tag:blogger.com,1999:blog-87352076546675199432024-03-21T00:30:09.262-07:00RIT Imaging Science: Visual Perception4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.comBlogger31125tag:blogger.com,1999:blog-8735207654667519943.post-82262803760203942702017-08-16T07:58:00.001-07:002017-08-16T07:58:37.861-07:00Day 29 In the morning, we had our practice presentation. Out of my expectation, my timing was actually pretty well.<br />
Right after I presented in the morning, I presented again to Dr. Pelz, and he had some small changes for me.<br />
I still need to practice more!4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-34370013062287046722017-08-16T07:57:00.001-07:002017-08-16T07:57:02.505-07:00Day 28 We're going to have a practice presentation tomorrow.<br />
In the morning, I practiced presenting to Jo right before Dr. Pelz came in. So I practiced again to Dr. Pelz. They had many good feedbacks like the number of texts and the pictures.<br />
Then I edited the power point. In the afternoon, I presented again to Ayush at 3pm right before Dr. Pelz came in again. So I presented again to Dr. Pelz and got a lot of feedbacks as well.<br />
In the evening, I presented to my mom and Ronny.<br />
<br />
Five presentations a day!<br />
<br />4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-70564994545333709272017-08-11T16:48:00.001-07:002017-08-11T16:48:48.309-07:00Day 27 Last full week of work.<br />
I prepared my presentation today. I'm going to see the presentation with Dr. Pelz on Monday and have the practice presentation on Tuesday.<br />
I'm adding notes to my presentation so I won't forget what information to talk about.<br />
I started to read some machine learning materials They seem to be really hard.4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-6680634218641053482017-08-10T15:00:00.000-07:002017-08-11T05:46:08.842-07:00Day 26 Today I finished making my presentation. Iyus helped me with formatting.<br />
In the afternoon, we had our group meetings. Titus and Aditi did their practice presentations and they sounded really good.<br />
Still, I'm testing the method on a series of images. The current results don't seem to be satisfying mainly because of the unsettled thresholds.<br />
I think I'll finish it by the end of the internship!<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgpFB_IZISCt7HiEYKJU400iqIUCoD7BPEoOqEXh6NB0AVAuLAnPpXix8pu6PDqD6mnxWgxw2CNjR51DUyxeUQloX7Lcri3J8bKTVzWM2zxv2ZXbpfnhfVA6FqMr4bgeG_SLuJKIn3SC34/s1600/125I1436.NEF.tif" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1056" data-original-width="1600" height="211" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgpFB_IZISCt7HiEYKJU400iqIUCoD7BPEoOqEXh6NB0AVAuLAnPpXix8pu6PDqD6mnxWgxw2CNjR51DUyxeUQloX7Lcri3J8bKTVzWM2zxv2ZXbpfnhfVA6FqMr4bgeG_SLuJKIn3SC34/s320/125I1436.NEF.tif" width="320" /></a></div>
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiKZ0SffX2AGKQiOkeZsPZ4G3vx8HK6A2HV8inegLWug6sK1vW61eaWjctft_g2ofB0CzljXoxW-w01HR9bbIRxv4W7RPl-x2Pj2mL7Xd4uq2c7FdKt0D1-Z-wWOeu7vahUvq56EZL16S0/s1600/demos125I1436.NEF.tif" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1056" data-original-width="1600" height="211" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiKZ0SffX2AGKQiOkeZsPZ4G3vx8HK6A2HV8inegLWug6sK1vW61eaWjctft_g2ofB0CzljXoxW-w01HR9bbIRxv4W7RPl-x2Pj2mL7Xd4uq2c7FdKt0D1-Z-wWOeu7vahUvq56EZL16S0/s320/demos125I1436.NEF.tif" width="320" /></a></div>
<br />4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-5834582919809424352017-08-10T06:05:00.000-07:002017-08-10T06:05:41.049-07:00Day25 I ran a sequence of images today and it worked out well. I'm still working on my presentations. I included some images in my presentation.<br />
Although Dr. Pelz is not here this week, he sent me the things I can do. I'll test on different sequences of images and see if the results will be the same.4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-82614226304523195272017-08-08T17:24:00.000-07:002017-08-08T17:24:30.309-07:00Day 24 I was the only one working in my lab today.<br />
In the morning, I started revising my code again. I updated the algorithm according to Dr. Pelz and Mr. Blacksberg's suggestion.<br />
However, because of the float data Python gives me, I have to wait for fifteen minutes to see the result. In the afternoon, I spent much time debugging the code.<br />
I was a little disappointed about the result. I'm trying to revise some of the former code so it will work hopefully before presentations.4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-54729735437242253552017-08-07T16:18:00.000-07:002017-08-07T16:18:24.292-07:00Day 23 Today I met with Mr. Blacksberg. He is such a nice man and he's humorous too.<br />
