Automatic registration of multisensor airborne imagery

Abstract

In this paper, we propose a novel technique based on maximization of mutual information (MMI) and multiresolution that is capable of automatic registration of multisensor images captured using multiple airborne cameras by utilizing maximization of mutual information, In contrast to conventional methods that extract and employ feature points, MMI-based algorithms utilize the mutual information found between two given images to compute the registration parameters. These, in turn, are then utilized to perform inter and intra sensor registration. Wavelet based techniques are also used in a multiresolution analysis framework yielding a significant increase in computational efficiency for images captured at different resolutions. Our results indicate that the proposed algorithms are very effective in registering infrared images taken at three different wavelengths with a high resolution visual image of a given scene. The techniques form the foundation of a real-time image processing pipeline for automatic geo-rectification, target detection and mapping