Pedestrian recognition with false positive detection by model-based tracking

Ryusuke Miyamoto, Hiroki Sugano, Yukihiro Nakamura

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

2 Citations (Scopus)

Abstract

Nowadays, pedestrian recognition based on image processing is widely tackled. Generally, pedestrian recognition is constructed by combining detection and tracking of pedestrians. However, accuracy of pedestrian recognition degrades since non-pedestrian objects are tracked once they are falsely detected as pedestrians. To overcome this problem, a novel pedestrian recognition by combining detection based on boosting and skeleton-based stochastic tracking with false positive detection is proposed. In the proposed scheme, false positives are detected based on the variance of predicted skeleton in a tracking phase. The experimental results by applying the proposed scheme to a sequence provided by PETS show that false positives can be detected by the proposed scheme based on the variance.

Original languageEnglish
Title of host publicationProceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007
Pages62-67
Number of pages6
Publication statusPublished - 1 Dec 2007
Event4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007 - Innsbruck, Austria
Duration: 14 Feb 200716 Feb 2007

Publication series

NameProceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007

Conference

Conference4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007
CountryAustria
CityInnsbruck
Period14/02/0716/02/07

Keywords

  • False positive detection
  • Particle filter
  • Pattern recognition
  • Pedestrian recognition
  • Stochastic tracking

Fingerprint Dive into the research topics of 'Pedestrian recognition with false positive detection by model-based tracking'. Together they form a unique fingerprint.

  • Cite this

    Miyamoto, R., Sugano, H., & Nakamura, Y. (2007). Pedestrian recognition with false positive detection by model-based tracking. In Proceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007 (pp. 62-67). (Proceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007).