A Stereo Matching System

A Stereo Matching System

Yingpeng Yang (Changzhou Vocational and Technical College, Cangzhou, China)
DOI: 10.4018/japuc.2013040101
OnDemand PDF Download:
No Current Special Offers


Determination of the depth of the image feature distinctive automation and other industries of machine vision and computer vision technology in everyday life are becoming increasingly popular. Some techniques have been proposed to extract from the current depth of a 2D image of the feature, which defines a particular object or structure of the information. In many cases, these techniques are automatic, such as a suitable carrier moving average depth identify objects placed in the 2D image. For this intensive depth cues to solve two stereo matching algorithm using a machine learning algorithm. Other methods, relative to the camera based on the motion of the object have been proposed and analyzed by estimating the optical flow calculation depth map. The method of dense and sparse three-dimensional surface of the object to provide the three-dimensional information. This paper discusses the evaluation of the depth cues, through intensive two standard fast algorithm for real-time stereo image matching algorithm.
Article Preview

1. Introduction

Three dimensional reconstruction of three-dimensional images and video scene analysis and computer vision, machine vision is an important step forward. Automation requires three-dimensional structure modeling environment. Can be classified as a measurement-based or rule-based approach. Rule-based approach uses compact rules or regulations, is used to create three-dimensional environment model. L-system is a well-known rule-based modeling method, which is widely used in the movement of a vehicle or slow growth for mechanical systems (Kolbe, 2009). Rule-based method, although capable of synthesizing an impressive natural environment, it is difficult to produce, if there are more symmetric model is very similar to the real-world conditions (Bleyer & Gelautz, 2007). Measurement-based method to directly measure samples from analog environmental parameters, and then simulate it. There are several ways to accomplish this task. Traditionally, a priori known environment to create and use a tape measure and a protractor geometry. This tool is the easiest, and that process is the most difficult, the result is not accurate (Markovic & Gelautz, 2006). Nowadays, more and more research has focused on using a digital camera, 3D digital model, and then rebuild a more accurate measurement standards built environment. However, the data processing is more complex than the traditional way (Stamos & Allen, 2002). Rapid City Regional System based on the introduction of the three-dimensional scene reconstruction of three-dimensional images of automatic data collection systems and processing pipeline. The system collects multiple video streams, as well as camera calibration measurements, in order to rebuild the model mapping coordinate system (Biber, Fleck, & Staneker, 2005). In addition to both the geometry and appearance of high quality, it is aimed at real-time performance. Processing pipeline, even if it is from the real time, the choice of technology and design processing modules can achieve fast performance of the image processing system related to the plurality of CCD image sensor and a dense two-frame intended for the near real-time performance the future. The algorithm is in a real video sequence captured test bench design and draw conclusions. The paper is organized as follows: Section 2 is related work methods and contributions, and the Section 3 defined pattern provides an overview. Section 4 is the proposed method intensive two stereo matching algorithm to define the imaging sensor depth cues. Section 5 describes the experimental apparatus system overview. Section 6 is grabbed from the environmental assessment results real-time image quality. Section 7 is summary and future work.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing