Swin-T-NFC CRFs: An encoder-decoder neural model for high-precision UAV positioning via point cloud super resolution and image semantic segmentation.
Suhong WangHongqing WangShufeng SheYanping ZhangQingju QiuZhifeng XiaoPublished in: Comput. Commun. (2023)
Keyphrases
- semantic segmentation
- super resolution
- high resolution
- point cloud
- conditional random fields
- low resolution
- single image
- superpixels
- motion estimation
- scene classification
- object categories
- input image
- image patches
- image features
- depth map
- object class
- object classes
- probabilistic model
- image representation
- hidden markov models
- viewpoint
- test images
- generative model
- image classification
- object detection
- structure from motion
- object recognition
- high quality
- higher order
- video sequences