Page 236 - Introduction to AI Robotics

219
6.6 Computer Vision
of the words “picture element.” The modality of the device determines what
the image measures. If a visible light camera is used, then the value stored
at each pixel is the value of the light (e.g., color). If a thermal camera is used,
then the value is the heat at that region. The function that converts a signal
IMAGE FUNCTION into a pixel value is called an image function.
Computer vision includes cameras, which produce images over the same
electromagnetic spectrum that humans see, to more exotic technologies: ther-
mal sensors, X-rays, laser range finders, and synthetic aperature radar. Sim-
ple forms of computer vision are becoming more popular due to the drop in
prices and miniaturization of cameras and because reactive robots need to
exploit affordances such as color or texture.
As noted in the Introduction, computer vision is a separate field of study
from robotics, and has produced many useful algorithms for filtering out
noise, compensating for illumination problems, enhancing images, finding
lines, matching lines to models, extracting shapes and building 3D represen-
tations. Reactive robots tend not to use those algorithms. Most of the algo-
rithms, especially those that remove noise, require many computations on
each pixel in the image; until recently, the algorithms were too computation-
ally expensive to run in real-time. Also, there was a resistance to algorithms
which required any type of memory or modeling. Therefore a robot designed
to follow paths which used vision to extract the path boundary lines in the
current image based on knowledge of the width, then predicted where the
path boundary lines should be in the next image would be on the borderline
of reactivity.

6.6.1 CCD cameras

Computer vision on reactive robots is most often from a video camera, which
uses CCD (charged couple device) technology to detect visible light. A video
camera, such as a camcorder, is arranged so that light falls on an array of
closely spaced metal-oxide semiconductor (MOS) capacitors. Interestingly,
the MOS capacitors are rectangular, not square, so there is some distortion
in creating the image. The capacitors form a shift register, and output is
either a line at a time (“line transfer”) or the whole array at one time (“frame
transfer").
The output of most consumer video signals is analog, and must be digi-
tized for use by a computer. Consumer digital cameras post an analog signal,
but the update rate is too slow at this time for real-time reactive robot con-
trol. The A/D conversion process takes longer than the CCD array can sense