The optimal partition of moving edge segments

Abstract

This paper presents a method to obtain the optimal motion description from two consecutive images including multiple moving parts. It copes with segmentation and motion estimation problems which resemble the well known "chicken and egg" relation. "Segmentation" is necessa y for amotion estimation" of each part, and vice versa. Unkke previous approaches based on the motion similarity between two pixels, we propose t o use an information measure ap roach, based on comparisons between an individual ( r pixel) and a class (or set of pixels,). First, the motion of an edge segment as optimally modeled. Next, merging and splitting processes are iterated until the minimum descriptaon is obtained for the whole image. As a result, the im.age is segmented into several regions, each of which is represented by an edge segment list, and at the same time the maximum likelihood motion estimation is obtained f o r each region. Experiments performed on real images are shown.

Unsupervised image restoration and edge location using compound Gauss-Markov random fields and the MDL principle

“…Keeler uses MDL in an MRF-type context pursuing a different goal: to build "complexity"-based priors for discontinuity configurations [29]. Recently, MDL and related ideas have seen several applications in the fields of image processing and computer vision: segmentation [9], [29], [32]; line and curve detection [47]; contour estimation [18]; motion and displacement segmentation and/or estimation [11], [23], [59]; and shape description [35].…”

Optical flow estimation and the interaction between measurement errors at adjacent pixel positions

“…The influence of particular assumptions regarding the estimation of optical flow on the segmentation results are not treated by these authors. More recent approaches have been reported by (Wang and Adelson 1993) and (Gu et al 1993). Problems with approaches to detect discontinuities in the optical flow field based on edge-detection techniques have been discussed by (Tort and Murray 1992).…”

“…The same implicit assumption regarding the error of each constraint equation is made as in the approaches discussed above. Gu et al (1993), at the end of their Section 3.1, however, at least mention this assumption explicitly in their study to segment images of moving objects from those of moving background, see also (Etoh and Shirai 1993, in particular their Eq. 2).…”