Configure an Align Color Depth Homography View
When you have a depth image and you need it to overlay on top of a color image exactly, a homography matrix can apply the necessary distortions to the depth image to make it align with the color image.
Use the align_color_depth_homography
camera model to do this alignment.
Navigate to the Config tab of your machine’s page in the Viam app.
Click on the Components subtab and click Create component.
Select the camera
type, then select the align_color_depth_homography
model.
Enter a name for your camera and click Create.
Copy and paste the following attribute template into your camera’s Attributes box. Then remove and fill in the attributes as applicable to your camera, according to the table below.
{
"intrinsic_parameters": {
"width_px": <int>,
"height_px": <int>,
"fx": <float>,
"fy": <float>,
"ppx": <float>,
"ppy": <float>
},
"homography": {
"transform": [ <float>, <float>, <float>,
<float>, <float>, <float>,
<float>, <float>, <float> ],
"depth_to_color": <boolean>,
"rotate_depth_degs": <int>
},
"color_camera_name": "<your-camera-name>",
"depth_camera_name": "<your-camera-name>",
"output_image_type": "<color|depth>",
"distortion_parameters": {
"rk1": <float>,
"rk2": <float>,
"rk3": <float>,
"tp1": <float>,
"tp2": <float>
},
"debug": <boolean>
}
{
"name": "<your-camera-name>",
"model": "align_color_depth_homography",
"type": "camera",
"namespace": "rdk",
"attributes": {
"intrinsic_parameters": {
"width_px": <int>,
"height_px": <int>,
"fx": <float>,
"fy": <float>,
"ppx": <float>,
"ppy": <float>
},
"homography": {
"transform": [ <float>, <float>, <float>,
<float>, <float>, <float>,
<float>, <float>, <float> ],
"depth_to_color": <boolean>,
"rotate_depth_degs": <int>
},
"color_camera_name": "<your-camera-name>",
"depth_camera_name": "<your-camera-name>",
"output_image_type": "<color|depth>",
"distortion_parameters": {
"rk1": <float>,
"rk2": <float>,
"rk3": <float>,
"tp1": <float>,
"tp2": <float>
},
"debug": <boolean>
}
}
The following attributes are available for align_color_depth_homography
views:
Name | Type | Inclusion | Description |
---|---|---|---|
intrinsic_parameters | object | Required | The intrinsic parameters of the camera used to do 2D <-> 3D projections:
|
homography | object | Required | Parameters that morph the depth points to overlay the color points and align the images:
|
color_camera_name | string | Required | name of the color camera to pull images from. |
depth_camera_name | string | Required | name of the depth camera to pull images from. |
output_image_type | string | Required | Specify color or depth for the output stream. |
distortion_parameters | object | Optional | Modified Brown-Conrady parameters used to correct for distortions caused by the shape of the camera lens:
|
debug | boolean | Optional | Enables the debug outputs from the camera if true .Default: false |
View the camera stream
Once your camera is configured and connected, go to the Control tab, and click on the camera’s dropdown menu. Then toggle the camera or the Point Cloud Data view to ON. If everything is configured correctly, you will see the live video feed from your camera. You can change the refresh frequency as needed to change bandwidth.
Next steps
Have questions, or want to meet other people working on robots? Join our Community Discord.
If you notice any issues with the documentation, feel free to file an issue or edit this file.
Was this page helpful?
Glad to hear it! If you have any other feedback please let us know:
We're sorry about that. To help us improve, please tell us what we can do better:
Thank you!