arXiv 2402.053492024-02cs.CV

构建用于早期野火检测的真实世界基准：新PYRONEAR-2025数据集

Constructing a Real-World Benchmark for Early Wildfire Detection with the New PYRONEAR-2025 Dataset

PyroNear Paris, France（PyroNear巴黎，法国）；Universidad de Chile — CENIA（智利大学——CENIA）；CENIA；DCC – Universidad de Chile — CENIA（DCC——智利大学——CENIA）

Mateo Lostanlen, Nicolas Isla, Jose Guillen, Renzo Zanca, Felix Veith, Cristian Buc, Valentin Barriere

备注：: Preprint of ongoing work

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出PYRONEAR-2025真实世界基准数据集，含图像和视频及15万标注，覆盖640起野火，跨四国，用于早期野火检测，实验显示挑战性但稳定，视频部分可提升早期检测召回率。

摘要：

早期野火检测（EWD）对于实现快速响应、从而最小化野火蔓延的负面影响至关重要。为此，我们提出了PYRONEAR-2025，一个由图像和视频组成的新数据集，支持烟雾羽流检测模型（包括序列模型）的训练和评估。数据来源包括：（i）从公共野火检测摄像机网络中抓取的野火网络视频，（ii）来自我们内部摄像机网络的视频，以及（iii）少量合成和真实图像。该数据集包含50,000张图像上的约150,000个手动标注，覆盖640起野火，PYRONEAR-2025在规模和多样性上超越了现有数据集。它包含来自法国、西班牙、智利和美国的数据。最后，它由图像和视频组成，支持烟雾羽流检测模型（包括序列模型）的训练和评估。我们使用轻量级最先进的目标检测模型（如实际应用中使用的模型）进行了跨数据集实验，发现所提出的数据集特别具有挑战性，F1分数约为70%，但比现有数据集更稳定。最后，它与其他公共数据集的结合使用有助于整体达到更高的结果。此外，数据集的视频部分可用于训练轻量级序列模型，在保持精度的同时提高整体召回率，从而实现更早的检测。我们在线提供代码和数据：https://github.com/joseg20/wildfires2025。

英文摘要：

Early wildfire detection (EWD) is of the utmost importance to enable rapid response efforts, and thus minimize the negative impacts of wildfire spreads. To this end, we present PYRONEAR-2025, a new dataset composed of both images and videos, allowing for the training and evaluation of smoke plume detection models, including sequential models. The data is sourced from: (i) web-scraped videos of wildfires from public networks of cameras for wildfire detection in-the-wild, (ii) videos from our in-house network of cameras, and (iii) a small portion of synthetic and real images. This dataset includes around 150,000 manual annotations on 50,000 images, covering 640 wildfires, PYRONEAR-2025 surpasses existing datasets in size and diversity. It includes data from France, Spain, Chile and the United States. Finally, it is composed of both images and videos, allowing for the training and evaluation of smoke plume detection models, including sequential models. We ran cross-dataset experiments using a lightweight state-of-the-art object detection model, as the ones used in-real-life, and found out the proposed dataset is particularly challenging, with F1 score of around 70\%, but more stable than existing datasets. Finally, its use in concordance with other public datasets helps to reach higher results overall. Last but not least, the video part of the dataset can be used to train a lightweight sequential model, improving global recall while maintaining precision for earlier detections. [We make both our code and data available online](https://github.com/joseg20/wildfires2025).

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。