I presented to him the things I've done, and he gave me some suggestions on future works. He also told me about his life including his educations and jobs.<br />
I was kind of nervous when I was presenting, which means I need to practice more in the future.4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-31986758196541947262017-08-06T11:58:00.002-07:002017-08-06T11:58:48.755-07:00Day22 Today is the undergrad symposium. I invited Zihao and we went to the posters and presentations together.<br />
In the morning, we visited the poster session. There're many different kinds of ideas including the new designs of laptops and soda machines.<br />
The lunch was really good, and we enjoyed a lot.<br />
In the afternoon, we went to the mathematical modeling presentations and more posters including Turing machines.<br />
After that, we took pictures with the whole eye tracking lab and said goodbye to Jeremy.<br />
It sure was a nice day!4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-57636569250661892662017-08-03T17:13:00.000-07:002017-08-03T17:13:32.551-07:00Day 21 Today is the last day for REU student. I feel a little sad because Jemery is leaving after his presentation tomorrow. This reminds me that my remaining time is not much.<br />
In the noon, I went to help Mingming move the simulator. It was not heavy but it took us an hour to move it. In the afternoon, we had lab meetings. Jo and Jeremy presented during the meeting. The presentations were impressive and incredible.<br />
Tomorrow is the undergraduate students' symposium and hoping I'll enjoy!4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-387892715321235602017-08-02T18:37:00.000-07:002017-08-02T18:37:32.276-07:00Day 20 It was a nice day!<br />
I sent Dr. Pelz the code explanation in the morning. He edited it and sent me back with comments and suggestions.<br />
It was a pity that I did not get a pizza for lunch.<br />
In the afternoon, I revised the code explanation. Dr. Pelz showed me a digital camera and how to use it. I have to admit that it's more complicated than I thought.<br />
I'm excited with my project because I can see hope everyday. I'm going to test the code on different images and see how it works!4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-13937665444310803542017-08-01T16:17:00.001-07:002017-08-01T16:17:57.159-07:00Day 19 It seems that Zihao is the only friend we invited today. Ronny and I showed him different labs and the projects we were working on after morning session. He left after about an hour.<br />
Today I finished writing the brief explanation about the code and Dr. Pelz read it through. After that, I read some papers about simple machine learning staff.<br />
In the afternoon, I started to compare the images, and I found that the parameters can be set in a better way. After that, I tried to change some parameters in the functions. I first used a tracker bar. However, the difference was too small for me to see. So I zoomed a small region and compared the difference only at that small region, and it worked pretty well.<br />
<br />4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-40816920203215404222017-07-31T19:06:00.000-07:002017-07-31T19:06:15.405-07:00Day 18 I pretty much finished my codes today.<br />
In the morning, I met Dr. Pelz and he suggested me write up a brief explanation about my code.<br />
In the afternoon, we went outside to take some videos about our eyes when wearing eye tracker. After that, I read something about basic machine learning.<br />
It sure is a busy day today!4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-52117765516703711202017-07-30T16:51:00.001-07:002017-07-30T16:51:53.814-07:00outline<div class="MsoNormal">
Outline<o:p></o:p></div>
<div class="MsoNormal">
Slide1: (title) Cosmic Ray Damaged Images Repair (picture1)Damaged (picture2)After repairing<o:p></o:p></div>
<div class="MsoNormal">
Slide2: (title) summary of the presentation<o:p></o:p></div>
<div class="MsoNormal">
What is cosmic rays and how do they affect the images?<o:p></o:p></div>
<div class="MsoNormal">
challenges we are facing<o:p></o:p></div>
<div class="MsoNormal">
brief history about previous works<o:p></o:p></div>
<div class="MsoNormal">
(*)The algorithm of removing the hot pixels<o:p></o:p></div>
<div class="MsoNormal">
(*)How the algorithm works.<o:p></o:p></div>
