TailoredBRIEF: Online per-feature descriptor customization

Andrew Richardson, Edwin Olson
2015 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
Image feature descriptors composed of a series of binary intensity comparisons yield substantial memory and runtime improvements over conventional descriptors, but are sensitive to viewpoint changes in ways that vary per feature. We propose a method to improve the matching performance of such descriptors by specifically reasoning about the reliability of test results on a feature-by-feature basis. We demonstrate an intuitive method to learn improved descriptor structures for individual
more » ... Further, these learned results can be efficiently applied during matching with little increase in runtime. We provide an evaluation using a standard, groundtruthed, multi-image dataset.
doi:10.1109/iros.2015.7353357 dblp:conf/iros/RichardsonO15 fatcat:6hme6fgfqzaovke5mifgwhminu