Abstract – Craters are surface characteristics, which are mostly generated after the impact of falling an asteroid over the planetary surface. Crater density on the lunar surface provide important information about the chronology of the lunar surface. Further, recent studies on crater morphology provided new insight about geomorphic processes in the absence of water and air. Crater detection is very crucial for the morphological study of the planetary system. The main challenges, this area has faced are :-
(i) Generating a large number of training samples, which is essential for greater accuracy in the crater detection. (ii) Detecting a large number of craters in different sizes from large sized high quality surface imagery is highly complex in nature.
Here, Highlight shadow algorithm used to generate all possible subsamples from the high quality imagery, which are to be verified using supervised algorithm such as CNN.
Acknowledgement
I would like to express the deepest appreciation to my project mentor Dr. Nitin Khanna and Dr. Vikrant Jain. They continually and convincingly conveyed a spirit of adventure in regard to the project, and an excitement in regard to the teaching. I would also like to thank Athira Haridas (MTech Student) and Atal Tewari (PhD Student) for helping me during this project. Without their persistent help, this project would not have been possible.
IIT Gandhinagar
Date: 14/07/2019Rajnish Kumar Ranjan