<div class="MsoNormal">
Possible applications<o:p></o:p></div>
<div class="MsoNormal">
Slide3: (title) How do Cosmic Rays Damage Images?<o:p></o:p></div>
<div class="MsoNormal">
The images taken by us on the earth won’t be affected by cosmic rays because the atmosphere blocks most of the cosmic rays. However, in the space there are many kinds of cosmic rays existing. We can’t see cosmic rays directly, but their energy is high enough to cause damage on the space camera. The damage may cause the resulting images to have hot pixels on them.<o:p></o:p></div>
<div class="MsoNormal">
Image of hot pixels. <o:p></o:p></div>
<div class="MsoNormal">
Slide4: (title) Challenges<o:p></o:p></div>
<div class="MsoListParagraphCxSpFirst" style="mso-list: l0 level1 lfo1; text-indent: -.25in;">
<!--[if !supportLists]-->1.<span style="font-size: 7pt; font-stretch: normal; font-variant-numeric: normal; line-height: normal;"> </span><!--[endif]-->Distinction between hot pixels and stars (image).<o:p></o:p></div>
<div class="MsoListParagraphCxSpLast" style="mso-list: l0 level1 lfo1; text-indent: -.25in;">
<!--[if !supportLists]-->2.<span style="font-size: 7pt; font-stretch: normal; font-variant-numeric: normal; line-height: normal;"> </span><!--[endif]-->Removing hot pixels from solar panels. (image)<o:p></o:p></div>
<div class="MsoNormal">
Silde5: (title) previous work<o:p></o:p></div>
<div class="MsoNormal">
Kevin Moser from RIT did an incredible work on this project. (with an Image)<o:p></o:p></div>
<div class="MsoNormal">
Limitations(maybe)<o:p></o:p></div>
<div class="MsoNormal">
Slide6: (title)algorithm—brief whole<o:p></o:p></div>
<div class="MsoNormal">
….<o:p></o:p></div>
<div class="MsoNormal">
Slide7: (title)algorithm sub-step1<o:p></o:p></div>
<div class="MsoNormal">
…<o:p></o:p></div>
<div class="MsoNormal">
Slide8: (title)algorithm sub-step2<o:p></o:p></div>
<div class="MsoNormal">
…<o:p></o:p></div>
<div class="MsoNormal">
Slide9: (title)algorithm sub-step3<o:p></o:p></div>
<div class="MsoNormal">
…<o:p></o:p></div>
<div class="MsoNormal">
Not sure how many slides will be used for sub-steps.<o:p></o:p></div>
<div class="MsoNormal">
Slide 11:<o:p></o:p></div>
<div class="MsoNormal">
(title)Comparison between the image before with the image after.<o:p></o:p></div>
<div class="MsoNormal">
Two images<o:p></o:p></div>
<div class="MsoNormal">
Some statistics. Chart true positives, true negatives, false positives, false negatives<o:p></o:p></div>
<div class="MsoNormal">
Slide 12:<o:p></o:p></div>
<div class="MsoNormal">
(title)Applications.<o:p></o:p></div>
<br />
<div class="MsoNormal">
Make the images look better. It can also help to clean the noise so we can see the stars more clearly.<o:p></o:p></div>
4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-13696861805916347222017-07-30T15:36:00.000-07:002017-07-30T15:36:32.008-07:00Day 17 Dr. Pelz is not here today, but he gave me many suggestions yesterday.<br />
I tried his suggestion today and it worked pretty well. Although I'm not sure if it will work on all kinds of images, I decide to keep it as it works on the images I'm working on. I haven't started my outline yet, but I don't think it will take too much effort.<br />
In the afternoon at around 2pm, I felt sleepy again -- maybe because it's kind of warm in our room. I went for a walk and drank some water, and they worked out significantly.<br />
I think I'm almost done with the project, but I still have more things to do and I'm still looking for a more convenient way to achieve it.<br />
<br />
<br />4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-77943317313148206392017-07-28T08:05:00.002-07:002017-07-28T08:05:37.314-07:00Day16 The most exciting day so far!<br />
In the morning, I wrote more code about my algorithm and read some paper about machine learning. After lunch, I went to the group meeting and "drove" a car on a simulator. It was the best game I've ever played in my life: real car, "real" traffic, real sound.<br />
After that, Dr. Pelz shared with me his way of removing hot pixels. Although it's more convenient and easy to code, his program met the same problem as mine -- they are not able to effectively remove the hot pixels on the solar panels. Nevertheless, Dr. Pelz gave me some really valuable suggestions and they can improve the algorithm very much.<br />
The observatory at night was overall satisfying. Although we were not able to actually observe any stars because of the cloudy sky, we had a wonderful meal and we learned a lot about both the history of the observatory and how an eclipse happens.<br />
