Traffic object detections and its action analysis

  • Authors:
  • Youfu Wu;Jun Shen;Mo Dai

  • Affiliations:
  • EGID Bordeaux 3, 1 Allée Daguin, Domaine Universitaire 33607 Pessac, Bordeaux, France;EGID Bordeaux 3, 1 Allée Daguin, Domaine Universitaire 33607 Pessac, Bordeaux, France;EGID Bordeaux 3, 1 Allée Daguin, Domaine Universitaire 33607 Pessac, Bordeaux, France

  • Venue:
  • Pattern Recognition Letters
  • Year:
  • 2005

Quantified Score

Hi-index 0.10

Visualization

Abstract

In this paper, we propose a new method to detect the moving objects using the orthogonal Gaussian-Hermite moments (OGHM). For the segmentation of moving objects in the moment images, we propose a fuzzy relaxation method (FRM) and 3D morphological relaxation method (3DMRM). Finally, the trajectories, speeds and accelerations of moving objects are analyzed to determine their moving direction. The experimental results show good performance of our methods in the noise scene for detecting the motion objects.