Whitepaper: new generation of image analysis software supports the analysis of large volumes of high resolution image data from different sources including LiDAR

Download here

An increasing number of local governments and organizations need standardized, high-quality spatial information across all terrain to aid infrastructure planning policies and activities, as well as to assess their impact. They also need to be able to compare different regions and cities in a standardized way. Many are coming under pressure to assess the cost- and environmental impact of impervious surfaces on their water resources, for example.

The purpose of image segmentation in general is the delineation of image objects (groups of picture elements) with a meaning in the real world. For forests with complex canopies, getting an initial segmentation to delineate all the different image objects (long snuous shadows,occluded crowns,compact whole crowns,multipart deciduous crowns,....) is infeasable.

This paper elucidates the potential of LiDAR data for information generation for security applications. The study is embedded in the EU Network of Excellence GMOSS. General, security applications cover a large area from infrastructure monitoring (e.g. power stations, pipelines) or border monitoring to less tangible threats like terrorism and civil security / homeland security.

This paper presents a scheme for building detection from LIDAR data and high resolution satellite imagery. The proposed scheme comprises two major parts: (1) segmentation, and (2) classification. Spatial registration of LIDAR data and high resolution satellite images are performed as data pre-processing. It is done in such a way that two data sets are unified in the object coordinate system. Then, a region-based segmentation and object-based classification are integrated for building detection.

By using high resolution imagery it is possible to detect individual buildings and tree crowns more easily than with conventional lower resolution satellite image data. However, due to the high spatial resolution, automatic classification of such imagery based only on the spectral characteristics of the features can become difficult, especially, in spectrally homogeneous areas. Object-based image processing techniques overcome this problem by incorporating both spectral and spatial characteristics of objects.

Using lidar point cloud data, the orientation and height of building roof faces can be estimated accurately but the outline of a roof face is more difficult to determine. To improve this part of the 3D building model reconstruction we make use of building footprints that are extracted from object-oriented classification of coincident high resolution imagery. In this process, the lidar derived DSM (Digital Surface Model) is used with high-resolution imagery for initial segmentation and subsequent classification.

As part of the 2000 PACRIM II Mission to Australia, polarimetric Synthetic Aperture Radar (SAR) data were acquired near Injune, central Queensland, Australia. The primary purpose of the acquisition was to better understand the role of SAR for retrieving biophysical properties of native forests through eitherempirical relationships or simulation modeling.

Three-dimensional forest model is important to forest ecosystem management. Traditional ground investigation requires vast amount of manpower, resources, costs, and time. Hence, it is difficult to promptly obtain accurate information by using ground investigation. Nowadays, Light Detection And Ranging (LIDAR) technology provides high density 3-D point clouds. It can rapidly obtain 3-D information of forest structure. On the other hand, the high resolution images provide plentiful spectral information of forest coverage.

This study explored a segment-based approach to coniferous and deciduous forest volume-by-type estimation using small-footprint lidar. The study area is located in the Appomattox Buckingham State Forest (Appomattox County, Virginia, USA) in the Virginia Piedmont physiographic region, and consists of a variety of pine, upland hardwood, and mixed stands. A multiresolution, hierarchical segmentation algorithm was applied to a lidar-derived canopy height model.