Lidar Cloud Detection With Fully Convolutional Networks

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.

[1]  David D. Turner,et al.  Full-Time, Eye-Safe Cloud and Aerosol Lidar Observation at Atmospheric Radiation Measurement Program Sites: Instruments and Data Analysis , 2013 .

[2]  Dong Liu,et al.  A new cloud and aerosol layer detection method based on micropulse lidar measurements , 2014 .

[3]  Jun Li,et al.  Nonlinear physical segmentation algorithm for determining the layer boundary from lidar signal. , 2015, Optics express.

[4]  Sebastian Thrun,et al.  Towards fully autonomous driving: Systems and algorithms , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).

[5]  Luis Gómez-Chova,et al.  Cloud detection machine learning algorithms for PROBA-V , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[6]  Saso Dzeroski,et al.  Estimating vegetation height and canopy cover from remotely sensed data with machine learning , 2010, Ecol. Informatics.

[7]  Jasper R. Lewis,et al.  Overview of MPLNET Version 3 Cloud Detection. , 2016, Journal of atmospheric and oceanic technology.

[8]  Jungho Im,et al.  Forest biomass estimation from airborne LiDAR data using machine learning approaches , 2012 .

[9]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[10]  Jay G Tarolli,et al.  Fully convolutional neural network for removing background in noisy images of uranium bearing particles. , 2017, The Analyst.

[11]  Seunghoon Hong,et al.  Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation , 2015, NIPS.

[12]  Steve Kroon,et al.  Unsupervised pre-training for fully convolutional neural networks , 2016, 2016 Pattern Recognition Association of South Africa and Robotics and Mechatronics International Conference (PRASA-RobMech).

[13]  Kenneth Sassen,et al.  Cloud Type and Macrophysical Property Retrieval Using Multiple Remote Sensors , 2001 .

[14]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[15]  Christopher Joseph Pal,et al.  Brain tumor segmentation with Deep Neural Networks , 2015, Medical Image Anal..

[16]  Jacques Pelon,et al.  STRAT: An Automated Algorithm to Retrieve the Vertical Structure of the Atmosphere from Single-Channel Lidar Data , 2007 .

[17]  Albert Mendoza,et al.  Novel polarization-sensitive micropulse lidar measurement technique. , 2007, Optics express.

[18]  George Papandreou,et al.  Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[19]  Chihway Chang,et al.  Radio frequency interference mitigation using deep convolutional neural networks , 2016, Astron. Comput..