Info hash | bdc435dc1ca872db0defb6e5b2aeb9a35d728186 |
Last mirror activity | 337d,23:35:04 ago |
Size | 3.07MB (3,069,990 bytes) |
Added | 2016-03-30 15:14:41 |
Views | 1345 |
Hits | 1773 |
ID | 3157 |
Type | single |
Downloaded | 310 time(s) |
Uploaded by | ghost |
Filename | 04674368.pdf |
Mirrors | 0 complete, 0 downloading = 0 mirror(s) total [Log in to see full list] |
04674368.pdf | 3.07MB |
Type: Paper
Tags:
Bibtex:
Tags:
Bibtex:
@ARTICLE{4674368, author={E. Rosten and R. Porter and T. Drummond}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, title={Faster and Better: A Machine Learning Approach to Corner Detection}, year={2010}, volume={32}, number={1}, pages={105-119}, abstract={The repeatability and efficiency of a corner detector determines how likely it is to be useful in a real-world application. The repeatability is important because the same scene viewed from different positions should yield features which correspond to the same real-world 3D locations. The efficiency is important because this determines whether the detector combined with further processing can operate at frame rate. Three advances are described in this paper. First, we present a new heuristic for feature detection and, using machine learning, we derive a feature detector from this which can fully process live PAL video using less than 5 percent of the available processing time. By comparison, most other detectors cannot even operate at frame rate (Harris detector 115 percent, SIFT 195 percent). Second, we generalize the detector, allowing it to be optimized for repeatability, with little loss of efficiency. Third, we carry out a rigorous comparison of corner detectors based on the above repeatability criterion applied to 3D scenes. We show that, despite being principally constructed for speed, on these stringent tests, our heuristic detector significantly outperforms existing feature detectors. Finally, the comparison demonstrates that using machine learning produces significant improvements in repeatability, yielding a detector that is both very fast and of very high quality.}, keywords={edge detection;feature extraction;learning (artificial intelligence);3D location;PAL video;corner detection;edge technique;feature detection;machine learning approach;real-world application;Computer vision;Detectors;Image edge detection;Image matching;Image recognition;Layout;Machine learning;Simultaneous localization and mapping;Streaming media;Testing;Corner detection;feature detection;feature detection.}, doi={10.1109/TPAMI.2008.275}, ISSN={0162-8828}, month={Jan},}