Multiple Future Prediction Leveraging Synthetic Trajectories

Autor: Lorenzo Berlincioni, Alberto Del Bimbo, Federico Becattini, Lorenzo Seidenari
Jazyk: angličtina
Rok vydání: 2020
Předmět:
FOS: Computer and information sciences
Computer science
Computer Vision and Pattern Recognition (cs.CV)
0211 other engineering and technologies
Data Augmentation
Autonomous Driving
Trajectory Prediction
Synthetic Data
Machine Learning

Computer Science - Computer Vision and Pattern Recognition
Markov process
02 engineering and technology
Machine learning
computer.software_genre
Synthetic data
Trajectory Prediction
Data-driven
Data modeling
Task (project management)
Autonomous Driving
Synthetic Data
Machine Learning
symbols.namesake
Computer Science - Robotics
Position (vector)
Data Augmentation
0202 electrical engineering
electronic engineering
information engineering

Markov chain
business.industry
021107 urban & regional planning
Trajectory
symbols
020201 artificial intelligence & image processing
Artificial intelligence
business
computer
Robotics (cs.RO)
Zdroj: 2020 25th International Conference on Pattern Recognition (ICPR)
ICPR
Popis: Trajectory prediction is an important task, especially in autonomous driving. The ability to forecast the position of other moving agents can yield to an effective planning, ensuring safety for the autonomous vehicle as well for the observed entities. In this work we propose a data driven approach based on Markov Chains to generate synthetic trajectories, which are useful for training a multiple future trajectory predictor. The advantages are twofold: on the one hand synthetic samples can be used to augment existing datasets and train more effective predictors; on the other hand, it allows to generate samples with multiple ground truths, corresponding to diverse equally likely outcomes of the observed trajectory. We define a trajectory prediction model and a loss that explicitly address the multimodality of the problem and we show that combining synthetic and real data leads to prediction improvements, obtaining state of the art results.
Accepted at ICPR2020
Databáze: OpenAIRE