cis 601 fall 2004 introduction to computer vision and intelligent systems longin jan latecki parts...

28
CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Parts are based on lectures of Rolf Lakaemper and David Young

Upload: clinton-robbins

Post on 15-Jan-2016

220 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

CIS 601 Fall 2004 Introduction to

Computer Visionand

Intelligent Systems

Longin Jan Latecki

Parts are based on lectures of Rolf Lakaemper and David Young

Page 2: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Computer Vision ?

Page 3: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Computer Vision ?

“Computer vision’s great trick is extracting descriptions of the world

from pictures or sequences of pictures”(Forsyth/Ponce: Computer Vision)

Page 4: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Pictures/Movies:

How to

• Represent• Process / Prepare• Handle• Recognize Objects

Page 5: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Representation

• Digital Images• Color Spaces• Gray Images• Binary Images• Geometrical Properties

Page 6: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Representation

• Digital Images• Color Spaces• Gray Images• Binary Images• Geometrical Properties

Page 7: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

How to process / prepare:

• Filters• Edges• Geometric Primitives• Lines, Circles

Page 8: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Introduction to Image Analysis and Processing

Page 9: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Low Level Object Handling:

• Image / Video Compression• Huffman • JPEG• MPEG• …

Page 10: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

JPEG - Joint Photographic Experts Group

JPEG is designed with photographs in mind. It is capable of handling all of the colors needed.JPEGs have a lossy way of compressing images. At a low compression value, this is largely not noticeable, but at high compression, an image can become blurry and messy.

BMP - Bitmap Format

uses a pixel map which contains line by line information.

It is a very common format, as it got its start in Windows.

This format can cause an image to be super large.

Image File Formats

Page 11: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

GIF - Graphics Interchange Format

GIF is the most popular on the Internet, mainly because of its small file size. It is ideal for small navigational icons and simple diagrams and illustrations where accuracy is required, or graphics with large blocks of a single color. The format is loss-less, meaning it does not get blurry or messy.     The 256 color maximum is sometimes tight, and so it has the option to dither, which means create the needed color by mixing two or more available colors. GIF use a simple technique called LZW compression to reduce the file sizes of images by finding repeated patterns, but this compression never degrades the image quality.GIF can also be animated.

Page 12: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Low Level Object Handling:

• Object representation

Page 13: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Low Level Object Handling:

• Segmentation

Page 14: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

The “bottom-up” approach

These operations fit into a processing scheme strongly associated with David

Marr, whose seminal book Vision appeared in 1980.

Marr espoused a principle of least commitment, and proposed a processing

scheme involving a series of representations:

• Grey level array (the image, in effect)

• Raw primal sketch (edges)

• Primal sketch (groupings of edges)

• Two-and-a-half-D sketch (surface depths and orientations, camera centered)

• 3-D model (object-centered shapes and relationships).

In some sense, the 3-D model is taken as the goal of the visual processing. It

can be used for matching against a database of object shapes to achieve object

identification.

Page 15: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

But that is not the whole story

A better goal is to produce systems that enable successful interaction with

the environment. Interaction may mean, for example:

•navigating a robot or autonomous vehicle through obstacles, or along a road;

•moving a robot arm to manipulate parts for assembly;

•recognizing human gestures and movements for computer control;

•identifying images in a database on the basis of their content.

Page 16: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

• For many applications, a top-down, model-based or hypothesis-driven

approach is more successful. In such an approach the system starts from an assumption about what is in front of it, and tests and updates this hypothesis to attempt to match the image data.

• Vision is becoming increasingly dynamic. Change and motion are integral

to the goals and methods, not simply techniques for recognizing shape or

inferring the third dimension. Dynamic vision needs to be predictive and

goal-directed.

• Biological vision remains the most important inspiration for computer

vision. Increasing attention is being paid to the role of foveal vision and

eye movements. And computer modeling continues to shed light on how

biological visual systems work.

Page 17: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Object Recognition:

• Color, Texture, Shape

Page 18: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Object Recognition:

• Applications

• Character recognition• Face Recognition• Shape Recognition (Image

Databases)

Page 19: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

3D Distance Histogram

Page 20: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

The Interface (JAVA – Applet)

Page 21: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

The Sketchpad: Query by Shape

Page 22: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

The First Guess: Different Shape - Classes

Page 23: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Selected shape defines query by shape – class

Page 24: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Result

Page 25: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Intelligent Systems?

Page 26: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

New sensors are about to make a breakthrough in development of intelligent systems

Laser Detection and Ranging (LADAR) is about to become the3D spatial sensing tool in many disciplines.

Photo from NIST

Page 27: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Swiss Ranger from CSEM

Page 28: CIS 601 Fall 2004 Introduction to Computer Vision and Intelligent Systems Longin Jan Latecki Parts are based on lectures of Rolf Lakaemper and David Young

Intelligent Systems in Close Future

• Rescue robots: http://www.isd.cme.nist.gov/projects/USAR/

• Autonomous transport vehicles

• Intelligent surveillance video analysis

• Visual control devices

• Image retrieval software