针对现有基于深度学习的遥感影像分割方法难以充分考虑像素之间关系,而全连接条件随机场(fully connected conditional random fields,FullCRF)后处理效率低下且难以训练的问题,提出了结合改进金字塔场景解析网络(pyramid scene parsing...针对现有基于深度学习的遥感影像分割方法难以充分考虑像素之间关系,而全连接条件随机场(fully connected conditional random fields,FullCRF)后处理效率低下且难以训练的问题,提出了结合改进金字塔场景解析网络(pyramid scene parsing network,PSPNet)算法与卷积条件随机场(convolutional condition random fields,ConvCRF)的方法。首先,在PSPNet中采用更加密集连接的DenseNet网络,并在高低层特征融合部分将原有的连接CNN网络末端特征图方式改为连接第三个dense模块。其次,在改进PSPNet基础上,设计与ConvCRF的集成方法,通过引入两个损失函数,设计两步法训练方式,实现了集成模型的端对端训练。最后,进行某区域无人机遥感影像4类要素分割及马萨诸塞州航空遥感影像道路分割试验。结果表明,改进PSPNet在无人机影像分割试验中MIoU(mean intersection over union)提升0.25%,总体精度提升0.47%;结合ConvCRF处理模块后,MIoU可进一步提升0.94%,总体精度进一步提升0.47%,单幅图像计算时间仅增加79 ms,且精度优于FullCRF,时间开销仅为FullCRF的35%,在马萨诸塞州道路分割试验中,本方法较其他精度更优。展开更多
The study of the spatial patterns and temporal changes of cropland is important to understand the underlying factors and the functional effects of the agricultural landscape. On the other hand, crop dynamics mapping i...The study of the spatial patterns and temporal changes of cropland is important to understand the underlying factors and the functional effects of the agricultural landscape. On the other hand, crop dynamics mapping is essential to know the overall agro-spatial diversity of the area. Therefore, this paper addressed a spatio-temporal analysis of cropland and cropping pattern change in the Bogra district of Bangladesh over the last 16 years （between 1988/89 and 2004/05）. In this paper, crop mapping from multi-temporal and multi-sensor satellite images was described. Landsat TM and IRS P6 LlSS Ⅲ satellite images were used with GIS for spatial dynamics of cropland and cropping pattern change analysis. First, seasonal cropland maps were derived from object-based classification of satellite images, then two-date classified image differencing with GIS overlay technique and decision rules were applied. Cropping pattern change was analyzed in a spatial and quantitative way for the 16 years and for this, Integrated Land and Water Information System （ILWIS） and Land Change Modular （LCM） of IDRISl Andes were used. The results showed that in the area, mono crop cultivation was found in summer, but in winter, areas under different crop cultivation had changed dramatically. Change analysis showed that the changes mainly occurred in the north northwest and southwest of the areas, and during the time the highest change area was found under the rice-potato pattern.展开更多
文摘针对现有基于深度学习的遥感影像分割方法难以充分考虑像素之间关系,而全连接条件随机场(fully connected conditional random fields,FullCRF)后处理效率低下且难以训练的问题,提出了结合改进金字塔场景解析网络(pyramid scene parsing network,PSPNet)算法与卷积条件随机场(convolutional condition random fields,ConvCRF)的方法。首先,在PSPNet中采用更加密集连接的DenseNet网络,并在高低层特征融合部分将原有的连接CNN网络末端特征图方式改为连接第三个dense模块。其次,在改进PSPNet基础上,设计与ConvCRF的集成方法,通过引入两个损失函数,设计两步法训练方式,实现了集成模型的端对端训练。最后,进行某区域无人机遥感影像4类要素分割及马萨诸塞州航空遥感影像道路分割试验。结果表明,改进PSPNet在无人机影像分割试验中MIoU(mean intersection over union)提升0.25%,总体精度提升0.47%;结合ConvCRF处理模块后,MIoU可进一步提升0.94%,总体精度进一步提升0.47%,单幅图像计算时间仅增加79 ms,且精度优于FullCRF,时间开销仅为FullCRF的35%,在马萨诸塞州道路分割试验中,本方法较其他精度更优。
文摘The study of the spatial patterns and temporal changes of cropland is important to understand the underlying factors and the functional effects of the agricultural landscape. On the other hand, crop dynamics mapping is essential to know the overall agro-spatial diversity of the area. Therefore, this paper addressed a spatio-temporal analysis of cropland and cropping pattern change in the Bogra district of Bangladesh over the last 16 years （between 1988/89 and 2004/05）. In this paper, crop mapping from multi-temporal and multi-sensor satellite images was described. Landsat TM and IRS P6 LlSS Ⅲ satellite images were used with GIS for spatial dynamics of cropland and cropping pattern change analysis. First, seasonal cropland maps were derived from object-based classification of satellite images, then two-date classified image differencing with GIS overlay technique and decision rules were applied. Cropping pattern change was analyzed in a spatial and quantitative way for the 16 years and for this, Integrated Land and Water Information System （ILWIS） and Land Change Modular （LCM） of IDRISl Andes were used. The results showed that in the area, mono crop cultivation was found in summer, but in winter, areas under different crop cultivation had changed dramatically. Change analysis showed that the changes mainly occurred in the north northwest and southwest of the areas, and during the time the highest change area was found under the rice-potato pattern.
