access icon openaccess Cargo pallets real-time 3D positioning method based on computer vision

This is an open access article published by the IET under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/)
Received 11/10/2018, Accepted 09/01/2019, Published 25/03/2019

In storage environment, aiming at the problem of goods positioning when picking, the pallet is firstly recognised based on deep learning. Then, algorithm of obtaining the pose of the pallet by the image processing and Kinect sensor is proposed in this study. The pallet is recognised and its selected box is obtained by deep learning. On this basis, the position and the angle of the pallet are obtained by the image processing method, and then RGB-D transforms the position and posture of the pallet into the three-dimensional (3D) coordinate for three-dimensional positioning. The experiment results show that the algorithm can obtain real-time pallet position with the success rate of 81.02%. Thus, the algorithm can meet the requirements of the efficiency and accuracy location requirements of the storage of goods when picking.

Inspec keywords: computerised instrumentation; image colour analysis; transforms; learning (artificial intelligence); goods distribution; freight handling; position measurement; image recognition; image sensors; computer vision

Other keywords: storage environment; cargo pallet real-time 3D positioning method; image processing method; Kinect sensor; goods positioning; deep learning; cargo pallet real-time three-dimensional positioning method; computer vision; RGB-D transforms; real-time cargo pallet position method

Subjects: Computerised instrumentation; Computer vision and image processing techniques; Computerised instrumentation; Spatial variables measurement; Image recognition; Integral transforms; Integral transforms; Spatial variables measurement; Image sensors; Function theory, analysis; Knowledge engineering techniques

References

    1. 1)
      • 5. Xie, Z.M., Gao, X.D.: ‘The edge extraction technology of weld image based on Canny operator’, Weld. J., 2006, (1), pp. 29–32 + 36 + 114.
    2. 2)
      • 11. Ye, R.Z.: ‘Investigation of 3D reconstruction technique base on that depth sensor of the Kinect’ (Huananligong University, China, 2013).
    3. 3)
      • 3. Liu, W., Anguelov, D., Erhan, D., et al: ‘SSD: single shot multibox detector’. European Conf. Computer Vision, Amsterdam, Netherlands, 2016, pp. 21–37.
    4. 4)
      • 6. Kang, J.X.: ‘Design and realization of license plate recognition system based on image’ (Jilin University, China, 2014).
    5. 5)
      • 10. Sui, H.Y.: ‘Investigation of erosion mechanism and protective technique for expansion joint of chemical pipelines’ (Daqing petroleum college, China, 2009).
    6. 6)
      • 9. Zhao, W.W.: ‘Based on the improved Hough transform detection method’, Manuf. Autom., 2010, (6), pp. 243–246.
    7. 7)
      • 2. Zheng, Y.F., Zhang, X.W., Cao, T.Y., et al: ‘The application of deep convolution neural network in image segmentation’, Military Commun. Technol., 2016, (2), pp. 98–104.
    8. 8)
      • 1. Xue, Y.J.: ‘Research on simulation and application of warehouse and logistics system’ (Dongnan University, China, 2006).
    9. 9)
      • 15. Xia, W.L., Gu, Z.P., Yang, T.S.H.: ‘The realization of real-time 3d reconstruction algorithm – based on the 3D reconstruction of the Kinect and the single vision SLAM’, Comput. Eng. Applic., 2014, (24), pp. 199–203.
    10. 10)
      • 12. Fan, Z.: ‘3D reconstruction based on Kinect’ (Xidian University, China, 2013).
    11. 11)
      • 14. Zhang, Z.: ‘Flexible camera calibration by viewing a plane from unknown orientations’. Proc. 7th Int. Conf. Computer Vision, Greece, Corfu, 1999, pp. 666–673.
    12. 12)
      • 8. Hu, B., Zhao, C.H.X.: ‘Fast lane line detection method based on probabilistic Hough transform’, Microelectron. Comput., 2011, (10), pp. 177–180.
    13. 13)
      • 4. Simonyan, K., Zisserman, A.: ‘Very deep convolutional networks for large-scale image recognition’, arXiv preprint arXiv, 2014, pp. 1409–1556.
    14. 14)
      • 7. Liu, G.Q., Zheng, X.S.H., Zhang, X.B.: ‘The license plate localization algorithm based on image texture feature extraction’, J. Chinese Image Graphics, 2005, (11), pp. 1419–1422.
    15. 15)
      • 13. Deng, R.: ‘The study and implementation of the gesture recognition system for the 3D scene video conference’ (Shanghai Jiaotong University, China, 2013).
http://iet.metastore.ingenta.com/content/journals/10.1049/joe.2018.9053
Loading

Related content

content/journals/10.1049/joe.2018.9053
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading