Professional Documents
Culture Documents
yogi.borhade@gmail.com
pratik069@gmail.com
sanketjog@gmail.com
Abstract— This document gives a brief description of stereo image is more than the sum of its parts. It is a three-
vision capabilities that can be used by autonomous robots. It can dimensional stereo picture.
detect different objects, its distance, its position in X, Y and Z With stereo vision you see an object as solid in three spatial
coordinate axes, its colour and shape, contour etc.
dimensions--width, height and depth--or x, y and z. It is the
added perception of the depth dimension that makes stereo
vision so rich and special.
Keywords— Intex USB Cameras,Stereo Vision,Linux (Ubuntu
9.10 version).
1. INTRODUCTION
In Robots, Visual interpretation is an extremely challenging
problem to fully solve. Robot vision technology is needed for
the stable walking, object recognition and the movement to
the target spot. By some sensors which use infrared rays and
ultrasonic, robot can overcome the urgent state. But stereo
vision of three dimensional spaces would make robot have
powerful artificial intelligence. With stereo vision, we can see where objects are in relation
to our own bodies with much greater precision--especially
when those objects are moving toward or away from us in the
2. STEREO VISION depth dimension. Instead of eyes, two USB Cameras are used
to obtain the two 2D images while Linux could be used for
Human beings are equipped with two eyes. Unlike performing the necessary operations instead of Brain to obtain
animals , humans have two eyes located side-by-side in the 3D coordinate of an object. Procedure to obtain 3D coordinate
front of their heads. Thanks to the close side-by-side is quite complicated and takes places in the following
positioning, each eye takes a view of the same area from a manner:-
slightly different angle. The two eye views have plenty in 1. Stereo Pipeline
common, but each eye picks up visual information that other 2. Epipolar Rectification
doesn't. 3. Stereo Matching
Two Eyes = Three Dimensions (3D)! 4. Depth via Triangulation
Each eye captures its own view and the two separate
images are sent to the brain for processing. When the two STEREO PIPELINING
images arrive simultaneously in the back of the brain, they are
united into one picture. The brain combines the two images by In the First Stage, global coordinate is captured by both the
matching up the similarities and adding in the small cameras and plotted on to the Image Planes of the cameras.
differences. The small differences between the two images
add up to a big difference in the final picture! The combined
EPIPOLAR RECTIFICATION
5. APPLICATIONS
6. CONCLUSION
Thus this concept of stereo vision mimics the human vision
thereby increasing accuracy.
REFERENCES
M. Wegmuller, J. P. von der Weid, P. Oberson, and N. Gisin, “High
resolution fiber distributed measurements with coherent OFDR,” in
The USB camera will capture the live real world video. Proc. ECOC’00, 2000, paper 11.3.4, p. 109.
By using two cameras, frames from the two videos would be
compared and processed to obtain a 3D image.
[1] (2002) The IEEE website. [Online]. Available: http://www.ieee.org/
[2] M. Shell. (2002) IEEEtran homepage on CTAN. [Online]. Available:
http://www.ctan.org/tex-
archive/macros/latex/contrib/supported/IEEEtran/
[3] Wireless LAN Medium Access Control (MAC) and Physical Layer
(PHY) Specification, IEEE Std. 802.11, 1997.
[4] www.wikipedia.com
[5] www.howstuffworks.com
[6] http://opensource.org