Vision-based Human Presence Detection by Means of Transfer Learning Approach

Tang, Jin Cheng and Ahmad Fakhri, Ab. Nasir and Anwar, P. P. Abdul Majeed and Mohd Azraai, Mohd Razman and Ismail, Mohd Khairuddin and Thai, Li Lim (2022) Vision-based Human Presence Detection by Means of Transfer Learning Approach. In: Enabling Industry 4.0 through Advances in Mechatronics. Lecture Notes in Electrical Engineering, 900 . Springer, Singapore, Singapore, pp. 571-580. ISBN 978-981-19-2094-3 (Printed); 978-981-19-2095-0 (Online)

Pdf Vision-Based Human Presence Detection by Means of Transfer Learning Approach.pdf - Published Version Restricted to Repository staff only Download (437kB) | Request a copy

Abstract

Human–robot interaction (HRI) and human–robot collaboration (HRC) has become more important as the industries are stepping towards the phase of digitalization and Industry 4.0. Indeed, the emphasis is often placed on the safety of the physical well-being of the human workers. To safeguard the human operators from being hurt by the robots or collaborative robots (cobots), a traditional method is to isolate the robots from the human workers by means of fences and sensors. However, the deployment of deep learning models is unknown and shown to be non-trivial in downstream tasks such as image classification and object detection. The present study aimed to exploit the effectiveness of object detection models, particularly EfficientDet models via a transfer learning approach—fine-tuning. A total of 1463 images were obtained from the surveillance cameras from TT Vision Holdings Berhad and split into training, validation, and test by a ratio of 70:20:10. The training images were further augmented using horizontal flip and scale jittering techniques to increase the total training images up to 3072 images. As an outcome, the result revealed that the EfficientDet-D2 fine-tuned model achieved a test AP of 81.70% with an inference speed of 97.06 ms on Tesla T4 while the EfficientDet-D0 fine-tuned model attained a test AP of 69.30% with an inference speed of 30.24 ms on Tesla T4. In comparison between the EfficientDet-D0 fine-tuned model and EfficientDet-D2 fine-tuned model, the performance improved in terms of AP with the inference speed as the trade-off. The research has shown that it is feasible to detect the presence of human workers and can possibly serve as the visual perception of the robot with regards to human presence detection. Last but not least, the present work proved the applicability of transfer learning methods in human presence detection, specifically fine-tuned object detection models.

Item Type:	Book Chapter
Uncontrolled Keywords:	Deep learning; EfficientDet; Transfer learning; Fine-tuning; Human detection
Subjects:	Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering
Faculty/Division:	Faculty of Manufacturing and Mechatronic Engineering Technology Institute of Postgraduate Studies Faculty of Computing
Depositing User:	Dr. Ahmad Fakhri Ab. Nasir
Date Deposited:	09 Mar 2023 04:41
Last Modified:	09 Mar 2023 04:41
URI:	http://umpir.ump.edu.my/id/eprint/37059
Download Statistic:	View Download Statistics

Actions (login required)

View Item