8000 @MuhammadAsadJaved I can send you the missing data set and share some results about the data set. I wonder if you have time to help me answer a few questions about experimenting on this data set · Issue #19 · SoonminHwang/rgbt-ped-detection · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

@MuhammadAsadJaved I can send you the missing data set and share some results about the data set. I wonder if you have time to help me answer a few questions about experimenting on this data set #19

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
JayAust opened this issue Aug 12, 2020 · 4 comments
Open

@MuhammadAsadJaved I can send you the missing data set and share some results about the data set. I wonder if you have time to help me answer a few questions about experimenting on this data set #19

JayAust opened this issue Aug 12, 2020 · 4 comments

Comments

@JayAust
Copy link
JayAust commented Aug 12, 2020

@MuhammadAsadJaved
Thanks for Sharing! Unfortunately your page seems to be not working either. It has the same dead links from this https://sites.google.com/site/pedestrianbenchmark/home
Do you download from this page recently?
Is it convenient for you to share any subset from day and night? For example set01 and set04.

Originally posted by @diciembre-noche in #18 (comment)
@MuhammadAsadJaved
Copy link

@MuhammadAsadJaved
Thanks for Sharing! Unfortunately your page seems to be not working either. It has the same dead links from this https://sites.google.com/site/pedestrianbenchmark/home
Do you download from this page recently?
Is it convenient for you to share any subset from day and night? For example set01 and set04.

Originally posted by @diciembre-noche in #18 (comment)

@JayAust

You can download complete sets or download sets in parts. Do not download
both. For example, download set00.zip (if you have a fast internet
connection to download big files)
or alternatively download set00_V000.zip, set00_V001.zip, set00_V00n
(small sets for slow internet connection). Don't download both,

https://onedrive.live.com/?authkey=%21ADG6wuQeYqCroBI&id=1570430EADF56512%21624&cid=1570430EADF56512

if you failed to use the above link, then use this link given below to submit a request and they will send you a link in the given email.

https://sites.google.com/site/pedestrianbenchmark/download

@JayAust
Copy link
Author
JayAust commented Aug 13, 2020

@MuhammadAsadJaved
Thanks for Sharing! Unfortunately your page seems to be not working either. It has the same dead links from this https://sites.google.com/site/pedestrianbenchmark/home
Do you download from this page recently?
Is it convenient for you to share any subset from day and night? For example set01 and set04.
Originally posted by @diciembre-noche in #18 (comment)

@JayAust

You can download complete sets or download sets in parts. Do not download
both. For example, download set00.zip (if you have a fast internet
connection to download big files)
or alternatively download set00_V000.zip, set00_V001.zip, set00_V00n
(small sets for slow internet connection). Don't download both,

https://onedrive.live.com/?authkey=%21ADG6wuQeYqCroBI&id=1570430EADF56512%21624&cid=1570430EADF56512

if you failed to use the above link, then use this link given below to submit a request and they will send you a link in the given email.

https://sites.google.com/site/pedestrianbenchmark/download

I have successfully loaded all the contents of the data set, but I don’t know how to deal with the data set and use it in my pedestrian detection framework. If you know something about this, can you briefly describe the process。Thanks a lot

@MuhammadAsadJaved
Copy link
MuhammadAsadJaved commented Aug 13, 2020 •
edited
Loading

@MuhammadAsadJaved
Thanks for Sharing! Unfortunately your page seems to be not working either. It has the same dead links from this https://sites.google.com/site/pedestrianbenchmark/home
Do you download from this page recently?
Is it convenient for you to share any subset from day and night? For example set01 and set04.
Originally posted by @diciembre-noche in #18 (comment)

@JayAust
You can download complete sets or download sets in parts. Do not download
both. For example, download set00.zip (if you have a fast internet
connection to download big files)
or alternatively download set00_V000.zip, set00_V001.zip, set00_V00n
(small sets for slow internet connection). Don't download both,
https://onedrive.live.com/?authkey=%21ADG6wuQeYqCroBI&id=1570430EADF56512%21624&cid=1570430EADF56512
if you failed to use the above link, then use this link given below to submit a request and they will send you a link in the given email.
https://sites.google.com/site/pedestrianbenchmark/download

I have successfully loaded all the contents of the data set, but I don’t know how to deal with the data set and use it in my pedestrian detection framework. If you know something about this, can you briefly describe the process。Thanks a lot

+The dataset contains annotations, color images, and corresponding infrared images. ,
+There are different classes like person, people, cyclist etc

Now you need to see what kind of algorithm and development framework (Tensorflow, PyTorch etc) you are going to use, you have to preprocess the dataset accordingly.

Unluckily non of the existing methods provide source code, they all provide papers. I have tried my best.
These are a few state of the art methods
1- https://arxiv.org/pdf/1808.04818.pdf
2- https://arxiv.org/pdf/1803.05347.pdf
3- https://www.sciencedirect.com/science/article/pii/S1110016820302507

The paper number 1 provides only demo code (https://github.com/Li-Chengyang/MSDS-RCNN)
Currently, I am implementing method number 3 and trying to improve it.

@JayAust
Copy link
Author
JayAust commented Aug 13, 2020

@MuhammadAsadJaved
Thanks for Sharing! Unfortunately your page seems to be not working either. It has the same dead links from this https://sites.google.com/site/pedestrianbenchmark/home
Do you download from this page recently?
Is it convenient for you to share any subset from day and night? For example set01 and set04.
Originally posted by @diciembre-noche in #18 (comment)

@JayAust
You can download complete sets or download sets in parts. Do not download
both. For example, download set00.zip (if you have a fast internet
connection to download big files)
or alternatively download set00_V000.zip, set00_V001.zip, set00_V00n
(small sets for slow internet connection). Don't download both,
https://onedrive.live.com/?authkey=%21ADG6wuQeYqCroBI&id=1570430EADF56512%21624&cid=1570430EADF56512
if you failed to use the above link, then use this link given below to submit a request and they will send you a link in the given email.
https://sites.google.com/site/pedestrianbenchmark/download

I have successfully loaded all the contents of the data set, but I don’t know how to deal with the data set and use it in my pedestrian detection framework. If you know something about this, can you briefly describe the process。Thanks a lot

+The dataset contains annotations, color images, and corresponding infrared images. ,
+There are different classes like person, people, cyclist etc

Now you need to see what kind of algorithm and development framework (Tensorflow, PyTorch etc) you are going to use, you have to preprocess the dataset accordingly.

Unluckily non of the existing methods provide source code, they all provide papers. I have tried my best.
These are a few state of the art methods
1- https://arxiv.org/pdf/1808.04818.pdf
2- https://arxiv.org/pdf/1803.05347.pdf
3- https://www.sciencedirect.com/science/article/pii/S1110016820302507

The paper number 1 provides only demo code (https://github.com/Li-Chengyang/MSDS-RCNN)
Currently, I am implementing method number 3 and trying to improve it.

Thank you very much for your reply. I found a paper about other uses of the KAIST dataset on GitHub. The address of GITHUB is https://github.com/CalayZhou/Multispectral-Pedestrian-Detection-Resource .The main problem I am facing now is that although I can find some comparative experimental data on the GITHUB of these papers, I have not been able to find out how to use these data to draw the MR vs FPPI curve. I tried to use the toolbox for evaluating the Caltech data set. Use the data found to draw a curve, but failed. If you have any good methods, can you tell me. If you are also studying this direction, I wonder if I can get in touch with you and communicate with you

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@MuhammadAsadJaved @JayAust
0