VisioDECT: a novel approach to drone detection using CBAM-integrated YOLO and GELAN-E models
Authors:
- Sakib Bin IslamSISakib Bin Islam
- Muhammad E. H. ChowdhuryMuhammad E. H. Chowdhury
- Mazhar Hasan-ZiaMHMazhar Hasan-Zia
- Saad Bin Abul KashemSKSaad Bin Abul Kashem
- Molla E. MajidMMMolla E. Majid
- Ali K. Ansaruddin KunjuAKAli K. Ansaruddin Kunju
- Amith KhandakarAKAmith Khandakar
- Azad AshrafAAAzad Ashraf
- Mohammad NashbatMNMohammad Nashbat
Open Access
- 9 July 2025
- journal article
- research article
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (24) , 20181-20204
Abstract
Unmanned aerial vehicles have revolutionized logistics, environmental monitoring, and aerial surveillance. Their widespread use has created security concerns, specifically regarding illegal spying, smuggling, and hazardous substance movement. Maintaining public safety and protecting sensitive locations requires effective drone detection and payload assessment. Our article proposes a vision-based system for real-time drone identification and classification utilizing YOLOv5, YOLOv8, and GELAN-E deep learning models, enhanced with novel attention mechanisms and interpretability techniques. By integrating the Convolutional Block Attention Module into the YOLO architecture, which is named AttnYOLO, the system enhances feature extraction and focuses on the most relevant regions in an image. This improvement in spatial and channel attention significantly boosts detection performance, particularly for small and occluded drones. Additionally, we employ Gradient-weighted Class Activation Mapping (EigenCAM) for visualizing model focus during detection, increasing the system’s transparency and interpretability. VisioDECT comprises 20,924 annotated photographs of six drone models in overcast, sunny, and evening circumstances. Under cloudy conditions, DenseNet201 achieved 100% classification accuracy, while DarkNet53 and InceptionV3 reached 99.99% and 99.9%, respectively. In evening scenarios, InceptionV3 had 100% accuracy, followed by DarkNet53 with 99.98%. Our proposed model, GELAN-E, excelled in detection and classification. In overcast settings, GELAN-E outperformed YOLOv8 with an accuracy of 0.988, a recall of 0.994, and a mAP50-95 score of 0.688. For evening conditions, GELAN-E achieved a higher mAP50-95 score of 0.642 compared to YOLOv8. These results demonstrate that the inclusion of attention mechanisms, along with visual interpretability, enhances drone detection performance, particularly in low-light and challenging environments, making this system ideal for real-time drone detection in civilian and military applications .Keywords
Funding Information
- Qatar University
This publication has 66 references indexed in Scilit:
- A deep learning approach for classification of COVID and pneumonia using DenseNet‐201International Journal of Imaging Systems and Technology, 2022
- A survey on deep learning-based identification of plant and crop diseases from UAV-based aerial imagesCluster Computing, 2022
- Deep learning techniques to classify agricultural crops through UAV imagery: a reviewNeural Computing and Applications, 2022
- Convolutional neural network and its pretrained models for image classification and object detection: A surveyConcurrency and Computation: Practice and Experience, 2021
- Thermal-based early breast cancer detection using inception V3, inception V4 and modified inception MV4Neural Computing and Applications, 2021
- A Comprehensive Review of Unmanned Aerial Vehicle Attacks and Neutralization TechniquesAd Hoc Networks, 2021
- Eigen-CAM: Visual Explanations for Deep Convolutional Neural NetworksSN Computer Science, 2021
- Convolutional neural network: a review of models, methodologies and applications to object detectionProgress in Artificial Intelligence, 2019
- CBAM: Convolutional Block Attention Module2018
- SSD: Single Shot MultiBox Detector2016