An Autonomous Vision-based Shelf-reader Robot using Faster R-CNN

Congrats and thanks to Mr. Amin Karimi and Mr. Hossein Rezaei for their collaborations on our recently accepted paper with the title of "An Autonomous Vision-based Shelf-reader Robot using Faster R-CNN" in a prestigious peer-reviewed journal of Industrial Robot.

 

In this work, we proudly received the help and support of Prof. Craig Yu, Mr. Michael Solah, and Prof. Maryam Ehteshamzadeh. We sincerely thanks all of them.

 

Abstract

An essential task in library maintenance is shelf-reading, which refers to the process of checking the disciplines of books based on their call numbers to ensure that they are correctly shelved. Shelf-reading is a routine yet challenging task for librarians, as it involves controlling call numbers on the scale of thousands of books promptly. Leveraging the strength of autonomous robots in handling repetitive tasks, we introduce a novel vision-based shelf-reader robot, called Pars, and demonstrate its effectiveness in accomplishing shelf-reading tasks. Also, we propose a novel supervised approach to power the vision system of Pars, allowing it to handle motion blur on images captured while it moves. An approach based on Faster R-CNN is also incorporated into the vision system, allowing the robot to efficiently detect the region of interest (ROI) for retrieving a book's information. We evaluated the robot's performance in a library with 120,000 books and discovered problems such as missing and misplaced books. Besides, we introduce a new challenging dataset of blurred barcodes free publicly available for similar researches. Our robot is equipped with six parallel cameras which enable it to check books and decide moving paths. Through its vision-based system, it is also capable of routing and tracking paths between bookcases in a library, and it can also turn around bends. Moreover, Pars addresses the blurred barcodes which may appear due to its motion.

 

Full paper on publisher site:  https://doi.org/10.1108/IR-10-2020-0225

Or: https://www.emerald.com/insight/content/doi/10.1108/IR-10-2020-0225/full/html

The Author Accepted Manuscript (AAM) version of our paper can be used for non-commercial purposes under CC BY-NC licence (more details) from here (main paper).


Home  |  Contact me  |  About me  | Mahdi Jampour 2008 ©