Correct way to convert AVDepthData.depthDataMap to gray depth image

Question

Created Jan ’24

Replies 2

Boosts 0

Participants 2

Hi all. I can get disparity/depth data map from AVDepthData.depthDataMap and directly use it to generate a depth image. I found that under some situations, objects on the depth image cannot be clearly distinguished.

When using disparity data, objects below 1 meter can't be clearly distinguished.
When using depth data, objects larger than 1 meter can't be clearly distinguished.

Does anyone know why this happens and how to fix it ?

Boost

Answer 1

DTS Engineer OP

Apple

Jan ’24

Hello,

The depthDataMap stores values in meters. When you attempt to convert this data to a color image and display it, you can normalize the depth values into the range of color values that you are able to display (usually that range is zero-to-one).

If you don't map the depth values into the valid color range, anything outside that range is clamped when the image is rendered.

0

Answer 2

Chanjug OP

Jan ’24

Hi, gchiste thanks for your reply. Some questions about normalization.

Is there a general normalization for reference ?
If I want the real distance values between 30cm and 1.5m to be easily distinguished, I must create a customized normalization feature?

0