Fast Algorithms for Low-Level Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Measurement and integration of 3-D structures by tracking edge lines
ECCV 90 Proceedings of the first european conference on Computer vision
An unbiased active contour algorithm for object tracking
Pattern Recognition Letters
Vision-Aided Outdoor Navigation of an Autonomous Horticultural Vehicle
ICVS '99 Proceedings of the First International Conference on Computer Vision Systems
Spatiotemporal oriented energy features for visual tracking
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
2D shape tracking using algebraic curve spaces
ISCIS'05 Proceedings of the 20th international conference on Computer and Information Sciences
Model-based tracking of complex innercity road intersections
Mathematical and Computer Modelling: An International Journal
FhG-Co-driver: From map-guided automatic driving by machine vision to a cooperative driver support
Mathematical and Computer Modelling: An International Journal
Journal of Visual Communication and Image Representation
Hi-index | 0.00 |
The development and implementation of a line segment-based token tracker is described. Given a sequence of time-varying images, the goal is to track line segments corresponding to the edges extracted from the image being analysed. Two representations for the line segments are presented and discussed. An uncertainty analysis on the parameters of each representation is performed, and the appropriate representation for the tracking problem is then derived. A tracking approach is presented that combines prediction and matching steps. The prediction step is a Kalman filtering-based approach that is used to provide reasonable estimates of the region where the matching process has to seek for a possible match between tokens. Correspondence in the search area is done through the use of a similarity function based on Mahalanobis distance between carefully chosen attributes of the line segments. It is worthwhile to note that tokens as points of interest (corners, triple points) can also be considered without affecting deeply the algorithm. The efficiency of the proposed approach is illustrated in several experiments that have been carried out considering noisy synthetic data and real scenes obtained from the INRIA mobile robot.