arXiv:2509.16519cs.CV2025-09ICCV被引 3

构建了超大规模街景空气质量估测数据集,支持高精度空气污染可视化分析。

PM25Vision: A Large-Scale Benchmark Dataset for Visual Estimation of Air Quality

  • 采集11年街景图像与3261个站点同步的PM2.5数据
  • 空间精度达5公里,覆盖超1.1万张图像
  • 适合研究城市空气污染视觉估计的学者与开发者

我们提出了PM25Vision(PM25V),目前规模最大、最全面的基于街景图像估算空气污染(具体为PM2.5浓度)的数据集。该数据集包含超过11,114张图像,与分布在3,261个空气质量监测站、跨越11年的时序化且地理定位准确的PM2.5读数相匹配,其规模远超以往基准。数据集的空间精度达到5公里,显著优于多数以城市为单位的数据集。本文描述了数据采集、同步及清洗流程,并使用卷积神经网络(CNN)和变换器(Transformer)架构提供了基线模型表现。该数据集已公开可用。

原文摘要 · Abstract (English)

We introduce PM25Vision (PM25V), the largest and most comprehensive dataset to date for estimating air quality - specifically PM2.5 concentrations - from street-level images. The dataset contains over 11,114 images matched with timestamped and geolocated PM2.5 readings across 3,261 AQI monitoring stations and 11 years, significantly exceeding the scale of previous benchmarks. The spatial accuracy of this dataset has reached 5 kilometers, far exceeding the city-level accuracy of many datasets. We describe the data collection, synchronization, and cleaning pipelines, and provide baseline model performances using CNN and transformer architectures. Our dataset is publicly available.

空气质量街景图像数据集深度学习

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。