Automatic measurement based on stereo vision system using a single PTZ camera

A parallel binocular stereo vision system and its application to dimensional measurement is introduced in this paper. The proposed system is established by controlling a single PTZ (pan-tilt-zoom) camera linear motion on a one dimensional precision displacement platform. To achieve accurate measurement results, an improved matching algorithm called as DC-SURF (Distortion Compensated-Speeded Up Robust Feature) by using adaptative filtering in terms of the image distortion during generating scale space is presented. Furthermore, the classic eight-point algorithm and the designed zoom strategy for PTZ camera are adopted for the measurement. The experimental results show that the proposed matching algorithm has better performance than other two classic matching algorithms over distorted images. Furthermore, the experiments demonstrate that without any reference materials the stereo vision dimensional measurement system proposed in this paper can be successfully applied to human height measurement with high precision. The results indicate a potential possibility of our approach to be used in other computer vision applications.

[1]  Yun-Su Chung,et al.  A 3D object measurement method using a single view camera , 2015, 2015 International Conference on Information and Communication Technology Convergence (ICTC).

[2]  Cheng Yang.  Structure Design of Binocular Vision Sensor Using Mono-camera with Mirrors , 2011 .

[3]  H. C. Longuet-Higgins,et al.  A computer algorithm for reconstructing a scene from two projections , 1981, Nature.

[4]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[5]  Cordelia Schmid,et al.  A Performance Evaluation of Local Descriptors , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Michael Petrov,et al.  Optical 3D Digitizers: Bringing Life to the Virtual World , 1998, IEEE Computer Graphics and Applications.

[7]  Takeo Kanade,et al.  A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[9]  M. Okutomi,et al.  A simple stereo algorithm to recover precise object boundaries and smooth surfaces , 2001, Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001).

[10]  Richard I. Hartley,et al.  In Defense of the Eight-Point Algorithm , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Wilfried Brauer,et al.  Intensity- and Gradient-Based Stereo Matching Using Hierarchical Gaussian Basis Functions , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Andrew W. Fitzgibbon,et al.  Simultaneous linear estimation of multiple view geometry and lens distortion , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[14]  C. Cristalli,et al.  Stereo Vision System for Accurate 3D Measurements of Connector Pins’ Positions in Production Lines , 2016, Experimental Techniques.

[15]  Hassan Foroosh,et al.  Optimizing PTZ camera calibration from two images , 2012, Machine Vision and Applications.

[16]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[17]  Yan Yuan,et al.  Image quality assessment using full-parameter singular value decomposition , 2011 .