Abstract

The automation of pallet recognition and localization is a widely investigated and sought topic, notably for forklift robots and pallet-picking instruments. Pallets are essential in warehouses and retail establishments. However, pallet recognition and pallet localization can be time-consuming and prone to errors, which can result in reduced efficiency and safety hazards. To address this, we develop the Pallet Detection System, a computer vision mechanism that detects and locates the coordinates of pallets in the environment, reducing errors and increasing warehouse efficiency. To achieve this, we are using computer vision algorithm YOLOX which is trained by large number of dataset images of pallets and non-pallet objects to optimize its accuracy in recognizing pallets in real time object. We have used a Python framework to support the pallet detection process and connected external webcams to obtain the location of pallets. This system reduces risk in warehouse, which increases the safety, reduces time complexity and optimizes the warehouse operations.

Keyworde: YOLOX, pallet detection system, python framework, warehouse operations, automated guided vehicles, real-time detection

Full Text PDF

Refrences:

1. Iinuma R, Hori Y, Onoyama H, Fukao T, Kubo Y. Pallet Detection and Estimation for Fork Insertion with RGB-D Camera. In 2021 IEEE International Conference on Mechatronics and Automation (ICMA). 2021 Aug 8; 854–859.
2. Molter B, Fottner J. Real-time pallet localization with 3d camera technology for forklifts in logistic environments. In 2018 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI). 2018 Jul 31; 297–302.
3. Garibott G, Masciangelo S, Ilic M, Bassino P. Robolift: a vision guided autonomous fork-lift for pallet handling. In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS’96. 1996 Nov 8; 2: 656–663.
4. Seelinger M, Yoder JD. Automatic visual guidance of a forklift engaging a pallet. Robot Auton Syst. 2006 Dec 31; 54(12): 1026–38.
5. Horng JR, Yang SY, Wang MS. Object localization and depth estimation for eye-in-hand manipulator using mono camera. IEEE Access. 2020 Jul 8; 8: 121765–79.
6. Syrjänen A. Experimental evaluation of depth cameras for pallet detection and pose estimation. Master’s thesis. Finland: Tampere University; 2021.
7. Zhao J, Li B, Wei X, Lu H, Lü E, Zhou X. Recognition and Location Algorithm for Pallets in Warehouses Using RGB-D Sensor. Appl Sci. 2022 Oct 13; 12(20): 10331.
8. Zaccaria M, Monica R, Aleotti J. A comparison of deep learning models for pallet detection in industrial warehouses. In 2020 IEEE 16th international conference on intelligent computer communication and processing (ICCP). 2020 Sep 3; 417–422.
9. Oh JY, Choi HS, Jung SH, Kim HS, Shin HY. Development of pallet recognition system using kinect camera. Int J Multimedia Ubiquitous Eng. 2014 Apr; 9(4): 227–32.
10. Kita Y, Takase R, Komuro T, Kato N, Kita N. Detection and localization of pallets on shelves using a wide-angle camera. In 2019 19th IEEE International Conference on Advanced Robotics (ICAR). 2019 Dec 2; 785–792.
11. Ge Z, Liu S, Wang F, Li Z, Sun J. Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430. 2021 Jul 18.
12. Zhang Z. A flexible new technique for camera calibration. IEEE Trans Pattern Anal Mach Intell. 2000 Nov; 22(11): 1330–4.
13. Torr PH, Zisserman A. MLESAC: A new robust estimator with application to estimating image geometry. Comput Vis Image Underst. 2000 Apr 1; 78(1): 138–56.
14. Li T, Huang B, Li C, Huang M. Application of convolution neural network object detection algorithm in logistics warehouse. J Eng. 2019 Dec; 2019(23): 9053–8.
15. Xiao J, Lu H, Zhang L, Zhang J. Pallet recognition and localization using an RGB-d camera. Int J Adv Robot Syst. 2017 Nov 23; 14(6): 1729881417737799.
16. Baglivo L, Biasi N, Biral F, Bellomo N, Bertolazzi E, Da Lio M, De Cecco M. Autonomous pallet localization and picking for industrial forklifts: a robust range and look method. Meas Sci Technol. 2011 Jul 7; 22(8): 085502.
17. Mohamed IS, Capitanelli A, Mastrogiovanni F, Rovetta S, Zaccaria R. A 2D laser rangefinder scans dataset of standard EUR pallets. Data Brief. 2019 Jun 1; 24: 103837.
18. Mohamed IS, Capitanelli A, Mastrogiovanni F, Rovetta S, Zaccaria R. Detection, localisation and tracking of pallets using machine learning techniques and 2D range data. Neural Comput Appl. 2020 Jul; 32: 8811–28.
19. Pages J, Armangué X, Salvi J, Freixenet J, Martí J. A computer vision system for autonomous forklift vehicles in industrial environments. In Proc of the 9th Mediterranean Conference on Control and Automation MEDS. 2001 Jun 27; 1–6.
20. Chen G, Peng R, Wang Z, Zhao W. Pallet recognition and localization method for vision guided forklift. In 2012 IEEE 8th International Conference on Wireless Communications, Networking and Mobile Computing. 2012 Sep 21; 1–4.