Antoni Gasull

A contour-based approach to binary shape coding using a multiple grid chain code

This paper presents a contour-based approach to efficiently code binary shape information in the context of object-based video coding. This approach meets some of the most important requirements identified for the MPEG-4 standard, notably efficient coding and low delay. The proposed methods support both object-based lossless and quasi-lossless coding modes. For the cases where low delay is a primary requirement, a macroblock-based coding mode is proposed which can take advantage of inter-frame coding to improve the coding efficiency. The approach presented here relies on a grid different from that used for the pixels to represent the shape – the hexagonal grid – which simplifies the task of contour coding. Using this grid, an appraoch based on a differential chain code (DCC) is proposed for the lossless mode while, for the quasi-lossless case, an approach based on the multiple grid chain code (MGCC) principle is proposed. The MGCC combines both contour simplification and contour prediction to reduce the number of bits needed to code the shapes. Results for alpha plane coding of MPEG-4 video test sequences are presented in order to illustrate the performance of the several modes of operation, and a comparison is made with the shape-coding tool chosen by MPEG-4.

Motion Estimation Techniques to Automatically Track Oceanographic Thermal Structures in Multisensor Image Sequences

The ocean involves a complex set of physical, chemical, biological, and geological processes, interacting with each other to influence our climate and natural environment. One of the most important disciplines in oceanography is the study of the ocean dynamics and, particularly, the ocean surface circulation. One can estimate this by the automated tracking of thermal infrared features in pairs of sequential satellite imagery. In this context, an extensive analysis of different motion estimation techniques has been performed by employing databases with synthetic sequences, real sequences, and in situ measurements. Four region- based metrics and two differential algorithms are proposed to estimate surface currents in multitemporal and multisensor AVHRR and MODIS image sequences. Once the appropriate motion estimation techniques have been selected, a new methodology to compute ocean currents is proposed. It includes a preliminary step to precisely segment the oceanographic structures and a second step to track its motion using additional modules (initialization, preprocessing, and postprocessing) to increase effectiveness. The information provided by the segmentation step reduces computing times, initializes the motion estimation parameters with appropriate values, and increases the overall performance. In summary, this two-stage approach combines image processing tools and physical oceanography knowledge to achieve a good ocean current estimation.

Caption text extraction for indexing purposes using a hierarchical region-based image model

This paper presents a technique for detecting caption text for indexing purposes. This technique is to be included in a generic indexing system dealing with other semantic concepts. The various object detection algorithms are required to share a common image description which, in our case, is a hierarchical region-based image model. Caption text objects are detected combining texture and geometric features, which are estimated using wavelet analysis and taking advantage of the region-based image model, respectively. Analysis of the region hierarchy provides the final caption text objects.

Hierarchical segmentation using compound Gauss-Markov random fields

The authors discuss an original approach for segmenting still images. In this approach, the image is initially decomposed in several levels of different resolution. The decomposition that has been chosen is a Gaussian pyramid. At each level of the pyramid, the image is modeled by a compound Gauss-Markov random field and the segmentation is obtained by using a maximum a posteriori criterion. The segmentation is carried out first at the top level of the pyramid. Once a level (l) has been segmented, this segmentation is projected onto the following level below it (l-1). The process is iterated until the segmentation at the bottom level (0) is performed.<<ETX>>

Partition coding using multi-grid chain code and motion compensation

In this paper, a lossy partition coding technique is presented which leads to decoded partitions with unnoticeable losses. It uses a hexagonal grid for contour representation and it is based on the concept of multi-grid chain code. This coding technique can be used in intra-frame mode or, in combination with partition prediction techniques, in interframe mode. In intra-frame mode, it leads to an average saving of 25% of the coding cost with respect to chain code techniques. The savings on inter-frame mode depend on the motion prediction approach. Results of coding binary shapes (concept of video object plane) as well as partitions with an arbitrary set of regions are presented.

Region-based caption text extraction

This paper presents a method for caption text detection. The proposed method will be included in a generic indexing system dealing with other semantic concepts which are to be automatically detected as well. To have a coherent detection system, the various object detection algorithms use a common image description. In our framework, the image description is a hierarchical region-based image model. The proposed method takes advantage of texture and geometric features to detect the caption text. Texture features are estimated using wavelet analysis and mainly applied for Text candidate spotting. In turn, Text characteristics verification is basically carry out relying on geometric features, which are estimated exploiting the region-based image model. Analysis of the region hierarchy provides the final caption text objects. The final step of Consistency analysis for output is performed by a binarization algorithm that robustly estimates the thresholds on the caption text area of support.

Prediction of image partitions using Fourier descriptors: application to segmentation-based coding schemes

This paper presents a prediction technique for partition sequences. It uses a region-by-region approach that consists of four steps: region parameterization, region prediction, region ordering, and partition creation. The time evolution of each region is divided into two types: regular motion and shape deformation. Both types of evolution are parameterized by means of the Fourier descriptors and they are separately predicted in the Fourier domain. The final predicted partition is built from the ordered combination of the predicted regions, using morphological tools. With this prediction technique, two different applications are addressed in the context of segmentation-based coding approaches. Noncausal partition prediction is applied to partition interpolation, and examples using complete partitions are presented. In turn, causal partition prediction is applied to partition extrapolation for coding purposes, and examples using complete partitions as well as sequences of binary images--shape information in video object planes (VOPs)--are presented.

Recursive image sequence segmentation by hierarchical models

This paper addresses the problem of image sequence segmentation. A technique using a sequence model based on compound random fields is presented. This technique is recursive in the sense that frames are processed in the same cadency as they are produced. New regions appearing in the sequence are detected by a morphological procedure.

Unsupervised image segmentation controlled by morphological contrast extraction

A novel approach for unsupervised image segmentation is described. This approach makes use of a Gaussian pyramid as multiresolution decomposition to analyze images. Compound random fields are used to model images at each resolution. The hierarchical image model is formed by a Strauss process in the lower level and a set of white Gaussian random fields in the upper level. This basic image model is adapted to the data present at each resolution. Segmentations at coarse resolutions are used to guide segmentations at finest resolutions. Segmentation quality is controlled, at each level, by means of morphological tools. The control procedure is based on the residue between the original image and a morphological center transform. This procedure checks whether the current segmentation contains all the relevant regions in the scene. If not, the algorithm introduces seeds into the segmented image in order to detect the new regions.<<ETX>>

Object detection and segmentation on a hierarchical region-based image representation

In this paper we present a general framework for object detection and segmentation. Using a bottom-up unsupervised merging algorithm, a region-based hierarchy that represents the image at different resolution levels is created. Next, top-down, object class knowledge is used to select and combine regions from the hierarchy, in order to define the exact object shape. We illustrate the usefulness of the approach with four different object classes: sky, caption text, traffic signs and faces.