07 history of cv vision paradigms - system - algorithms - applications - evaluation
-
Upload
zukun -
Category
Technology
-
view
399 -
download
0
description
Transcript of 07 history of cv vision paradigms - system - algorithms - applications - evaluation
Institute of Electrical Measurement and Measurement Signal Processing
VISION:
• Paradigms• SystemsSystems• Algorithms
Axel PinzAxel Pinz
• Applications• EvaluationEvaluation
A Graph-based structure !
Professor Horst Cerjak, 19.12.20051
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
The Graph of Vision HistorySystems Image UnderstandingSystems
1978Artificial Intelligence
1971
Image Understanding1980s
Pattern RecognitionImage Proc. 1970s Cognitive Psychology
1985 ? Neurophysiology1985 ?
Algorithms
Neurophysiology1963
Robotics1994 ?
Marr1978
Algorithms1962
R itiReconstruction
1980 ?
Recognition1970s R+R
1990
Professor Horst Cerjak, 19.12.20052
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Artificial Intelligence
• SHRDLU [Winograd 1971]• Blocks world
i i l di l (MIT AI L b) l t l d i (U i Ut h)
Professor Horst Cerjak, 19.12.20053
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
original screen display (MIT AI Lab) later color rendering (Univ. Utah)
Institute of Electrical Measurement and Measurement Signal Processing
Blocks World – 1970s
• Natural language understanding• Spatio-temporal reasoning• LISP• Visual input would be nice• Visual input would be nice
Vi i “ bli d l ” i AI• Vision as an “enabling sensory module” in AI– Patrick Henry Winston “The Psychology of Computer Vision” 1975
M i Mi k “A f k f ti k l d ” 1975– Marvin Minsky “A framework for representing knowledge” 1975• Frames• Frame Representation Language FRL
Professor Horst Cerjak, 19.12.20054
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
g g
Institute of Electrical Measurement and Measurement Signal Processing
Blocks World – Today• Still an issue of ongoing researchStill an issue of ongoing research…• EU FP 6 project MACS
2004 2008• 2004-2008
Learning !“Affordances” …
Professor Horst Cerjak, 19.12.20055
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Affordances …
Institute of Electrical Measurement and Measurement Signal Processing
AI Methods for Vision – 1980s
• “Image Understanding”• Expert systemsExpert systems
– SIGMA Aerial Image Understanding– Matsuyama Hwang– Matsuyama, Hwang, …
• Reasoning, Blackboard system– VISIONS, Draper, OHM, …
• Schema learningg– SLS, Draper,…
Professor Horst Cerjak, 19.12.20056
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
SIGMA [Matsuyama]
Professor Horst Cerjak, 19.12.20057
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
VISIONS [Hanson+Riseman], SLS [Draper]
A Massachusetts “road”-scene
Professor Horst Cerjak, 19.12.20058
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
“Image Understanding” – 1980s
• Integrating bottom-up and top-down processes combinatorial explosionp p
• “knowledge engineers”, hand-crafted knowledge base learning is a mustknowledge-base learning is a must
Professor Horst Cerjak, 19.12.20059
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Systems 1990 – 200+
• “Computer Vision Systems”– [Hanson+Riseman 1978]
• UMass VISIONS KBVision– AAI Amerinex Artificial intelligence– AAI Amerinex Artificial intelligence– AAI Amerinex Applied Imaging
G i C• Grimson Cognex– PatMax • Matlab
• OpenCV• IUE
– TargetJr Joe Mundy
• OpenCV• toolboxes, libraries
Professor Horst Cerjak, 19.12.200510
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
g y
Institute of Electrical Measurement and Measurement Signal Processing
Robotics
B k “b ildi b i f b di ”• Brooks: “building brains for bodies”– Autonomous Robots 1:7-25, 1994
• Learning!• Interaction!Interaction!• Reward by survival…!
• Active, purposive, qualitative– Bajcsy 1988– Aloimonos 1989
Professor Horst Cerjak, 19.12.200511
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Babybot Lira Lab [Sandini]Babybot – Lira Lab [Sandini]learning to pushg p
learntlearnt
Professor Horst Cerjak, 19.12.200512
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Babybot’s view
Institute of Electrical Measurement and Measurement Signal Processing
Neurophysiology
• Retina visual cortex• Layered representation in visual cortexLayered representation in visual cortex• Receptive fields• Hubel+Wiesel
– Gradients– Oriented “edgels”– At various scales– Bottom-up grouping recognition– Visual pathway stereo, reconstruction
Professor Horst Cerjak, 19.12.200513
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
p y ,
Institute of Electrical Measurement and Measurement Signal Processing
Visual Pathway [Hubel+Wiesel]
Professor Horst Cerjak, 19.12.200514
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Receptive Fields [Hubel+Wiesel]
on-off simple complexon off simple complex
Professor Horst Cerjak, 19.12.200515
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Pattern Recognition + Image Processing – PRIP
• Structural [Pavlidis 1972, Fu 1982]• Statistical [Fukunaga 1990]Statistical [Fukunaga 1990]
R t ti ( l i l l )• Representation (regular, irregular, scale,…) pyramids, scale space, graphs,…
• Feature sets, feature selection, classifiers, learning,…
• 2D (discrete) signal processing
Professor Horst Cerjak, 19.12.200516
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Maximum Likelihood Classification
Professor Horst Cerjak, 19.12.200517
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Scale Space [Lindeberg]
Space + timeSpace + time[Laptev + Lindeberg][Laptev + Lindeberg]
Professor Horst Cerjak, 19.12.200518
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Cognitive Psychology
• Perceptual grouping– Lowe 1985– Sarkar 1994– LLVE Matsuyama
• Qualitative volumetric models (Geons)Biederman 1985 Bergevin+Levine 1988– Biederman 1985, Bergevin+Levine 1988
– Dickinson 1992: Aspect Hierarchy
A i i t d ’ h d l f• A renaissance in today’s shape models for category detection…
Professor Horst Cerjak, 19.12.200519
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
My Favorite Example [Lowe]
Very hard !!!
