This is a linux package to create a global map of an environment using the D435 - Depth camera, and T265 - Tracking camera.
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
The following packages are required for the project:
- Realsense SDK 2.0 - Used to interface with the cameras
- OpenCV 3.0
- CUDA - Used to run C code on NVIDIA GPUs
- GNUPlot - Used to display pointcloud data
- GNUPlot IO stream - Used to interface GNUPlot with C++
- Thrust - Data parallel primitives on GPU
- Boost - Collection of portable C++ source libraries
- Change the current working directory to the location where you want the cloned directory to be made, and clone the GitHub repository
# Change to working directory
$ cd project-dir
# Clone the repository
$ git clone https://github.com/AkshayThiru/Mapping
- Change to source directory and compile the code.
# Change to source directory
$ cd project-dir/src
# Compile the CPU version of the code
$ g++ -std=c++11 CPU_main.cpp -o CPU_main -lrealsense2 -lboost_iostreams -lboost_system -lboost_filesystem `pkg-config opencv --cflags --libs` -lpthread
- Compile the GPU version of the code if applicable. CUDA version > 8.0 is required, and NVIDIA GPU should have compute capability > 2.0
# Compile the GPU version of the code
$ nvcc -std=c++11 GPU_main.cu -o GPU_main -lrealsense2 -lboost_iostreams -lboost_system -lboost_filesystem `pkg-config opencv --cflags --libs` -lpthread -Wno-deprecated-gpu-targets
- Connect both the cameras and run the code.
# Run the CPU code
$ ./CPU_main
# Or run the GPU code
$ ./GPU_main
- T Akshay - Initial work - AkshayThiru
See also the list of contributors who participated in this project.