Optimization and Estimation Algorithm of Vehicle Spatial Form Based on Monocular Traffic Camera

Accurate and rapid acquisition of vehicle spatial form is of great significance to the fields of intelligent transportation and autonomous driving. However, due to the limitations of projective geometry, it is difficult for monocular cameras to obtain the three-dimensional structure of the object. Therefore, the goal of this paper is to estimate the vehicle spatial form under monocular traffic cameras. To begin with, the authors establish a calibration model of the road scene, and jointly build the geometric constraint model of the vehicle spatial form by combining the vanishing point constraint. Furthermore, based on Mask-Rcnn, the contour and boundary constraints of the vehicle are obtained, and based on these constraints, an error constraint function to estimate the projection error of the vehicle spatial form is constructed. Finally, particle swarm algorithm is used to iteratively optimize the parameters in the constraint space to obtain accurate vehicle spatial form information. Experimental results show that the algorithm can effectively complete various types of vehicle spatial forms estimation with accuracy of 94% and real-time processing, which outperforms existing methods.

Language

  • English

Media Info

  • Media Type: Digital/other
  • Features: Figures; Photos; References; Tables;
  • Pagination: 15p

Subject/Index Terms

Filing Info

  • Accession Number: 01764195
  • Record Type: Publication
  • Report/Paper Numbers: TRBAM-21-01192
  • Files: TRIS, TRB, ATRI
  • Created Date: Dec 23 2020 11:22AM