Digital Mapping Laboratory
Carnegie Mellon University
|
``SiteCity: A Semi-Automated Site Modelling System''.
(PDF, 2.436 Mb;
PostScript, 3.101 Mb) Y. Hsieh, in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, California, June 18-20 1996, pages 499-506. [grayscale] |
| This paper describes the design and evaluation of SITECITY, a semi-automated building extraction system integrating photogrammetry, geometric constraints, image understanding and user interfaces. Existing automated building extraction systems often produce mixed results and it is clear that human intervention is required to correct mistakes from fully automated systems. SITECITY gives human operators the ability to construct and manipulate three dimensional building objects using multiple images. Image understanding algorithms are integrated into SITECITY to assist users. These automated processes are selected and integrated based on methods and criteria derived from the GOMS (Goals, Operators, Methods and Selection Rules) human-computer interaction principle. The performance of these automated processes are rigorously evaluated. Twelve human subjects were used to evaluate the usability of the semi-automated system in comparison with the fully manual version. The methodology for the usability evaluation is described and the result of this evaluation shows that automated processes in SITECITY enhance the overall usability of the system and reduce the complexity of manual mensuration of three dimensional building objects. |
maps+webmaster@cs.cmu.edu