computer vision: intro

52
Computer Vision: Intro. What are its goals? What are the applications What are some ways of using images (Later: methods and programming)

Upload: others

Post on 12-Sep-2021

3 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Computer Vision: Intro

Computer Vision: Intro.What are its goals?What are the applicationsWhat are some ways of using images(Later: methods and programming)

Page 2: Computer Vision: Intro

Finding ships in an aerial photograph

Page 3: Computer Vision: Intro

A corresponding map

Page 4: Computer Vision: Intro

Dock areaRegistered map and image

Page 5: Computer Vision: Intro

Finding a kidney in computer-aided tomographic scan

Page 6: Computer Vision: Intro

Prototype kidney model and model fitting

Page 7: Computer Vision: Intro

Resulting kidney and spinal cord instances

Page 8: Computer Vision: Intro

Goal of computer visionMake useful decisions about real physical objects and scenes based on sensed images.Alternative (Aloimonos and Rosenfeld): goal is the construction of scene descriptions from images. (Read reference S1)How do you find the door to leave?How do you determine if a person is friendly or hostile? .. an elder? .. a possible mate?

Page 9: Computer Vision: Intro

Critical IssuesSensing: how do sensors obtain images of the world?Information: how do we obtain color, texture, shape, motion, etc.?Representations: what representations should/does a computer [or brain] use?Algorithms: what algorithms process image information and construct scene descriptions?

Page 10: Computer Vision: Intro

Images: 2D projections of 3D3D world has color, texture, surfaces, volumes, light sources, objects, motion, betweeness, adjacency, connentions, etc.2D image is a projection of a scene from a specific viewpoint; many 3D features are captured, some not.Brightness or color = g(x,y) or f(row, column) for a certain instant of timeImages indicate familiar people, moving objects or animals, health of people or machines

Page 11: Computer Vision: Intro

Image receives reflectionsLight reaches surfaces in 3DSurfaces reflectSensor element receives light energyIntensity countsAngles countMaterial counts

Page 12: Computer Vision: Intro

CCD Camera has discrete eltsLens collects light raysCCD eltsreplace chemicals of filmNumber of eltsless than with film (so far)

Page 13: Computer Vision: Intro

Resolution is “pixels per unit of length”

Resolution decreases by one half in cases at leftHuman faces can be recognized at 64 x 64 pixels per face

Page 14: Computer Vision: Intro

Features detected depend on the resolution

Can tell hearts from diamondsCan tell face valueGenerally need 2 pixels across line or small region (such as eye)

Page 15: Computer Vision: Intro

Camera + Programs = DisplayCamera inputs to frame bufferProgram can interpret dataProgram can add graphicsProgram can add imagery

Page 16: Computer Vision: Intro

Computer Vision-Rosenfeld

VisionThe most powerful sense for many living organismsFiled related to visual perception: physiology, psychology, computational and robot vision, and engineeringLarge part of the human brain is devoted to visual perception

Computational algorithms

Page 17: Computer Vision: Intro

Computer Vision-Rosenfeld

Do you see as it is?

Page 18: Computer Vision: Intro

Totally straight line

Page 19: Computer Vision: Intro

How many black dots?

Page 20: Computer Vision: Intro
Page 21: Computer Vision: Intro

Computer Vision-Rosenfeld

The Goal of Image UnderstandingWe use vision to interact with our environments and survivePerform visual tasks: engage in many kinds of behaviors that are guided by visual inputsDavid Marr: construction of a detailed representation of the physical world

Transform 2D data into a description of the 3D spatiotemporal world

Page 22: Computer Vision: Intro

Computer Vision-Rosenfeld

Scene RecoveryWhat properties of a scene can be recovered by means of vision?Inverse optics problem

Optics map: the world into the imageVision: attempts to invert the optical map

Page 23: Computer Vision: Intro
Page 24: Computer Vision: Intro

Computer vision and other fields

http://en.wikipedia.org/wiki/Computer_vision

Page 25: Computer Vision: Intro

A Range of representationsGeneralized images

Iconic(image-like)Low level processing

Page 26: Computer Vision: Intro

A Range of representations

Segmented images

Edge segmentation

Page 27: Computer Vision: Intro

A Range of representationsGeometric representation

3D Shape Prior knowledge

Page 28: Computer Vision: Intro

A Range of representationsRelational models

Semantic netsHigh level processing

Page 29: Computer Vision: Intro

Look at some CV applications

Graphics or image retrieval systems; Geographical: GIS;

