Balancing performance and effort in deep learning via the fusion of real and synthetic cultural heritage photogrammetry training sets

Balancing performance and effort in deep learning via the fusion of real and synthetic cultural heritage photogrammetry training sets

Cultural heritage presents both challenges and opportunities for the adoption and use of deep learning in 3D digitisation and digitalisation endeavours. While unique features in terms of the identity of artefacts are important factors that can contribute to training performance in deep learning algo...

Full description

Bibliographic Details
Main Authors: Ch’ng, Eugene, Feng, Pinyuan, Yao, Hongtao, Zeng, Zihao, Cheng, Danzhao, Cai3, Shengdan
Format: Book Section
Language:English
Published: SCITEPRESS 2021
Subjects:
digital heritage；deep learning；object detection； data augmentation； photogrammetry； fusion dataset
Online Access:https://eprints.nottingham.ac.uk/65359/

Similar Items

Similar Items