Integrating spatial information and image analysis - one plus one makes ten
Emmanuel P. Baltsavias, Michael A. Hahn · Repository for Publications and Research Data (ETH Zurich) · 2000
Photogrammetry and remote sensing have proven their efficiency for spatial data collection in many ways.Interactive mapping at digital workstations is performed by skilled operators, which guarantees excellent quality in particular of the geometric data.In this way, worldwide acquisition of a large number of national GIS databases has been supported and still a lot of production effort is devoted to this task.In the field of image analysis, it has become evident that algorithms for scene interpretation and 3D reconstruction of topographic objects, which rely on a single data source, cannot function efficiently.Research in two directions promises to be more successful.Multiple, largely complementary, sensor data like range data from laser scanners, SAR and panchromatic or multi-/hyper-spectral aerial images have been used to achieve robustness and better performance in image analysis.On the other hand, given GIS databases, e.g.layers from topographic maps, can be considered as virtual sensor data which contain geometric information together with its explicitly given semantics.In this case, image analysis aims at supplementing missing information, e.g. the extraction of the third dimension for 2D databases.A second goal, which is expected to become more important in future, is the revision and update of existing GIS databases.This paper is intended to give an overview and the state-ofthe-art on topics related to the terms of references of the IC WG "Integration of Image Analysis and GIS".We will refer not only to activities of the ca. 100 members of our WG, but also other internationally active groups and will try to recapitulate the developments in this field since the previous Congress in 1996.The need of such an overview is great, as the increasing scientific activities in this field are quite fragmented and in various heterogeneous fields and applications, and a clear overview of these developments and underlying unifying theories is missing.Thereby, we will concentrate on 3 topics on which most activities were observed: (a) use of GIS data and models to support image analysis ; (b) matching of image features and GIS objects for change detection and database revision; (c) use of image analysis techniques to extract height information for 2D databases.In all these topics an important component is the integration of various cues, and of different algorithms and their partial results for object recognition and reconstruction.On the data side, we focus on different sensor data in conjunction with GIS databases.Analysis of this data aims at almost all aspects of knowledge-based image analysis like detection, localisation, reconstruction and identification.The paper presents research activities and applications, methods and approaches used, as well as problems faced.We analyse how a priori GIS/map knowledge can be exploited in image analysis and underline the prerequisites for information fusion.Conceptual aspects behind new developments are also described.1