article · Ecological Informatics
Monitoring wildlife populations and protecting endangered species requires reliable animal recognition tools. Although deep learning frameworks such as YOLOv5 perform well in real-time detection, demanding processing requirements often prevent their deployment on standard hardware in remote environments. A modified lightweight model, WildARe-YOLO, addresses these constraints by incorporating Mobile Bottleneck Blocks, an improved StemBlock, a BiFPN neck, and a Focal-EIoU loss function. Evaluated on three datasets, including Wild Animal Facing Extinction, Fishmarket, and MS COCO 2017, the architecture achieves a 17.65 percent increase in frame rate alongside reductions of 28.55 percent in parameters and 50.92 percent in floating-point operations relative to the baseline. Faster loading speeds further support rapid data processing in isolated regions. These technical improvements demonstrate that accurate, real-time ecological monitoring can operate efficiently on resource-limited computing equipment.
Wildlife monitoring frequently takes place in remote conservation areas where high-performance computing infrastructure is unavailable. By significantly lowering computing demands and file loading times without sacrificing detection capability, this lightweight model allows conservationists to run real-time image analysis on basic, low-cost hardware. This makes field-level tracking of endangered species faster, cheaper, and far more accessible.
This applied and tested research provides a direct software pathway for conservation organisations, wildlife reserve managers, and environmental monitoring equipment developers. The lightweight architecture can be integrated into low-cost camera traps, field surveillance devices, or edge computing hardware deployed in remote regions with limited infrastructure. It has been validated against benchmark datasets, positioning it as an applied model ready for software integration and field trials in practical ecological surveillance systems.
AI-generated from the published abstract. Always read the original work before citing.
For the protection of endangered species and successful wildlife population monitoring, wild animal recognition is essential. While deep learning models like YOLOv5 have shown promise in real-time object recognition, their practical applicability may be constrained by their high processing requirements. In this paper, we suggest a faster and lighter version of YOLOv5s for wild animal recognition. To lower computational costs for model parameters and floating-point operations (FLOPs) for the backbone, our suggested model includes Mobile Bottleneck Block modules and an improved StemBlock. We also use Focal-EIoU as a loss function to gauge the accuracy of the predicted bounding boxes during inference and employ a BiFPN-based neck. We tested our technique on three datasets, including Wild Animal Facing Extinction, Fishmarket, and MS COCO 2017. Additionally, our technique is compared with state-of-the-art deep learning models, and from the baseline model we recorded a 17.65% increase in FPS, 28.55% model parameters reduction, and 50.92% in FLOPs reduction. Furthermore, our model has a faster model loading time, which is critical for deployment in remote areas. This enables real-time species recognition on basic hardware, aiding conservation efforts through rapid analysis. The model advances deep learning in ecology by balancing efficiency with performance. • Introducing a new, lightweight, and efficient animal recognition model. • Combines modified Stem Block, DWConv, and MBBlock for enhanced speed and accuracy. • Feature fusion enhanced with BiFPN for better accuracy. • CIoU loss was replaced with Focal-EIoU for class balance. • WildARe-YOLO – New approach in the limited infrastructure environment.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.ecoinf.2024.102541
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
