2006 · 127 citations · 9 references
ComputingComputer ScienceComputer VisionMachine VisionRobot VisionMotion EstimationOptical FlowParticle TracingPoint Cloud ProcessingVideo AnalysisVisual TrackingFeature TrackingMotion RepresentationOptical Flow EstimationParticle LocalizationParticle TrajectoriesPoint Cloud MatchingPoint Cloud TrackingPoint Tracking
This paper describes a new approach to motion estimation in video. We represent video motion using a set of particles. Each particle is an image point sample with a longduration trajectory and other properties. To optimize these particles, we measure point-based matching along the particle trajectories and distortion between the particles. The resulting motion representation is useful for a variety of applications and cannot be directly obtained using existing methods such as optical flow or feature tracking. We demonstrate the algorithm on challenging real-world videos that include complex scene geometry, multiple types of occlusion, regions with low texture, and non-rigid deformations.
9
Motion segmentation and tracking using normalized cuts
Jianbo Shi, Jitendra Malik · 2002 · 344 citations
Robust dynamic motion estimation over time
Michael J. Black, P. Anandan · 2002 · 241 citations
Morphable 3D models from video
W. Brand · 2005 · 151 citations
Multi-frame optical flow estimation using subspace constraints
M. Irani · 1999 · 140 citations