Skip to content
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.

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

Where is SVM classifier clue on this package? #11

Open
agn-7 opened this issue Apr 19, 2019 · 13 comments
Open

Where is SVM classifier clue on this package? #11

agn-7 opened this issue Apr 19, 2019 · 13 comments

Comments

@agn-7
Copy link
Contributor

agn-7 commented Apr 19, 2019

According to your published paper, the selected classifier is SVM and AdaBoost ([43] Kidono reference), but I cannot find SVM clue on your package.

I found the only AdaBoost model and its code (people_detector.cpp).

@koide3
Copy link
Owner

koide3 commented Apr 21, 2019

We tested several classifiers (SVM, AdaBoost, RandomForest) with Kidono's features. Since AdaBoost showed a bit better accuracy than the other ones, in this work, we are using AdaBoost instead of SVM.

@agn-7
Copy link
Contributor Author

agn-7 commented Apr 21, 2019

Do you have the SVM classifier version of this code?

@koide3
Copy link
Owner

koide3 commented Apr 22, 2019

Since I did it a few years ago, and I left my former university last year, I'm not sure if I can find the SVM model... If you want, I can share the dataset I used to train the classifiers so that you can train the model by yourself.

@agn-7
Copy link
Contributor Author

agn-7 commented Apr 23, 2019

Any help would be greatly appreciated. May you share it?

@agn-7
Copy link
Contributor Author

agn-7 commented Apr 24, 2019

Another question:

What are the extracted features on this project? And are these features the same in AdaBoost and SVM?

@koide3
Copy link
Owner

koide3 commented Apr 26, 2019

We are using the features proposed in the following paper:
Kidono et al., Pedestrian Recognition Using High-definition LIDAR, IV, 2011

You can extract the features from a point cloud with this code.
https://github.com/koide3/hdl_people_tracking/blob/master/include/hdl_people_detection/kidono_feature_extractor.hpp

@koide3
Copy link
Owner

koide3 commented Apr 27, 2019

Here, you can find the dataset for pedestrian detection. It consists of KITTI, sydney, and our own dataset. To avoid some copyright problems, I put only the extracted features saved in the libsvm format.

https://drive.google.com/open?id=1ovFA9gwjo1zD6cj_q0dnGFR6XYapxbxk

@agn-7
Copy link
Contributor Author

agn-7 commented Apr 27, 2019

Thanks a lot.

Now, can I use any classifier to train with this dataset?

@tkbtvrobert
Copy link

I would also like to know how to train on custom data(AdaBoost, RandomForest), any guidance to save hours reverse understanding the code would be great. Thank you very much!!

@koide3
Copy link
Owner

koide3 commented Feb 21, 2022

This package uses the standard cv::ml model, and you can replace it with any custom model you want to use.
https://github.com/koide3/hdl_people_tracking/blob/master/src/kidono_human_classifier.cpp

@tkbtvrobert
Copy link

Very thank you for your advice, it helped me a lot.

@agn-7
Copy link
Contributor Author

agn-7 commented Feb 21, 2022

@koide3
Thanks for your response.
However, I wish you had answered in 2019 😀

@tkbtvrobert
Copy link

@koide3
Hello, I have another question to ask you, is the feature format of adaboost the same as libsvm? I want to train an adaboost model, how can I use kidono_feature_extractor.hpp to extract features?
Thank you very much!!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants