Object Detection with Hyperparameter and Image Enhancement Optimisation for a Smart and Lean Pick-and-Place Solution

被引：0

作者：

Kee, Elven ^{[1
]}

Chong, Jun Jie ^{[1
]}

Choong, Zi Jie ^{[1
]}

Lau, Michael ^{[1
]}

机构：

[1] Nanyang Polytech Singapore, Newcastle Univ Singapore, Fac Sci Agr & Engn, SIT Bldg, Singapore 567739, Singapore

来源：

SIGNALS | 2024年 / 5卷 / 01期

关键词：

Single Shot Detector; MobileNet; object detection; pick-and-place solution; RGB saturation; hyperparameter;

D O I：

10.3390/signals5010005

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

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.

引用

页码：87 / 104

页数：18