Paper Title:

Design and Implementation of a Computer Vision Based Inspection System Using CUDA

Periodical Advanced Materials Research (Volumes 383 - 390)
Main Theme Manufacturing Science and Technology
Edited by Wu Fan
Pages 18-24
DOI 10.4028/www.scientific.net/AMR.383-390.18
Citation Yan Shi et al., 2011, Advanced Materials Research, 383-390, 18
Online since November, 2011
Authors Yan Shi, Ai Guo Li, Lin Wang
Keywords Automated Inspection, Automobile, Computer Vision, CUDA, Hardware-in-Loop, Instrument Cluster
Price US$ 28,-
Article Preview
View full size
Abstract

In the production process of electronic Instrument Clusters (IC) used in automobiles, a need for automated inspection of dynamic characteristics is identified. An inspection system based on hardware-in-loop emulation and computer vision using Computer Unified Device Architecture (CUDA) is proposed. The system generates network signals that emulate a real vehicle, sends the signals to an IC to turn it into various work conditions, captures the IC’s response into a graphic processing unit for real-time computer-vision processing and records inspection results into databases. An implementation of the design and performance analysis is provided.