Real-time object-based image registration using multilayer perceptron

Pramod L. Narasimha; Zhanfeng Yue; Pankaj Topiwala

doi:10.1117/12.778091

Translator Disclaimer

17 March 2008 Real-time object-based image registration using multilayer perceptron

Pramod L. Narasimha, Zhanfeng Yue, Pankaj Topiwala

Author Affiliations +

Proceedings Volume 6974, Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2008; 697409 (2008) https://doi.org/10.1117/12.778091
Event: SPIE Defense and Security Symposium, 2008, Orlando, Florida, United States

Abstract

The registration of images from cameras of different types and/or at different locations is well researched topic. It is of great interest for both military and civilian applications. Researchers have come up with pixel level registration techniques by exploiting intensity correlations to spatially align pixels from the two cameras. This is a computationally expensive method as it requires pixel level operation on the images and this would make it difficult to register the images in real time. Furthermore, images from different types of cameras may have different intensity distributions for corresponding pixels which will degrade the registration accuracy. In this paper we propose to use Multilayer Perceptron (MLP) neural network to solve the image registration problem. The experimental results show that the performance of the proposed method is suited for registration both in speed and accuracy.

Citation Download Citation

Pramod L. Narasimha, Zhanfeng Yue, and Pankaj Topiwala "Real-time object-based image registration using multilayer perceptron", Proc. SPIE 6974, Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2008, 697409 (17 March 2008); https://doi.org/10.1117/12.778091

ACCESS THE FULL ARTICLE