H8/AHI卫星数据的白天陆地雾检测

Daytime Land Fog Detection based on H8/AHI Satellite Data

雾是一种灾害性天气,严重影响交通秩序,造成生命财产的严重损失。10 min时间分辨率的Himawari-8/AHI(H8/AHI)卫星数据为近实时雾检测提供了可能,但白天影像反射率受太阳高度角影响较大,常规雾检测算法较难适合该卫星数据的雾检测。以该数据时序影像间云、雾与地表的光谱特征和运动特征差异为切入点,利用多幅时序影像合成晴空底图,采用背景差分法去除地表,相邻时刻时序影像取比值去除影像中运动较快且纹理粗糙的云,最后结合传统云雾分离算法去除影像中零散的未被分离检测的云,实现白天陆地雾近实时快速检测。检测结果表明:该算法可实现近实时白天雾检测,算法适用时段为白天9:00~15:00,算法定量验证精度较高,冬季连续6天雾检测正确率平均值为96.6%,错误率平均值为9.4%,可靠性因子平均值为87.9%。算法优点为检测阈值不受太阳高度角影响,与已有白天雾检测算法相比,本算法检测精度有较大提高。冬春季2月~5月120 d雾检测结果误检率仅3.6%,证明算法具有一定的可靠性和稳定性。

Fog is a kind of disastrous weather,which seriously affects traffic order and causes serious loss of life and property.The Himawari-8/AHI(H8/AHI)image with 10-minute time resolution,which provides the possibility for near-real-time fog detection,but the reflectivity of the image is greatly affected by the sun alti⁃tude angle during the day,and the conventional fog detection algorithms are difficult to adapt.This paper takes the differences in spectral characteristics and motion characteristics of clouds,fog and the surface between time series images as the starting point,uses time series images to synthesize clear sky surface,uses the background difference method to remove the surface,and uses the ratio of adjacent time series images to remove the fastmoving and rough-textured clouds in images,finally combined with the traditional cloud and fog separation algo⁃rithm to remove scattered and unseparated clouds in the image,realized the rapid detection of land fog in the daytime.The test results show that the algorithm can realize near real-time automatic daytime fog detection.The algorithm is applicable in the daytime from 9:00 to 15:00.The algorithm has high quantitative verification accuracy.The average probability of detection for 6 consecutive days in winter is 96.6%,the false alarm ratio is 9.4%,and the critical success index is 87.9%.The advantage of this algorithm is that the detection threshold is not affected by the angle of the sun's altitude.Compared with the existing detection algorithms of daytime land fog,this algorithm has higher detection accuracy.The false alarm ratio of fog detection results for 120 days from Feb⁃ruary to May in winter and spring is 3.6%,which proves that the algorithm has certain reliability and stability.