A New Microscopic Approach to Traffic Flow Classification Using a Convolutional Neural Network Object Detector and a Multi-Tracker Algorithm.
Matheus Vieira Lessa RibeiroJorge Leonid Aching SamateloAna LĂșcia Cetertich BazzanPublished in: IEEE Trans. Intell. Transp. Syst. (2022)
Keyphrases
- traffic flow
- convolutional neural network
- detection algorithm
- learning algorithm
- decision trees
- expectation maximization
- text classification
- superpixels
- region of interest
- segmentation method
- segmentation algorithm
- neural network
- small number
- probabilistic model
- high resolution
- reinforcement learning
- feature selection
- machine learning