Affiliation:
1. Faculty of Science, Agriculture and Engineering, SIT Building at Nanyang Polytechnic Singapore, Newcastle University in Singapore, Singapore 567739, Singapore
Abstract
Pick-and-place operations are an integral part of robotic automation and smart manufacturing. By utilizing deep learning techniques on resource-constraint embedded devices, the pick-and-place operations can be made more accurate, efficient, and sustainable, compared to the high-powered computer solution. In this study, we propose a new technique for object detection on an embedded system using SSD Mobilenet V2 FPN Lite with the optimisation of the hyperparameter and image enhancement. By increasing the Red Green Blue (RGB) saturation level of the images, we gain a 7% increase in mean Average Precision (mAP) when compared to the control group and a 20% increase in mAP when compared to the COCO 2017 validation dataset. Using a Learning Rate of 0.08 with an Edge Tensor Processing Unit (TPU), we obtain high real-time detection scores of 97%. The high detection scores are important to the control algorithm, which uses the bounding box to send a signal to the collaborative robot for pick-and-place operation.
Reference39 articles.
1. (2024, January 03). Singapore Busineess Review. Available online: https://sbr.com.sg/information-technology/news/time-saving-top-benefit-ai-singaporean-businesses-zoom.
2. Lin, T.Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2017, January 22–29). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.
3. Aamir, S.M., Ma, H., Khan MA, A., and Aaqib, M. (2024). Real-Time Object Detection in Occluded Environment with Background Cluttering Effects Using Deep Learning. arXiv.
4. Nurfirdausi, A.F., Soekirno, S., and Aminah, S. (2021, January 23–25). Implementation of Single Shot Detector (SSD) MobileNet V2 on Disabled Patient’s Hand Gesture Recognition as a Notification System. Proceedings of the 2021 International Conference on Advanced Computer Science and Information Systems (ICACSIS), Depok, Indonesia.
5. Faster r-cnn: Towards real-time object detection with region proposal networks;Ren;Adv. Neural Inf. Process. Syst.,2015