You are on page 1of 16

Craters, Mountains

on the Moon
19BCE0542 - Karnala Venkata Sumanth
19BCE0562 - Sai Anirudh Guduru
19BCE2224 - B. Sai Madesh Pretam
19BCE2326 - P Chaitanya Sayee
19BCE2330 - B. Rahul Reddy
Abstract

● Collection of Images and data of various Planets, Stars and Satellites could
help discover the possibility of identifying the three critical ingredients of
life.
● As Earth's resources are depleting, alternate possibility to sustain life has to
be figured out.
● This proposed application project could help scientists and data analysts
identify different features on Planets with CNN
OBJECTIVE

The main objective of the project is to discover different features on the Moon's
surface.The features that would be concentrated in this project would be finding
the existence of craters and mountains,the number of craters at the terminator
positions of the Moon. Graphical visualization of the heights and depths of the
Mountains using Convolutional Neural Networks, as well as craters at different
terminator positions, would also be produced.
Scope

● Mars has been discovered with an abundance of chemical building blocks,


liquid water on its surface, and an energy source (volcanic activity) to
power the chemical reactions that make life possible.
● This project could help scientists and data analysts identify different
features on Planets that are yet to be discovered to interpret the
possibility of life.
● This project could help them understand different geographical features
of the planet,this may help them in further research and increase their
understanding of the planet or star.
Literature Review

The Literature Review Link for our Project is given below:

https://docs.google.com/presentation/d/1TlUYUXVjpP4cXaYMC0klL_IyNECd0HpgoDJqts4O
Wvo/edit#slide=id.gda13d08c73_0_5
Log File
Convolutional Neural Network

In neural networks, Convolutional neural network (ConvNets or CNNs) is one of the main categories to do
images recognition, images classifications. Objects detections, recognition faces etc., are some of the areas
where CNNs are widely used. Technically, deep learning CNN models to train and test, each input image will
pass it through a series of convolution layers with filters . Pooling, fully connected layers (FC) and apply
Softmax function to classify an object with probabilistic values between 0 and 1. The below figure is a
complete flow of CNN to process an input image and classifies the objects based on values.
Convolution of an image with different filters can perform operations such as edge detection, blur and
sharpen by applying filters. The below example shows various convolution image after applying
different types of filters (Kernels)
Proposed method

Step 1: -
Data Preprocessing :
● (a) Data Reduction using python script
● (b) .FIT to .tiff conversion using python script
Step 2 :
Autostakkert:
To stack similar images as well as reduce noise
Step 3 :
Virtual Atlas Moon :
To compare the obtained final .tiff images of the 1 terminator positions with the
Atlas to find the exact location of the Craters and Mountains
Autostakkert Tool
Final Moon Images after Reducing Noise
Results

The Following outputs are the results from the algorithm and achieved using
python script.

Wire Grid Format image


Conclusion

One of the main purposes of our project is to identify and detect Craters and
Mountains on the lunar surface, and to also provide 3D visualization of 2D
image using Deep learning techniques; to analyse the surface better . The other
goal is to develop immersive visualize and analyze tools that increase planetary
information with AI techniques.We will also continue to improve the toolset
guided by the needs of real-world geoscience research questions, especially
those made possible by recently acquired Mars data.
References

● Ercan, Gurcharan, and Peter Whyte. "Digital image processing." U.S.


Patent 6,240,217, issued May 29, 2001.
● Starck, J-L., and Fionn Murtagh. Astronomical image and data analysis.
Springer Science & Business Media, 2007.
● Murtagh, F. "Image analysis problems in astronomy." In Image Analysis
and Processing II, pp. 81-94. Springer, Boston, MA, 1988.
● Chong, Rachel Mabanag, and Toshihisa Tanaka. "Image extrema analysis
and blur detection with identification." In Signal-Image Technology and
Internet-Based Systems, 2008.
● Tao, Bo, and Bradley W. Dickinson. "Texture recognition and image
retrieval using gradient indexing." Journal of Visual Communication and
Image Representation 11, no. 3 (2015): 327-342.

You might also like