Best open-source pedestrian detection library for commercial use?

Best open-source pedestrian detection library for commercial use?

• people_detection

asked Aug 19 '15

Tommi 
21  ●2 ●3 ●7

Hi there,

I'm looking for the best real-time image-based people detection software that is available for commercial use, and easily integrated to ROS. So preferably C++ with a simple structure and clear documentation. I know the state-of-art in people detection; it's easily available from surveys, e.g.

What I would like to have is something similar to the algorithms marked M-Q in the image. However, all seem to be shared with a non-commercial license.

Here is what I've come up so far:

1. OpenCV HOG implementation as ROS package -- however, basic HOG is probably not very accuratehttps://github.com/angusleigh/hog_haa...
2. SPENCER implementation -- again, just basic HOG? Plus, it's an EU project.https://github.com/spencer-project/sp...
3. Munaro et al -- basic Haar & HOG?https://github.com/ros-industrial/hum...

As a bonus, a good tracker that is integrated with the detector would be nice, but not it's not required.

Comments

Can you comment on why you feel they "all seem to be shared with a non-commercial license"? Some open-source licenses explicitly allow commercial use, with just the requirement that you mention the use of the those libraries / dependencies. They don't require you to make your work open source.

gvdhoorn  (Aug 24 '15)

They explicitly mention that the code is shared for research use only.

Tommi  (Aug 25 '15)

All of them? Are these actual open-source licenses then?

gvdhoorn  (Aug 25 '15)

add a comment

1 answer

Sort by » oldest newest most voted

1

answered Sep 14 '15

Tommi 
21  ●2 ●3 ●7

I spent some time reading the FPDW and VeryFast papers. The conclusion is that they are mostly performance optimizations and small tweaks, while the fundamental detector is still HOG. Also, the classifier (SVM, NN, decision forest) does not make a huge difference. Therefore, I decided to go with HOG+SVM because it's fast and simple, and I found a good implementation from http://dlib.net . Example:http://blog.dlib.net/2014/02/dlib-186... Dlib uses an improved version of HOG, by Felzenszwalb et al. Also, performance _should_ be better than OpenCV.

link

add a comment

Your Answer

Please start posting anonymously - your entry will be published after you log in or create a new account.