3D Object Detection and Segmentation

3D Object Detection and Segmentation

  • Jan. 2014 - Apr. 2014, Ecole Centrale de Nantes, Nantes, France
  • Graduate Project supervised by Prof. Guillaume Morreau.

I conducted my graduate project under the supervision of Prof. Guillaume Morreau in Ecole Centrale de Nantes. In the project, a real-time program which realized 3D object visualization, detection, and segmentation has been developed. This project was based on Microsoft Kinect and Point Cloud Library (PCL). Thereinto, the registration, segmentation, and polygon mesh reconstruction for objects are realized, respectively, by the iterative closest points algorithm, the color-based region growing algorithm and the normal estimation method. Here is the demo: