Cronje, J2011-12-122011-12-122011-11Cronje, J. 2011. BFROST: binary features from robust orientation segment tests accelerated on the GPU. 22nd Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), Emerald Casino and Resort, Vanderbijlpark, South Africa, 22-25 November 2011http://hdl.handle.net/10204/538722nd Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), Emerald Casino and Resort, Vanderbijlpark, South Africa, 22-25 November 2011A fast local image feature detector and descriptor that is implementable on the GPU is proposed. This method is the first GPU implementation of the popular FAST detector. A simple but novel method of feature orientation estimation which can be calculated in constant time is proposed. The robustness and reliability of our orientation estimation is validated against rotation invariant descriptors such as SIFT and SURF. Furthermore, a binary feature descriptor is proposed which is robust to noise, scalable, rotation invariant, fast to compute in parallel and maintains low memory consumption. The proposed method demonstrates good robustness and very fast computation times, making it usable in real-time applications.enComputer visionFeature detectionFeature extractionFAST detectorBFROSTPattern recognition associationPRASA 2011Conference PresentationCronje, J. (2011). BFROST: binary features from robust orientation segment tests accelerated on the GPU. http://hdl.handle.net/10204/5387Cronje, J. "BFROST: binary features from robust orientation segment tests accelerated on the GPU." (2011): http://hdl.handle.net/10204/5387Cronje J, BFROST: binary features from robust orientation segment tests accelerated on the GPU; 2011. http://hdl.handle.net/10204/5387 .TY - Conference Presentation AU - Cronje, J AB - A fast local image feature detector and descriptor that is implementable on the GPU is proposed. This method is the first GPU implementation of the popular FAST detector. A simple but novel method of feature orientation estimation which can be calculated in constant time is proposed. The robustness and reliability of our orientation estimation is validated against rotation invariant descriptors such as SIFT and SURF. Furthermore, a binary feature descriptor is proposed which is robust to noise, scalable, rotation invariant, fast to compute in parallel and maintains low memory consumption. The proposed method demonstrates good robustness and very fast computation times, making it usable in real-time applications. DA - 2011-11 DB - ResearchSpace DP - CSIR KW - Computer vision KW - Feature detection KW - Feature extraction KW - FAST detector KW - BFROST KW - Pattern recognition association KW - PRASA 2011 LK - https://researchspace.csir.co.za PY - 2011 T1 - BFROST: binary features from robust orientation segment tests accelerated on the GPU TI - BFROST: binary features from robust orientation segment tests accelerated on the GPU UR - http://hdl.handle.net/10204/5387 ER -