Vehicle Position Recognition Using Modified Neural Network
AssigneesThe Regents of the University of Michigan, Budapest University of Technologies and Economics
InventorsGabor OROSZ, Tian MI, Denes TAKACS
Life of this patent
Estimating the term…
Loading patent…
AssigneesThe Regents of the University of Michigan, Budapest University of Technologies and Economics
InventorsGabor OROSZ, Tian MI, Denes TAKACS
Estimating the term…
A methodology is developed to extract vehicle kinematic information from roadside cameras at an intersection using deep learning. The ground truth data of top view bounding boxes are collected with the help of unmanned aerial vehicles (UAVs). These top view bounding boxes containing vehicle position, size, and orientation information, are converted to the roadside view bounding boxes using homography transformation. The ground truth data and the roadside view images are used to train a modified YOLOv5 neural network, and thus, to learn the homography transformation matrix. The output of the neural network is the vehicle kinematic information, and it can be visualized in both the top view and the roadside view. In this algorithm, the top view images are only used in training, and once the neural network is trained, only the roadside cameras are needed to extract the kinematic information.
A method for detecting a vehicle passing through a region of interest, comprising:
A method for detecting a vehicle passing through a region of interest, comprising:
A non-transitory computer-readable medium having computer-executable instructions that, upon execution of the instructions by a processor of a computer, cause the computer to
Dependencies are inferred from the claim text.