Prepoznavanje objekata
Prepoznavanje objekata – tehnologija u oblasti računarskog vida za pronalaženje i identifikaciju objekata na slici ili video sekvenci. Ljudi prepoznaju mnoštvo objekata na slikama uz malo truda, uprkos činjenici da slika objekata može donekle varirati u raznim tačkama gledišta, u mnogo različitih veličina i razmera ili čak kada su translirani ili rotirani. Objekti se mogu prepoznati čak i kada su delimično zaklonjeni od pogleda. Ovaj zadatak je i dalje izazov za sisteme računarskog vida. Mnogi pristupi zadatku su implementirani tokom više decenija.
Pristupi zasnovani na objektnim modelima sličnim CAD-u
- Detekcija ivice
- Iskonska skica
- Mar, Mohan i Nevatija[1]
- Olivier Faugeras
Prepoznavanje po delovima
- Generalizovani cilindri (Tomas Binford)
- Džioni (Erving Biderman)
- Dikinson, Forsajt i Pons
Aplikacije
Metode prepoznavanja objekata imaju sledeće primene:
- Prepoznavanje aktivnosti[2]
- Automatsko označavanje slika[3][4]
- Automatsko prepoznavanje cilja
- Androidne oči - Prepoznavanje objekata[5][6]
- Kompjuterska dijagnoza[7]
- Panorame slika[8]
- Vodeni žig slike[9]
- Globalna robotska lokalizacija[10]
- Prepoznavanje lica[11]
- Optičko prepoznavanje znakova[12]
- Kontrola kvaliteta proizvodnje[13]
- Preuzimanje slika zasnovano na sadržaju[14]
- Brojanje i praćenje objekata[15]
- Automatski parking sistemi[16]
- Vizuelno pozicioniranje i praćenje[17]
- Video stabilizacija[18]
- Detekcija pešaka
- Inteligentno prilagođavanje brzine (u automobilu i drugim vozilima)
Reference
- ^ Rahesh Mohan; Rakamant Nevatia (1992). „Perceptual organization for scene segmentation and description” (PDF). IEEE Trans Pattern Anal Mach Intell.
- ^ Donahue, Jeffrey, et al. "Long-term recurrent convolutional networks for visual recognition and description." Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
- ^ Karpathy, Andrej, and Li Fei-Fei. "Deep visual-semantic alignments for generating image descriptions." Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
- ^ P Duygulu; K Barnard; N de Fretias; D Forsyth (2002). „Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary”. Proceedings of the European Conference on Computer Vision. стр. 97—112. Архивирано из оригинала 2005-03-05. г.
- ^ „Android Eyes Computer Vision”.
- ^ Martha J. Farah "Visual Agnosia", Computer Vision Computing Cognitive Neuroscience, MIT Press, 2011-05-01, Pages 760-781, ISSN 1468-4233
- ^ Esteva, Andre, et al. "Dermatologist-level classification of skin cancer with deep neural networks." Nature 542.7639 (2017): 115.
- ^ Brown, M., and Lowe, D.G., "Recognising Panoramas Архивирано на сајту Wayback Machine (25. децембар 2014)," ICCV, p. 1218, Ninth IEEE International Conference on Computer Vision (ICCV'03) - Volume 2, Nice,France, 2003
- ^ Li, L., Guo, B., and Shao, K., "Geometrically robust image watermarking using scale-invariant feature transform and Zernike moments," Chinese Optics Letters, Volume 5, Issue 6, pp. 332-335, 2007.
- ^ Se,S., Lowe, D.G., and Little, J.J.,"Vision-based global localization and mapping for mobile robots", IEEE Transactions on Robotics, 21, 3 (2005), pp. 364-375.
- ^ Thomas Serre, Maximillian Riesenhuber, Jennifer Louie, Tomaso Poggio, "On the Role of Object-Specific features for Real World Object Recognition in Biological Vision." Artificial Intelligence Lab, and Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Center for Biological and Computational Learning, Mc Govern Institute for Brain Research, Cambridge, MA, USA
- ^ Permaloff, Anne; Grafton, Carl (1992). „Optical Character Recognition”. PS: Political Science and Politics. 25 (3): 523—531. ISSN 1049-0965. JSTOR 419444. S2CID 64806776. doi:10.2307/419444.
- ^ Christian Demant, Bernd Streicher-Abel, Peter Waszkewitz, "Industrial image processing: visual quality control in manufacturing" Prepoznavanje objekata на сајту Гугл књиге
- ^ Nuno Vasconcelos "Image Indexing with Mixture Hierarchies" Архивирано 2011-01-18 на сајту Wayback Machine Compaq Computer Corporation, Proc. IEEE Conference in Computer Vision and Pattern Recognition, Kauai, Hawaii, 2001
- ^ Heikkilä, Janne; Silvén, Olli (2004). „A real-time system for monitoring of cyclists and pedestrians”. Image and Vision Computing. 22 (7): 563—570. doi:10.1016/j.imavis.2003.09.010.
- ^ Jung, Ho Gi; Kim, Dong Suk; Yoon, Pal Joo; Kim, Jaihie (2006). Yeung, Dit-Yan; Kwok, James T.; Fred, Ana; Roli, Fabio; de Ridder, Dick, ур. Structure Analysis Based Parking Slot Marking Recognition for Semi-automatic Parking System. Structural, Syntactic, and Statistical Pattern Recognition. Lecture Notes in Computer Science (на језику: енглески). 4109. Berlin, Heidelberg: Springer. стр. 384—393. ISBN 978-3-540-37241-7. doi:10.1007/11815921_42
.
- ^ S. K. Nayar, H. Murase, and S.A. Nene, "Learning, Positioning, and tracking Visual appearance" Proc. Of IEEE Intl. Conf. on Robotics and Automation, San Diego, May 1994
- ^ Liu, F.; Gleicher, M.; Jin, H.; Agarwala, A. (2009). „Content-preserving warps for 3D video stabilization”. ACM Transactions on Graphics. 28 (3): 1. CiteSeerX 10.1.1.678.3088
. doi:10.1145/1531326.1531350.
Literatura
- Elgammal, Ahmed "CS 534: Computer Vision 3D Model-based recognition", Dept of Computer Science, Rutgers University;
- Hartley, Richard and Zisserman, Andrew "Multiple View Geometry in computer vision", Cambridge Press, 2000, ISBN 0-521-62304-9.
- Roth, Peter M. and Winter, Martin "Survey of Appearance-Based Methods for Object Recognition", Technical Report ICG-TR-01/08, Inst. for Computer Graphics and Vision, Graz University of Technology, Austria; January 15, 2008.
- Collins, Robert "Lecture 31: Object Recognition: SIFT Keys", CSE486, Penn State
- IPRG Архивирано на сајту Wayback Machine (28. децембар 2020) Image Processing - Online Open Research Group
- Christian Szegedy Архивирано на сајту Wayback Machine (6. септембар 2015), Alexander Toshev Архивирано на сајту Wayback Machine (4. октобар 2015) and Dumitru Erhan. Deep Neural Networks for Object Detection. Advances in Neural Information Processing Systems 26 Архивирано на сајту Wayback Machine (5. септембар 2020), 2013. page 2553–2561.
- Daniilides and Eklundh, Edelman.
- Roth, Peter M.; Winter, Martin (2008). „SURVEYOFAPPEARANCE-BASED METHODS FOR OBJECT RECOGNITION” (PDF). Technical Report. ICG-TR-01/08. Архивирано из оригинала (PDF) 21. 09. 2015. г. Приступљено 28. 03. 2024.