- PCL
- OpenCV
- Eigen
In this project, there four major tasks:
- First, matching 3D objects over time by using keypoint correspondences.
- Second, Computing time to collision (TTC) based on Lidar measurements.
- Computing TTC based the camera, which requires to first associate keypoint matches to regions of interest and then to compute the TTC based on those matches.
- And lastly, conducting various tests with the framework. Goal is to identify the most suitable detector/descriptor combination for TTC estimation based measurements by the camera or Lidar sensor.
Make sure the system has C++ (>+11), and the dependencies mentioned above.
- Clone this repository:
git clone https://github.com/mayankysharma/3D-Time-to-Collision-using-Sensor-Fusion.git
- Make a build directory in the top level project directory:
mkdir build && cd build
- Compile:
cmake .. && make
- download yolo.weights file in dat/yolo/
- Run the executable:
./3D_object_tracking
.