Matching Algorithms and Feature Match Quality Measures for Model-Based Object Recognition with Applications to Automatic Target Recognition

摘要

In the fields of computational vision and image understanding, the object recognition problem can be formulated as a problem of matching a collection of model features to features extracted from an observed scene. This thesis is concerned with the use of feature-based match similarity measures and feature match algorithms in object detection and classification in the context of image understanding from complex signature data. Applications are in the domains of target vehicle recognition from radar imagery, and binocular stereopsis. The author considers image understanding to encompass the set of activities necessary to identify objects in visual imagery and to establish meaningful 3-D relationships between the objects themselves, or between the object and the viewer. The main goal in image understanding involves the transformation of images to symbolic representation, effectively providing a high-level description of an image in terms of objects, object attributes, and relationships between known objects. As such, image understanding subsumes the capabilities traditionally associated with image processing, object recognition, and artificial vision. In human and/or biological vision systems, the task of object recognition is a natural and spontaneous one. Humans can recognize immediately and without effort a huge variety of objects from diverse perceptual cues and multiple sensorial inputs. The operations involved are complex and inconspicuous psychophysical and biological processes, including the use of properties such as shape, color, texture, pattern, motion, context, as well as considerations based on contextual information, prior knowledge, expectations, functionality hypothesis, and temporal continuity. This research considers only the simpler problem of model-based vision, where the objects to be recognized come from a library of 3-D models known in advance, and the problem is constrained using context and domain-specific knowledge.