Learning and matching multiscale template descriptors for real-time detection, localization and tracking

Authors:
Taehee Lee;S. Soatto
Affiliations:
Comput. Sci. Dept., Univ. of California, Los Angeles, CA, USA;Comput. Sci. Dept., Univ. of California, Los Angeles, CA, USA
Venue:
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Year:
2011

Citing 0
Cited 3

Orientation-aware scene understanding for mobile cameras

Proceedings of the 2012 ACM Conference on Ubiquitous Computing
Real-time mobile recipe recommendation system using food ingredient recognition

Proceedings of the 2nd ACM international workshop on Interactive multimedia on mobile and portable devices
Information-Seeking Control Under Visibility-Based Uncertainty

Journal of Mathematical Imaging and Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe a system to learn an object template from a video stream, and localize and track the corresponding object in live video. The template is decomposed into a number of local descriptors, thus enabling detection and tracking in spite of partial occlusion. Each local descriptor aggregates contrast invariant statistics (normalized intensity and gradient orientation) across scales, in a way that enables matching under significant scale variations. Low-level tracking during the training video sequence enables capturing object-specific variability due to the shape of the object, which is encapsulated in the descriptor. Salient locations on both the template and the target image are used as hypotheses to expedite matching.