Lidar Cloud Detection with Fully Convolutional Networks
This work addresses cloud segmentation for lidar data analysis, presenting an incremental improvement over existing methods.
The paper tackles cloud detection in lidar imagery by using a fully convolutional network with a semi-supervised training approach, achieving higher cloud identification levels compared to the MPLCMASK cloud mask algorithm.
In this contribution, we present a novel approach for segmenting laser radar (lidar) imagery into geometric time-height cloud locations with a fully convolutional network (FCN). We describe a semi-supervised learning method to train the FCN by: pre-training the classification layers of the FCN with image-level annotations, pre-training the entire FCN with the cloud locations of the MPLCMASK cloud mask algorithm, and fully supervised learning with hand-labeled cloud locations. We show the model achieves higher levels of cloud identification compared to the cloud mask algorithm implementation.