Mono-DCNet: Monocular 3D Object Detection via Depth-based Centroid Refinement and Pose Estimation.
Armando AstudilloAbdulla Al-KaffFernando GarcíaPublished in: IV (2022)
Keyphrases
- pose estimation
- d objects
- depth images
- viewpoint
- multi view
- object recognition
- human body
- multiple views
- range data
- depth map
- three dimensional
- monocular images
- shape descriptors
- human pose
- computer vision
- position and orientation
- invariant recognition
- recognition and pose estimation
- object detection
- body parts
- pose parameters
- camera calibration
- face recognition
- bounding box
- image sequences