Point cloud sensors

Hello
I want to share a post to awaken on capture technologies !

I am interested in knowing the best solution for capturing a point cloud in real time to realize interactive screen walls for example.

The intel Realsense look pretty good to me :

http://www.pattenstudio.com/works/intel-nyfw2015/
http://www.pattenstudio.com/works/intel/
http://www.pattenstudio.com/works/intel-2016/

My interrogation is how to merge properly and easily point cloud (depthmap) between multiple sensors like realsense ?

Interesting tool :

Other track :
3D LIDAR like SICK, VELODYNE…

Thanks to share your experience !

I am using an Intel RealSense D435 for a project at the moment. The SDK is solid, but lacks a great amount of features. For example, there is no support for human tracking, let alone skeleton tracking. It only supports connecting/disconnecting, obtaining the color and depth streams, correcting the camera shift between color and depth cameras and creating a point cloud from the depth stream.

The SDK supports multithreading through the use of concurrent buffers and is pretty stable.

To align multiple cameras, I wrote a tool to change each camera’s virtual position, height and pan&tilt angles. Results are more than adequate for our use case. I tried using Perspective-N-Point calibration, but could not get OpenCV’s solvePnP to work at all. I honestly believe it’s broken.

-Paul

Realtime is a tough thing to crack. The best way is definitely something like Paul suggested, and to know the real-world positions of your cameras and position them similarly in code. Otherwise, use some kind of real world calibration like openCVs checkerboard.

It’s something the guys at http://www.depthkit.tv/ have also done a lot of work on with pretty cool results. They are more focused on volumetric filmmaking, but still super cool.

Hello,
Do you know solution to track people with multiple camera like
https://www.youtube.com/watch?v=J_XJ2lYzHmk or https://vimeo.com/131585517 ?

Have you tested http://openptrack.org/ with OpenPose, ROS, PCL and Yolo ?

Colin

I don’t know if there is necessarily a best practices for it, but at least for Connected Worlds, Theo did a really nice video where he broke down some of the challenges they had while making it https://vimeo.com/131665883

1 Like