• Publications
  • Influence
Online Selection of Discriminative Tracking Features
TLDR
This paper presents an online feature selection mechanism for evaluating multiple features while tracking and adjusting the set of features used to improve tracking performance. Expand
A System for Video Surveillance and Monitoring
Under the three-year Video Surveillance and Monitoring (VSAM) project (1997‐1999), the Robotics Institute at Carnegie Mellon University (CMU) and the Sarnoff Corporation developed a system forExpand
Mean-shift blob tracking through scale space
  • R. Collins
  • Mathematics, Computer Science
  • IEEE Computer Society Conference on Computer…
  • 18 June 2003
TLDR
We adapt Lindeberg's (1998) theory of feature scale selection based on local maxima of differential scale-space filters to the problem of selecting kernel scale for mean-shift blob tracking. Expand
On-line selection of discriminative tracking features
We present a method for evaluating multiple feature spaces while tracking, and for adjusting the set of features used to improve tracking performance. Our hypothesis is that the features that bestExpand
A space-sweep approach to true multi-image matching
  • R. Collins
  • Computer Science
  • Proceedings CVPR IEEE Computer Society Conference…
  • 18 June 1996
TLDR
A new space-sweep approach to true multi-image matching is presented that simultaneously determines 2D feature correspondences and the 3D positions of feature points in the scene. Expand
Silhouette-based human identification from body shape and gait
TLDR
We present a viewpoint-dependent technique based on template matching of body silhouettes. Expand
Deformed Lattice Detection in Real-World Images Using Mean-Shift Belief Propagation
TLDR
We formulate the 2D lattice detection as a spatial, multitarget tracking problem, solved within an MRF framework using a novel and efficient mean shift belief propagation (MSBP) method. Expand
Three-dimensional scene flow
TLDR
We describe three algorithms, the first two for computing scene flow from optical flows and the third for constraining scene structure from the inconsistencies in multiple optical flows. Expand
Algorithms for cooperative multisensor surveillance
The Video Surveillance and Monitoring (VSAM) team at Carnegie Mellon University (CMU) has developed an end-to-end, multicamera surveillance system that allows a single human operator to monitorExpand
Online selection of discriminative tracking features
  • R. Collins, Yanxi Liu
  • Mathematics, Medicine
  • IEEE Transactions on Pattern Analysis and Machine…
  • 13 October 2003
TLDR
This paper presents an online feature selection mechanism for evaluating multiple features while tracking and adjusting the set of features used to improve tracking performance. Expand
...
1
2
3
4
5
...