{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T23:03:20Z","timestamp":1777676600694,"version":"3.51.4"},"reference-count":23,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2016,7,28]],"date-time":"2016-07-28T00:00:00Z","timestamp":1469664000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of High Performance Computing Applications"],"published-print":{"date-parts":[[2016,8]]},"abstract":"<jats:p>The random forests (RF) classifier has recently gained momentum in the computer vision field, thanks to its successful application in human body tracking, hand pose estimation and object detection. In this article, we present a novel approach to train RF on a graphics processing unit (GPU) for computer vision applications where simple per-pixel features are computed. Besides leveraging the processing power of the GPU to accelerate the training, we reformulate the training problem to limit costly image transfers when it is not possible to store the entire data set in GPU memory. Furthermore, our implementation supports arbitrary image types and allows the user to specify custom features. We extensively compare our approach with the state of the art on publicly available data sets, and we obtain a reduction in training time of up to 18 times. Finally, we train our implementation on a large data set (around 100\u2009K images), demonstrating that our approach is suitable for training RF on the vast data sets typically used in computer vision.<\/jats:p>","DOI":"10.1177\/1094342015622672","type":"journal-article","created":{"date-parts":[[2015,12,30]],"date-time":"2015-12-30T20:34:55Z","timestamp":1451507695000},"page":"290-304","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":2,"title":["A novel approach to train random forests on GPU for computer vision applications using local features"],"prefix":"10.1177","volume":"30","author":[{"given":"Daniele","family":"Pianu","sequence":"first","affiliation":[{"name":"Institute of Electronics, Computer and Telecommunication Engineering, National Research Council, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Nerino","sequence":"additional","affiliation":[{"name":"Institute of Electronics, Computer and Telecommunication Engineering, National Research Council, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claudia","family":"Ferraris","sequence":"additional","affiliation":[{"name":"Institute of Electronics, Computer and Telecommunication Engineering, National Research Council, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Chimienti","sequence":"additional","affiliation":[{"name":"Institute of Electronics, Computer and Telecommunication Engineering, National Research Council, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2016,7,28]]},"reference":[{"key":"bibr1-1094342015622672","volume-title":"Learning OpenCV: Computer Vision with the OpenCV Library","author":"Bradski G","year":"2008"},{"key":"bibr2-1094342015622672","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"bibr3-1094342015622672","first-page":"1","volume-title":"Big learning: Algorithms, Systems and Tools for Learning at Scale","author":"Budiu M","year":"2011"},{"key":"bibr4-1094342015622672","volume-title":"Decision Forests: A Unified Framework for Classification, Regression, Density Estimation, Manifold Learning and Semi-supervised Learning","author":"Criminisi A","year":"2012"},{"key":"bibr5-1094342015622672","doi-asserted-by":"publisher","DOI":"10.1109\/AICCSA.2011.6126612"},{"key":"bibr6-1094342015622672","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2014.180"},{"key":"bibr7-1094342015622672","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2014.93"},{"key":"bibr8-1094342015622672","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130391"},{"key":"bibr9-1094342015622672","unstructured":"Khronos Group (2015) OpenCL\u2014the open standard for parallel programming of heterogeneous systems. Available at: https:\/\/www.khronos.org\/opencl (accessed 8 July 2015)."},{"issue":"3","key":"bibr10-1094342015622672","first-page":"18","volume":"2","author":"Liaw A","year":"2002","journal-title":"R News"},{"key":"bibr11-1094342015622672","unstructured":"Microsoft Research (2015) Image understanding. Available at: http:\/\/research.microsoft.com\/en-us\/projects\/objectclassrecognition (accessed 8 July 2015)."},{"key":"bibr12-1094342015622672","author":"Munshi A","year":"2011","journal-title":"OpenCL Programming Guide"},{"key":"bibr13-1094342015622672","unstructured":"NVIDIA Corporation (2015) About CUDA. Available at: https:\/\/developer.nvidia.com\/about-cuda (accessed 8 July 2015)."},{"key":"bibr14-1094342015622672","first-page":"2825","volume":"12","author":"Pedregosa F","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"bibr15-1094342015622672","doi-asserted-by":"publisher","DOI":"10.5772\/60416"},{"key":"bibr16-1094342015622672","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.54"},{"key":"bibr17-1094342015622672","doi-asserted-by":"publisher","DOI":"10.5220\/0005316201560164"},{"key":"bibr18-1094342015622672","first-page":"595","volume-title":"10th European Conference on Computer Vision","author":"Sharp T."},{"key":"bibr19-1094342015622672","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"bibr20-1094342015622672","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"bibr21-1094342015622672","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385983"},{"key":"bibr22-1094342015622672","doi-asserted-by":"publisher","DOI":"10.1145\/1342250.1342263"},{"key":"bibr23-1094342015622672","volume-title":"Accelerating random forests on CPUs and GPUs for object-class image segmentation","author":"Waldvogel B","year":"2013"}],"container-title":["The International Journal of High Performance Computing Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1094342015622672","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/1094342015622672","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1094342015622672","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T08:19:36Z","timestamp":1777450776000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/1094342015622672"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7,28]]},"references-count":23,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2016,8]]}},"alternative-id":["10.1177\/1094342015622672"],"URL":"https:\/\/doi.org\/10.1177\/1094342015622672","relation":{},"ISSN":["1094-3420","1741-2846"],"issn-type":[{"value":"1094-3420","type":"print"},{"value":"1741-2846","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,7,28]]}}}