Showing papers by "Michael G. Strintzis published in 1997"

Object-based coding of stereo image sequences using joint 3-D motion/disparity compensation

Abstract: An object-based coding scheme is proposed for the coding of a stereoscopic image sequence using motion and disparity information. A hierarchical block-based motion estimation approach is used for initialization, while disparity estimation is performed using a pixel-based hierarchical dynamic programming algorithm. A split-and-merge segmentation procedure based on three-dimensional (3-D) motion modeling is then used to determine regions with similar motion parameters. The segmentation part of the algorithm is interleaved with the estimation part in order to optimize the coding performance of the procedure. Furthermore, a technique is examined for propagating the segmentation information with time. A 3-D motion-compensated prediction technique is used for both intensity and depth image sequence coding. Error images and depth maps are encoded using discrete cosine transform (DCT) and Huffman methods. Alternately, an efficient wireframe depth modeling technique may be used to convey depth information to the receiver. Motion and wireframe model parameters are then quantized and transmitted to the decoder along with the segmentation information. As a straightforward application, the use of the depth map information for the generation of intermediate views at the receiver is also discussed. The performance of the proposed compression methods is evaluated experimentally and is compared to other stereoscopic image sequence coding schemes.

Network and data security design for telemedicine applications.

Abstract: The maturing of telecommunication technologies has ushered in a whole new era of applications and services in the health care environment. Teleworking, teleconsultation, mutlimedia conferencing and medical data distribution are rapidly becoming commonplace in clinical practice. As a result, a set of problems arises, concerning data confidentiality and integrity. Public computer networks, such as the emerging ISDN technology, are vulnerable to eavesdropping. Therefore it is important for telemedicine applications to employ end-to-end encryption mechanisms securing the data channel from unauthorized access of modification. We propose a network access and encryption system that is both economical and easily implemented for integration in developing or existing applications, using well-known and thoroughly tested encryption algorithms. Public-key cryptography is used for session-key exchange, while symmetric algorithms are used for bulk encryption. Mechanisms for session-key generation and exchange are also provided.

Coding of video-conference stereo image sequences using 3D models

Abstract: In this paper we propose an object-based stereo image coding algorithm. The algorithm relies on modeling of the object structure using 3D wire-frame models, and motion estimation using globally rigid and locally deformable motion models. Algorithms for the estimation of motion and structure parameters from stereo images are described. Motion parameters are used to construct predicted images at subsequent time instances by mapping the image texture on the object surface. Coding of object parameters, appearing background regions and prediction errors is investigated and experimental results with video-conference scenes are presented. The proposed algorithm is very efficient for applications like stereoscopic video transmission, and is especially suited to advanced applications such as generation and transmission of intermediate views for multiview receiver systems, as well as applications in which an object-wise editing of the bit-stream is required, such as video-production using preanalysed scenes or virtual reality applications.

Three-dimensional camera motion estimation and foreground/background separation for stereoscopic image sequences

Abstract: This work examines the problem of foreground/background extraction when stereoscopic image information is available. A two-stage algorithm is proposed, followed by postprocessing for the estimation of the global motion in the scene and the identification of moving objects. At the first stage, an estimate of the 2-D global motion in the scene is formed which then serves as an initial estimate for the algorithm for a robust 3-D global motion estimate. The 3-D global motion estimation procedure is interleaved with a procedure for removal of the outlier vec- tors from the initial set of training vectors. Postprocessing of the foreground/background map produced results in an improved motion de- tection mask, which may then be used for 3-D motion compensation. © 1997 Society of Photo-Optical Instrumentation Engineers.

Design of CSCW applications for medical teleconsultation and remote diagnosis support.

Abstract: Recent advances in telecommunication technology have permitted the implementation of tools for Computer Supported Cooperative Work (CSCW) based on real time transmission of different information types between two or more stations. The present paper describes methods for the design of both synchronous and asynchronous CSCW procedures suitable for the medical application area and specifically for the purpose of medical teleconsultation and more generally, remote diagnosis support. The experimental implementation of such a CSCW system built upon a Personal Computer/Windows platform is detailed as an example of such a low-cost system suitable for adoption in a wide-range of medical teleconsultation applications.

