Crop Weed Detection to Improve the Crop Yield Using AI and IoT

DOI

10.2991/978-94-6463-948-3_54How to use a DOI?

Keywords

Object detection; YOLOv10n; YOLOv10b; Detectron2; ESP32-CAM; Wireless communication; Precision agriculture

Abstract

Weed infestation remains one of the most persistent challenges in modern agriculture, as weeds compete with crops for nutrients, water, and sunlight, ultimately reducing yield and profitability. Conventional management practices rely heavily on chemical herbicides, which not only increase production costs but also contribute to environmental degradation and health hazards. To overcome these limitations, this study proposes an integrated artificial intelligence (AI) and Internet of Things (IoT) framework for early and accurate weed detection in precision agriculture.

The system utilizes an ESP32-CAM module for real-time image capture that was chosen due to its low cost, small form factor, and energy efficiency, making it ideal for resource-limited farms. Images captured are sent wirelessly to a central server, where weed detection occurs through utilization of the YOLOv10n (You Only Look Once, v10 Nano) deep learning model. YOLOv10n was selected based on its well-tuned trade-off between detection precision and computational cost, supporting deployment in real-time systems. Experimental results show that the framework delivers consistent detection performance with low latency, thus confirming its practicability in field-scale agricultural applications. The results indicate that the integration of lightweight computer vision models with IoT-centric sensing infrastructure has the potential to minimize unnecessary herbicide applications, reduce operational expenses, and support sustainable agriculture. In summary, the outlined system makes a contribution to yield optimization and delivers an economical and scalable solution to enable the increased adoption of precision agriculture.

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  - Bhagyalaxmi Kanchalwar
AU  - Vimudha Dhobale
AU  - Mansi Chandurkar
AU  - Shivani Marne
AU  - Shivprasad Chavan
AU  - Pranav Patil
PY  - 2026
DA  - 2026/01/06
TI  - Crop Weed Detection to Improve the Crop Yield Using AI and IoT
BT  - Proceedings of the International Conference on Sustainable Innovation with Artificial Intelligence and Machine Learning 2025 (ICSIAIML 2025)
PB  - Atlantis Press
SP  - 773
EP  - 782
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-948-3_54
DO  - 10.2991/978-94-6463-948-3_54
ID  - Kanchalwar2026
ER  -