<div dir="auto"></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">---------- Forwarded message ---------<br>From: <strong class="gmail_sendername" dir="auto">Naman Jain</strong> <span dir="auto"><<a href="mailto:naman1205jain@gmail.com">naman1205jain@gmail.com</a>></span><br>Date: Tue, Mar 10, 2020, 08:57<br>Subject: Re: Robotics Academy Project for GSoc 2020<br>To: <<a href="mailto:edupergar@gmail.com">edupergar@gmail.com</a>>, <<a href="mailto:n.arranz.agueda@gmail.com">n.arranz.agueda@gmail.com</a>><br></div><br><br><div dir="ltr">Hi,<div>I contacted you two weeks ago for queries about the computer vision GSoC project. I understand you might have missed the mails due to your busy schedule, I thought it best to remind you.</div><div>Specifically, my queries were:</div><div><br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><strong style="background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">Queries: </span></strong><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">I had some queries about the end goals of the project. Particularly, I am interested in how are the exercises to be integrated with ROS and cameras. While computer vision exercise can be performed solely on offline videos, I understand that using webcam input would be exciting and add more interest to them. So I wanted to ask, what kind of integration do you plan to use between camera input and exercises. For some exercises I was thinking about, it might not be possible to have real-time algorithms too. </span></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">Secondly, in one of the computer vision exercise on FollowFace, you have an explicit requirement of Sony Evi dp100 camera. Would there be other hardware requirements for working on the project? </span></p></blockquote><div><br></div><div>I also had some mentioned project ideas, which I would be glad if you could comment on. </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Apart from some simple and fundamental exercises on image gradients and using different filters, corner detection we could add interesting exercises such as <span style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt">panorama stitching, image alignment, noise removal, </span><a href="https://en.wikipedia.org/wiki/Inpainting" style="color:rgb(74,110,224);background:transparent;margin-top:0pt;margin-bottom:0pt" target="_blank" rel="noreferrer"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">image inpainting</span></a><span style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt">, cartoonifying images (using edge detection and noise addition), style transfer (based on image processing techniques). We could also operate on video tasks using KLT Tracking, video stabilization, optical flow etc.</span></blockquote><div><br></div><div>Thanking you in advance,</div><div>Naman</div><div> </div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Mon, Feb 24, 2020 at 2:57 PM Naman Jain <<a href="mailto:naman1205jain@gmail.com" target="_blank" rel="noreferrer">naman1205jain@gmail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">Hi,</span></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">I am a final year undergraduate studying computer science at IIT Bombay. I am enthusiastic about research primarily in areas of machine learning applied to computer vision. I will be continuing to take graduate studies in computer vision starting Fall'20. </span></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><br></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><strong style="background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">Motivation: </span></strong><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">I was looking at GSoC 2020 projects and came across the Robotics Academy project for adding new computer vision exercises and found it matching my interests. I believe with my strong background in computer vision, I would be a good fit for this position and it would also be a nourishing opportunity for me. </span></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><br></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><strong style="background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">Previous Open Source Work: </span></strong><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">My work on </span><a style="background:transparent;margin-top:0pt;margin-bottom:0pt;color:rgb(74,110,224)" href="https://github.com/Naman-ntc/Pytorch-Human-Pose-Estimation/" target="_blank" rel="noreferrer"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">human pose estimation</span></a><span style="background:transparent;margin-top:0pt;margin-bottom:0pt"> has been used in several people around the globe. I have also contributed to </span><a style="background:transparent;margin-top:0pt;margin-bottom:0pt;color:rgb(74,110,224)" href="https://github.com/pytorch/pytorch/pull/6136" target="_blank" rel="noreferrer"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">Pytorch</span></a><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">, a deep learning library and committed the `randint` function along with relevant documentation and tests. You can find my other work on my </span><a style="background:transparent;margin-top:0pt;margin-bottom:0pt;color:rgb(74,110,224)" href="https://github.com/Naman-ntc/" target="_blank" rel="noreferrer"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">github page</span></a><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">.</span></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><br></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><strong style="background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">Queries: </span></strong><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">I had some queries about the end goals of the project. Particularly, I am interested in how are the exercises to be integrated with ROS and cameras. While computer vision exercise can be performed solely on offline videos, I understand that using webcam input would be exciting and add more interest to them. So I wanted to ask, what kind of integration do you plan to use between camera input and exercises. For some exercises I was thinking about, it might not be possible to have real-time algorithms too. </span></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">Secondly, in one of the computer vision exercise on FollowFace, you have an explicit requirement of Sony Evi dp100 camera. Would there be other hardware requirements for working on the project? </span></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><br></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><strong style="background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">Ideas: </span></strong><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">I was thinking of possible exercises to add and I was able to come up with many interesting ideas for the exercises based on projects I have completed or seen. We could add exercises on panorama stitching, image alignment, noise removal, </span><a style="background:transparent;margin-top:0pt;margin-bottom:0pt;color:rgb(74,110,224)" href="https://en.wikipedia.org/wiki/Inpainting" target="_blank" rel="noreferrer"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">image inpainting</span></a><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">, cartoonifying images (using edge detection and noise addition), style transfer (based on image processing techniques). We can also come up with exercises on video (KLT tracking, video stabilization), etc. </span></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">I would think of more cases that can be used to teach computer vision. Please let me know what do you think about these ideas and if I should explore some particular direction you might have in mind. </span></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><br></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt">Looking towards a positive response.</p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><br></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">Thanking You,</span></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">Naman Jain</span></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">Final Year UG</span></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">CSE, IIT Bombay</span></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><br></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">Web: </span><a style="background:transparent;margin-top:0pt;margin-bottom:0pt;color:rgb(74,110,224)" href="http://naman-ntc.github.io/" target="_blank" rel="noreferrer"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">http://naman-ntc.github.io/</span></a></p><p style="color:rgb(14,16,26);background:transparent;margin-top:0pt;margin-bottom:0pt"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">Mail: </span><a style="background:transparent;margin-top:0pt;margin-bottom:0pt;color:rgb(74,110,224)" href="mailto:naman1205jain@gmail.com" target="_blank" rel="noreferrer"><span style="background:transparent;margin-top:0pt;margin-bottom:0pt">naman1205jain@gmail.com</span></a></p></div>
</blockquote></div>
</div>