Back to results
US 12,749,201 B2Granted
Pedestrian trajectory prediction method
AssigneeGIST(Gwangju Institute of Science and Technology)
InventorsHae Gon Jeon, In Hwan Bae, Jin Hwi Park
Life of this patent
Estimating the term…
Abstract
The present disclosure relates to a method for sampling a random vector corresponding to an intention of a pedestrian non-stochastically or applying a social statistical element that the majority of pedestrians move in groups to training, in training a neural network model for pedestrian trajectory prediction.
Claims9
A method for predicting a pedestrian trajectory, performed by a processor, the method comprising:
- collecting, by the processor, pedestrian images from a Closed-Circuit Television (CCTV) or a predetermined database;
- identifying, by the processor, the pedestrian trajectory of a target pedestrian in the pedestrian images;
- sampling, by the processor, based on the pedestrian trajectory of the target pedestrian, a predetermined number of latent vectors among a plurality of random vectors, which are determined according to a Monte Carlo or a Quasi-Monte Carlo method and are corresponding to an intention of the target pedestrian non-stochastically;
- extracting, by the processor, a pedestrian feature vector from the pedestrian trajectory;
- determining, by the processor, an expected trajectory of the target pedestrian by applying the pedestrian feature vector and the latent vectors to a neural network model;
- and
- outputting, by the processor, the expected trajectory of the target pedestrian by applying the pedestrian feature vector and the latent vector to one of Gaussian distribution, Generative Adversarial Network (GAN), and Conditional Variational AutoEncoder (CVAE), and calculating and outputting, by the processor, an occurrence probability of the expected trajectory,
- wherein the sampling of the latent vectors non-stochastically includes
- sampling the predetermined number of latent vectors so that a distance between respective trajectories predicted by the plurality of random vectors are largest while the trajectories predicted by the plurality of random vectors are most similar to an actual trajectory of the target pedestrian.
6 more elements
A method for predicting a pedestrian trajectory, performed by a processor, the method comprising:
- collecting, by the processor, pedestrian images from a Closed-Circuit Television (CCTV) or a predetermined database;
- identifying, by the processor, the pedestrian trajectory of a target pedestrian in the pedestrian images;
- sampling, by the processor, based on the pedestrian trajectory of the target pedestrian, a predetermined number of latent vectors among a plurality of random vectors, which are determined according to a Monte Carlo or a Quasi-Monte Carlo method and are corresponding to an intention of the target pedestrian non-stochastically;
- extracting, by the processor, a pedestrian feature vector from the pedestrian trajectory;
- determining, by the processor, an expected trajectory of the target pedestrian by applying the pedestrian feature vector and the latent vectors to a neural network model;
- and
- outputting, by the processor, the expected trajectory of the target pedestrian by applying the pedestrian feature vector and the latent vector to one of Gaussian distribution, Generative Adversarial Network (GAN), and Conditional Variational AutoEncoder (CVAE), and calculating and outputting, by the processor, an occurrence probability of the expected trajectory,
- wherein the sampling of the latent vectors non-stochastically includes
- sampling the predetermined number of latent vectors in an order in which a distance between respective trajectories predicted by the plurality of random vectors are largest upon learning the neural network model, and
- wherein the sampling of the latent vectors non-stochastically includes
- sampling the predetermined number of latent vectors by applying a loss function which decreases as the distance between the respective trajectories predicted by the plurality of random vectors to the neural network model.
8 more elements
Dependencies are inferred from the claim text.