Automatic Image Registration
Automatic Image Registration (AIR) provides assistance to image analysts in performing their tasks. AIR could be used to facilitate strategic, operational and tactical decisions, in both military and civilian applications.
In comparison with other registration methods, such as manual or intensity-based registration, AUG-H’s AIR product has several advantages and innovations, providing:
- Fully automatic multi-layer co-registration of images from similar or dissimilar sensors
- Increased number of automatically identified control points between multi-sensor image pair
- Increased spatial registration accuracy for multi-sensor image co-registration
- Increased similarities between the images by extracting feature layers
- Automatic vector-to-image data conflation
- Fully automatic processing, the algorithm does not require any prior knowledge of the images
- Sub-pixel accuracy – in the RMS error sense
- Automatic registration capabilities that employ different transformation functions
- Intelligent and efficient control points estimation and global consistency checking to eliminate mismatched points
- Robust and works for many different kinds of multi-sensor images
miliAIR is a leading edge, fully automatic image registration technology aimed specifically at the military market, designed to improve Intelligence, Surveillance and Reconnaissance (ISR) capabilities by providing image analysts and the command centre with an improved understanding of air, ground and sea targets, both moving and stationary. Improved strategic, operational and tactical decision-making is facilitated by the production of reliable and consistent information that reduces target uncertainty, allowing real-time mapping and time-crucial target detection scenarios.
miliAIR software toolkit automatically registers temporal hyperspectral, polarimetric SAR or multi-sensor images at sub-pixel registration accuracy, and is built on an area-based feature-matching algorithm that intelligently identifies control points between two images. It then aligns one image with the other, using high order polynomial transformation. A consistency check determines the number of valid control points – and together with the calculated Root-Mean-Square (RMS) error can be used as a metric in measuring registration accuracy.
ERSS is an innovative toolbox for the processing of remote sensing data that integrates many of AUG-H’s innovative algorithms and serves as the main avenue for the distribution of AUG-H’s leading edge image processing technology. ERSS provides advanced solutions in image registration, detection, region classification, restoration, fusion, and hyperspectral data analysis.
