Maximum Likelihood Classification of LIDAR Data incorporating multiple co-registered Bands

In the past decade, LIght Detection And Ranging (LIDAR) has been recognised by both the commercial and public sector as a reliable and accurate source for land surveying. Object classification in LIDAR data tends towards data fusion by employing additional simultaneously recorded bands. In this paper, a supervised classification algorithm based on Maximum Likelihood is presented using high resolution first, last echo and intensity LIDAR data and co-registered line scanner bands such as aerial photos and near infra-red photos. The issues regarding feature and class selection as well as accuracy assessment are addressed in this paper. The presented results show the suitability of the classification approach for fused LIDAR data sets.