Gaussian and Laplacian of Gaussian weighting functions for robust feature based tracking
Pattern Recognition Letters
Registration Using Natural Features for Augmented Reality Systems
IEEE Transactions on Visualization and Computer Graphics
ACM Computing Surveys (CSUR)
Segmentation and tracking of multiple video objects
Pattern Recognition
Multi-view correspondence by enforcement of rigidity constraints
Image and Vision Computing
Computer Vision and Image Understanding
CIARP '09 Proceedings of the 14th Iberoamerican Conference on Pattern Recognition: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
Real-time automatic kinematic model building for optical motion capture using a Markov random field
HCI'07 Proceedings of the 2007 IEEE international conference on Human-computer interaction
Behavior based robot localisation using stereo vision
RobVis'08 Proceedings of the 2nd international conference on Robot vision
Efficient marker matching using pair-wise constraints in physical therapy
ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part II
Tracking humans using novel optical flow algorithm for surveillance videos
COMPUTE '11 Proceedings of the Fourth Annual ACM Bangalore Conference
Maneuvering head motion tracking by coarse-to-fine particle filter
ICIAR'11 Proceedings of the 8th international conference on Image analysis and recognition - Volume Part I
Optimal multi-frame correspondence with assignment tensors
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
Exploiting eye-hand coordination to detect grasping movements
Image and Vision Computing
Robotics and Autonomous Systems
Hierarchical fuzzy logic based approach for object tracking
Knowledge-Based Systems
A visualization framework for team sports captured using multiple static cameras
Computer Vision and Image Understanding
Persistent tracking of static scene features using geometry
Computer Vision and Image Understanding
| Hi-index | 0.01 |
This paper presents a framework for finding point correspondencesin monocular image sequences over multiple frames.The generalproblem of multi-frame point correspondence is NP Hard for three ormore frames. A polynomial time algorithm for a restriction of thisproblem is presented, and is used as the basis of proposed greedyalgorithm for the general problem. The greedy nature of theproposed algorithm allows it to be used in real time systems fortracking and surveillance etc. In addition, the proposed algorithmdeals with the problems of occlusion, missed detections, and falsepositives, by using a single non-iterative greedy optimizationscheme, and hence, reduces the complexity of the overall algorithmas compared to most existing approaches, where multiple heuristicsare used for the same purpose.While most greedy algorithms forpoint tracking do not allow for entry and exit of points from thescene, this is not a limitation for the proposed algorithm.Experiments with real and synthetic data show that the proposedalgorithm outperforms the existing techniques and is applicable inmore general settings.