Differential snakes for change detection in road segments

The automation of object extraction from digital imagery has been a key res earch issue in digital photogrammetry and computer vision. In the spatiotem poral context of modern GIS, with constantly changing environments and peri odic database revisions, change detection is becoming increasingly importan t. In this paper, we present a novel approach for the integration of object extraction and image-based geospatial change detection. We extend the mode l of deformable contour models (snakes) to function in a differential mode, and introduce a new framework to differentiate change detection from the r ecording of numerous slightly different versions of objects that may remain unchanged. We assume the existence of prior information for an object (an older record of its shape available in a GIS) with accompanying accuracy es timates. This information becomes input for our "differential snakes" appro ach. In a departure from standard techniques, the objective of our object e xtraction is not to extract yet another version of an object from the new i mage, but instead to update the preexisting GIS information (shape and corr esponding accuracy). By incorporating accuracy information in our technique , we identify local or global changes to this prior information, and update the GIS database accordingly. This process is complemented by versioning, where, in the absence of change, the pre-existing information may be improv ed in terms of accuracy if the new image so permits. Experimental results ( using synthetic and real images) are presented to demonstrate the performan ce of our approach.