<br />
<br />4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-71194190262560735742017-07-26T16:35:00.001-07:002017-07-26T16:35:39.548-07:00Day15 I'm at half way through the internship.<br />
In the morning, we shared the projects we are doing. It seems that most of other interns had accomplished a lot on their projects. I tested different thresholds on the algorithm, and chose a suitable one and sent it to Dr. Pelz to see if it works. I also helped Jeremy with his Pupil Lab calibration.<br />
In the afternoon, I was trying to increase my algorithm's accuracy. I tested new method and I haven't finished coding yet. I helped Jeremy test both the Pupil Lab calibration and the Positive Science calibration.<br />
I forgot to take my lunch today. Instead, I had Pizza for lunch. How lucky!4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-57362915470610333462017-07-25T16:19:00.001-07:002017-07-25T16:19:44.727-07:00Day14 First thing of today is finding a way to read h5 files. After searching online, I found some libraries that support reading hdf5 files. However, they only seem to be friendly to Visual C++. While I was thinking if I should try to move to Visual C++, I found a software which is published by hdf5 company saying that it can read hdf5 files. After actually looking at it, I found it more powerful than it looked like: it can export hdf5 to text files. Although using C++ to read text files is not that fast, it's now the best way for me to at least read a raw image.<br />
<br />
After lunch, I started to write codes for it. After about half an hour of coding, my code gave me the result I wanted which was kind of out of my expectation. Then I was kind of wandering around and reading more tutorials. Then Dr. Pelz came in and we looked at the resulting image. Dr. Pelz seemed to be excited and he immediately asked me to perform Bayer filter on it. After doing some research, I performed Bayer filter on the images. I'm still a little afraid that the program is not able to effectively keep all the original features when removing most of the noises.<br />
<br />
I will try changing some of the constants tomorrow and see how the program works out.4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-80073023497040160442017-07-25T10:32:00.000-07:002017-07-25T10:32:12.086-07:00Day 13 This morning, Dr. Pelz met with us and he patiently and carefully helped me make the algorithm more clear so I can start implementing the algorithm on raw images.<br />
I don't know why C++ makes it so hard to read and write raw images. I spent so much time trying to figure out how to read a raw image. In the end, Dr. Pelz exported the raw image as a hdf5 file for me to read when I was about to learn Python. What I'm going to do is to modify my previous code that can only run on tiff images so it can directly run on NEF images. I'm going to have a lot of code to write I can't wait to see the result!4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-85624625187796215532017-07-21T17:07:00.000-07:002017-07-21T18:01:40.537-07:00Day 12 It was a short morning session, and we didn't talk about anything particularly important.<br />
In the morning, I combined Dr. Pelz's idea and the method I used before on jpg files together and how well it worked on the dead pixels. As there are too many variables for different images and it seems like the way I used before can only be used to preserve the useful pixels, I decided to update the method I used before on jpg files.<br />
In this afternoon, I was trying to think up a new way of detecting, and I'm still estimating the availability of the method. Hopefully, I will see the result on Monday!4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-39189587826296861552017-07-20T15:59:00.002-07:002017-07-20T15:59:36.190-07:00Day11 We successfully finished reading all of our abstracts today!<br />
As usual, I met Dr. Pelz in the morning and we talked more about the CRDIR project. He had some work for me to do.<br />
In order to have a good plan for what to do next after this project, I went to the REU meeting and the group meeting. Both include incredible presentations. I'm going to finish my tutorial tomorrow, hopefully, and start my next project next week.<br />
<br />4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-35482887804708434492017-07-20T06:19:00.001-07:002017-07-20T06:19:13.609-07:00Day10 In the morning session, we read more people's abstracts and gave suggestions to them.<br />
