Lidar Cloud Detection with Fully Convolutional Networks

TL;DR

This paper introduces a semi-supervised fully convolutional network approach for lidar cloud detection, improving accuracy over existing cloud mask algorithms by leveraging multiple training strategies.

Contribution

It presents a novel semi-supervised training method for FCNs to enhance lidar cloud segmentation accuracy.

Findings

Higher cloud identification accuracy than cloud mask algorithm

Effective semi-supervised training strategy demonstrated

Model achieves improved segmentation performance

Abstract

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.