WorldCat Linked Data Explorer

Turtle N-Triple JSON-LD RDF/XML HTML Contact Us Home

http://worldcat.org/entity/work/id/377947390

Parallel Algorithms for Computer Vision

The main effort in this project has been directed towards the development of an integrated vision system, - the Vision Machine - based on a parallel supercomputer. The core of the Vision Machine is in fact a set of parallel algorithms for visual recognition and navigation in an unstructured environment. The present version of the Vision Machine has been demonstrated to process images in close to real time by (1) computing first several low-level cues, such as edges, stereo disparity, optical flow, color and texture, (2) integrating them to extract a cartoon-like description of the scene in terms of the physical discontinuities of surfaces, and (3) using this cartoon in a recognition stage, based on parallel model matching. In addition to the development of the parallel algorithms, their implementation and testing, we have also done substantial work in several areas that are very closely related. These include (1) design and fabrication of VLSI circuits to transfer to potentially cheap and fast hardware some of the software algorithms, (2) initial development of techniques to synthesize by learning vision algorithms, and (3) several projects involving autonomous navigation of small robots.

Open All Close All

type

about

http://schema.org/about

contributor

description

http://schema.org/description

  • "The main effort in this project has been directed towards the development of an integrated vision system, - the Vision Machine - based on a parallel supercomputer. The core of the Vision Machine is in fact a set of parallel algorithms for visual recognition and navigation in an unstructured environment. The present version of the Vision Machine has been demonstrated to process images in close to real time by (1) computing first several low-level cues, such as edges, stereo disparity, optical flow, color and texture, (2) integrating them to extract a cartoon-like description of the scene in terms of the physical discontinuities of surfaces, and (3) using this cartoon in a recognition stage, based on parallel model matching. In addition to the development of the parallel algorithms, their implementation and testing, we have also done substantial work in several areas that are very closely related. These include (1) design and fabrication of VLSI circuits to transfer to potentially cheap and fast hardware some of the software algorithms, (2) initial development of techniques to synthesize by learning vision algorithms, and (3) several projects involving autonomous navigation of small robots."@en
  • "The time period covered is the second year that we have had the Connection Machine (CM) Available to us. During the same period of time, we successfully demonstrated the Vision Machine system processing images and recognizing objects through the integration of several visual cues. The first version of the Vision Machine system, which is based on the CM and uses an Eye-Head robot as an input device, is now complete and functional. In parallel with the development of the Vision Machine, we have also continued to study the performance of alternative, nonconventional architectures for navigation. The body of this report gives an overview of the results of our research during the third year of funding. Details can be found in the appendices. Computer vision, Parallel algorithms, Computer architectures. (JES)."@en

name

http://schema.org/name

  • "Parallel Algorithms for Computer Vision"@en

workExample