A Development of Object Position Information Extraction Algorithm using Stereo Vision

Model Based Object Recognition using Stereo Vision

Model-Based Object Tracking Using Stereo Vision

Robust and accurate object recognition and tracking is a necessary pre-requisite for visual servoing tasks. While most approaches use monocular vision in order to solve this problem, this paper presents a new approach using disparity images provided by a stereo vision system from which 3-D models are reconstructed. We use a segmentation procedure based on a simple region growing process to segm...

Object Discrimination Using Stereo Vision for Blind through Stereo Sonification

In this paper, a development of image processing, stereovision methodology and a sonification procedure for image sonification system for vision substitution are presented. The hardware part consists of a sunglass fitted with two mini cameras, laptop computer and stereo earphones. The image of the scene in front of blind people is captured by stereo cameras. The captured image is processed to e...

Parallel Stereo Vision Algorithm

Integrating a stereo-photogrammetric robot head into a real-time system requires software solutions that rapidly resolve the stereo correspondence problem. The stereo-matcher presented in this paper uses therefore code parallelisation and was tested on three different processors with x87 and AVX. The results show that a 5mega pixels colour image can be matched in 5,55 seconds or as monochrome i...

Object Tracking with Stereo Vision

Task directed, active vision techniques are beginning to produce vision systems capable of providing real-time depth perception for robots. The concepts of shallow disparity filters and coarse disparity segmentation show particular promise for several reasons: they require minimal correlation search, thus they are fast; they employ redundant measurements, so they are noise tolerant; and they ar...