Graduate Exam Abstract
May 14, 2010, 11AM
Block-Based Detection Methods for Underwater Target Detection and Classification from Electro-Optical Imagery
Abstract: Detection and classification of underwater mine-like objects is a complicated problem due to various factors such as variations in the operating and environmental conditions, presence of spatially varying clutter, target obstruction and occlusion, variations in target shapes, compositions, and orientation. Also contributing to the difficulty of the problem is the lack of a priori knowledge about the shape and geometry of new non-mine-like objects that may be encountered, as well as changes in the environmental or operating conditions encountered during data collection. Two different block-based methods are proposed for detecting frames and localization of mine-like objects from a new CCD-based Electro-optical (EO) imaging system. The block-based methods proposed in this study serve as an excellent tool for detection in low contrast frame sequences, as well as providing means for classifying detected objects as target or non-target objects. The detection methods employed provide frame location, automatic object segmentation, and accurate spatial locations of detected objects.
The problem studied in this work is the detection of mine-like objects from new CCD imagery data. The new CCD imagery data consists of runs containing tens to hundreds of frames (ocean bottom photographs). The problem studied in this research is detection of frames containing mine-like objects, as well as localizing detected objects and segmenting them from the frame to be subsequently classified as mine-like objects or background clutter. While object segmentation and classification of detected objects are a requirement as with the previous EO systems, in the new CCD system a new challenge of frame detection presents itself with CCD system. It is this main difference in the data collected from the different sensors which has prompted research on new detection methods which utilize block-based snapshot information in order to identify potential frames containing targets, and spatially localize detected objects within those detected frames.
Adviser: Mahmood R. Azimi-Sadjadi
Co-Adviser: Ali Pezeshki
Non-ECE Member: Mingzhong Wu
Member 3: N/A
Addional Members: N/A
Program of Study: