Scribd
Upload
6 views39 pages

Giriş 1

Uploaded by

Rıdvan Çartı
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
6 views39 pages

Giriş 1

Uploaded by

Rıdvan Çartı
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 39

Bilgisayarla Görmeye Giriş

2024 Güz Dönemi


Gülşah Tümüklü Özyer

1
Suplemental Resources
◼ Computer Vision: Algorithms and
Applications, 2nd Edition by Richard
Szeliski.
◼ Concise Computer Vision by Reinhard
Klette
◼ Gonzalez and Woods. Digital Image
Processing, Prentice Hall

2
•

What is Computer Vision?


◼ Make the computer SEE
◼ SEE: Extracting Visual information from any
sensed data

◼ Goal : Make useful decisions about objects


and scenes based on sensed data

3
OBJECT

perceptible material
vision
thing
OBJECTS

ANIMALS PLANTS INANIMATE

NATURAL MAN-MADE
….. VERTEBRATE

MAMMALS BIRDS

TAPIR BOAR GROUSE CAMERA


How many object categories are there?

o 3 0 , 0 0 0
1 0 , 0 0 0 t
~

Biederman 198
SCENE
◼ Consists of multiple objects

Goal : Make useful decisions about objects and scenes


based on sensed data
7
Bruegel,
Sensed Data: Images
◼ All sorts of sensor data carying visual info
◆ Optic

◆ Thermal

◆ IR

◆ MR

◆ SAR

◆ ….
Goal : Make useful decisions about objects and scenes based on
sensed data 9
IMAGES: Sattelite,CT, SAR,
Thermal, scientific

10
Useful Decisions
◼ Recognize, classify, detect, locallize,
retrieve, annotate, varify

Goal : Make useful decisions about objects and scenes based on


sensed data 11
So what does recognition involve?
Verification: is that a lamp?
Detection: are there people?
Identification: is that Potala Palace?
Object categorization

mountain

tree
building
banner

street lamp

vendor
people
Scene and context categorization
• outdoor
• city
•…
APPLİCATİON DOMAİNS OF
COMPUTER VISION
18
Traffics
Pedestrian and car detection

Ped

meters
Ped

Car

meters

Assisted driving
Lane detection
• Collision warning systems with
adaptive cruise control,
• Lane departure warning
systems,
• Rear object detection systems,
Retrieval: Improving online search
Picsearch - the search engine for pictures and images

Query:
STREET

Digital Album
Similarity Retrieval of Brain Data

21
Image Databases: Content-Based Retrieval

Images from my Ground-Truth collection.

What categories of image databases exist today?

22
Abstract Regions for Object Recognition

Original Images Color Regions Texture Regions Line Clusters

23
Insect Identification for Ecology Studies

Calineuria (Cal) Doroneuria (Dor) Yoraperla (Yor)

24
Document Analysis

25
Surveillance: Object and Event Recognition in Aerial Videos

Original Video Frame

26
Color Regions Structure Regions
Video Analysis

What are the objects? What are the events?


27
3D Reconstruction of the Blood Vessel Tree

28
Recognition of 3D Object Classes from Range Data

29
3D Scanning
David2

Scanning Michelangelo’s “The David”


• The Digital Michelangelo Project
- http://graphics.stanford.edu/projects/mich/
• UW Prof. Brian Curless, collaborator
• 2 BILLION polygons, accuracy to .29mm
30
31
32
33
Tasks in Computer Vision
• Segment an image into useful regions

• Perform measurements on certain areas

• Determine what object(s) are in the scene liver


kidney spleen

• Calculate the precise location(s) of objects

• Visually inspect a manufactured object

• Construct a 3D model of the imaged object

• Find “interesting” events in a video


34
HISTORY OF COMPUTER VISION
1970
1980s
1990
2000s

You might also like