Towards Automatic Single-Sensor Mapping by Multispectral Airborne Laser Scanning

Abstract

ABSTRACT:This paper describes the possibilities of the Optech Titan multispectral airborne laser scanner in the fields of mapping and forestry. Investigation was targeted to six land cover classes. Multispectral laser scanner data can be used to distinguish land cover classes of the ground surface, including the roads and separate road surface classes. For forest inventory using point cloud metrics and intensity features combined, total accuracy of 93.5% was achieved for classification of three main boreal tree species (pine, spruce and birch).When using intensity features -without point height metrics -a classification accuracy of 91% was achieved for these three tree species. It was also shown that deciduous trees can be further classified into more species. We propose that intensity-related features and waveform-type features are combined with point height metrics for forest attribute derivation in area-based prediction, which is an operatively applied forest inventory process in Scandinavia. It is expected that multispectral airborne laser scanning can provide highly valuable data for city and forest mapping and is a highly relevant data asset for national and local mapping agencies in the near future.

Performance Analysis of Multispectral LiDAR in Land Cover Classification

“…The highest classification accuracy of multispectral LIDAR was 95% achieved by Huang et al (2011) who also tied Morsy et al (2017) for the largest increase in classification accuracy, ~12%, by using LIDAR's Z-attribute. M. Sitar (2015) and Miller et al (2016) were able to increase their results by ~9% when using LIDAR attributes with multispectral imagery but Ahokas et al (2016) was only able to increase their result by 2.5%. Ahokas et al (2016) were performing a much more difficult classification by distinguishing three different vegetation in a scene and therefore only had a minor improvement in classification accuracy between multispectral imagery and multispectral LIDAR.…”

“…M. Sitar (2015) and Miller et al (2016) were able to increase their results by ~9% when using LIDAR attributes with multispectral imagery but Ahokas et al (2016) was only able to increase their result by 2.5%. Ahokas et al (2016) were performing a much more difficult classification by distinguishing three different vegetation in a scene and therefore only had a minor improvement in classification accuracy between multispectral imagery and multispectral LIDAR. Even though Wichmann et al (2015) and Morsy et al (2016)…”

Mapping multispectral Digital Images using a Cloud Computing software: applications from UAV images

“…NIR has become a robust technique that permits to evaluate or reveal different properties related to moisture, oils or proteins which are used in agricultural products and in the fields in which they are executed as in the case of this research [26, 27, 28]). In order to know soil quality and functioning, a wide range of physical, chemical and biological properties must be analyzed.…”

Geospatial Computer Vision Based on Multi-Modal Data—How Valuable Is Shape Information for the Extraction of Semantic Information?

“…Further investigations on land cover and land use classification involved a multi-wavelength airborne LiDAR system delivering 3D data as well as three reflectance images corresponding to the green, near-infrared, and short-wave infrared bands, using either three independent sensors [34], or a single sensor such as the Optech Titan sensor which carries three lasers of different wavelengths [34,35]. While the classification may also be based on spectral patterns [36] or different spectral indices [37,38], further work focused on the extraction of geometric and intensity features on the basis of segments for land cover classification and change detection [39][40][41]. Further improvements regarding scene analysis may be achieved via the use of multi-modal data in the form of co-registered hyperspectral imagery and 3D point cloud data for scene analysis.…”