Geomagnetic/Astronomical Autonomous Orbit Determination Based on Remote Sensing Image

A new orbit determination scheme targeting communication and remote sensing satellites in a hybrid constellation is investigated in this paper. We first design one such hybrid constellation with a two-layer configuration (LEO/MEO) by optimizing coverage and revisit cycle. The main idea of the scheme is to use a combination of imagery, altimeter data, and inter-satellite range data as measurements and determine orbits of the satellites in the hybrid constellation with the help of the extended Kalman filter (EKF). The performance of the new scheme is analyzed with Monte Carlo simulations. We first focus on an individual remote sensing satellite and compared the performance of orbit determination using only imagery with its counterpart using both imagery and altimeter measurements. Results show that the performance improves when imagery is used with altimeter data pointing to geometer calibration sites but declines when used with ocean altimeter data. We then expand the investigation to the whole constellation. When inter-satellite range data is added, orbits of all the satellites in the hybrid constellation can be autonomously determined. We find that the combination of inter-satellite range data with remote sensing observations lead to a further improvement in orbit determination precision for LEO satellites. Our results also show that the performance of the scheme would be affected when remote sensing observations on certain satellites are absent.

Download Full-text

Autonomous Orbit Determination using Observations of a Sodium Guide-Star Network

Proceedings of the 30th International Technical Meeting of The Satellite Division of the Institute of Navigation (ION GNSS+ 2017) ◽

10.33012/2017.15202 ◽

2017 ◽

Author(s):

Mark L. Psiaki

Keyword(s):

Orbit Determination ◽

Star Network ◽

Autonomous Orbit Determination ◽

Guide Star

Download Full-text

Deep Learning Based High-Resolution Remote Sensing Image classification

International Journal of Advanced Research in Computer Science and Software Engineering ◽

10.23956/ijarcsse.v7i10.384 ◽

2017 ◽

Vol 7 (10) ◽

pp. 22

Author(s):

Sumit Kaur

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Deep Learning ◽

Image Classification ◽

Language Processing ◽

Object Perception ◽

Remote Sensing Image ◽

Research Area ◽

Remote Sensing Image Classification ◽

Unsupervised Algorithms

Abstract- Deep learning is an emerging research area in machine learning and pattern recognition field which has been presented with the goal of drawing Machine Learning nearer to one of its unique objectives, Artificial Intelligence. It tries to mimic the human brain, which is capable of processing and learning from the complex input data and solving different kinds of complicated tasks well. Deep learning (DL) basically based on a set of supervised and unsupervised algorithms that attempt to model higher level abstractions in data and make it self-learning for hierarchical representation for classification. In the recent years, it has attracted much attention due to its state-of-the-art performance in diverse areas like object perception, speech recognition, computer vision, collaborative filtering and natural language processing. This paper will present a survey on different deep learning techniques for remote sensing image classification.

Download Full-text