Fast vision algorithms on compact and imbeddable hardware are developed for the guidance and control of an autonomous underwater vehicle. The specific application involves tracking underwater cables and chains. Feature points are identified in the underwater video images using a technique which combines segmentation by gray level and run length. A Hough transformation is then used to find the straight line in the image. The process is performed at a throughput of approximately one image per second using a PC-bus video frame grabber and a PC/AT compatible microcomputer.>

This research is concerned with the feasibility of automated visual inspection of holes drilled in aircraft engine combustor assemblies. Using a digital image processor and necessary optics, combustor assemblies were examined, and scanned images were processed for analysis such as hole areas and diameters. The limitations of the automated visual inspection system including its accuracy and repeatability, were determined. Experimental results were compared with reference data for a non-coated combustor sample. The results indicate that these automated visual inspection methods produce reasonable results for the feasibility of their use in the inspection of aircraft engine combustor assemblies.