tracking

L. Sevilla-Lara, E. Learned-Miller

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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.
Original languageEnglish
Title of host publication2012 IEEE Conference on Computer Vision and Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1910-1917
Number of pages8
DOIs
Publication statusPublished - 1 Jun 2012
Event25th IEEE Conference on Computer Vision and Pattern Recognition - Providence, United States
Duration: 18 Jun 201220 Jun 2018

Conference

Conference25th IEEE Conference on Computer Vision and Pattern Recognition
Abbreviated titleCVPR 2012
Country/TerritoryUnited States
CityProvidence
Period18/06/1220/06/18

Keywords / Materials (for Non-textual outputs)

  • gradient methods
  • image restoration
  • object tracking
  • distribution fields
  • visual tracking
  • gradient descent
  • alignment function
  • image blurring
  • image information
  • image descriptor
  • pixel values
  • occlusions
  • tracking algorithm
  • Target tracking
  • Smoothing methods
  • Kernel
  • Standards
  • Histograms
  • Convolution

Fingerprint

Dive into the research topics of 'Distribution fields for tracking'. Together they form a unique fingerprint.

Cite this