by Kentaro Toyama, Gregory D. Hager
International Journal of Computer Vision
http://www.cs.yale.edu/users/toyama/papers/layered.ps.gz
Add To MetaCart
Abstract:
We present an incremental focus of attention (IFA) architecture for adding robustness to software-based, real-time, motion trackers. The framework provides a structure which, when given the entire camera image to search, efficiently focuses the attention of the system into a narrow set of configurations that includes the target configuration. IFA offers a means for automatic tracking initialization and reinitialization when environmental conditions momentarily deteriorate and cause the system to lose track of its target. Systems based on the framework degrade gracefully as various assumptions about the environment are violated. In particular, when constructed with multiple tracking algorithms of varying precision, the failure of a single algorithm causes another, less precise algorithm to take over, thereby allowing the system to return approximate information on feature location or configuration.
Citations
|
2142
|
A robust layered control system for a mobile robot
– Brooks
- 1986
|
|
1397
|
STRIPS: A new approach in the application of theorem proving to problem solving
– Fikes, Nilsson
- 1971
|
|
967
|
Intelligence without representation
– Brooks
- 1991
|
|
669
|
Good features to track
– Shi, Tomasi
- 1994
|
|
250
|
The HEARSAY-II speech understanding system: Integrating knowledge to resolve uncertainty
– Erman, Hayes-Roth, et al.
- 1980
|
|
145
|
Robust model-based motion tracking through the integration of search and estimation
– Lowe
- 1992
|
|
128
|
Visual tracking of known three-dimensional objects
– Gennery
- 1992
|
|
54
|
Measurement and integration of 3-D structures by tracking edge lines
– Crowley, Stelmaszyk, et al.
- 1992
|
|
44
|
Calibration-free visual control using projective invariance
– Hager
- 1995
|
|
36
|
Animat vision: Active vision in artificial animals,” Videre
– Terzopoulos, Rabie
- 1997
|
|
30
|
SCARF: a color vision system that tracks roads and intersections
– Crisman, Thorpe
- 1993
|
|
28
|
An attentional prototype for early vision
– Culhane, Tsotsos
- 1992
|
|
26
|
The "XVision" system: A general purpose substrate for real-time vision applications
– Hager, Toyama
- 1998
|
|
14
|
An inhibitory beam for attentional selection
– Tsotsos
- 1993
|
|
13
|
Toward a computational model of visual attention
– Tsotsos
- 1995
|
|
8
|
Vision-based motion tracking of rigid objects using prediction of uncertainties
– Kosaka, Nakazawa
- 1995
|
|
6
|
Tracker fusion for robustness in visual feature tracking
– Toyama, Hager
- 1995
|
|
4
|
Keeping your eye on the ball: Tracking occluding contours of unfamiliar objects without distraction
– Toyama, Hager
- 1995
|
|
2
|
Model-based edge selection for 2-D object recognition
– Tagare, McDermott
- 1994
|
