Combining features and semantics for low-level computer vision
Başlık çevirisi mevcut değil.
- Tez No: 523516
- Danışmanlar: Dr. ANDREAS GEIGER
- Tez Türü: Doktora
- Konular: Matematik, Bilim ve Teknoloji, Mathematics, Science and Technology
- Anahtar Kelimeler: Belirtilmemiş.
- Yıl: 2017
- Dil: İngilizce
- Üniversite: Eberhard-Karls-Unıversıtat Tubıngen
- Enstitü: Yurtdışı Enstitü
- Ana Bilim Dalı: Belirtilmemiş.
- Bilim Dalı: Belirtilmemiş.
- Sayfa Sayısı: Belirtilmemiş.
Özet
Özet yok.
Özet (Çeviri)
Visual perception of depth and motion plays a significant role in understanding and navigating the environment. Reconstructing outdoor scenes in 3D and estimating the motion from video cameras are of utmost importance for applications like autonomous driving. The corresponding problems in computer vision have witnessed tremendous progress over the last decades, yet some aspects still remain challenging today. Striking examples are reflecting and textureless surfaces or large motions which cannot be easily recovered using traditional local methods. Further challenges include occlusions, large distortions and difficult lighting conditions. In this thesis, we propose to overcome these challenges by modeling non-local interactions leveraging semantics and contextual information. Firstly, for binocular stereo estimation, we propose to regularize over larger areas on the image using object-category specific disparity proposals which we sample using inverse graphics techniques based on a sparse disparity estimate and a semantic segmentation of the image. The disparity proposals encode the fact that objects of certain categories are not arbitrarily shaped but typically exhibit regular structures. We integrate them as non-local regularizer for the challenging object class 'car' into a superpixelbased graphical model and demonstrate its benefits especially in reflective regions. Secondly, for 3D reconstruction, we leverage the fact that the larger the reconstructed area, the more likely objects of similar type and shape will occur in the scene. This is particularly true for outdoor scenes where buildings and vehicles often suffer from missing texture or reflections, but share similarity in 3D shape. We take advantage of this shape similarity by localizing objects using detectors and jointly reconstructing them while learning a volumetric model of their shape. This allows to reduce noise while completing missing surfaces as objects of similar shape benefit from all observations for the respective category. Evaluations with respect to LIDAR ground-truth on a novel challenging suburban dataset show the advantages of modeling structural dependencies between objects. Finally, motivated by the success of deep learning techniques in matching problems, we present a method for learning context-aware features for solving optical flow using discrete optimization. Towards this goal, we present an efficient way of training a context network with a large receptive field size on top of a local network using dilated convolutions on patches. We perform feature matching by comparing each pixel in the reference image to every pixel in the target image, utilizing fast GPU matrix multiplication. The matching cost volume from the network's output forms the data term for discrete MAP inference in a pairwise Markov random field. Extensive evaluations reveal the importance of context for feature matching. v
Benzer Tezler
- Karıştırıcılar ve karıştırma kabındaki akım olaylarının incelenmesi
Başlık çevirisi yok
NADİR İLTEN
Yüksek Lisans
Türkçe
1986
Makine MühendisliğiUludağ ÜniversitesiMakine Mühendisliği Ana Bilim Dalı
DOÇ.DR. ÖMER SAMİH MERTBAŞ
- Bir pamuk iplikhanesinde fiili çalışma metodlarının incelenmesi ve mevcut işlemlerin standart sürelerinin saptanması
Başlık çevirisi yok
MÜRŞİDE KESEROĞLU
Yüksek Lisans
Türkçe
1985
İşletmeEge ÜniversitesiTekstil Mühendisliği Ana Bilim Dalı
DOÇ. DR. MUSTAFA NAZMİ ERCAN
- Arpada diallel melez analizleri ile bazı tarımsal özelliklerin kalıtımı üzerinde araştırmalar
Başlık çevirisi yok
KAYIHAN Z. KORKUT
Doktora
Türkçe
1981
ZiraatEge ÜniversitesiBitki Islahı ve Genetik Ana Bilim Dalı
PROF. DR. İBRAHİM DEMİR
- Bertrand eğri çiftleri üzerine genelleştirmeler
Başlık çevirisi yok
NAZMİ ERDOĞAN
Yüksek Lisans
Türkçe
1986
MatematikGazi ÜniversitesiMatematik Ana Bilim Dalı
PROF. DR. HASAN HİLMİ HACISALİHOĞLU
- Devlet orman işletmelerinde optimal stok düzeyi ve bunu etkileyen amiller
Başlık çevirisi yok
YÜCEL ÇAĞLAR