Optimized pedestrian detection for multiple and occluded people

Sitapa Rujikietgumjorn, Robert T. Collins

Research output: Contribution to journalConference articlepeer-review

21 Scopus citations

Abstract

We present a quadratic unconstrained binary optimization (QUBO) framework for reasoning about multiple object detections with spatial overlaps. The method maximizes an objective function composed of unary detection confidence scores and pairwise overlap constraints to determine which overlapping detections should be suppressed, and which should be kept. The framework is flexible enough to handle the problem of detecting objects as a shape covering of a foreground mask, and to handle the problem of filtering confidence weighted detections produced by a traditional sliding window object detector. In our experiments, we show that our method outperforms two existing state-of-the-art pedestrian detectors.

Original languageEnglish (US)
Article number6619317
Pages (from-to)3690-3697
Number of pages8
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOIs
StatePublished - Nov 15 2013
Event26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013 - Portland, OR, United States
Duration: Jun 23 2013Jun 28 2013

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Optimized pedestrian detection for multiple and occluded people'. Together they form a unique fingerprint.

Cite this