International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Lightweight Object Detector for Pest Detection on Crops Under Field Conditions |
|---|---|
| ABSTRACT | This paper outlines a light object recognition system that can be used to detect pests on crops under field scenarios in reality. The infestation of pests leads to low agricultural production and pests need to be identified at the right time in order to manage them. Nevertheless, current object detectors based on deep learning are usually computationally demanding and cannot be used with edge computing devices in smart agriculture. In order to overcome this shortcoming, a small and lean detector model is suggested that focuses on the low level of computation but high detection rate.A set of 2,000 images and 5,167 instances of pests of four types aphids, whiteflies, caterpillars, and beetles were evaluated using a compact and efficient detector model. The model proposed combines a lightweight backbone and depthwise separable convolution and feature pyramid boosting to enhance small pest detection. The experimental results show that the proposed detector has a precision of 91.6, a recall of 89.8 and a mean Average Precision ([email protected]) of 91.0. The model is highly efficient with only 6.8 million parameters, consumes 24 MB of storage, and the inference speed of 45 frames per second, which is significantly higher than those of conventional detectors like Faster R-CNN, and SSD in both speed and model size. The findings show that the suggested lightweight framework is efficient in harmonizing accuracy and computational power thus it can be used in real-time pest monitoring tasks. This method helps in early detection of pests, minimizing the amount of manual inspection as well as facilitating sustainable practices of precision agriculture. |
| AUTHOR | P. CHITRA, V. SURENDHIRAN, DR. KRISHNAKUMAR ME, Department of Computer Science and Engineering, Excel Engineering College (Autonomous), Komarapalayam, India Assistant Professor, Department of Computer Science and Engineering, Excel Engineering College (Autonomous), Komarapalayam, India Department of Computer Science and Engineering, SIMATS Engineering, Saveetha School of Engineering, Chennai, India |
| VOLUME | 187 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1408027 |
| pdf/27_Lightweight Object Detector for Pest Detection on Crops Under Field Conditions.pdf | |
| KEYWORDS | |
| References |
[1] I. Izquierdo-bueno, J. Moraga, V. E. Gonz, and C. Garrido, “Smart Viniculture : Applying Artificial Intelligence for Improved Winemaking and Risk Management,” 2024. [2] R. Kundu, U. Chauhan, and S. P. S. Chauhan, “Plant Leaf Disease Detection using Image Processing,” Proc. 2nd Int. Conf. Innov. Pract. Technol. Manag. ICIPTM 2022, vol. 2, no. 4, pp. 393–396, 2022, doi: 10.1109/ICIPTM54933.2022.9754170. [3] I. Rakhmatuiln, A. Kamilaris, and C. Andreasen, “Deep neural networks to detectweeds from crops in agricultural environments in real-time: A review,” Remote Sens., vol. 13, no. 21, 2021, doi: 10.3390/rs13214486. [4] R. Hammad, M. Barhoush, and B. H. Abed-alguni, “A Semantic-Based Approach for Managing Healthcare Big Data : A Survey,” vol. 2020, 2020. [5] S. C. Shrawne, J. Sawant, O. Chaubal, K. Suryawanshi, D. Sirwani, and V. K. Sambhe, “Multiclass Fruit Detection Using Improved YOLOv3 Algorithm,” vol. 15, no. 9, 2024. [6] D. G. V, A. M. Ahmed, and M. Mahfuri, “Edge AI for Smart Healthcare : Real-Time Vital Sign Monitoring and Predictive Alerts in Emergency Care,” 2025 3rd Int. Conf. Cyber Resil., pp. 1–6, 2025, doi: 10.1109/ICCR67387.2025.11291857. [7] Y. Bu, H. Ye, Z. Tie, Y. Chen, and D. Zhang, “OD-YOLO: Robust Small Object Detection Model in Remote Sensing Image with a Novel Multi-Scale Feature Fusion,” Sensors, vol. 24, no. 11, pp. 1–23, 2024, doi: 10.3390/s24113596. [8] L. Ali, D. G. V, T. J. Nandhini, R. Almajed, and P. Johri, “Intelligent Security Framework for Real-Time Threat Detection and Response in Cloud Networks Using Deep Reinforcement Learning and Federated Anomaly Detection,” 2025 3rd Int. Conf. Cyber Resil., pp. 1–7, 2025, doi: 10.1109/ICCR67387.2025.11292287. [9] I. A. and O. L. N., “Digital Image Processing for Detecting and Classifying Plant Diseases,” Circ. Comput. Sci., vol. 2, no. 11, pp. 1–7, 2017, doi: 10.22632/ccs-2017-252-66. [10] P. S. Kanda, K. Xia, A. Kyslytysna, and E. O. Owoola, “Tomato Leaf Disease Recognition on Leaf Images Based on Fine-Tuned Residual Neural Networks,” Plants, vol. 11, no. 21, 2022, doi: 10.3390/plants11212935. [11] S. Sai et al., “Irrigation in Precision Agriculture Using Blockchain Ethereum Based on IoT †,” pp. 2–5, 2024. [12] D. G. V, L. Ali, and M. Mahfuri, “Enhancing Healthcare Cybersecurity : A Novel Homomorphic Encryption Framework for Cloud- Based Medical Records,” 2025 3rd Int. Conf. Cyber Resil., pp. 1–7, 2025, doi: 10.1109/ICCR67387.2025.11292100. [13] D. G. V, T. Erkinjon, L. H. Alzubaidi, K. Vijayakumar, K. R. Singh, and A. K. Rahuman, “Revolutionizing Talent Acquisition in Human Resources with Advanced Deep Learning-Based Resume Screening and Candidate Matching Algorithms,” 2025 Int. Conf. Autom. Comput., pp. 1289–1293, 2025, doi: 10.1109/AUTOCOM64127.2025.10957186. [14] T. R. Kumar, T. J. Nandhini, I. Jumaniyazova, H. Abdulla, Y. Jumaniyozov, and V. Bhatt, “Swarm Robotics for Search and Rescue Operations in Disaster Zones Using Particle Swarm Optimization ( PSO ) Algorithms,” 2025 Int. Conf. Networks Cryptol., pp. 870–875, 2025, doi: 10.1109/NETCRYPT65877.2025.11102388. [15] D. G. V, A. Ibrahim, A. Ain, and A. A. Elngar, “Blockchain-Powered Secure Health Data Exchange For Enhancing Patient Privacy And Interoperability,” 2025 3rd Int. Conf. Cyber Resil., pp. 1–7, 2025, doi: 10.1109/ICCR67387.2025.11292265. |
