Instructor:
Dr. George Bebis
- Email:
bebis@cse.unr.edu
- Phone:
784-6463
- Office: 235 SEM
- Office Hours: MW 2:30pm - 4:00pm and by appointment.
Prerequisites
Background in image processing (CS474/674), computer vision (CS485/685),
pattern recognition (CS479/679), linear algebra, probabilities, and statistics.
Text
No text is required in this course; all material will be drawn from
research papers.
Useful Texts
Computer Vision resources
Object Recognition Datasets
Useful Software
Description and Objectives
Interest point detectors and descriptors are now at the core of many Computer
Vision applications such as object recognition, 3D reconstruction, image
retrieval and camera localization. The purpose of this course is to review
recent advances in this important area by discussing research papers and
attending video lectures. The course is intended for students interested in
computer vision research. Good background in computer vision, linear algebra,
probability, statistics, and calculus are required.
Syllabus
Schedule of Presentations
W 1/23 Interest Point Detection (Bebis)
M 1/28 Interest Point Detection (Bebis)
W 1/30 Interest Point Descriptors (Bebis)
M 2/4 Object Recognition (Name)
W 2/6 No class - attend Friday's colloquia
M 2/11 Chen09 (Rory Pierce)
W 2/13 VL4
M 2/18 President's Day (no class)
W 2/20 VL1
M 2/25 Tuytelars07 (Abbas Roayaei)
W 2/27 VL2
M 3/4 Rosten06 (David Leblanc)
W 3/6 VL3
M 3/11 Leutenegger11 (Joshua Gleason)
W 3/13 Project Proposals (write-up and 10 min presentation)
M 3/18 Spring Break
W 3/20 Spring Break
M 3/25 Calonder10 (Touqeer Ahmad)
W 3/27 VL5 (related paper: here)
M 4/1 Ahonen06 (Rory Pierce)
W 4/3 VL7 (related paper: here), VL9 (related paper: here)
M 4/8 No class
W 4/10 Interim Project Presentations (25 min, Leblanc, Pierce)
M 4/15 Interim Project Presentations (25 min, Gleason, Roayaei, Ahmad)
W 4/17 Ozuysal10 (David Leblanc)
M 4/22 Murphy06 (Joshua Gleason)
W 4/24 Hinterstoisser10 (Abbas Roayaei)
M 4/29 Jegu09 (Touqeer Ahmad)
W 5/1 Ozuysal10 (David Leblanc)
M 5/6 Jegu09 (Touqeer Ahmad)
M 5/13 Project Presentations (25 min)
Video Lectures
[VL10] Compressive Sensing for Computer Vision: Hype vs Hope (Rama Chellappa, Univ of Maryland) (58 min)
Local Detectors and Descriptors
[Lowe04] D. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints", International Journal of Computer Vision, vol. 60, no. 2, pp. 91-110, 2004. SIFT demo program
[Ke04] Yan Ke and Rahul Sukthankar, "PCA-SIFT: A More Distinctive Representation for Local Image Descriptors", CVPR, 2004.
[Bay06] Herbert Bay, Tinne Tuytelaars, and Luc Van Gool, "SURF: Speeded Up Robust Features", , ECCV, 2006.
[Tuytelaars07] Tinne Tuytelaars and Cordelia Schmid, "Vector Quantizing Feature Space with a Regular Lattice", CVPR 2007.
[Schmid00] C. Schmid, R. Mohr, and C. Bauckhage, "Evaluation of Interest Point Detectors", International Journal of Computer Vision 37(2), 151.172, 2000.
[Mikolajczyk05] K. Mikolajczyk and C. Schmid, "A Performance Evaluation of Local Descriptors", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 10, pp. 1615-1630, 2005.
[Obdrzalek06] S. Obdrzalek and J. Matas, "Object Recognition Using Local Affine Frames on Maximally Stable Extremal Regions", J. Ponce et al. (Eds): Toward Category-Level Object Recognition, LNCS 4170, pp. 83-104, 2006.
[Tuytelaars00]T. Tuytelaars and L. Van Gool, "Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions" British Machine Vision Conference, 2000.
[Rosten06]Edward Rosten and Tom Drummond, "Machine learning for high-speed corner detection" ECCV 2006.
[Calonder10]Michael Calonder, Vincent Lepetit, Christoph Strecha, and Pascal Fua, "BRIEF: Binary Robust Independent Elementary Features" ECCV, 2010.
[Leutenegger11]Stefan Leutenegger, Margarita Chli and Roland Y. Siegwart, "BRISK: Binary Robust Invariant Scalable Keypoints" ICCV 2011.
[Alahi12]Alexandre Alahi, Raphael Ortiz, Pierre Vandergheynst, "FREAK: Fast Retina Keypoint" CVPR, 2012.
[Rublee11]Ethan Rublee, Vincent Rabaud, Kurt Konolige, and Gary Bradski, "ORB: an efficient alternative to SIFT or SURF" ICCV 2011.
