Scribd
Upload
108 views11 pages

Cloud Avoidance Scheduling in Satellite Systems: PROJECT GUIDE: Prof. Reena Kumbhare

This document summarizes a student project on cloud avoidance scheduling in satellite systems. The project aims to use convolutional neural networks (CNN) to classify clouds and land covers in satellite images to improve scheduling efficiency and avoid capturing images obscured by clouds. The project will involve collecting a satellite image dataset, training a CNN model on cloud classification, and developing a scheduling algorithm that considers factors like cloud cover percentage to reject images that don't meet quality standards.

Uploaded by

Arnold
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
108 views11 pages

Cloud Avoidance Scheduling in Satellite Systems: PROJECT GUIDE: Prof. Reena Kumbhare

This document summarizes a student project on cloud avoidance scheduling in satellite systems. The project aims to use convolutional neural networks (CNN) to classify clouds and land covers in satellite images to improve scheduling efficiency and avoid capturing images obscured by clouds. The project will involve collecting a satellite image dataset, training a CNN model on cloud classification, and developing a scheduling algorithm that considers factors like cloud cover percentage to reject images that don't meet quality standards.

Uploaded by

Arnold
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

CLOUD AVOIDANCE SCHEDULING IN

SATELLITE SYSTEMS
PROJECT MEMBERS : Arnold Fonseca
Soham Jagtap
Shreeram Narayanan

PROJECT GUIDE : Prof. Reena Kumbhare


INTRODUCTION

● Cloud Cover is one of the major problems in the acquisition of optical


satellite remote sensing data and has a negative impact on the efficiency
of data scheduling.
● The necessary global cloud information derived from meteorological
satellites has to be incorporated in the planning system to improve the
planning efficiency.
MOTIVATION

● The various capabilities of IRS Satellites and its resources call for a
meticulous planning.
● Data quality, correct area of coverage (targeting accuracy), timeliness and
cloud free acquisition are parameters which are of importance for the
optimum use of satellite resources to satisfy User requirements.
● Improvement in performance, efficiency and cost.
LITERATURE SURVEY
● Convolutional neural network (CNN) has been successfully used in many
computer vision tasks, such as image classification, object detection,
object segmentation and so on. CNN can automatically learn both
low-level and high-level features. Here, we extract the cloud features and
classify clouds from land covers based on CNN [1].
LITERATURE SURVEY
● In paper “An adaptive process-based cloud infrastructure for space
situational awareness applications” a conceptual capability is proposed
will potentially support space situation monitoring and tracking, object
identification, and threat assessment.
● In paper ‘’ Cloud Avoidance Scheduling Algorithm for agile optical satellites
“ an algorithm is suggested which will avoid the clouds which includes a
framework that also provides re-scheduling tactics.
● “ Cloud cover avoidance in space-based remote sensing acquisition ”
trains the model on the basis of historical, actual and modelled results
based on the different class of satellites.
LITERATURE SURVEY
● The paper " Cloud cover avoidance in space-based remote sensing acquisition "
focuses on improving the image resolution of the optical remote sensing
satellite.
● “ The impact of collision avoidance maneuvers on satellite constellation
management “ primarily focuses on the geospatial satellite RapidEye the
influence of the impact of collision avoidance maneuvers on the satellite
constellation management and the subsequent actions that have to be
undertaken.
● The paper “ CLIMAS, a simulation tool for cloud avoidance scheduling in optical
remote sensing missions ” provides an analysis on the negative impact of
decreasing image are per unit time such as revisit time and image delivery time.
LITERATURE SURVEY
● In the paper " Multilevel cloud detection in remote sensing images based on
deep learning “ uses CNN to detect thin and thick clouds and percentage of
cloud cover in an image but avoidance algorithm is not discussed.
PLANNING
1. Information about the various varieties of images and their conditions will
be obtained by using the requisite database
2. Successful training of the CNN will be done by using the dataset of the
satellite images
3. Parameters like percentage of cloud cover, climatic conditions, solar
interference will be compared with and the decisions will be made on
these basis
4. Based on the comparison of parameters, the model will be trained to
reject certain images which do not comply to the set of constraints
REFERENCES
[1] Cloud Detection via Convolutional Neural Network in Visible Light Remote
Sensing Images Wen-jia CHEN, Jiang-yong DUAN and Juan MENG

[2] Bingwei Liu, Yu Chen, Dan Shen, Genshe Chen, Khanh Pham, Erik Blasch,
and Bruce Rubin "An adaptive process-based cloud infrastructure for space
situational awareness applications", Proc. SPIE 9085, Sensors and Systems for
Space Applications VII, 90850M (3 June 2014)

[3] He, Lei; Liu, Xiaolu; Xing, Lining; Chen, Yingwu ‘’ Cloud Avoidance
Scheduling Algorithm for agile optical satellites “, Journal of Computational
and Theoretical Nanoscience, Volume 13, Number 6, June 2016, pp.
3691-3705(15)
REFERENCES
[4] John R. Gasch; Kenneth A. Campana “ Cloud cover avoidance in
space-based remote sensing acquisition ” Proceedings Volume 4049,
Algorithms for Multispectral, Hyperspectral, and Ultraspectral Imagery VI;
Event: AeroSense 2000, 2000, Orlando, FL, United States

[5] . J. Gasch K.A. Campana "Cloud cover avoidance in space-based remote


sensing acquisition" Algorithms for Multispectral Hyperspectral and
Ultraspectral Imagery IV Proc. SPIE vol. 4049 pp. 336-347 2000.

[6] Stoll, E., Schulze, R., D’Souza, B., & Oxfort, M. (2011). The impact of collision
avoidance maneuvers on satellite constellation management. In proc. Of
European Space Surveillance Conference, Madrid, Spain.
REFERENCES
[7] Gil, J. C., Honold, A. P., & Noguero, J. S. (2004). Results with CLIMAS, a
simulation tool for cloud avoidance scheduling in optical remote sensing
missions. In Space OPS 2004 Conference (p. 162).

[8] Xie, F., Shi, M., Shi, Z., Yin, J., & Zhao, D. (2017). Multilevel cloud detection in
remote sensing images based on deep learning. IEEE Journal of Selected
Topics in Applied Earth Observations and Remote Sensing, 10(8), 3631-3640.

You might also like