用点标注训练多类动物检测模型，提升无人机影像计数准确率
POLO -- Point-based, multi-class animal detection
- 基于YOLOv8改进，仅需点标注即可训练多类动物检测
- 在单图数千只水鸟场景下，同等标注成本下精度优于传统YOLOv8
- 适合需要高效标注的野生动物监测项目
基于无人机影像与目标检测技术的自动化野生动物调查是保护生物学中强大且日益流行的工具。大多数检测器需要带有标注边界框的训练图像，这些标注耗时、昂贵且并不总是明确。为降低此类标注带来的负担，我们开发了POLO，一种完全基于点标签训练的多类目标检测模型。POLO基于对YOLOv8架构的简单但有效的修改，包括预测过程、训练损失和后处理的调整。我们在包含多达数千只个体的水鸟无人机影像上测试POLO，并与标准YOLOv8进行对比。实验表明，在相同标注成本下，POLO在航空影像中动物计数任务上实现了更高的准确性。
原文摘要 · Abstract (English)
Automated wildlife surveys based on drone imagery and object detection technology are a powerful and increasingly popular tool in conservation biology. Most detectors require training images with annotated bounding boxes, which are tedious, expensive, and not always unambiguous to create. To reduce the annotation load associated with this practice, we develop POLO, a multi-class object detection model that can be trained entirely on point labels. POLO is based on simple, yet effective modifications to the YOLOv8 architecture, including alterations to the prediction process, training losses, and post-processing. We test POLO on drone recordings of waterfowl containing up to multiple thousands of individual birds in one image and compare it to a regular YOLOv8. Our experiments show that at the same annotation cost, POLO achieves improved accuracy in counting animals in aerial imagery.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。