Depth data output has many zero distance

[MFuji9]

I'm writing python application which measures the distance from D435 to an obstacle.

I found the simple alignment code in GitHub, then I downloaded and ran it.

https://github.com/IntelRealSense/librealsense/blob/master/wrappers/python/examples/align-depth2color.py librealsense/align-depth2color.py at master · IntelRealSense/librealsense · GitHub

As a result, depth data output has many zero distance and discontinuous(sparce).

But not using 'align' code I wrote, depth data output has few zero distance.

Is there any good method for this situation?

Best regards,

[idata · Accepted solution]

Hello fjmkt,

Thank you for your interest in the Intel RealSense D435 camera. If a device fails to determine the depth of a given image pixel, a value of zero will be stored in the depth image. This is a reasonable sentinel for "no depth" because all pixels with a depth of zero would correspond to the same physical location, the location of the imager itself. Undefined depth is 0. https://github.com/IntelRealSense/librealsense/wiki/Projection-in-RealSense-SDK-2.0You should try the "High Density" preset and Hole filling Post processing filter toggled on in RealSense Viewer. This should generate the most points. Then you can use the align example to align the depth image to color.Let me know if this helps.Regards,Alexandra