MODULE 1

CHAPTER 1
INTRODUCTION

 The forward models that we use in computer vision are usually

developed in physics (radiometry, optics, and sensor design) and in
computer graphics.
 Both of these fields model how objects move and animate, how light
reflects off their surfaces, is scattered by the atmosphere, refracted
through camera lenses (or human eyes), and finally projected onto a
flat (or curved) image plane
 computer vision,
 describe the world that we see in one or more images and to reconstruct its properties, such
as shape, illumination, and color distributions.
 It is amazing that humans and animals do this so effortlessly, while computer vision
algorithms are so error prone.
 EXAMPLES

(a) The classic Muller-

Lyer illusion, where the
length of the two
horizontal lines appear
¨ different, probably
due to the imagined
perspective effects.
(b) The “white” square B in
the shadow and the “black”
square A in the light actually
have the same absolute
intensity value.
The percept is due to
brightness constancy, the
visual system’s attempt to
discount illumination when
interpreting colors.
A variation of the
Hermann grid illusion
As you move your eyes
over the figure, gray
spots appear at the
intersections.
d) Count the red Xs
in the left half of the
figure.
Now count them in
the right half. Is it
significantly harder?
Applications
 Optical character recognition (OCR): reading handwritten postal codes on letters
(and automatic number plate recognition (ANPR);
 Machine inspection: rapid parts inspection for quality assurance using stereo vision
with specialized illumination to measure tolerances on aircraft wings or auto body
parts or looking for defects in steel castings using X-ray vision;
 Retail: object recognition for automated checkout lanes
 3D model building (photogrammetry): fully automated construction of 3D models
from aerial photographs used in systems such as Bing Maps;
 Medical imaging: registering pre-operative and intra-operative imagery or
performing long-term studies of people’s brain morphology as they age;
 Automotive safety: detecting unexpected obstacles such as pedestrians on the
street, under conditions where active vision techniques such as radar or lidar do not
work well
 Match move: merging computer-generated imagery (CGI) with live
action footage by tracking feature points in the source video to
estimate the 3D camera motion and shape of the environment.
 Such techniques are widely used in Hollywood (e.g., in movies such as
Jurassic Park) (Roble 1999; Roble and Zafar 2009);
 Motion capture (mocap): using retro-reflective markers viewed from
multiple cameras or other vision-based techniques to capture actors
for computer animation;
 Surveillance: monitoring for intruders, analyzing highway traffic and
monitoring pools for drowning victims;
 Fingerprint recognition and biometrics: for automatic access
authentication as well as forensic applications
Consumer-level applications, such as fun things
you can do with your own personal photographs
and video
 Stitching: turning overlapping photos into a single seamlessly stitched panorama
 Exposure bracketing: merging multiple exposures taken under challenging lighting
conditions (strong sunlight and shadows) into a single perfectly exposed image
 Morphing: turning a picture of one of your friends into another, using a seamless morph
transition
 3D modeling: converting one or more snapshots into a 3D model of the object or person
you are photographing
 Video match move and stabilization: inserting 2D pictures or 3D models into your
videos by automatically tracking nearby reference points
 Photo-based walkthroughs: navigating a large collection of photographs, such as the
interior of your house, by flying between different photos in 3D
 Face detection: for improved camera focusing as well as more relevant image search
 Visual authentication: automatically logging family members onto your home computer
as they sit down in front of the webcam
A brief history
A rough timeline of some of the most active
topics of research in computer vision.
Chapter 2 : Image Formation

 Photometric image formation

Lighting
 Images cannot exist without light.
 To produce an image, the scene must be illuminated with one
or more light sources.
 Light sources can generally be divided into point and area
light sources.
 A point light source originates at a single location in space
(e.g., a small light bulb), potentially at infinity (e.g., the sun).
 In addition to its location, a point light source has an intensity
and a color spectrum, i.e., a distribution over wavelengths
L(λ).
 The intensity of a light source falls off with the square of
the distance between the source and the object being lit,
because the same light is being spread over a larger
(spherical) area.
 Area light sources are more complicated. A simple area light source
such as a fluorescent ceiling light fixture with a diffuser can be
modeled as a finite rectangular area emitting light equally in all
directions (When the distribution is strongly directional, a four-
dimensional light field can be used instead