Neslužbene stranice predmeta Analiza dinamičkih scena
O predmetu:
Predmet razmatra područja računalnog vida
koja proučavaju kretanje objekata ili kamere.
Službene stranice su ovdje.
Predavači:
Zoran Kalafatić i Siniša Šegvić
Predavanja
-
Oduzimanje pozadine
pdf
-
Optički tok
pdf
-
Stohastičko praćenje objekata
pdf
-
Izlučivanje, praćenje, i podudaranje slikovnih značajki
pdf
-
Razumijevanje scena procjenom parametara
pdf
LIteratura
Duboki modeli za optički tok
-
Fischer et al.
FlowNet: Learning Optical Flow with Convolutional Networks.
ICCV 2015
(arxiv)
-
Ilg et al.
FlowNet 2.0: Evolution of Optical Flow Estimation
with Deep Networks.
CVPR 2017.
(arxiv)
-
Teed et al.
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow.
ECCV 2020.
(arxiv)
Modeliranje pozadine
-
C. Stauffer; W. Grimson.
Adaptive background mixture models for real-time tracking.
CVPR 1999.
pp. 246-252.
pdf.
-
Massimo Piccardi.
Background subtraction techniques: a review.
CSMC 2004. pp. 3099–3104.
pdf.
-
Sebastian Brutzer, Benjamin Hoferlin and Gunther Heidemann.
Evaluation of background subtraction techniques for video surveillance
CVPR 2011. pp. 1937–1944.
pdf.
Izlučivanje značajki
-
C. Harris and M. Stephens.
A combined corner and edge detector.
Alvey Vision Conference.
pp. 147-151. 1988.
pdf
-
D. Lowe.
Distinctive Image Features from Scale-Invariant Keypoints.
International Journal of Computer Vision.
60(2):91-110. 2004.
pdf
Praćenje značajki i optički tok
-
B.D. Lucas and T. Kanade.
An Iterative Image Registration Technique with an Application to Stereo Vision.
International Joint Conference on Artificial Intelligence.
pp. 674-679. Vancouver, Canada, 1981.
CiteSeer
-
J. Shi and C. Tomasi.
Good Features to Track.
IEEE Conference on Computer Vision and Pattern Recognition.
1994.
pdf
-
B.K.P. Horn and B.G. Schunck.
Determining optical flow.
Artificial Intelligence.
vol 17. pp 185-203. 1981.
CiteSeer
-
Deqing Sun, Stefan Roth, and Michael J. Black.
A quantitative analysis of current practices
in optical flow estimation and the principles behind them.
IJCV 106(2) 2014. pp. 115–137.
pdf.
Praćenje objekata
-
Dorin Comaniciu, Visvanathan Ramesh and Peter Meer.
Kernel-based object tracking.
PAMI 25 2003. pp. 564–577.
pdf.
-
Gary R. Bradski.
Real time face and object tracking
as a component of a perceptual user interface.
WACV 1998. pp. 214–219.
pdf.
-
Zdenek Kalal, Krystian Mikolajczyk and Jiri Matas.
Tracking-learning-detection.
PAMI 34(7) 2012. pp. 1409–1422.
pdf.
Estimacija i filtriranje
-
S. Choi, T. Kim, W. Yu.
Performance Evaluation of RANSAC Family.
British Machine Vision Conference. 2009.
pdf
-
M. Isard and A. Blake.
CONDENSATION -- conditional density propagation for visual tracking.
International Journal of Computer Vision.
29(1):5-28. 1998.
home
-
Greg Welch and Gary Bishop.
An Introduction to the Kalman Filter.
TR 95-041 2006.
pdf.
Kalibracija kamere, geometrija više pogleda
-
Z. Zhang.
A flexible new technique for camera calibration.
IEEE Transactions on Pattern Analysis and Machine Intelligence.
22(11):1330-1334. 2000.
home
-
H. C. Longuet-Higgins.
A computer algorithm for reconstructing a scene from two projections.
Nature 293(5828):133-135. 1981.
pdf
-
David Nistér.
An Efficient Solution to the Five-Point Relative Pose Problem.
IEEE Trans. Pattern Anal. Mach. Intell.
26(6):756-777 (2004)
pdf
-
Richard I. Hartley.
In Defense of the Eight-Point Algorithm.
IEEE Trans. Pattern Anal. Mach. Intell.
19(6): 580-593 (1997)
pdf