Medical image analysis; manufacturing

Page 30: Computer Vision: Intro

Image Database SearchCompany wants a new logoMake several designsSearch logo database for infringement

Page 31: Computer Vision: Intro

Aerial images & GISAerial image of WenatchieRiver watershedCan correspond to map; can inventory snow coverage

Page 32: Computer Vision: Intro

Medical imaging is critical

Visible human project at NLMAtlas for comparisonTestbed for methods

Page 33: Computer Vision: Intro

Medical Imaging

CT image of a patient’s abdomen

3D reconstruction of Blood Vessel Tree

Page 34: Computer Vision: Intro

Medical Imaging

Cardiac tagged MRIs

Page 35: Computer Vision: Intro

Manufacturing case 100 % inspection neededQuality demanded by major buyerAssembly line updated for visual inspection well before today’s powerful computers

Page 36: Computer Vision: Intro

Simple Hole Counting Alg.Customer needs 100% inspectionAbout 100 holesBig problem if any hole missingImplementation in the 70’sAlg also good for counting objects

Page 37: Computer Vision: Intro

Imaging added to lineCamera placed above conveyor lineBack lighting added1D of image from motion of object past the camera

Page 38: Computer Vision: Intro

Critical “corner patterns”“external corner”has 3(1)s and 1(0)“internal corner”has 3(0)s and 1(1)Holes computed from only these patterns!

Page 39: Computer Vision: Intro

Hole (Object) Counting Alg.

Page 40: Computer Vision: Intro

#holes = (#e - #i)/4

Page 41: Computer Vision: Intro

Variations on AlgorithmEasy if entire image is in memoryOnly need to have 2 rows in memory at any time

* used in the 1970’s* can allow special hardware

Page 42: Computer Vision: Intro

Some other methods

Finding contrast in an image; using neighborhoods of pixels;

detecting motion across 2 images

Page 43: Computer Vision: Intro

Differentiate to find object edges

For each pixel, compute its contrastCan use max difference of its 8 neighborsDetects intensity change across boundary of adjacent regions

Page 44: Computer Vision: Intro

4 and 8 neighbors of a pixel4 neighbors are at multiples of 90 degrees

. N .W * E. S .

8 neighbors are at every multiple of 45 degrees

NW N NEW * ESW S SE

Page 45: Computer Vision: Intro

Detect Motion via SubtractionConstant backgroundMoving objectProduces pixel differences at boundaryReveals moving object and its shape

Page 46: Computer Vision: Intro

Some image format issues

Spatial resolution; intensity resolution; image file format

Page 47: Computer Vision: Intro

Resolution is “pixels per unit of length”

Resolution decreases by one half in cases at leftHuman faces can be recognized at 64 x 64 pixels per face

Page 48: Computer Vision: Intro

Features detected depend on the resolution

Can tell hearts from diamondsCan tell face valueGenerally need 2 pixels across line or small region (such as eye)

Page 49: Computer Vision: Intro

Many different image file forms

Portable gray map (PGM) older formGIF was early commercial versionJPEG (JPG) is modern versionMany others existDo they handle color?Do they provide for compression?Need to have size & parameters & pixels

Page 50: Computer Vision: Intro

PGM image with ASCII info.P2 means ASCII grayCommentsW=16; H=8192 is max intensityCan be made with editor

P1: binary, P3: RGB, P4 and P6: binary format

Page 51: Computer Vision: Intro

JPG current popular formPublic, not private, standardAllows for image compression; often 10:1 or 30:1 are easily possible8x8 intensity regions are fit with basis of cosinesError in cosine fit coded as wellParameters then compressed with Huffman codingVERY TECHNICAL!

Page 52: Computer Vision: Intro

First day course businessSyllabus on web (read for next time)Course web pages (www.research.rutgers.edu/~chansu/CS580Web/ ) Textbook by Shapiro and StockmanRead Chapters 1 and 2 Read Chapter 1 for Ballard Computer Vision book (Available online: http://homepages.inf.ed.ac.uk/rbf/BOOKS/BANDB/bandb.htm)