An adapted vision measurement method for package volume based on Kinect

In this paper, we present a method for measuring package volume with multi-source vision sensor — Kinect. Firstly, the foreground segmentation and the algorithm of minimum-area bounding rectangle are used to computed the package dimensions. Secondly, the height of package is obtained by background subtraction method. Finally, the package volume is calculated by integration method. The experimental results show that the relative error is less than 4.10%, which improves the efficiency and accuracy of package volume measurement. This method has the features of non-contact and non-stop run. It can be adapted to different applications.

[1]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[2]  Feng Fa.  A Visual Measurement Algorithm of Vehicle Length , 2015 .

[3]  Rahul Nair,et al.  A State of the Art Report on Kinect Sensor Setups in Computer Vision , 2013, Time-of-Flight and Depth Imaging.

[4]  Rafael C. González,et al.  Digital image processing using MATLAB , 2006 .

[5]  Yonghua Chen,et al.  Determining parting direction based on minimum bounding box and fuzzy logics , 1997 .

[6]  Pushmeet Kohli,et al.  When Can We Use KinectFusion for Ground Truth Acquisition , 2012 .

[7]  Jana Abhijit.  Kinect for Windows SDK Programming Guide , 2012 .

[8]  Rafael C. González,et al.  Local Determination of a Moving Contrast Edge , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Chi-Ren Shyu,et al.  A system for limb-volume measurement using 3D models from an infrared depth sensor , 2013, 2013 IEEE Symposium on Computational Intelligence in Healthcare and e-health (CICARE).

[10]  Herbert Freeman,et al.  Determining the minimum-area encasing rectangle for an arbitrary closed curve , 1975, CACM.

[11]  Wan Ya.  3D Body Scanning Measurement Techniques Based on Kinect , 2015 .

[12]  Andreas Kolb,et al.  Kinect range sensing: Structured-light versus Time-of-Flight Kinect , 2015, Comput. Vis. Image Underst..

[13]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Suat Karakaya,et al.  Image processing based package volume detection with Kinect , 2015, 2015 23nd Signal Processing and Communications Applications Conference (SIU).