Iterative application of generative adversarial networks for improved buried pipe detection from images obtained by ground-penetrating radar.
Pang-jo ChunM. SuzukiY. KatoPublished in: Comput. Aided Civ. Infrastructure Eng. (2023)
Keyphrases
- ground penetrating radar
- image database
- image data
- input image
- image classification
- extracted from images
- three dimensional
- detection rate
- image retrieval
- false detections
- image registration
- image collections
- texture and shape features
- sample images
- complex background
- segmentation algorithm
- image analysis
- object detection
- test images
- lighting conditions
- image annotation
- edge detection
- image features
- orientation estimation
- social networks
- image regions
- object recognition
- ground truth
- discriminative classifiers
- bounding box
- partial occlusion
- image set