Comparison of Maximum Distance Metrics for Use in the Remote Sensing of Small Targets

There are many applications for small target detection in engineering: topographic mapping, infrastructure inventories, and pre-engineering design. Near shore marine applications include: mapping breakwaters, piers, navigation structures, pilings, and vessel traffic patterns. The application driving this research is the development of a surveillance system for the Canadian Coast Guard. As a result, a new and innovative application of small target detection techniques is being developed at the Department of Geodesy and Geomatics Engineering, UNB, Canada. This work is being done in support of the development of a strategic decision making tool to be used to predict where in Canadian waters marine incidents are most likely to occur. Previous research in the use of hyperspectral imaging for search and rescue, resulted in the development of fast, nonparametric “spatio-spectral” template subpixel object detection algorithm. The results of this work are being adapted and enhanced for use with the new, commercially available spaceborne high-resolution optical imagery. Research is being performed on the employment of a weighted Euclidean distance metric to enhance the “spatio-spectral” template by exploiting the variance/covariance information surrounding a potential target. The detection results using the new weighted Euclidean distance metric were excellent. The best results were had using a $3\times 3$ kernel with all 16 targets being detected.