Geometric invariance in computer vision
Geometric invariance in computer vision
Planar object recognition using projective shape representation
International Journal of Computer Vision
VideoQ: an automated content based video search system using visual cues
MULTIMEDIA '97 Proceedings of the fifth ACM international conference on Multimedia
VideoTrails: representing and visualizing structure in video sequences
MULTIMEDIA '97 Proceedings of the fifth ACM international conference on Multimedia
Monitoring Activities from Multiple Video Streams: Establishing a Common Coordinate Frame
IEEE Transactions on Pattern Analysis and Machine Intelligence
Applications of Invariance in Computer Vision: Second Joint European-U. S. Workshop, Ponta Delgada, Azores, Portugal, October 9-14, 1993
How to Use the Cross Ratio to Compute Projective Invariants from Two Images
Proceedings of the Second Joint European - US Workshop on Applications of Invariance in Computer Vision
Point Projective and Permutation Invariants
CAIP '97 Proceedings of the 7th International Conference on Computer Analysis of Images and Patterns
Recognizing Action at a Distance
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
A hybrid system for affine-invariant trajectory retrieval
Proceedings of the 6th ACM SIGMM international workshop on Multimedia information retrieval
Efficient similar trajectory-based retrieval for moving objects in video databases
CIVR'03 Proceedings of the 2nd international conference on Image and video retrieval
Automated multi-camera planar tracking correspondence modeling
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Practical error analysis of cross-ratio-based planar localization
PSIVT'07 Proceedings of the 2nd Pacific Rim conference on Advances in image and video technology
Hi-index | 0.00 |
We introduce a view–point invariant representation of moving object trajectories that can be used in video database applications. It is assumed that trajectories lie on a surface that can be locally approximated with a plane. Raw trajectory data is first locally–approximated with a cubic spline via least squares fitting. For each sampled point of the obtained curve, a projective invariant feature is computed using a small number of points in its neighborhood. The resulting sequence of invariant features computed along the entire trajectory forms the view–invariant descriptor of the trajectory itself. Time parametrization has been exploited to compute cross ratios without ambiguity due to point ordering. Similarity between descriptors of different trajectories is measured with a distance that takes into account the statistical properties of the cross ratio, and its symmetry with respect to the point at infinity. In experiments, an overall correct classification rate of about 95% has been obtained on a dataset of 58 trajectories of players in soccer video, and an overall correct classification rate of about 80% has been obtained on matching partial segments of trajectories collected from two overlapping views of outdoor scenes with moving people and cars.