This paper describes ReVision , a software engineering methodology and a support ing computer enivornment for parallel computations based on the behavior-oriented formalism. A key feature provided by the environment is support for multiple views of the problem. Two levels of data transformation are supported: metamodeling and modeling. At the metamod-eling level, methods used to construct diier...

Constructive Solid Geometry (CSG) has been used in several model-based vision programs, most notably in ACRONYM. This paper examines some of the problems that arise with CSG and proposes constraints that make CSG a unique representation of scenes. It is also suggested that Additive Constructive Solid Geometry (ACSG) is more useful for vision because it leads to simpler computation of connectivi...

In this paper we present the PC cluster built at R.V. College of Engineering (with great help from the Department of Computer Science and Electrical Engineering). The structure of the cluster is described and the performance is evaluated by rendering of complex 3D Persistence of Vision (POV) images by the Ray-Tracing algorithm. Here, we propose an unexampled method to render such images, distri...

In this paper we present a visual navigation system for retrieving untethered autonomous underwater vehicle (AW). The vision qstern guides the .4LV into a retriever which is a tethered underwater robot. The visual navigation modules include target searchin& line tracking, and positioning. The vision system is a dedicated parallel image processor composed of three T800 (Transputer). The processi...

We investigate dual decomposition approaches for optimization problems arising in low-level vision. Dual decomposition can be used to parallelize existing algorithms, reduce memory requirements and to obtain approximate solutions of hard problems. An extensive set of experiments are performed for a variety of application problems including graph cut segmentation, curvature regularization and mo...

This paper is a theoretical and experimental study of how interval arithmetic and analysis methods can be used to achieve (1) numerical certification of the kinematic calibration of parallel robots, and (2) a possible validation of the kinematic model used in calibration. First, a detailed description is given of our experimental device and vision-based measurement method. The usual calibration...

A novel reconfigurable architecture based on a multiring multiprocessor network is described. The reconfigurability of the architecture is shown to result in a low network diameter and also a low degree of connectivity for each node in the network. The mathematical properties of the network topology and the hardware for the reconfiguration switch are described. Primitive parallel operations on ...

In this paper a consistent and efficient but yet convenient system for parallel computer vision, and in fact also realtime actuator control is proposed. The system implements the multi-agent paradigm and a blackboard information storage. This, in combination with a generic interface for hardware abstraction and integration of external software components, is setup on basis of the message passin...

Previous matching algorithms have achieved high speeds through algorithm simplification and/or relied on custom hardware. The objective of our work has been the development a robust high-speed stereo matcher by exploiting parallel algorithms executing on general purpose SIMD machines. Our approach is based on several existing techniques dealing with the classification and evaluation of matches,...

We present a semi-interactive method for 3D reconstruction specialized for indoor scenes which combines computer vision techniques with efficient interaction. We use panoramas, popularly used for visualization of indoor scenes, but clearly not able to show depth, for their great field of view, as the starting point. Exploiting user defined knowledge, in term of a rough sketch of orthogonality a...