TY - GEN
T1 - Applying Deep Learning in Mars Exploration
T2 - 10th International Conference on Reliability, Infocom Technologies and Optimization ,Trends and Future Directions, ICRITO 2022
AU - Lodhi, Sachin
AU - Sakshi, Sakshi
AU - Kukreja, Vinay
AU - Bansal, Ankit
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022/1/1
Y1 - 2022/1/1
N2 - The red planet has persisted in being the top destination for space exploration and has also fascinated researchers to experiment with frequently launched its dataset of images. NASA has launched various missions on the track of space expeditions to explore the surface and the environment of the potential life-sustaining planet. Among all the missions for capturing images of the Martian terrain, the HiRISE experiment has been successful in coming up with the best datasets featuring the surface of Mars. In this research study, the authors have targeted the classification of this high-quality image dataset produced as the outcome of the HiRISE using a deep learning model. The proposed model is convoluted and built with the help of neural network layers (neuron layers). Based on the classification, the authors were able to classify the images of 7 terrain features of Mars, namely Crater, Impact Ejecta, Bright Dune, Dark Dune, Slope Streak, Spider, and Swiss Cheese. And the classification accuracy achieved by the model is 94.8%.
AB - The red planet has persisted in being the top destination for space exploration and has also fascinated researchers to experiment with frequently launched its dataset of images. NASA has launched various missions on the track of space expeditions to explore the surface and the environment of the potential life-sustaining planet. Among all the missions for capturing images of the Martian terrain, the HiRISE experiment has been successful in coming up with the best datasets featuring the surface of Mars. In this research study, the authors have targeted the classification of this high-quality image dataset produced as the outcome of the HiRISE using a deep learning model. The proposed model is convoluted and built with the help of neural network layers (neuron layers). Based on the classification, the authors were able to classify the images of 7 terrain features of Mars, namely Crater, Impact Ejecta, Bright Dune, Dark Dune, Slope Streak, Spider, and Swiss Cheese. And the classification accuracy achieved by the model is 94.8%.
KW - climate change
KW - innovation
KW - research and development
KW - resource efficiency
KW - science corporation agreements
KW - technological progress
UR - http://www.scopus.com/inward/record.url?scp=85144593315&partnerID=8YFLogxK
U2 - 10.1109/ICRITO56286.2022.9964662
DO - 10.1109/ICRITO56286.2022.9964662
M3 - Conference contribution
AN - SCOPUS:85144593315
T3 - 2022 10th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions), ICRITO 2022
BT - 2022 10th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions), ICRITO 2022
PB - Institute of Electrical and Electronics Engineers
Y2 - 13 October 2022 through 14 October 2022
ER -
