Deep learning methods for object detection in smart manufacturing: A survey

Abstract

Object detection for industrial applications refers to analyzing the captured images and videos and finding the relationship between the detected objects for better optimization, data mining for decision making, and improved system performances. The dawn of the Internet of Things and the massive deployment of electronic sensors in the industrial floor lines, such as vision, opened new horizons for the analytics tools for processing. Fundamentals of Computer Vision are being used for analyzing big manufacturing data. Deep learning-based methods have recently overcome the problems existing in traditional methods by constructing deep Convolutional Neural Networks that extract multiple low-level and high-level features from the massive volume of labeled and unlabeled data. This paper presents a comprehensive survey of deep learning-based state-of-the-art object detection methods. It discusses their applications in an industrial setting where human workers perform specific tasks using different tools on assembly lines. Firstly, object detection methods using deep learning are discussed while their advantage over traditional methods is introduced. The current techniques for object detection algorithms and their deployment in industrial applications are also discussed. Lastly, challenges and future trends associated with object detection using deep learning are summarized with potential research on improving object detection for smart industrial manufacturing.