skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: A hybrid approach to estimate the complex motions of clouds in sky images

Journal Article · · Solar Energy
 [1];  [2];  [3];  [4];  [4]
  1. Stony Brook Univ., NY (United States). Dept. of Electrical and Computer Engineering; Brookhaven National Lab. (BNL), Upton, NY (United States)
  2. New Jersey Inst. of Technology, Newark, NJ (United States). Martin Tuchman School of Management
  3. NASA Goddard Space Flight Center (GSFC), Greenbelt, MD (United States)
  4. Brookhaven National Lab. (BNL), Upton, NY (United States)
+ Show Author Affiliations

Tracking the motion of clouds is essential to forecasting the weather and to predicting the short-term solar energy generation. Existing techniques mainly fall into two categories: variational optical flow, and block matching. In this article, we summarize recent advances in estimating cloud motion using ground-based sky imagers and quantitatively evaluate state-of-the-art approaches. Then we propose a hybrid tracking framework to incorporate the strength of both block matching and optical flow models. To validate the accuracy of the proposed approach, we introduce a series of synthetic images to simulate the cloud movement and deformation, and thereafter comprehensively compare our hybrid approach with several representative tracking algorithms over both simulated and real images collected from various sites/imagers. The results show that our hybrid approach outperforms state-of-the-art models by reducing at least 30% motion estimation errors compared with the ground-truth motions in most of simulated image sequences. Furthermore, our hybrid model demonstrates its superior efficiency in several real cloud image datasets by lowering at least 15% Mean Absolute Error (MAE) between predicted images and ground-truth images.

Research Organization:
Brookhaven National Laboratory (BNL), Upton, NY (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Biological and Environmental Research (BER)
Grant/Contract Number:
SC0012704
OSTI ID:
1341691
Report Number(s):
BNL-113436-2017-JA; R&D Project: 07230; YN0100000
Journal Information:
Solar Energy, Vol. 138, Issue C; ISSN 0038-092X
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 31 works
Citation information provided by
Web of Science

References (37)

Continuous short-term irradiance forecasts using sky images journal December 2014
The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields journal January 1996
Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation journal March 2011
LIBSVM: A library for support vector machines journal April 2011
Intra-hour forecasting with a total sky imager at the UC San Diego solar energy testbed journal November 2011
Cloud motion and stability estimation for intra-hour solar forecasting journal May 2015
Hybrid intra-hour DNI forecasts with sky image processing enhanced by stochastic learning journal December 2013
A neural network-based method for tracking features from satellitesensor images journal December 1995
Cloud detection, classification and motion estimation using geostationary satellite imagery for cloud cover forecast journal June 2013
Cloud Motion Analysis Using Multichannel Correlation-Relaxation Labeling journal July 2006
Comparison of Block Matching and Differential Methods for Motion Analysis of the Carotid Artery Wall From Ultrasound Images journal September 2012
A Short-Term Cloud Forecast Scheme Using Cross Correlations journal December 1993
Three-Dimensional Motion Estimation of Atmospheric Layers From Image Sequences journal August 2008
Layered Estimation of Atmospheric Mesoscale Dynamics From Satellite Imagery journal December 2007
Modeling PV fleet output variability journal August 2012
Cloud detection and classification with the use of whole-sky ground-based images journal September 2012
Cloud speed impact on solar variability scaling – Application to the wavelet variability model journal May 2013
The determination of cloud pattern motions from geosynchronous satellite image data journal December 1970
An Automated Technique for Obtaining Cloud Motion from Geosynchronous Satellite Data Using Cross Correlation journal February 1971
Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention journal December 1993
Retrieving Cloud Characteristics from Ground-Based Daytime Color All-Sky Images journal May 2006
Intra-hour DNI forecasting based on cloud tracking image analysis journal May 2013
Hybrid solar forecasting method uses satellite imaging and ground telemetry as inputs to ANNs journal June 2013
Stereographic methods for cloud base height determination using two sky imagers journal September 2014
3D cloud detection and tracking system for solar forecast using multiple sky imagers journal August 2015
Cloud Coverage Based on All-Sky Imaging and Its Impact on Surface Solar Irradiance journal October 2003
Operational production of winds from cloud motions journal July 1991
Image compression via improved quadtree decomposition algorithms journal March 1994
Automated ground-based cloud recognition journal October 2005
Deformable Medical Image Registration: A Survey journal July 2013
A fast direct Fourier-based algorithm for subpixel registration of images journal October 2001
An Improvement of the IGMK Model to Derive Total and Diffuse Solar Radiation at the Surface from Satellite Data journal July 1990
A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them journal September 2013
Image matching as a diffusion process: an analogy with Maxwell's demons journal September 1998
Development of a sky imaging system for short-term solar power forecasting posted_content May 2014
Short-term irradiance forecasting using skycams: Motivation and development journal December 2014
Solar irradiance forecasting using a ground-based sky imager developed at UC San Diego journal May 2014

Cited By (2)

Automatic Cloud-Type Classification Based On the Combined Use of a Sky Camera and a Ceilometer: Cloud class using ceilometer and camera journal October 2017
Nowcasting Surface Solar Irradiance with AMESIS via Motion Vector Fields of MSG-SEVIRI Data journal May 2018

Similar Records

Related Subjects

54 ENVIRONMENTAL SCIENCES
Sky imagery
Cloud motion tracking
Optical flow