-
Notifications
You must be signed in to change notification settings - Fork 0
beam_cv
Jake McLaughlin edited this page Aug 19, 2019
·
4 revisions
This module contains commonly used image processing/computer vision operations used throughout beam_robotics
This file contains the implementation for our ray casting algorithm with a customizable function for the behaviour when a ray hits a point.
This file contains commonly used functions including morphological operations, segmentation, histogram equalization etc...
This class represents a point cloud as a depth image. It contains operations to convert between point clouds and depth images, means of upsampling the depth data, and performing geometric calculations on the depth data.
#include "beam_cv/DepthMap.h"
#include "beam_cv/Utils.h"
#include <pcl/io/pcd_io.h>
#include <pcl/point_types.h>
int main() {
Mat img = imread(image_location, IMREAD_COLOR);
shared_ptr<beam_calibration::CameraModel> F1 = beam_calibration::CameraModel::LoadJSON(intrinsics_loc);
pcl::PointCloud<pcl::PointXYZ>::Ptr cloud(new pcl::PointCloud<pcl::PointXYZ>);
pcl::io::loadPCDFile<pcl::PointXYZ>(cur_dir + "test.pcd", *cloud);
beam_cv::DepthMap dm(F1, cloud);
dm.ExtractDepthMap(0.001, 3);
dm.KMeansCompletioN(11, img)
Mat viz = beam_cv::VisualizeDepthImage(dm.GetDepthImage());
imshow("Depth Image", viz);
waitKey(0);
}
- Home
- Onboarding
- Installation Guide
- Libbeam
- Mapping
- Calibration
- Hardware Instructions
- Deep Learning
- Formatting
- PoTree Maps
- Supported Hardware
- Additional Resources