Detekce objektů z mnoha tříd
Large Scale Object Detection
Typ dokumentu
diplomová prácemaster thesis
Autor
Novotný David
Vedoucí práce
Matas Jiří
Oponent práce
Zitová Barbara
Studijní obor
Počítačové vidění a digitální obrazStudijní program
Otevřená informatikaInstituce přidělující hodnost
katedra kybernetikyObhájeno
2015-01-20Práva
A university thesis is a work protected by the Copyright Act. Extracts, copies and transcripts of the thesis are allowed for personal use only and at one?s own expense. The use of thesis should be in compliance with the Copyright Act http://www.mkcr.cz/assets/autorske-pravo/01-3982006.pdf and the citation ethics http://www.cvut.cz/sites/default/files/content/d1dc93cd-5894-4521-b799-c7e715d3c59e/cs/20160901-metodicky-pokyn-c-12009-o-dodrzovani-etickych-principu-pri-priprave-vysokoskolskych.pdfVysokoškolská závěrečná práce je dílo chráněné autorským zákonem. Je možné pořizovat z něj na své náklady a pro svoji osobní potřebu výpisy, opisy a rozmnoženiny. Jeho využití musí být v souladu s autorským zákonem http://www.mkcr.cz/assets/autorske-pravo/01-3982006.pdf a citační etikou http://www.cvut.cz/sites/default/files/content/d1dc93cd-5894-4521-b799-c7e715d3c59e/cs/20160901-metodicky-pokyn-c-12009-o-dodrzovani-etickych-principu-pri-priprave-vysokoskolskych.pdf
Metadata
Zobrazit celý záznamAbstrakt
This thesis focuses on the problem of large scale visual object detection and classification in digital images. A new type of image features that are derived from state-of-the-art convolutional neural networks is proposed. It is further shown that the newly proposed image signatures bare a strong resemblance to the Fisher Kernel classifier, that recently became popular in the object category retrieval field. Because this new method suffers from having a large memory footprint, several feature compression / selection techniques are evaluated and their performance is reported. The result is an image classifier that is able to surpass the performance of the original convolutional neural network, from which it was derived. The new feature extraction method is also used for the object detection task with similar results. This thesis focuses on the problem of large scale visual object detection and classification in digital images. A new type of image features that are derived from state-of-the-art convolutional neural networks is proposed. It is further shown that the newly proposed image signatures bare a strong resemblance to the Fisher Kernel classifier, that recently became popular in the object category retrieval field. Because this new method suffers from having a large memory footprint, several feature compression / selection techniques are evaluated and their performance is reported. The result is an image classifier that is able to surpass the performance of the original convolutional neural network, from which it was derived. The new feature extraction method is also used for the object detection task with similar results.
Kolekce
- Diplomové práce - 13133 [503]