Monitoring of Hermit Crabs Using drone-captured imagery and Deep Learning based Super-Resolution Reconstruction and Improved YOLOv8

2024-08-07

arXiv.org

AI Summary

Traditional quadrat-based hermit crab surveys suffer from high labor intensity, poor timeliness, and strong environmental dependency. To address these limitations, this study proposes an automated monitoring framework leveraging unmanned aerial vehicle (UAV) remote sensing. We introduce CRAB-YOLO, a novel detection network specifically designed for hermit crabs’ small scale, high mobility, and morphological variability—incorporating attention mechanisms, a lightweight detection head, and adaptive anchor box optimization. Additionally, we propose a Robust Deep Super-Resolution (RDN)-based reconstruction pipeline tailored to enhance low-resolution, motion-blurred UAV imagery. Experimental results demonstrate that super-resolution preprocessing boosts CRAB-YOLO’s mean Average Precision (mAP) on the test set to 69.5%, representing a 40-percentage-point improvement over bicubic interpolation, and significantly enhances detection accuracy for small and blurred targets. The proposed method enables large-scale, cost-effective, and high-precision intelligent monitoring of benthic organisms in coastal zones.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: State Estimation
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Search and Retrieval-Augmented AI: Web crawling and indexing
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Hermit crabs play a crucial role in coastal ecosystems by dispersing seeds, cleaning up debris, and disturbing soil. They serve as vital indicators of marine environmental health, responding to climate change and pollution. Traditional survey methods, like quadrat sampling, are labor-intensive, time-consuming, and environmentally dependent. This study presents an innovative approach combining UAV-based remote sensing with Super-Resolution Reconstruction (SRR) and the CRAB-YOLO detection network, a modification of YOLOv8s, to monitor hermit crabs. SRR enhances image quality by addressing issues such as motion blur and insufficient resolution, significantly improving detection accuracy over conventional low-resolution fuzzy images. The CRAB-YOLO network integrates three improvements for detection accuracy, hermit crab characteristics, and computational efficiency, achieving state-of-the-art (SOTA) performance compared to other mainstream detection models. The RDN networks demonstrated the best image reconstruction performance, and CRAB-YOLO achieved a mean average precision (mAP) of 69.5% on the SRR test set, a 40% improvement over the conventional Bicubic method with a magnification factor of 4. These results indicate that the proposed method is effective in detecting hermit crabs, offering a cost-effective and automated solution for extensive hermit crab monitoring, thereby aiding coastal benthos conservation.

Problem

• Improving hermit crab detection accuracy using UAV imagery and SRR.
• Enhancing YOLOv8 for efficient hermit crab monitoring in coastal ecosystems.
• Automating hermit crab surveys to replace labor-intensive traditional methods.

Innovation

• UAV-based remote sensing with Super-Resolution Reconstruction
• CRAB-YOLO network improves YOLOv8 for hermit crabs
• RDN networks enhance image reconstruction performance