|
CPSC 601.58 - Winter 2015:
Motion, Optical Flow, and Video
consult D2L for most current information
Instructor | Dr. J. E. Boyd |
| Department of Computer Science |
| University of Calgary |
| 2500 University Drive NW |
| Calgary Alberta Canada T2N 1N4 |
| |
| Email: boyd at cpsc ucalgary ca |
| |
| Office: ICT 711 |
| Office hours: TR 0930-1030h |
| Lectures: TR 1400-1515h in ST 027A |
Selected Course Material
Description
In this course, students will read a selection of papers covering
topics related to motion in computer and human vision. The reading will be
supplemented by student-led discussions of the papers, and
lectures covering fundamental techniques such as optical flow,
segmentation in video, tracking, and sonification.
Prerequisites
There are no formal prerequisites, but it is recommend that students have taken
CPSC 535 or 635, or equivalent.
Evaluation
Students will be evaluated on in-class participation in the student-led discussion of papers, and on a project proposal, report, and oral presentation:
In-class participation | 15% |
Oral Presentation | 30% |
Project Proposal | 15% |
Project Report | 40% |
Tentative Outline - see D2L page for current info
Week | Date | Topic | Reading |
1 | 13-Jan-15 | Course Organization/Introduction | |
| 15-Jan-15 | Tracking 1 - Mean Shift | Comaniciu et al. 2000 |
2 | 20-Jan-15 | Tracking 2 - Kalman | Welch and Bishop 2006, Podesta 1994 |
| 22-Jan-15 | Sonification 1 - Audio basics | Begault 2000 Chapter 1 |
3 | 27-Jan-15 | Tracking 3 - Particle Filter | Isard and Blake 1998 |
| 29-Jan-15 | Tracking 4 - EKF and UKF | Welch and Bishop 2006, Wan and van der Merwe 2000 |
4 | 03-Feb-15 | Sonfication 2 - Spatial Hearing | Begault 2000 Chapter 2 |
| 05-Feb-15 | Tracking 5 - Multi-target | Reid 1979, Cox and Hingorani 1996 |
5 | 10-Feb-15 | Features 1 - SIFT, SURF | Lowe 2004, Bay et al. 2006 |
| 12-Feb-15 | Sonification 3 - Ambisonics |
6 | 17-Feb-15 | Reading Break | |
| 19-Feb-15 | Reading Break | |
7 | 24-Feb-15 | Features 2 - BRIEF, ORB, BRISK | Calonder et al. 2010, Rublee et al. 2011, Leuenegger 2011, Muja and Lowe 2012 |
| 26-Feb-15 | Sonification 4 - Beam Forming | van Veen and Buckley 1988, Gauthier and Pasquier 2010 |
8 | 03-Mar-15 | Adaboost 1 | Freund and Schapire 1997 |
| 05-Mar-15 | Adaboost 2 | Viola and Jones 2001, Andoni and Indyk 2008 |
9 | 10-Mar-15 | Sonification 5 - Visisonics | |
| 12-Mar-15 | Pose Estimation 1 | Bregler and Malik 1998, Cipolla et al. 2003 |
10 | 17-Mar-15 | Pose Estimation 2 | |
| 19-Mar-15 | Sonification 6 | Godbout and Boyd 2010, Godbout, Thornton and Boyd 2014 |
11 | 24-Mar-15 | TBA | |
| 26-Mar-15 | TBA |
12 | 31-Mar-15 | TBA | |
| 02-Apr-15 | TBA | |
13 | 07-Apr-15 | Pose Estimation 3 - Kinect | Shotton et al. 2011 |
| 09-Apr-15 | Oral Presentations | |
14 | 14-Apr-15 | TBA | |
Important Dates
9-Feb-2015 0900h | Project proposal due |
9-Apr-2015 | In-class oral presentations |
17-Apr-2015 1600h | Project report due |
Some of the reading from previous terms - see D2L for current readings
- A. Andoni and P. Indyk, "Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions", Communications of the ACM, Vol. 51, No. 1, January, 2008, p 117-122.
- H. Bay, T. Tuytelaars and L. van Gool, "SURF: Speeded Up Robust Features", ECCV 2006.
- D. R. Begault, 3-D Sound for Virtual Reality and Multimedia, NASA, 2000.
- J. E. Boyd and A. Sadikali, "Rhythmic gait signatures from video without motion capture", in proceedings of International Conference on Auditory Display, Washington, DC, June, 2010, p187-191.
- C. Bregler and J. Malik, "Tracking People with Twists and Exponential Maps", in proceedings of IEEE Computer Vision and Pattern Recognition, 1998.
