Robust Height Estimation of Moving Objects From Uncalibrated Videos
Authors:
- 22 March 2010
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 19 (8) , 2221-2232
Abstract
This paper presents an approach for video metrology. From videos acquired by an uncalibrated stationary camera, we first recover the vanishing line and the vertical point of the scene based upon tracking moving objects that primarily lie on a ground plane. Using geometric properties of moving objects, a probabilistic model is constructed for simultaneously grouping trajectories and estimating vanishing points. Then we apply a single view mensuration algorithm to each of the frames to obtain height measurements. We finally fuse the multiframe measurements using the least median of squares (LMedS) as a robust cost function and the Robbins-Monro stochastic approximation (RMSA) technique. This method enables less human supervision, more flexibility and improved robustness. From the uncertainty analysis, we conclude that the method with auto-calibration is robust in practice. Results are shown based upon realistic tracking data from a variety of scenes.Keywords
This publication has 22 references indexed in Scilit:
- Appearance Modeling Using a Geometric TransformIEEE Transactions on Image Processing, 2009
- Visual Tracking and Recognition Using Appearance-Adaptive Models in Particle FiltersIEEE Transactions on Image Processing, 2004
- About conditions for recovering the metric structures of perpendicular planes from the single ground plane to image homography2002
- Reconstruction of a scene with multiple linearly moving objects2002
- Automatic recovery of relative camera rotations for urban scenes2002
- A new approach to vanishing point detection in architectural environmentsImage and Vision Computing, 2002
- Vanishing points and 3D lines from omnidirectional video2002
- Accurate Visual Metrology from Single and Multiple Uncalibrated Images2001
- Learning patterns of activity using real-time trackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Distortion invariant object recognition in the dynamic link architectureIEEE Transactions on Computers, 1993