Showing papers by "Sidharta Gautama published in 2003"
01 Jan 2003
TL;DR: A system based on computer vision for automated detection of change and anomalies in GIS road networks using very high resolution satellite images and shows how a measure of change defined based on the number of null assignments is useful and reliable to characterize inconsistencies between image and vector data.
Abstract: In this paper we examine a system based on computer vision for automated detection of change and anomalies in GIS road networks using very high resolution satellite images. The system consists out of a low-level feature detection process, which extracts road junctions, and a high-level matching process, which uses graph matching to find correspondences between the detected image information and the road vector data. The matching process is based on continuous relaxation labelling. It is driven by spatial relations between the objects and takes into account different errors that can occur. The result is an object-to-object mapping between image and vector dataset. The mapping result can be used to calculate a rubbersheeting transformation which is able to compensate for local distortions. A measure of change is defined based on the number of null assignments. We show how combined with a condition to characterize acceptable errors this measure is useful and reliable to characterize inconsistencies between image and vector data.
9 citations
21 Jul 2003
TL;DR: A graph matching methodology based on relaxation labeling to compare road junction in VHR satellite images with GIS road data is proposed and finds correspondences between set of points taking into account error on the spatial location and spurious or missing points.
Abstract: We propose a graph matching methodology based on relaxation labeling to compare road junction in VHR satellite images with GIS road data. Use is made of the spatial layout between points based on the relative angle. The technique finds correspondences between set of points taking into account error on the spatial location and spurious or missing points. An analysis is given to determine the weights of the algorithm based on the expected graph error.
7 citations
21 Jul 2003
TL;DR: The method is based on measured image statistics of the road and its immediate surroundings and predicts the performance of the detection as well as the optimal parameter set which is needed for this detection.
Abstract: We introduce a methodology to predict the performance of road detection based on the ridge detector. The method is based on measured image statistics of the road and its immediate surroundings. It predicts the performance of the detection as well as the optimal parameter set which is needed for this detection.
01 Jan 2003
TL;DR: The major positional error components in the process of registering SAR image data to vector data are studied to attach a spatial quality measure to said image, in order to assess the level of change a change detection process will be able to detect.
Abstract: We have studied the major positional error components in the process of registering SAR image data to vector data. This way we intend to attach a spatial quality measure to said image, in order to assess the level of change a change detection process will be able to detect. Keywords— Change detection; error analysis; remote sensing; SAR; image registration; GIS