Skip to main navigation Skip to search Skip to main content

An Elastic Deformation Field Model for Object Detection and Tracking

  • KU Leuven

Research output: Contribution to journal › Journal Article › peer-review

13 Citations (Scopus)

Abstract

Deformable Parts Models (DPM) are the current state-of-the-art for object detection. Nevertheless they seem sub-optimal in the representation of deformations. Object deformations are often continuous and not confined to big parts. Therefore we propose to replace the DPM star model based on big parts by a deformation field. This consists of a grid of small parts connected with pairwise constraints which can better handle continuous deformations. The naive application of this model for object detection would consist of a bounded sliding window approach: for each possible location of the image the best part configuration within a limited bound around this location is found. This is computationally very expensive.Instead, we propose a different inference procedure, where an iterative image-level search finds the best object hypothesis. We show that this approach is faster than bounded sliding windows yet produces comparable accuracy. Experiments further show that the deformation field can better approximate real object deformations and therefore, for certain classes, produces even better detection accuracy than state-of-the-art DPM. Finally, the same approach is adapted to model-free tracking, showing improved accuracy also in this case.

Original languageEnglish
Pages (from-to)137-152
Number of pages16
JournalInternational Journal of Computer Vision
Volume111
Issue number2
DOIs
Publication statusPublished - 1 Jan 2015
Externally publishedYes

Keywords

  • Deformable Part Models
  • Deformation field
  • Latent SVM
  • Object detection
  • Tracking

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'An Elastic Deformation Field Model for Object Detection and Tracking'. These topics are generated from the title and abstract of the publication. Together, they form a unique fingerprint.

Cite this