Intermediate Level Computer Vision Processing Algorithm Development for the Content Addressable Array Parallel Processor

摘要

From September through November the author concentrated on the development of an Integrated Image Understanding Benchmark for computer vision architectures. Unlike previous vision benchmarks, this new benchmark is designed to test machine performance on a complete interpretation task. The task chosen will require not only that common low-level vision operations be performed, but that intermediate-level operations and interactions between operations be tested as well. In fact, the emphasis of the benchmark is on intermediate - or high-level processes controlling lower level processing in a top-down manner. The goal of the interpretation task is to recognize a modeled object in a cluttered environment. The input to the system is a set of models, any one of which may be present in the scene, and a pair of registered images. One of the images is from a black and white 8-bit intensity sensor, and the other is from a 32-bit floating-point range sensor. For the purposes of the benchmark, the images are artificially created.