tools and applications regarding intel realsense

• MartyG

  • November 27, 2019 18:35
  • Edited

  Support for pose data is built in to the RealSense T265 Tracking Camera. 

  https://store.intelrealsense.com/buy-intel-realsense-tracking-camera-t265.html 

  On the depth camera models (D415, D435, etc), pose is not built-in.  However, a couple of depth camera users have come up with workarounds that use OpenCV or ROS to get pose for tasks such as using a robot arm for bin-picking.

  https://forums.intel.com/s/question/0D50P00004VEnqUSAT/i-want-to-implement-3d-pose-estimation-using-intel-realsense-d435-is-there-any-sdk-available-which-can-be-used 

  If you are interested in the T265 Tracking Camera and its pose support, a range of example programs for the RealSense SDK that use pose data can be found here:

  https://github.com/IntelRealSense/librealsense/blob/master/doc/t265.md#examples-and-tools 

  For TensorFlow support, a machine-learning processing stick called the Intel Neural Compute Stick 2 can be plugged into a USB port and used alongside a RealSense camera.  It is available from Intel's online RealSense store in a camera and stick bundle, or with the stick on its own if you already have a camera.

  On the store listing in the link below, please click on the 'NCS2 specs' option tab to read the stick's specifications, including its TensorFlow support.

  https://store.intelrealsense.com/buy-depth-camera-and-neural-compute-stick-2-bundle.html 

  Here is an example of the RealSense D435 depth camera being used with TensorFlow:

  https://github.com/PINTO0309/MobileNet-SSDLite-RealSense-TF 

   

  0

  Comment actions Permalink

Please sign in to leave a comment.