hi I am sandhya I would like to get details on object detection using ultrasonic sensor ppt will be available here and now I am living at......and I last studied in the college/school.....and now am doing ....I need help on.....etc
Posts: 2,532
Threads: 0
Joined: Aug 2016
Senix ToughSonic® Ultrasonic Sensors detect objects or materials through the air using “non-contact” technology. They are easy to use and reliable. Most materials can be detected: hard or soft, any color or transparency, flat or curved. Unlike traditional proximity sensors, they operate over longer distances and can be set up to limit object detection within a user-specified distance band (“window”).
Introduction
At last year’s CIRA Symposium our group introduced a
novel system for recognizing objects using the spectral information
contained in sonar echoes (Streilein, Gaudiano,
& Carpenter, 1998). The system we presented uses the
readily available 6500-series Polaroid sonar and an inexpensive
data acquisition board that can operate under the
LINUX operating system (DAS16-M1, Computer Boards,
Inc., with a LINUX driver written by Warren Jasper of
North Carolina State University).
Our work was based on the observation that animals such
as bats and dolphins can perform remarkable sensory feats
using ultrasound signals (Dror, Zagaeski, Rios, & Moss,
1993; Moore, Roitblat, Penner, & Nachtigall, 1991). In
contrast, typical robotics applications only use sonar as a
range finder, measuring the time-of-flight of the leading
edge of the ultrasonic echo to determine the distance of
the object that generated the echo (Borenstein, Everett, &
Feng, 1996; Leonard & Durrant-Whyte, 1992).
This work is supported by the Office of Naval Research and the
Navy Research Laboratory through grant N00014-96-1-0772. We thank
William Streilein for his contribution to an earlier version of this work,
and Matt Giamporcaro for his electronic wizardry. P. Gaudiano’s current
address is: Artificial Life, Inc., Four Copley Place, Suite 102, Boston, MA
02116, USA.
In our first study we used a Fuzzy ARTMAP neural
network (Carpenter, Grossberg, Markuzon, Reynolds, &
Rosen, 1992) to classify echoes from five objects placed
at various distances from the sonar. We chose ARTMAP
because of its speed, its ability to learn incrementally and
its proven performance on a variety of real-world pattern
recognition problems. For a description of Fuzzy
ARTMAP please refer to the original publication (Carpenter
et al., 1992) or our earlier article (Streilein et al., 1998).
The results we presented last year were very encouraging:
the recognition system was able to perform with an
accuracy as high as 96% (Streilein et al., 1998). In that
work, we used Matlab (Wolfram Research) to calculate the
power spectral density (PSD) of each echo. The frequency
information was then used as input to the Fuzzy ARTMAP
neural network.
