HomeCloudSoftwareHardware
DepthAI Components
DepthAI Tutorials
Tools
ROS
Neural Networks
DepthAI API References

ON THIS PAGE

  • PointCloud
  • How to place it
  • Inputs and Outputs
  • Example visualization with Open3D
  • Examples using PointCloud
  • Reference

PointCloud

The PointCloud node enables on-device point cloud generation from depth map.

How to place it

Python
C++
Python
1pipeline = dai.Pipeline()
2pointCloud = pipeline.create(dai.node.PointCloud)

Inputs and Outputs

Command Line
1/
2               ┌─────────────────────┐  
3               │                     │        
4  inputConfig  │     PointCloud      │
5  ────────────►│                     │       outputPointCloud
6               │                     ├───────────►
7  inputDepth   │                     │       passthroughDepth
8  ────────────►│---------------------├───────────►
9               └─────────────────────┘
Message types

Example visualization with Open3D

Python
C++
Python
1import open3d as o3d
2import numpy as np
3import depthai as dai
4
5pcd = o3d.geometry.PointCloud()
6vis = o3d.visualization.VisualizerWithKeyCallback()
7vis.create_window()
8
9with dai.Device(pipeline) as device:
10    coordinateFrame = o3d.geometry.TriangleMesh.create_coordinate_frame(size=1000, origin=[0,0,0])
11    vis.add_geometry(coordinateFrame)
12    
13    while device.isPipelineRunning():
14        inMessage = q.get()
15        inColor = inMessage["rgb"]
16        inPointCloud = inMessage["pcl"]
17        cvColorFrame = inColor.getCvFrame()
18      
19        if inPointCloud:
20            points = inPointCloud.getPoints().astype(np.float64)
21            pcd.points = o3d.utility.Vector3dVector(points)
22            colors = (cvRGBFrame.reshape(-1, 3) / 255.0).astype(np.float64)
23            pcd.colors = o3d.utility.Vector3dVector(colors)
24            vis.update_geometry(pcd)
25
26        vis.poll_events()
27        vis.update_renderer()
28
29    vis.destroy_window()

Examples using PointCloud

Reference

Python
C++
class

depthai.node.PointCloud(depthai.Node)

method
setNumFramesPool(self, arg0: int)
Specify number of frames in pool.

Parameter ``numFramesPool``:
    How many frames should the pool have
property
initialConfig
Initial config to use when computing the point cloud.
property
inputConfig
Input PointCloudConfig message with ability to modify parameters in runtime. Default queue is non-blocking with size 4.
property
inputDepth
Input message with depth data used to create the point cloud. Default queue is non-blocking with size 4.
property
outputPointCloud
Outputs PointCloudData message
property
passthroughDepth
Passthrough depth from which the point cloud was calculated. Suitable for when input queue is set to non-blocking behavior.

Need assistance?

Head over to Discussion Forum for technical support or any other questions you might have.