arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.09784eess.IVcs.CV
收藏

AQPDCITY数据集:大城市城区基于图像的PM监测

AQPDCITY Dataset: Picture-Based PM Monitoring in the Urban Area of Big Cities

Beijing Key Laboratory of Computational Intelligence and Intelligent System(计算智能与智能系统北京市重点实验室);Beijing Artificial Intelligence Institute(北京人工智能研究院);Beijing University of Technology(北京工业大学)

Yonghui Zhang, Ke Gu

摘要:

由于颗粒物与人们的生活和健康密切相关,它已成为世界各地空气质量监测的最重要指标之一。但现有的基于传感器的颗粒物监测方法存在着监测点密度低、监测条件要求高等显著缺点。因此,迫切需要设计一种方法,可以在任何位置获得PM浓度,以便及时进行后续空气质量控制。现有的工作表明,PM浓度可以通过使用无处不在的照片进行监测。为了进一步研究这个问题,我们在大城市收集了1,500张照片,建立了一个新的AQPDCITY数据集。对该数据集进行的九种最先进方法的实验表明,上述方法在AQPDCITY数据集中的性能较差。

英文摘要:

Since Particulate Matters (PMs) are closely related to people's living and health, it has become one of the most important indicator of air quality monitoring around the world. But the existing sensor-based methods for PM monitoring have remarkable disadvantages, such as low-density monitoring stations and high-requirement monitoring conditions. It is highly desired to devise a method that can obtain the PM concentration at any location for the following air quality control in time. The prior works indicate that the PM concentration can be monitored by using ubiquitous photos. To further investigate such issue, we gathered 1,500 photos in big cities to establish a new AQPDCITY dataset. Experiments conducted to check nine state-of-the-art methods on this dataset show that the performance of those above methods perform poorly in the AQPDCITY dataset.

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。

↑