An Investigation of Vehicle Behavior Prediction Using a Vector Power Representation to Encode Spatial Positions of Multiple Objects and Neural Networks.
Florian MirusPeter BlouwTerrence C. StewartJörg ConradtPublished in: Frontiers Neurorobotics (2019)
Keyphrases
- multiple objects
- neural network
- multiple object tracking
- individual objects
- multi object
- occlusion handling
- spatial location
- relative position
- complex scenes
- spatial relations
- tracking of multiple objects
- pedestrian detection
- spatial data
- artificial neural networks
- data association
- particle filter
- multiple images
- spatial information
- occlusion reasoning
- real time
- image representation
- vision system
- state space
- spatial structure
- robot soccer
- object recognition
- electric vehicles
- spatial configuration
- reinforcement learning
- computer vision
- spatial configurations
- learning algorithm