How did you measure the Realsense D435 accuracy?
I'm trying to measure the real precision using Intel Realsense D435 and our target objects. I found the document (https://www.intel.com/content/www/us/en/support/articles/000026260/emerging-technologies/intel-realsense-technology.html) which describe the accuracy is < 1%, but how did you measure that? In other words, how did you get the ground truth?
-
The depth accuracy of the D400 series cameras is less than one percent of the distance from the object. So if the camera is 1m from the object, the expected accuracy is between 2.5mm to 5mm.
The new RealSense L515 lidar camera is also stated in its official pre-release FAQ to have a depth error average of < 5 mm at 1 m range.
In real world conditions though, accuracy is more complex than that and a range of factors such as camera depth units, resolution and environmental lighting may factor into it. The D435 also has around double the 'RMS Error' (depth noise that increases linearly over distance) compared to the D415 model due to its hardware configuration. These concepts are explained in Intel's camera tuning guide.
The guide contains a formula for calculating RMS Error.
You may also find useful a white paper that Intel published on depth testing methodology.
-
It looks as though the document is suggesting that a laser rangefinder or tape measure are methods by which people can calculate ground truth, but the camera itself does not do the full ground truth calculation.
In Intel's instructions for the RealSense SDK's Depth Quality Tool program, they suggest enabling the 'Ground Truth' option in the tool's user interface and then modifying it with the values obtained from external tools (such as the ones mentioned above).
https://github.com/IntelRealSense/librealsense/tree/master/tools/depth-quality#quick-start
Ground truth is also discussed later in the document.
https://github.com/IntelRealSense/librealsense/tree/master/tools/depth-quality#z-accuracy
-
Thank you for your quick reply. I didn't notice Intel already provide depth accuracy evaluation tool with GUI. That would be really helpful.
I understand Intel recommends to use laser rangefinder or tape measure as a ground truth.
So just for confirmation, even for getting the nominal value(<1%), Intel used those. Correct?
-
I am not on the Intel developer or engineer team, so a member of those teams will be better able to tell you about how RealSense handles ground truth. You can enquire to them by visiting the RealSense GitHub forum at the link below and clicking on the New Issue button to post a question.
https://github.com/IntelRealSense/librealsense/issues
I do know that for an advanced project where up to 20 RealSense cameras were used to stitch together point clouds into a single large cloud, the CONIX Research Center at Carnegie Mellon calibrated using an expensive precision laser surveying device called a Theodolite.
Please sign in to leave a comment.
Comments
6 comments