TY - GEN
T1 - Space Object classification using deep Convolutional Neural Networks
AU - Linares, Richard
AU - Furfaro, Roberto
N1 - Publisher Copyright:
� 2016 ISIF.
PY - 2016/8/1
Y1 - 2016/8/1
N2 - Tracking and characterizing both active and inactive Space Objects (SOs) is required for protecting space assets. Characterizing and classifying space debris is critical to understanding the threat they may pose to active satellites and manned missions. This work examines SO classification using brightness measurements derived from electrical-optical sensors. The classification approach discussed in this work is data-driven in that it learns from data examples how to extract features and classify SOs. The classification approach is based on a deep Convolutional Neural Network (CNN) approach where a layered hierarchical architecture is used to extract features from brightness measurements. Training samples are generated from physics-based models that account for rotational dynamics and light reflection properties of SOs. The number of parameters involved in modeling SO brightness measurements make traditional estimation approaches computationally expensive. This work shows that the CNN approach can efficiently solve classification problem for this complex physical dynamical system. The performance of these strategies for SO classification is demonstrated via simulated scenarios.
AB - Tracking and characterizing both active and inactive Space Objects (SOs) is required for protecting space assets. Characterizing and classifying space debris is critical to understanding the threat they may pose to active satellites and manned missions. This work examines SO classification using brightness measurements derived from electrical-optical sensors. The classification approach discussed in this work is data-driven in that it learns from data examples how to extract features and classify SOs. The classification approach is based on a deep Convolutional Neural Network (CNN) approach where a layered hierarchical architecture is used to extract features from brightness measurements. Training samples are generated from physics-based models that account for rotational dynamics and light reflection properties of SOs. The number of parameters involved in modeling SO brightness measurements make traditional estimation approaches computationally expensive. This work shows that the CNN approach can efficiently solve classification problem for this complex physical dynamical system. The performance of these strategies for SO classification is demonstrated via simulated scenarios.
UR - http://www.scopus.com/inward/record.url?scp=84992135133&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84992135133&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84992135133
T3 - FUSION 2016 - 19th International Conference on Information Fusion, Proceedings
SP - 1140
EP - 1146
BT - FUSION 2016 - 19th International Conference on Information Fusion, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 19th International Conference on Information Fusion, FUSION 2016
Y2 - 5 July 2016 through 8 July 2016
ER -