Feature Harvesting for Tracking-by-DetectionReport as inadecuate




Feature Harvesting for Tracking-by-Detection - Download this document for free, or read online. Document in PDF available to download.

Presented at: European Conference on Computer Vision, Graz, May 7-13, 2006 Published in: Computer Vision – ECCV 2006, p. 592-605 Series: Lecture Notes in Computer Science 3953 Berlin / Heidelberg: Springer, 2006

We propose a fast approach to 3D object detection and pose estimation that owes its robustness to a training phase during which the target object slowly moves with respect to the camera. No additional information is provided to the system, save a very rough initialization in the first frame of the training sequence. It can be used to detect the target object in each video frame independently. Our approach relies on a Randomized Tree-based approach to wide baseline feature matching. Unlike previous classification-based approaches to 3-D pose estimation, we do not require an a priori 3-D model. Instead, our algorithm learns both geometry and appearance. In the process, it collects, or harvests, a list of features that can be reliably recognized even when large motions and aspect changes cause complex variations of feature appearances. This is made possible by the great fl exibility of Randomized Trees, which lets us add and remove feature points to our list as needed with a minimum amount of extra computation.

Keywords: Computer Vision ; Object Detection ; Tracking by Detection ; Pose Estimation Reference CVLAB-CONF-2008-002





Author: Ozuysal, Mustafa; Lepetit, Vincent; Fleuret, Francois; Fua, Pascal

Source: https://infoscience.epfl.ch/record/126373?ln=en







Related documents