FE-Fusion-VPR: Attention-Based Multi-Scale Network Architecture for Visual Place Recognition by Fusing Frames and Events.
Kuanxu HouDelei KongJunjie JiangHao ZhuangXinjie HuangZheng FangPublished in: IEEE Robotics Autom. Lett. (2023)
Keyphrases
- network architecture
- multiscale
- fusion method
- artificial neural
- neural network
- selective attention
- fusing multiple
- image fusion
- decision level
- feature fusion
- event detection
- neural network model
- finite element
- edge detection
- data fusion
- information fusion
- moving objects
- combining multiple
- interesting events
- multi sensor
- decision level fusion
- fusion methods
- video frames
- visual features
- natural images
- low level
- visual processing
- connection weights
- wavelet transform
- optic flow
- fusion algorithm
- visual field
- visual stimuli
- motion estimation
- web services