Vehicle pose estimation is a vital technology for reconstructing the circumstaces of traffic accidents. We propose a novel method for reconstructing the trajectory of vehicles from drive recorder images and a point cloud around the road. First, we apply ORB-SLAM to image sequence of the drive recorder for obtaining the vehicle pose trajectory; however this is based on relative coordinates and a relative scale. For estimating the absolute coordinates and scale of the trajectory, which cannot be obtained from a monocular SLAM like ORB-SLAM, we match the feature points detected in the image sequence with the three-dimensional (3D) point cloud of surrounding environment. For finding 3D points matching the feature points, we generate candidate images by the rendering 3D point cloud of the surrounding environment using the position initially estimated by the Global Positioning System (GPS). Next, we match to obtain the 3D two-dimensional (2D) generated images and drive recorder image to get 3D-2D point correspondences between the 3D point cloud and the drive recorder images; thus, we can convert the relative estimation of the camera pose by ORB-SLAM to the coordinates of the 3D point cloud of the surrounding environment. In the evaluation experiments, we confirmed the effectiveness of our method by comparing the vehicle poses estimated by our method, with those of RTKGPS, which exhibits high measurement precision.
In automatic picking by robot, it is the important to estimate the grasping parameters (grasping position, direction and angle) of the object. In this paper, we propose a method for approximating an object with primitive shape in order to estimate the grasping parameters. The basic idea of this research is to approximate the object by object primitive (hexahedron/cylinder/sphere), based on the object's surface. First, we classify the surface shape that constitutes the object using 3D-Deep Neural Network. Then, we approximate the object with object primitive using the recognition result of 3D-DNN. After that, we estimate the grasping parameters based on preset grasping rules. The success rate of approximating the object primitive with our method was 94.7%. This result is 6.7% higher than the 3D ShapeNets using 3D-DNN. Also, as an experimental result of grasping simulation using Gazebo, the success rate of grasping with our method was 85.6%.