Basic Information
- Course Code: GNR607
- Course Name: Principles of Satellite Image Processing
- Course Offered In: 2023-‘24
- Semester Season: Autumn
- Instructors: Bal Krishan Mohan
- Prerequisites: None
- Difficulty (1 being easy and 5 being tough): 2
Course Content
Introduction to Digital Image Processing, Sensors for Remote Sensing, Histogram and Image Enhancement Methods, Neighborhood Operations, Various types of filters such as Sobel Filter, Prewitt and many more, Hough Transform, Color Models, PCT, Data Fusion and Band Arithmetic, Texture Analysis Principles, Fourier Transform and Filters, Morphological Image Processing, Image Classification Methods, Supervised vs. Unsupervised Classifiers and their subtypes, Likelihood Calculation, NDVI calculations and various small sub topics related to remote sensing.
Feedback on Lectures
The course was a introductory course and covered lot of topics with little depth. The prof taught everything on board but also gave slides which were enough even if you didn’t take the lectures but then ofc, some effort to understand(GPT xd) topics was required. The lecture pace is quite slow throughout the course, so prof took 2-3 extra classes in the entire semester. The professor was quite slow, lacked enthusiasm but If you attend the lectures then just that day 1hr recap is sufficient. If you are from EE, then the Fourier part which the prof teaches gets perfectly complimented by the Signals(EE229) Fourier part. The course has very good applicative knowledge of Fourier transforms.
Also attendance was compulsory and in each class attendance was there. The prof had said if it falls below 75% he would give DX, but no one received it.
There is a project in the end (The prof floats multiple topics form which you can choose one). It’s quite easy to do (Thanks to GPT these days) along with which a small ppt is to be made for submission.
Feedback on Evaluations
There were 2 quizzes(10%+10%), midsem(20%), endsem(40%) and project(20%). Reading the slides and understanding concepts is more than sufficient.
The only thing which I disliked about this course was the factual knowledge of Remote Sensing. Although it’s important to know, but due to large number of topics, memorizing them is not easy & the prof does ask 5-6% questions from those facts in quizzes and midsem.
The Grading was a little bit disappointing the year which I took the course, although the same professor had done very very generous grading last year( Autumn’22). Refer asc for more info.
Study Material and Resources
Since a very huge no. of topics were covered, if you want a deeper dive, The prof said to read Digital Image Processing Book by Rafael C. Gonzalez and Richard E. Woods
Follow-up Courses
GNR602 - Advanced Methods in Satellite Image Processing
Final Takeaway
The course is very shallow with a huge array of topics covered, so serves as a perfect introductory course. So if you are curious about Remote sensing or Image processing, then this is a perfect course to serve as a start.