Data Fusion for Audiovisual Speaker Localization: Extending Dynamic Stream Weights to the Spatial Domain.
Julio WissingBenedikt T. BoenninghoffDorothea KolossaTsubasa OchiaiMarc DelcroixKeisuke KinoshitaTomohiro NakataniShoko ArakiChristopher SchymuraPublished in: ICASSP (2021)
Keyphrases
- data fusion
- spatial domain
- frequency domain
- transform domain
- information fusion
- multi sensor
- wavelet domain
- multi source
- motion estimation
- dct domain
- audio visual
- multiple sensors
- multi sensor data fusion
- fusion process
- fusion algorithm
- fusion method
- data hiding
- temporal domain
- fusion methods
- visual information
- source selection
- low frequency
- image fusion
- image compression
- feature vectors
- situation assessment
- feature space