Advanced Object Counting System for Inventory Management Using YOLOv7 and Lightweight Attention Mechanisms

DOI

10.2991/978-94-6463-718-2_6How to use a DOI?

Keywords

YOLOv7; lightweight attention mechanisms; object detection; inventory management; real-time performance; small object detection; computational efficiency; scalability; robust performance; system integration

Abstract

In this paper, we propose a novel lightweight attention-based object counting system for inventory management using the YOLOv7 object detector model. It aims to enhance real-time and operational efficiency in changing environments while having improved performance accuracy for small and overlapping objects. The system achieves this by adopting the lightweight attention mechanism proper for the resource-constrained platforms, thus reducing the computational overhead while maintaining comparable detection speed and accuracy. In addition, the system performs well in cluttered, messy environments, allowing them to detect everything in sight — even in contrasting conditions and orientations. The approach is scalable and flexible, allowing us to integrate with current inventory management systems and to deploy in retail, warehouse, and manufacturing settings. The experimental results obtain that the system presents a better performance than traditional models, with greater flexibility, better detection in complex environments and efficiency in large-scale inventory system.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - S. Sadhasivam
AU  - R. Banupriya
AU  - D. Sathiya
AU  - V. Guru Prasad
AU  - R. S. Hari Haran
AU  - P. Harish
PY  - 2025
DA  - 2025/05/23
TI  - Advanced Object Counting System for Inventory Management Using YOLOv7 and Lightweight Attention Mechanisms
BT  - Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
PB  - Atlantis Press
SP  - 52
EP  - 64
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-718-2_6
DO  - 10.2991/978-94-6463-718-2_6
ID  - Sadhasivam2025
ER  -