Browsing by Author "Qian, Jianzhong"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Discrimination of water from shadow regions on radar imagery using computer vision techniques
    Qian, Jianzhong (Virginia Polytechnic Institute and State University, 1985)
    Unlike MSS LANDSAT imagery and other photography, the specific characteristics of the intensity of water and shadow in an SAR image make the task of discriminating them extremely difficult. In this thesis, we analyze the reflectivity mechanism of water and shadow on radar imagery and describe a scene analysis system which consists of a texture preserving noise removal procedure as the preprocessing step, a probabilistic relaxation algorithm to do the low level labeling and a spatial reasoning procedure based on a relational model to perform the high level interpretation. The experimental results obtained from the SAR images are presented to illustrate the performance of this system.
  • Thumbnail Image
    DNESYS--An Expert System for Automatic Extraction of Drainage Networks from Digital Elevation
    Qian, Jianzhong; Ehrich, Roger W.; Campbell, J. B. (Department of Computer Science, Virginia Polytechnic Institute & State University, 1988)
    The determination of drainage networks and drainage basins is one of the more tedious yet important uses of topographic maps, and geographic information systems are now used extensively as a manual aid to facilitate that task. However, the wide availability of digital elevation maps has stimulated attempts to automate the process even further. In this paper, the problems that arose in earlier programs to map drainage systems are analyzed in detail. An expert system called the Drainage Network Extraction System (DNESYS) is described which uses both local operators and global reasoning to extract drainage networks and ridge lines. A stream representation called a parameterized directed graph (PDG) is constructed to model a drainage system. The construction of a model begins with an initial pixel labeling procedure. Then a network tracing and property measurement procedure converts the 2-D low-level labeling information into a symbolic database for high -level processing. By applying Dempster- Shafer evidence theory, evidence collection and uncertain reasoning are performed against the DNESYS knowledge-base that contains the drainage system model and the organized expert knowledge. By discarding erroneous information and supplying missing information, DNESYS produces a complete PDG which can be converted into the final drainage system.
  • Thumbnail Image
    Uncertainty reasoning in hierachical visual evidence space
    Qian, Jianzhong (Virginia Tech, 1990-04-01)
    One of the major problems in computer vision involves dealing with uncertain information. Occlusion, dissimilar views, insufficient illumination, insufficient resolution, and degradation give rise to imprecise data. At the same time, incomplete or local knowledge of the scene gives rise to imprecise interpretation rules. Uncertainty arises at different processing levels of computer vision either because of the imprecise data or because of the imprecise interpretation rules. It is natural to build computer vision systems that incorporate uncertainty reasoning. The Dempster-Shafer (D-S) theory of evidence is appealing for coping with uncertainty hierarchically. However, very little work has been done to apply D-S theory to practical vision systems because some important problems are yet to be resolved.