Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 9, Issue 3, 2025

Research on SSD-Mobilenet-Based Electronic Component Object Detection Algorithm

Download as PDF

DOI: 10.23977/acss.2025.090320 | Downloads: 1 | Views: 26

Author(s)

Xianshuang Zhao 1

Affiliation(s)

1 Guangzhou College of Applied Science and Technology, Zhaoqing, Guangdong, China

Corresponding Author

Xianshuang Zhao

ABSTRACT

This paper designs an electronic component detection system for physics teaching experiments in educational courses. The system model has been successfully deployed on NPU-embedded mobile devices. The SSD (Single Shot Multi-Box Detector) network serves as the foundation for model training. To adapt the trained model to NPU-based embedded devices, we replace the basic convolutional layer with lightweight depth-separable convolutions. To improve object detection accuracy under high overlap conditions, we employ GIoU (Generalized Intersection-Union) to mitigate missed detection caused by excessive overlap.

KEYWORDS

SSD; NPU; Deep Separable Convolution; GIoU

CITE THIS PAPER

Xianshuang Zhao, Research on SSD-Mobilenet-Based Electronic Component Object Detection Algorithm. Advances in Computer, Signals and Systems (2025) Vol. 9: 168-174. DOI: http://dx.doi.org/10.23977/acss.2025.090320.

REFERENCES

[1] Gao Wen, Chen Xilin. Computer Vision: Principles of Algorithms and Systems [M]. Tsinghua University Press, 1999.
[2]Zhang H, Wang K F, Wang F Y. Advances and Perspectives on Applications of Deep Learning in Visual Object Detection [J]. Acta Automatica Sinica, 2017, 43(8):1289-1305.
[3] Feng Jingchuan, Hu Xiaolong, Li Bin. Research on Feature Fusion-Based Object Detection Algorithms [J]. Digital Technology and Applications, 2018,36(12):124-125.
[4] Wang Caiyun. Research Progress in Object Detection [C]// Proceedings of the 23rd Annual Conference on New Network Technologies and Applications, 2019, organized by the Network Application Branch of China Computer Users Association. 2019.
[5] Neubeck A, Gool L J V. Efficient Non-Maximum Suppression [C]// International Conference on Pattern Recognition. IEEE Computer Society, 2006.
[6] Li X, Di X, Liu M, et al. Feature-aligned distillation for dense object detection via refined semantic guidance and distribution consistency [J]. Computer Vision and Image Understanding, 2025, 262104519.
[7] Liu H, Wan Y, Zhang M, et al. LGRDet: A Light Object Detection Network for Gesture Recognition [J]. Concurrency and Computation: Practice and Experience, 2025, 37(25-26):e70350.
[8] Qiao W, Yin C, Huang W .Improved method for small target detection based on infrared sensing images and wearable IoT [J]. Journal of Radiation Research and Applied Sciences,2025,18(4):102002.
[9] Ha K C, Than M P, Nguyen H. Adaptive query allocation for dense object detection in deformable transformers [J]. Results in Engineering,2025,28107571.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 40421
Visits: 793894

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.