SemanticDepth: Fusing Semantic Segmentation and Monocular Depth Estimation for Enabling Autonomous Driving in Roads without Lane Lines.
Pablo R. PalafoxJohannes BetzFelix NobisKonstantin RiedlMarkus LienkampPublished in: Sensors (2019)
Keyphrases
- street scenes
- depth estimation
- semantic segmentation
- stereo vision
- depth map
- stereo matching
- image sequences
- depth information
- scene understanding
- dynamic scenes
- pose estimation
- superpixels
- real scenes
- disparity map
- stereo pair
- super resolution
- traffic flow
- low resolution
- high resolution
- stereo images
- face recognition
- specular reflection
- object recognition
- three dimensional
- feature matching
- object segmentation
- machine learning
- d scene
- image matching
- input data
- optical flow