ConvSequential-SLAM: A Sequence-Based, Training-Less Visual Place Recognition Technique for Changing Environments.
Mihnea-Alexandru TomitaMubariz ZaffarMichael J. MilfordKlaus D. McDonald-MaierShoaib EhsanPublished in: IEEE Access (2021)
Keyphrases
- changing environment
- dynamic environments
- mobile robot
- autonomous agents
- object and scene recognition
- visual information
- simultaneous localization and mapping
- training process
- visual perception
- visual slam
- training set
- training samples
- e learning
- sensory information
- supervised learning
- particle filter
- video sequences
- high level
- training algorithm
- training phase
- machine learning