- P. A. Cariani, "Temporal Codes and Computations for Sensory Representation and Scene Analysis", IEEE Transactions on Neural Networks, Vol. 15, No. 5, September 2004, p 1100-1111.
- D. Comaniciu, V. Ramesh and P. Meer, "Real-time tracking of non-rigid objects using mean shift", proceedings of IEEE Computer Vision and Pattern Recognition, 2000.
- M. Calonder, V. Lepetit, C. Strecha and P. Fua, "BRIEF: Binary Robust Independent Elementary Features", ECCV 2010.
- R. Cipolla, B. Stenger, A. Thayananthan and P. H. S. Torr, "Hand Tracking Using A Quadric Surface Model", Lecture Notes in Computer Science Volume 2768, 2003, pp 129-141.
- I. J. Cox and S. L. Hingorani, "An efficient implementation of reid's multiple hypothesis tracking algorithm and its evaluation for the purpose of visual tracking", IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 18, No. 2, February, 1996.
- N.H. Dardas and N.D. Georganas, "Real-Time Hand Gesture Detection and Recognition Using Bag-of-Features and Support Vector Machine Techniques", IEEE Transactions on Instrumentation and Measurement, Vol. 60, No. 11, p 3592-3607, November, 2011.
- Y. Freund and R.E. Schapire, "A Decision-Theoretic Generalization of on-Line Learning and an Application to Boosting", Journal of Computer and System Sciences, Vol 55, 1997, p 119-139.
- P-A. Gauthier and P. Pasquier, "Auditory Tactics: A Sound Installation in Public Space Using Beamforming Technology", Leonardo, Vol. 43, No. 5, October 2010, p 426-433.
- A. Godbout and J. E. Boyd, "Corrective sonic feedback for speed skating: a case study", in proceedings of International Conference on Auditory Display, Washington, DC, June, 2010, p 23-30.
- T. Hermann, A. Hunt and J.G. Neuhoff eds, The Sonification Handbook, Logos Publishing House, Berlin, 2011.
- M. Isard and A. Blake, "CONDENSATION - conditional density propagation for visual tracking", International Journal of Computer Vision Vol. 29, No. 1, 1998.
- S. Ivekovic, E. Trucco and Y.R. Petillot, "Human Body Pose Estimation With Particle Swarm Optimisation", Evolutionary Computation, Vol. 16, No. 4, 2008, p 509-528.
- K. Karsch, C. Liu and S. B. Kang, "Depth Extraction from Video Using Non-parametric Sampling", in proceedings of European Conference on Computer Vision, 2012.
- S. Leutenegger, M. Chli and R. Siegwart, “BRISK: Binary Robust Invariant Scalable Keypoints,” in IEEE International Conference on Computer Vision, 2011.
- D. Lowe, "Distinctive image features from scale-invariant keypoints", International Journal of Computer Vision, 60, 2, 2004.
- M. Muja and D. G. Lowe, "Fast Matching of Binary Features,", CRV 2012.
- J. Podesta, "A Brief Tutorial on the Kalman Filter", US Army Armament Research, Development and Engineering Center, Technical Report, ARFSD-SP-94001, 1994.
- D. B. Reid, "An algorithm for tracking multiple targets", IEEE Transaction on Automatic Control, Vol AC-24, No. 6, December 1979.
- E. Rublee, V. Rabaud, K. Konolige and G. Bradski, “ORB: an efficient alternative to SIFT or SURF", in International Conference on Computer Vision, Barcelona, 2011.
- J. Shotton, A. Fitzgibbon, M. Cook, T. Sharp, M. Finocchio, R. Moore, A. Kipman and A. Blake, "Real-Time Human Pose Recognition in Parts from Single Depth Images", Proceedings of Computer Vision and Pattern Recognition, 2011.
- B.D. Van Veen and K.M. Buckley, "Beamforming: A Versatile Approach to Spatial Filtering", IEEE Acoustics, Speach and Signal Processing Magazine, Vol. 5, No. 2, April, 1998, p 4-24.
- P. Viola and M. Jones, "Robust Real-time Object Detection", International Journal of Computer Vision, 2001.
- E. A. Wan and R. Van Der Merwe, "The unscented Kalman filter for nonlinear estimation," Adaptive Systems for Signal Processing, Communications, and Control Symposium 2000.
- G. Welch and G. Bishop, "An Introduction to the Kalman Filter", Technical Report, University of North Carolina at Chapel Hill, Department of Computer Science, TR 95-041, 2006.
Other Resources
|
|