[JdeRobot] Fwd: GSoC 2020 - Project Idea for Robotics Academy: new computer vision exercises

[Eduardo Perdices]

---------- Forwarded message ---------
From: Shantam Shorewala <shantamshorewala at gmail.com>
Date: Thu, Mar 19, 2020 at 7:31 AM
Subject: GSoC 2020 - Project Idea for Robotics Academy: new computer vision
exercises
To: <n.arranz.agueda at gmail.com>, <edupergar at gmail.com>


Dear Sir

Hello, hope you are safe during the current pandemic.

I am writing this mail to express in my interest in the project idea for
GSoC 2020 proposed by JdeRobot on developing computer vision exercises
using OpenCV library over ROS framework. I have substantial experience
working with Python and OpenCV as well as intermediate experience with ROS.
For reference, you can view my Github profile at
https://github.com/ShantamShorewala

For the project, I will be preparing a detailed proposal for submission
which I aim to complete by the end of this week in order to share with you.
In a rudimentary sense, I propose to plan computer vision exercises around
the following topics:

1. Different segmentation techniques (color, shape) in various colorspaces
such as RGB, HSV, LAB, etc.
2. Feature detection and object tracking across frames using these features
(in-built feature detectors such as SURF, SIFT, ORB, etc). For object
detection, I suggest both integrated techniques like optical flow, matching
as well as others like Kalman filters.
3. Object pose estimation using PnP.
4. Contours and their properties, edge detectors.

I would appreciate any feedback on the above mentioned. If you have any
other suggestions, I look forward to hearing them.

Kind regards
Shantam Shorewala

P.S. I completed by bachelor's last summer (2019). I have applied for
graduate programs for this Fall and I hope to hear from some of them before
the proposal submission deadline (29th March). I felt I should let you know
about the same.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://gsyc.urjc.es/pipermail/jde-developers/attachments/20200319/6f0f8c28/attachment.html>