RealSense R200 getting started

[BKain]

I am starting my senior design project and currently have 2 RDKs with the UP boards and RealSense R200 cameras. I have been doing a load of research to figure out how to use their capabilities, the official startup guide from Intel has a lot of steps, but once it gets to using rviz I do not understand how the realsense can be used for anything. My main goal is to use the camera to help detect people for a mobile robot we are building, so I would like to be able to process the imaging to recognize if their are people / objects in front of it, in which case it would be able to take the data and tell a motor to stop moving the robot. I am not really understanding what platform I can use to do this type of application and rviz does not seem like something I would use. Are there any sources out there with very detailed instructions on how to get started with the realsense R200 and detect people / objects / depth and be able to process the data. Any information will help

Thank you!

[MartyG]

You may be interested in the guide linked to below, which provides complete instructions and links to resources for constructing a RealSense R200-equipped mobile robot.

https://software.intel.com/en-us/articles/build-an-autonomous-mobile-robot-with-the-intel-realsense-camera-ros-and-sawr?wapkw=slam+vision+library Build an Autonomous Mobile Robot with the Intel® RealSense™ Camera, ROS*, and SAWR | Intel® Software

There has also been a project called Spatial Awareness Wearable (SAW) for using an R200 as an aid to vision-impaired people to detect approaching obstacles and generate alert feedback to the person.

https://software.intel.com/en-us/spatial-awareness-wearable Spatial Awareness Wearable | Intel® Software

[idata]

Hi Brandon,

I recommend using a RealSense D400 Series camera for this project. ROS is not supported with the R200 cameras. With the D400 series camera, you can use ROS and the Nuitrack SDK to implement human and object recognition. Please let me know if you have any further questions.Regards,Sahira

[idata]

Also, there is a video posted here by a RealSense user where he was able to implement both object detection and human detection with a RealSense SR300 camera. In his description of the GUI, he briefly describes how he was able to implement these features and he linked the source and binary builds as well. The video can be found https://www.youtube.com/watch?v=PoBSpZ8VH08 here

I hope this helps!Regards,Sahira