By Topic

A new approach to automatic object Detection and tracking using wavelet features and ANN

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Ali Ziaei ; Speech Processing Research Laboratory, Electrical Engineering Department, Amirkabir University of Technology, Hafez Avenue, Tehran 15914, Iran ; Seyed Mohammad Ahadi ; Hojatollah Yeganeh

In this paper we describe an automatic system for airplane Detection and tracking based on wavelet transform and Artificial Neural Networks (ANN). Our method is fully automatic and more effective than other conventional approaches. Initially, we prepared a good database that includes images (about 100) from different airplanes in different positions. Then, we manually labeled airplane pixels and background pixels as foreground and background objects. Then, in order to reduce the overall computation, using wavelet transform, images were compressed. A MLP was then trained using the resultant image values and the foreground/background labels (MLP1). In fact, object color information is used as the input to the neural network for detection purposes. We have used MLP1 for automatic airplane detection in the first frame. Then, a second neural network with the same structure as above was trained by only the first frame of our video (MLP2). So, we can use this method for each image to object detection in other frames. Simulation results have shown that this approach leads to promising performance in airplane detection and tracking.

Published in:

2008 9th International Conference on Signal Processing

Date of Conference:

26-29 Oct. 2008