Network access and data security design for telemedicine applications

Abstract: The maturing of telecommunication technologies has ushered a whole new era of applications and services in the health care environment. Teleworking, teleconsultation, multimedia conferencing and medical data distribution are rapidly becoming commonplace in clinical practice. As a result, a set of problems arises, concerning data confidentiality and integrity. Public computer networks, such as the emerging ISDN technology, are vulnerable to eavesdropping. Therefore it is important for telemedicine applications to employ end-to-end encryption mechanisms securing the data channel from unauthorised access or modification. We propose a network access and encryption system that is both economical and easily implemented for integration in developing or existing applications, using well-known and thoroughly tested encryption algorithms. Public-key cryptography is used for session-key exchange, while symmetric algorithms are used for bulk encryption. Mechanisms for session-key generation and exchange are also provided.

A new automated method for three-dimensional registration of MR images of the head.

Abstract: A new technique for three-dimensional image registration was developed and tested using T1 and T2 weighted Magnetic Resonance image studies of the head. The method uses the fuzzy c-means classification algorithm for outlining the surface contours and then minimizes iteratively the mean squared value of the voxel per voxel weighted ratio of the two trilinearly interpolated cubic voxel volumes. A total of 200 two-dimensional and 240 three-dimensional registration experiments were performed and showed that the method is signal intensity independent, it has registration accuracy better than 1 degree for rotations and 1 voxel for translations and it is not affected by the deterioration in the imaging resolution for voxel sizes up to 1.8 mms.

Motion and disparity estimation using rate-distortion theory for very low bit rate and multiview image sequence coding

Abstract: A rate-distortion framework is used to define a displacement vector-field estimation technique for use in video coding. This technique achieves maximum reconstructed image quality under the constraint of a target bitrate for the coding of the vector sequence. Use of this technique is evaluated for two application areas in which the need for high compression of displacement vector fields in particularly acute. The first is motion-field coding for very low bit rate image sequence transmission as in videophone applications. The second application area is coding for the transmission of disparity fields. This is needed for the generation at the receiver of intermediate viewpoints through spatial interpolation. It is also needed in a number of other applications requiring accurate depth knowledge, including 3D medical data transmission and transmission of scenes to be postprocessed using depth-keyed segmentation. Experimental results illustrating the performance of the proposed technique in these application areas are presented and evaluated.© (1997) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Video coding for wireless varying bit-rate communications based on area of interest and region representation

Abstract: A coding method for videophone communications over wireless, varying bit-rate, channels, is proposed. This method is based on defining one or more areas of interest and breaking them into a number of arbitrarily shaped regions which are homogeneous in their motion. The interest areas in the current implementation are human faces. They are detected with the help of a 2D scene model which is a-priori constructed and is based on knowledge of the application context. A mixed intra/inter-frame coding method is used for the description of the shape and topology of the regions where each polygonal vertex is encoded in a costless manner, either with regards to its predecessor in the same frame, or to the corresponding vertex in the previous frame. This coding is based on rate/distortion optimization constrained by the instantaneously available bit-rate. The error coding is also performed in an adaptive prioritized manner and is restricted within the detected areas of interest.

Use of Object Articulation and Motion Estimation for Video Production

Abstract: This paper describes a procedure for stereo video production using model-based processing of both left and right channels of a stereoscopic image sequence. The proposed scheme uses an original video and the first / basic frame of a video to be produced according to the original one. A 3D model is created first for both the original and the basic images using consistent depth information. Robust classification techniques are then used to obtain an articulated description of the foreground of the scene (head, neck, shoulders). The object articulation procedure is based on a novel scheme for the segmentation of the rigid 3D motion fields of the triangle patches of the 3D model object. This procedure is applied for both the original and basic images resulting to corresponding sub-objects of the two images. The rigid 3D motion is then re-computed for each sub-object of the original image sequence and finally, the motion parameters produced for each sub-object of the original video are applied to the corresponding sub-objects of the first image of the video to be produced. The model of the produced image is moved according to the original one and the result is a new video with the same motion but different shape, size and texture than the original one. The described method is demonstrated over two stereoscopic videoconference image sequences.

Neural nonlinear classifiers with synaptic weight commitment

Abstract: We develop a theory for immediately detecting patterns violating linear separability in a training set, as soon as they are presented to the classifier. The theory is based on the computation of the solution cone in the weight space of a single linear threshold unit (LTU). The separability-violating patterns can be skipped and in the end, we obtain a linearly separable subset of the original training set together with the subset's solution cone. We further propose an iterative algorithm for computing the solution cone and we introduce the concept of garbage collection for removing redundancy from the cone representation. The algorithm can be implemented by a novel neural network architecture where the synaptic weights have constant values throughout the life of the synapse. We show that by combining multiple such models we can construct a larger network capable of learning the classification boundaries of convex classes, therefore solving an important class of nonlinearly separable problems.