Constraints on deformable models: recovering 3D shape and nongrid motion
Artificial Intelligence
Building, registrating, and fusing noisy visual maps
International Journal of Robotics Research - Special Issue on Sensor Data Fusion
Integration of visual modules: an extension of the Marr paradigm
Integration of visual modules: an extension of the Marr paradigm
Bayesian modeling of uncertainty in low-level vision
International Journal of Computer Vision
Robust regression methods for computer vision: a review
International Journal of Computer Vision
Fitting Parameterized Three-Dimensional Models to Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Feature extraction from faces using deformable templates
International Journal of Computer Vision
Physical modeling and combination of range and intensity edge data
CVGIP: Image Understanding
Planning under time constraints in stochastic domains
Artificial Intelligence - Special volume on planning and scheduling
Optimal composition of real-time systems
Artificial Intelligence
Image segmentation from consensus information
Computer Vision and Image Understanding
Integrated Person Tracking Using Stereo, Color, and Pattern Detection
International Journal of Computer Vision - Special issue on a special section on visual surveillance
Optical Flow Constraints on Deformable Models with Applications to Face Tracking
International Journal of Computer Vision
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Integrating Vision Modules: Stereo, Shading, Grouping, and Line Labeling
IEEE Transactions on Pattern Analysis and Machine Intelligence
Performance Analysis of Stereo, Vergence, and Focus as Depth Cues for Active Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hierarchical Model-Based Motion Estimation
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Learning Dynamics of Complex Motions from Image Sequences
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
A Model-Free Voting Approach for Integrating Multiple Cues
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Reliable Tracking of Human Arm Dynamics by Multiple Cue Integration and Constraint Fusion
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Joint Probabilistic Techniques for Tracking Multi-Part Objects
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Multi-Modal System for Locating Heads and Faces
FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
Perception, attention, and resources: a decision-theoretic approach to graphics rendering
UAI'97 Proceedings of the Thirteenth conference on Uncertainty in artificial intelligence
Integrating cue descriptors in bubble space for place recognition
ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
| Hi-index | 0.00 |
Typical cue integration techniques work by combining estimates produced by computations associated with each visual cue. Most of these computations are iterative, leading to partial results that are available upon each iteration, culminating in complete results when the algorithm finally terminates. Combining partial results upon each iteration would be the preferred strategy for cue integration, as early cue integration strategies are inherently more stable and more efficient. Surprisingly, existing cue integration techniques cannot correctly use partial results, but must wait for all of the cue computations to finish. This is because the intrinsic error in partial results, which arises entirely from the fact that the algorithm has not yet terminated, is not represented. While cue integration methods do exist which attempt to use partial results (such as one based on an iterated extended Kalman Filter), they make critical errors.I address this limitation with the development of a probabilistic model of errors in estimates from partial results, which represents the error that remains in iterative algorithms prior to their completion. This enables existing cue integration frameworks to draw upon partial results correctly. Results are presented on using such a model for tracking faces using feature alignment, contours, and optical flow. They indicate that this framework improves accuracy, efficiency, and robustness over one that uses complete results.The eventual goal of this line of research is the creation of a decisiontheoretic meta-reasoning framework for cue integration--a vital mechanism for any system with real-time deadlines and variable computational demands. This framework will provide a means to decide how to best spend computational resources on each cue, based on how much it reduces the uncertainty of the combined result.