A Novel Approach to Generate Dataset for Object Detection in Assembly Lines
Published in Proc. International Conference on Mechanical, Automotive and Mechatronics Engineering (ICMAME 2023), 2023
This paper presents a deep learning approach to automate quality assurance in vehicle assembly, focusing on detecting cross marks on vehicle chassis. The researchers used the YOLOv5 model, adapting its architecture and parameters for this specific task. Achieved high accuracy, with a mean average precision (mAP) of 98% or higher, demonstrating the potential of deep learning to improve precision and reduce errors in vehicle assembly quality control.
Recommended citation: Ramesh kaki, samarth Soni, Sandip Deshmukh, Tathagata Ray, Chandu Parimi, A Novel Approach to Generate Dataset for Object Detection in Assembly Lines, Proc. International Conference on Mechanical, Automotive and Mechatronics Engineering (ICMAME 2023).
Download Paper