I met Dr. Pelz after that. He told me that he found a function in Rawpy library that can actually detect dead pixels by using two sentences. It seems like both Kevin and I did not do enough reading before starting our project. I started to read some "literature" and see what others had done on this project.<br />
It seems like my project is going to end. But I still want to finish this with a way that does not require multiple pictures. I started to debug the code I've done and added more constraints on it. Now it works pretty well and the method can be used on both raw and jpg images noise and defective pixel clearance.4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-88398289458835467402017-07-18T16:34:00.002-07:002017-07-18T16:34:34.171-07:00Day9 In the morning, we shared several abstracts and I got valuable suggestions from both peers and Joe.<br />
I met Dr. Pelz in the morning and he had a really cool idea relating to the project I'm doing. After absorbing his idea and algorithm, I started to write code for it. The code itself worked well. However, I used a wrong way to convert NEF files to Tiff files, which took me a lot of time to debug. Hopefully, this will work tomorrow.<br />
After figuring out the error of the conversion of NEF files, I started to think about our former method which doesn't require more than one frames. I think I can figure both ways out.4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-55577366843312359802017-07-17T16:40:00.000-07:002017-07-17T19:38:21.894-07:00Day 8 In the morning session, I shared my project and abstract with the group.<br />
After that, I proofread Kevin's paper again. Although his used kernels well, I still had some confusions about what kinds of defective pixels his algorithm can clean.<br />
After lunch, Ronny joined my lab. We had several long nice conversations with Dr. Pelz about both the effective ways to read raw images and the algorithm Ronny and I designed last week. Dr. Pelz had many helpful suggestions towards our algorithms and our algorithms both ran faster and found targets more accurately.<br />
Our next step is actually implementing our algorithms on raw images. We are also trying to update our algorithm to recognize the defective pixels more accurately.4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-62380858016458901292017-07-16T11:05:00.001-07:002017-07-16T11:05:12.104-07:00Abstract<div class="MsoNormal" style="text-indent: .5in;">
<span style="font-family: "Times New Roman",serif; font-size: 12.0pt; line-height: 107%;">Particles that bombard the Earth from anywhere beyond its atmosphere are known as cosmic rays. Although we can’t see the cosmic rays or feel it, it does exit outside the atmosphere and it may cause people who work at space some trouble, one of which is the damage to the pictures taken by the digital cameras. If you zoom in the pictures taken by NASA, you may find some defective pixels which are damaged by cosmic rays. Those defective pixels will not only reduce the quality of the pictures, but will also distract the analysis of the stars. Cosmic Ray Damaged Image Repair requires to come up with an effective way to clean up as many as defective pixels while keep as much as effective pixels unchanged. We will both analysis briefly about summarized previous methods and the new way of detecting and cleaning defective pixels along with proofs and evaluations.<o:p></o:p></span></div>
4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0tag:blogger.com,1999:blog-8735207654667519943.post-34580501450179623912017-07-16T09:35:00.000-07:002017-07-16T09:35:42.815-07:00Day 7 I learned a lot today. In the morning, we had a small lab meeting. First, Iyus made a short presentation about his Iris detection lab. Dr. Pelz gave him some valuable suggestions about the priority of detections. After that, Dr. Pelz showed us his previous version of eye trackers and the way they work. They record the gradient vectors of each pixel and see them as unique. Dr. Pelz also shared his next possible version of eye tracker with us.<br />
<br />
In the afternoon, we worked individually. I started writing my Cosmic Ray Damaged Image Repair project and made some progress. Dr. Pelz also sent me Kevin Moser's email because he was a former student who made progress on this project.<br />
<br />
I started to write the abstract for my paper and I hope I can make more progress on my project!4Dmoviehttp://www.blogger.com/profile/09122290391986616784noreply@blogger.com0