MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detection.
Taeheon KimSangyun ChungDamin YeomYoungjoon YuHak Gu KimYong Man RoPublished in: CoRR (2024)
Keyphrases
- multispectral
- pedestrian detection
- human body
- multi modal fusion
- remote sensing
- object detection
- multispectral images
- image data
- remote sensing images
- human detection
- spatial resolution
- detection rate
- image analysis
- benchmark datasets
- hyperspectral
- histograms of oriented gradients
- multispectral satellite images
- multispectral imaging
- object recognition
- hyperspectral images
- pattern recognition
- spectral characteristics
- detection algorithm
- high quality
- viewpoint
- feature space
- histogram intersection kernel
- multiscale