M2Tracker: A Multi-View Approach to Segmenting and Tracking People in a Cluttered Scene

By Anurag Mittal, Larry S. Davis. International Journal of Computer Vision, 2003

437 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5d3e56c19608a32751203ef5367ade3e6e7159d5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Modeling inter-camera space-time and appearance relationships for tracking across non-overlapping views (2008, methodology): “Mittal and Davis [ 25 ] used a region-based stereo algorithm to estimate the depth of points potentially lying on foreground objects and projected them on the ground plane.”
A Multiview Approach to Tracking People in Crowded Scenes Using a Planar Homography Constraint (2006, methodology): “[12] use a similar method to combine information in pairs of stereo cameras.”
A system for learning statistical motion patterns (2006, background): “While there exist some algorithms [23], [24], [28], [31], [39], [51] for tracking multiple objects, most of them fail due to the complexity of motions in crowded traffic scenes.”
Crowd analysis: a survey (2008, background): “[70] present a system named M2Tracker using multiple synchronized cameras located far from each other for segmenting, detecting and tracking multiple people in a cluttered scene.”
Multiple Object Tracking Using K-Shortest Paths Optimization (2011, positive): “A wide range of approaches relies on the recursive updateoftrackswiththemostrecentdetections.Forinstance, Kalman filtering is an efficient way to address multitarget tracking [7], [ 8 ], [9], [10], [11] when the number of objects remainssmall.Itisalsowellsuitedforreal-timeapplications.”
Object tracking: A survey (2006, methodology): “Multiple cameras viewing the same scene can also be used to resolve object occlusions during tracking [Dockstader and Tekalp 2001a; Mittal and Davis 2003].”
Intelligent multi-camera video surveillance: A review (2013, background): “…is to track objects in a 3D coordinate system (Mikic et al., 1998; Dockstader and Tekalp, 2001; Li et al., 2002; Focken and Stiefelhagen, 2002; Mittal and Davis, 2003; Pflugfelder and Bischof, 2007) or on a single global ground plane (Chang and Gong, 2001; Black et al., 2002; Otsuka and…”
Multicamera People Tracking with a Probabilistic Occupancy Map (2008, methodology): “2 Color-Based Methods [15] proposes a system that segments, detects and tracks multiple people in a scene using a widebaseline setup of up to 16 synchronized cameras.”
Robust video segment proposals with painless occlusion handling (2015, background): “There are works that handle occlusion in video segmentation under some assumptions, either only segmenting humans [13, 25] or utilizing multi-view cameras [33].”
Tracking Multiple Occluding People by Localizing on Multiple Scene Planes (2009, methodology): “Integration of stereo pairs is another popular approach, adopted by [31], [37], [9], [1] among others.”