[Ahonen06]Timo Ahonen and Matti Pietikainen, "Face Description with Local Binary Patterns: Application to Face Recognition" IEEE PAMI, 2006.
[Dalal05]Navneet Dalal and Bill Triggs, "Histograms of Oriented Gradients for Human Detection", CVPR 2005.
[Wang09]Xiaoyu Wang, Tony Han, and S. Yan, "An HOG-LBP Human Detector with Partial Occlusion Handling", ICCV 2009.
[Agrawal08] Motilal Agrawal, Kurt Konolige, and Morten Rufus Blas, "CenSurE: Center Surround Extremas for Realtime Feature Detection and Matching", ECCV 2008.
[Ebrahimi09]Mosalam Ebrahimi and Walterio W. Mayol-Cuevas "SUSurE: Speeded Up Surround Extrema feature detector and descriptor for realtime applications", CVPR Workshops 2009.
[Chen09]Jie Chen, Shiguang Shan, Chu He, Guoying Zhao, Matti Pietikaien, Xilin Chen, and Wen Gao "WLD: A Robust Local Image Descriptor", PAMI, 2009.
[Winder07] Simon A. J. Winder and Matthew Brown "Learning Local Image Descriptors", CVPR 2007.
[Tola09] E. Tola, V. Lepetit, and P. Fua, "Daisy: An Efficient Dense Descriptor Applied to Wide Baseline Stereo", IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009.
Applications
[Cruska04] G. Cruska et al., "Visual Categorization with Bags of Keypoints", European Conference on Computer Vision, Czech Republic, 2004.
[Lazebnik06] Svetlana Lazebnik, Cordelia Schmid, and Jean Ponce,"Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories", CVPR 2006.
[Cao10] Y. Cao et al. ,"Spatial-Bag-of-Features", CVPR 2010.
[O'Hara11] STEPHEN O.HARA AND BRUCE A. DRAPER, "INTRODUCTION TO THE BAG OF FEATURES PARADIGM FOR IMAGE
CLASSIFICATION AND RETRIEVAL", (on-line)
[Nister06] David Nister and Henrik Stewenius "Scalable Recognition with a Vocabulary Tree", CVPR 2006.
[Jegu09] Herve Jegou, Matthijs Douze, and Cordelia Schmid, "Packing bag-of-features", CVPR 2009.
[Ozuysal10] Mustafa Ozuysal, Michael Calonder, Vincent Lepetit, and Pascal Fua, "Fast Keypoint Recognition Using Random Ferns", PAMI, 2010.
[Lepetit05] Vincent Lepetit Pascal Lagger Pascal Fua, "Randomized Trees for Real-Time Keypoint Recognition, CVPR 2005.
[Barnes11] Connelly Barnes, Dan B Goldman, Eli Shechtman, and Adam Finkelstein, "The PatchMatch Randomized Matching Algorithm for Image Manipulation , Communications of the ACM, Nov 2001,
[Torralba06] A. Torralba, K. Merphy, and W. Freeman, "Shared Features for Multiclass Object Detection", J. Ponce et al. (Eds): Toward Category-Level Object Recognition, LNCS 4170, pp. 345-361, 2006.
[Sivic06a] J. Sivic and A. Zisserman, "Video Google: Efficient Visual Search of Videos" , J. Ponce et al. (Eds): Toward Category-Level Object Recognition, LNCS 4170, pp. 127-144, 2006.
[Murphy06] K. Murphy et al. "Object Detection and Localization Using Local and Global Features", J. Ponce et al. (Eds): Toward Category-Level Object Recognition, LNCS 4170, pp. 382-400, 2006.
[Ulusoy06] I. Ulusoy and C, Bishop, "Comparison of Generative and Discriminative Techniques for Object Detection and Classification", J. Ponce et al. (Eds): Toward Category-Level Object Recognition, LNCS 4170, pp. 173-195, 2006.
[Schaffalitzky02] F. Schaffalitzky and A. Zisserman "Multi-view matching for unordered image sets, or How do I organize my holiday snaps?", European Conference on Computer Vision, Denmark, 2002.
[Fergus03] R. Fergus, P. Perona, and A. Zisserman, "Object Class Recognition by Unsupervised Scale-Invariant Learning", CVPR 2003.
[Fergus04] R. Fergus, P. Perona, and A. Zisserman, "A visual category filter for google images", ECCV 2004.
[Mikolajczyk01] K. Mikolajczyk and C. Schmid, "Indexing Based on Scale Invariant Interest Points", ICCV 2001.
[Deselaers05]T. Deselaers, D. Keysers, and H. Ney, "Discriminative training for object recognition using image patches", CVPR 2005.
[Hinterstoisser10]Stefan Hinterstoisser, Vincent Lepetit, Slobodan Ilic,
Pascal Fua, Nassir Navab, "Dominant Orientation Templates for Real-Time Detection of Texture-Less Objects", CVPR 2010.
Department of Computer Science & Engineering, University of Nevada, Reno, NV 89557
Page created and maintained by:
Dr. George Bebis
(bebis@cse.unr.edu)