Md Auhidur Rahman

Mr. Md Auhidur Rahman

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 August 2025 in IEEE Access
Verified
Journal Article
Open access
MRMd Auhidur Rahman
Md Auhidur Rahman
TBTesfalem Mehari Berhe
Tesfalem Mehari Berhe
LBLuca Borgianni
Luca Borgianni
SASabbir Ahmed
Sabbir Ahmed
CBCristian Bua
Cristian Bua
SGStefano Giordano
Stefano Giordano
Wildlife monitoring in remote field environments presents significant challenges owing to energy constraints, limited network connectivity, and the need for real-time processing. This study proposes a scalable framework that integrates artificial intelligence (AI) and edge computing for autonomous wildlife detection, class-based object counting in frames, distance measurement, and geolocation estimation of key European wildlife species. The system leverages deep learning-based object detection models, specifically YOLOv8m and YOLOv10m trained by the European Animal Detection Dataset, deployed on power-efficient embedded platforms such as the NVIDIA Jetson Orin Nano and Raspberry Pi 5. The experimental evaluation assesses detection accuracy, computational efficiency, and energy consumption across different hardware configurations, ensuring an optimal trade-off between performance and resource utilization. Our findings demonstrate that the proposed approach enables real-time inference while maintaining high mean average precision (mAP) and minimizing power consumption, ensuring feasibility in resource-limited field conditions. A comprehensive cost-performance analysis highlights the Jetson Orin Nano as the optimal choice for balancing accuracy and efficiency, achieving 40.1 Frame Per Second (FPS) at just 8W in 25W power mode using a TensorRT-optimized YOLO model. Meanwhile, the Raspberry Pi 5 serves as a cost-effective alternative for lightweight models. Beyond technical performance, this work underscores the transformative role of edge AI in supporting ecologists and agronomists with actionable insights for biodiversity conservation, human wildlife conflict mitigation, and sustainable ecosystem management.

30 July 2025 in Computers
Verified
Journal Article
Open access
PDF file
MRMd Auhidur Rahman
Md Auhidur Rahman
SGStefano Giordano
Stefano Giordano
MPMichele Pagano
Michele Pagano
Real-time wildlife monitoring on edge devices poses significant challenges due to limited power, constrained bandwidth, and unreliable connectivity, especially in remote natural habitats. Conventional object detection systems often transmit redundant data of the same animals detected across multiple consecutive frames as a part of a single event, resulting in increased power consumption and inefficient bandwidth usage. Furthermore, maintaining consistent animal identities in the wild is difficult due to occlusions, variable lighting, and complex environments. In this study, we propose a lightweight hybrid tracking framework built on the YOLOv8m deep neural network, combining motion-based Kalman filtering with Local Binary Pattern (LBP) similarity for appearance-based re-identification using texture and color features. To handle ambiguous cases, we further incorporate Hue-Saturation-Value (HSV) color space similarity. This approach enhances identity consistency across frames while reducing redundant transmissions. The framework is optimized for real-time deployment on edge platforms such as NVIDIA Jetson Orin Nano and Raspberry Pi 5. We evaluate our method against state-of-the-art trackers using event-based metrics such as MOTA, HOTA, and IDF1, with a focus on detected animals occlusion handling, trajectory analysis, and counting during both day and night. Our approach significantly enhances tracking robustness, reduces ID switches, and provides more accurate detection and counting compared to existing methods. When transmitting time-series data and detected frames, it achieves up to 99.87% bandwidth savings and 99.67% power reduction, making it highly suitable for edge-based wildlife monitoring in resource-constrained environments.


19 September 2026 in Sensors
Verified
Journal Article
Open access
PDF file
MRMd Auhidur Rahman
Md Auhidur Rahman
EMErvisa Marku
Ervisa Marku
SMSunil Mathew
Sunil Mathew
DADavide Adami
Davide Adami
MPMichele Pagano
Michele Pagano
SGStefano Giordano
Stefano Giordano
Deploying artificial intelligence (AI) for wildlife monitoring in remote environments remains challenging due to limited energy, computational resources, and unreliable communication. Conventional edge AI systems rely on continuous sensing, high-power communication, and full-precision models, resulting in excessive energy consumption. This paper presents a green-energy-based hierarchical network architecture for sustainable wildlife monitoring at the extreme edge. The framework distributes sensing, communication, and AI inference across edge, far-edge, and extreme-edge layers. A low-power IEEE 802.11ah network with on-demand channel allocation reduces transmission overhead, while passive infrared (PIR)-based event-driven activation replaces continuous camera operation. Model quantization (FP32, FP16, INT8) and distributed split inference improve computational efficiency, and tracking-assisted communication eliminates redundant transmissions. Experimental results demonstrate significant sustainability improvements. PIR-based operation reduces daily energy consumption by 95.11% compared with continuous operation. Tracking-assisted communication reduces both bandwidth requirements and energy consumption by more than 99% (p<0.001). Token-based channel allocation provides 39.4% energy savings compared with Target Wake Time (TWT)-based scheduling (sensitivity range: 29.2–45.1%). INT8 quantization delivers 4.7× higher throughput, 61% lower memory usage, and 39% lower power consumption, with a 2.6% mean average precision (mAP) reduction. Field validation confirms the INT8 model’s effectiveness with an overall mAP of 82.89% (86.40% daytime, 79.37% nighttime) and precision above 96%. Combined with PIR activation, the INT8 system achieves 63.76 Wh/day—a 95.17% reduction versus FP32 continuous operation. The integration of renewable energy harvesting, efficient sensing, lightweight AI, and communication optimization enables scalable, autonomous, and sustainable wildlife monitoring in resource-constrained environments.