Professor Horst Cerjak, 19.12.200520
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
My Favorite Example [Lowe]
Very easy !!!
Professor Horst Cerjak, 19.12.200521
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Geons [Biederman], Aspect Hierarchy [Dickinson]
Professor Horst Cerjak, 19.12.200522
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Geons [Biederman], Aspect Hierarchy [Dickinson]
Professor Horst Cerjak, 19.12.200523
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
The Marr Paradigm – 1978-?Systems approach to vision computational• Systems approach to vision computational model– Algorithm, data, hardware implementationg , , p– Low level modules
• Representational levels P i l k t h li– Primal sketch saliency
– 2-1/2 D reconstruction ! – 3D object model is it really required?
• “reconstruction school”• “visual modules”, “shape from X”• Zerroug 1994• Structure + Motion 200x
Professor Horst Cerjak, 19.12.200524
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Marr (~1978) – “primal sketch”
“saliency” !
“Harris” corners
Professor Horst Cerjak, 19.12.200525
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Harris corners
Institute of Electrical Measurement and Measurement Signal Processing
Marr (~1978) –“2-1/2-D sketch”, “generalized cone”2 1/2 D sketch , generalized cone
Professor Horst Cerjak, 19.12.200526
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Marr (~1978) – 3D hierarchical models
Professor Horst Cerjak, 19.12.200527
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Marr ~1978, Aloimonos ~1988
“robustness”
Professor Horst Cerjak, 19.12.200528
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Zerroug 1994
Professor Horst Cerjak, 19.12.200529
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Algorithms• Convolution kernels• Convolution kernels• Mathematical morphology structuring elements Serra• Fourier transform spectrum, phase, descriptors, Gabor filter bank
H h t f ti• Hough transform voting space• PCA• Pyramids (regular, irregular) graphs• Scale space theory in CV Lindeberg• Algebraic projective geometry Hartley, Zisserman• Color (good chapters in Forsyth+Ponce, Burger+Burge)(g p y , g g )• Texture invariant moments (Hu … Haralick … VanGool)• Interest point detection (Schmid, …) affine covariance• Pattern Classification Duda+HartPattern Classification Duda Hart• Machine Learning Hastie et al.
Professor Horst Cerjak, 19.12.200530
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Reconstruction
P j ti t• Projective geometry• Photogrammetryg y• Essential, fundamental, multiview, …• Calibrated uncalibrated autocalibration• Calibrated, uncalibrated, autocalibration,
calibration-free,…St t d M ti• Structure and Motion
Professor Horst Cerjak, 19.12.200531
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Structure and motion [Schweighofer 2008][ g ]
Professor Horst Cerjak, 19.12.200532
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Recognition
S ifi bj t• Specific objects– PCA [Murase+Nayar 95], Eigenfaces [Pentland 93]
• Categories• Categories– Generative [Fergus 2003], discriminative [Opelt 2004]
• Recognition vs localization• Recognition vs. localization• Features (descriptors), grouping
Shape texture color proximity similarity– Shape, texture, color, proximity, similarity,…
• Saliency (detectors)• Active• Active
– Motion, space+time …
Professor Horst Cerjak, 19.12.200533
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
Shape-Based Category Detection [Opelt 2006]
Professor Horst Cerjak, 19.12.200534
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
“R + R”: Confluence ofR + R : Confluence of Recognition and Reconstruction
“ iti d t ti h l ill ”• “recognition and reconstruction schools will merge” [Aloimonos+Shulman 1989]
• “Marr paradigm – use of 2-1/2D complicates the problem”Marr paradigm use of 2 1/2D complicates the problem [Medioni et al. 2000] tensor voting
• Spatio-temporal reasoning and representation
Professor Horst Cerjak, 19.12.200535
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz
Institute of Electrical Measurement and Measurement Signal Processing
The Graph of Vision HistorySystems Image UnderstandingSystems1990s
Artificial Intelligence1971
Image Understanding1980s
Pattern RecognitionImage Proc. 1970s Cognitive Psychology
1985 ? Neurophysiology1985 ?
Algorithms
Neurophysiology1963
Robotics1994 ?
Marr1978
Algorithms1962
R itiReconstruction
1980 ?
Recognition1970s R+R
1990
Professor Horst Cerjak, 19.12.200536
9.5.2008History of Computer Vision Paradigms-Systems-Algorithms-Applications-Evaluation Axel Pinz