Animal populations worldwide are rapidly declining, and a technology that can
accurately count endangered species could be vital for monitoring population
changes over several years. This research focused on fine-tuning object
detection models for drone images to create accurate counts of animal species.
Hundreds of images taken using a drone and large, openly available drone-image
datasets were used to fine-tune machine learning models with the baseline
YOLOv8 architecture. We trained 30 different models, with the largest having
43.7 million parameters and 365 layers, and used hyperparameter tuning and data
augmentation techniques to improve accuracy. While the state-of-the-art YOLOv8
baseline had only 0.7% accuracy on a dataset of safari animals, our models had
95% accuracy on the same dataset. Finally, we deployed the models on the Jetson
Orin Nano for demonstration of low-power real-time species detection for easy
inference on drones.

动物种群数量急剧下降，精确计数濒危物种的技术对于长期监测种群变化至关重要。本研究侧重于优化用于无人机图像的目标检测模型，以创建准确的动物物种计数。通过使用无人机拍摄的数百张图片和大量可获取的无人机图像数据集，我们将传统的 YOLOv8 架构进行了优化。我们训练了 30 个不同的模型，其中最大的模型具有 4370 万个参数和 365 个层，并利用超参数调整和数据增强技术来提高准确性。尽管最先进的 YOLOv8 基线在野生动物数据集上只有 0.7％的准确性，但我们的模型在相同数据集上达到 95％的准确性。最后，我们将模型部署在 Jetson Orin Nano 上，演示了低功耗实时物种检测，便于在无人机上进行推断。

用于濒危动物种群监测的多物种目标检测无人机图像系统

Multi-Species Object Detection in Drone Imagery for Population  Monitoring of Endangered Animals

It is desirable for detection and classification algorithms to generalize to
unfamiliar environments, but suitable benchmarks for quantitatively studying
this phenomenon are not yet available. We present a dataset designed to measure
recognition generalization to novel environments. The images in our dataset are
harvested from twenty camera traps deployed to monitor animal populations.
Camera traps are fixed at one location, hence the background changes little
across images; capture is triggered automatically, hence there is no human
bias. The challenge is learning recognition in a handful of locations, and
generalizing animal detection and classification to new locations where no
training data is available. In our experiments state-of-the-art algorithms show
excellent performance when tested at the same location where they were trained.
However, we find that generalization to new locations is poor, especially for
classification systems.

利用 20 个固定的相机捕获的图像构建了一个检测与分类数据库，研究旧数据处理模型对新环境的适应度，发现分类系统的泛化性表现较差。