Hierarchical morphological segmentation for image sequence coding

Abstract

Abstract-This paper deals with a hierarchical morphological segmentation algorithm for image sequence coding. Mathematical morphology is very attractive for this purpose because it efficiently deals with geometrical features such as size, shape, contrast, or connectivity that can be considered as segmentationoriented features. The algorithm follows a Top-Down procedure. It first takes into account the global information and produces a coarse segmentation, that is, with a small number of regions. Then, the segmentation quality is improved by introducing regions corresponding to more local information. The algorithm, considering sequences as being functions on a 3-D space, directly segments 3-D regions. A 3-D approach is used to get a segmentation that is stable in time and to directly solve the region correspondence problem.Each segmentation stage relies on four basic steps: simplification, marker extraction, decision, and quality estimation. The simplification removes information from the sequence to make it easier to segment. Morphological filters based on partial reconstruction are proven to be very efficient for this purpose, especially in the case of sequences. The marker extraction identifies the presence of homogeneous 3-D regions. It is based on constrained flat region labeling and morphological contrast extraction. The goal of the decision is to precisely locate the contours of regions detected by the marker extraction. This decision is performed by a modified watershed algorithm. Finally, the quality estimation concentrates on the coding residue all the information about the 3-D regions that have not been properly segmented and therefore coded. The procedure allows the introduction of the texture and contour coding schemes within the segmentation algorithm. The coding residue is transmitted to the next segmentation stage to improve the segmentation and coding quality. Finally, segmentation and coding examples are presented to show the validity and interest of the coding approach.

Properties of magnetic elements in the quiet Sun using the marker-controlled watershed method

“…The first one involves merging adjacent regions according to some criterion after the use of the watershed algorithm (Courses & Surveys 1999;Haris et al 1998;Tremeau & Colantoni 2000). The second one uses markers to reduce over-segmentation (Salembier & Pardas 1994;Salembier & Marques 1999). Since we can get the centers of magnetic elements as markers, we chose the second approach.…”

Design of Real-Time Self-Frame-Rate-Control Foreground Detection for Multiple Camera Surveillance System

“…After thresholding, opening by partial reconstruction and closing by partial reconstruction [12] are applied to eliminate misclassified foreground pixel in O.…”

Segmentation-based video coding system allowing the manipulation of objects

“…Note that the Decision algorithm has selected a quite different strategy for the two bit rates: for low bit rates almost 20% of the bit stream is devoted to the partition information, whereas less than 10% is used for this type of information for higher bit rates. Finally, let us mention that by comparison with the algorithm presented in [32] using a much simpler bit allocation rule, the current algorithm provides between 2 and 3 dB of PSNR for very low bit rates (30)(31)(32)(33)(34)(35)(36)(37)(38)(39)(40).…”

“…Note that the problem is similar to the one of creating the fine partition in the projection step, but the procedure has to be done now in a hierarchical way. The morphological approach described in [27], [30], and [32] is particularly suitable for this step: without getting into details let us mention that this segmentation approach involves 1) the computation of the difference between the original frame and the mean of each region called "residue," 2) the simplification of the residue by "connected operators" [31], 3) a marker extraction step, and 4) finally a watershed algorithm [16]. In our implementation, all segmentation steps are size-oriented except the last one which is contrast-oriented (see [27], [30], [32], and [24] for more details).…”