This package provides:
- Cluster lib implemented by CUDA
- Sample code can show the lib usage and also be used to check perf and accuracy by comparing its output with PCL
NOTE: Cluster can be used to extract objects from points cloud after road plane was removed by Segmentation. The sample will use a PCD(sample.pcd) file which had been removed road plane.
$sudo apt-get update
$sudo apt-get install libpcl-dev
$ make
Please boost CPU and GPU firstly
sudo nvpmodel -m 0
sudo jetson_clocks
Usage:
./demo [*.pcd]
We can get output as below:
-------------- test CUDA lib -----------
-------------- cudaExtractCluster -----------
CUDA extract by Time: 10.3122 ms.
PointCloud representing the Cluster: 162152 data points.
PointCloud representing the Cluster: 7098 data points.
PointCloud representing the Cluster: 1263 data points.
PointCloud representing the Cluster: 257 data points.
-------------- test PCL lib -----------
PCL(CPU) cluster kd-tree by Time: 60.8192 ms.
PCL(CPU) cluster extracted by Time: 4016.85 ms.
PointCloud cluster_indices: 4.
PointCloud representing the Cluster: 166789 data points.
PointCloud representing the Cluster: 7410 data points.
PointCloud representing the Cluster: 1318 data points.
PointCloud representing the Cluster: 427 data points.
GPU CPU
Count of points cloud 17w+ 17w+
Cluster cost time(ms) 10.3122 4016.85
$ strings lib* | grep version | grep lib<br>
lib* version: 1.0 Jun 2 2019 09:30:19<br>
Jetson Xavier AGX 8GB
Jetpack 4.4.1
CUDA 10.2
PCL 1.8
Eigen 3