A Real-time Range Finding System with Binocular Stereo Vision

Abstract

To acquire range information for mobile robots, a TMS320DM642 DSP-based range finding system with binocular stereo vision is proposed. Firstly, paired images of the target are captured and a Gaussian filter, as well as improved Sobel kernels, are achieved. Secondly, a feature-based local stereo matching algorithm is performed so that the space location of the target can be determined. Finally, in order to improve the reliability and robustness of the stereo matching algorithm under complex conditions, the confidence filter and the left-right consistency filter are investigated to eliminate the mismatching points. In addition, the range finding algorithm is implemented in the DSP/BIOS operating system to gain real-time control. Experimental results show that the average accuracy of range finding is more than 99% for measuring single-point distances equal to 120cm in the simple scenario and the algorithm takes about 39ms for ranging a time in a complex scenario. The effectivity, as well as the feasibility, of the proposed range finding system are verified.

Stereo kamera sisteminde aykırılık haritaları yardımıyla nesne uzaklıklarının tespit edilmesi

“…Lai ve ark. [9] mobil robotlarda uzaklık bilgisini elde etmek için TMS320DM642 DSP tabanlı bir stereo görme sistemi tasarlamışlardır.…”

3D Size-Estimation based on the Geodesic Distance Measured by Photogrammetric Scanning Device

“…The problem of approximating 3D sizes and geodesic distances has been investigated from numerous perspectives by researchers. For instance, some of the strategies from the latter list are developed on the basis of binocular stereo vision [1]. Some others are concerned with devising indices representing anthropomorphic biometric characteristics via home-based imaging approaches [2], which requires taking images of the body with different orientations of the camera, and subsequently, reconstructing the whole body by means of image processing techniques with the consistency between the different segments of the silhouettes as the objective of the optimization algorithm.…”

“…In what follows, a summary of the details, along with the outstanding advantages and disadvantages, of the most recent studies carried out in the foregoing field is provided, in order to illustrate the current state of the art, as well as to clarify the prospective contributions of the strategy proposed in this paper to the ones that are either directly connected with it or could well benefit from appropriately extending it. One of the studies that has tried to develop a methodology aiming at solving the range finding problem is [1], which concentrates, particularly, on taking into account the specifications of mobile robots, by means of DSP, through utilizing the so-called "binocular stereo vision". The algorithm is devised such that first paired images of the target objects are captured, which are processed using Gaussian filter and improved Sobel kernels.…”

Accurate 3D measurement using optical depth information

“…In what follows, a selection of the studies conducted in the foregoing field is briefly reviewed so as to provide a background to the approach proposed and implemented in this Letter. In [1], the focus is specifically on finding the range for mobile robots through DSP (digital signal processing) with the so-called 'binocular stereo vision'. The proposed methodology consists in capturing paired images of the target, along with Gaussian filter and improved Sobel kernels, and then determining its location through implementing feature-based local stereo matching.…”