Off-campus UMass Amherst users: To download dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.
Non-UMass Amherst users, please click the view more button below to purchase a copy of this dissertation from Proquest.
(Some titles may also be available free of charge in our Open Access Dissertation Collection, so please check there first.)
INTERPRETING OPTICAL FLOW (VISION, DYNAMIC SCENE ANALYSIS, GENERALIZED HOUGH TRANSFORM, MULTIPLE MOVING OBJECTS, SEGMENTATION)
Abstract
A new approach for the interpretation of optical flow fields is presented. The flow field, which can be produced by a sensor moving through an environment with several, independently moving, rigid objects, is allowed to be sparse, noisy and partially incorrect. The approach is based on two main stages. In the first stage the flow field is partitioned into connected segments of flow vectors, where each segment is consistent with a rigid motion of a roughly planar surface. Such a segment is assumed to correspond to a part of only one rigid object. This initial organization of the data is utilized in the second stage without the assumption of planar surfaces, and segments are now grouped under the hypothesis that they are induced by a single rigidly moving object and/or by the camera motion. Each hypothesis is tested by searching for 3-D motion parameters which are compatible with all the segments in the corresponding group. Once the motion parameters are recovered, the relative environmental depth can be estimated as well. Experiments based on real and simulated data are presented. Two inherent ambiguities, which may arise due to the presence of noise in the flow field, are analyzed and demonstrated. First, motion parameters of the sensor or a moving object may be extremely difficult to estimate because there may exist a large set of significantly incorrect solutions which induce flow fields similar to the correct one. Second, the decomposition of the flow field into sets corresponding to independently moving objects may be ambiguous because two such objects may induce optical flows which are compatible with the same motion parameters. These ambiguity analyses are general in the sense that they are algorithm-independent. Constraints and parameters which can be recovered even in ambiguous situations are presented.
Subject Area
Computer science
Recommended Citation
ADIV, GILAD, "INTERPRETING OPTICAL FLOW (VISION, DYNAMIC SCENE ANALYSIS, GENERALIZED HOUGH TRANSFORM, MULTIPLE MOVING OBJECTS, SEGMENTATION)" (1985). Doctoral Dissertations Available from Proquest. AAI8602605.
https://scholarworks.umass.edu/dissertations/AAI8602605