The issues of using errorful data in motion estimation and of using feedback to improve feature extraction and matching in incremental analysis are addressed. Initial noisy correspondence data are continously refined by removing those parts that do not fit the estimated 3-D motion parameters. The extraction of a tracked region is guided by its expected properties obtained from the corresponding objects in the previous frames. The surfaces of objects are reconstructed from a sparse depth map.>

In automated feature-based motion analysis of multiple frames, correspondence data are usually noisy and fragmented. A technique that gradually refines the initial noisy correspondence data and links fragments of a single trajectory using feedback from 3D motion estimation is presented. First, 3D motion parameters are estimated using the initial correspondence data. Then, each noisy trajectory is partitioned into subsets of points, each of which conforms to the estimated motion. The best set is used as the input to the next motion estimation. This process is repeated, and the gaps in the refined correspondence data are filled by guidance from the predicted motion. Test results for a standard real image sequence are presented.>

The history of the image understanding environment (IUE) project, a five-year program to develop a common software environment for the development of algorithms and application systems, is reviewed. An overview of some of the data structures that are currently evolving as a specification for the IUE is provided. The ultimate goal of the project is to provide the basic data structures and algorithms that are required to carry state-of-the-art research in image understanding.>

An overview is given of the important aspects of feature-based motion analysis, especially with regard to more than two frames. These topics include some history of feature-based techniques, reasons to use feature-based techniques and longer sequences, applications to real motion sequences, and some directions for this kind of research. It is pointed out that feature-based motion analysis involves work on several subproblems such as feature extraction, feature matching, motion estimation, and the use of the motion estimates. The final use of the motion analysis can be for target tracking 3D reconstruction and improved matching results. Real-world motion analysis programs must assume that the computed feature matches are only good enough for motion estimation, and not perfect. Feature-based systems offer many ways to achieve good performance with real-world data.>

This correspondence describes research in the development of symbolic registration techniques directed toward the comparison of pairs of images of the same scene to ultimately generate descriptions of the changes in the scene. Unlike most earlier work in image registration, all the matching and analysis will be performed at a symbolic level rather than a signal level. We have applied this registration procedure on several different types of scenes and the system appears to work well both on pairs of images which may be analyzed in part by signal based systems and those which cannot be so analyzed.