ISPRS Int. J. Geo-Inf., Volume 9, Issue 5 (May 2020) – 53 articles
Cover Story (view full-size image): This paper proposes a workflow to improve ways to search for architectural heritage in video material for the documentation of a lost monument and its 3D virtual reconstruction. Starting from the standard photogrammetric pipeline, two new steps were added: the use of deep learning for the detection of lost heritage in historical film footage, minimizing the human effort to select the frames; and the validation of photogrammetric reconstruction through the metric quality assessment of the obtained model. The workflow was evaluated on two test cases using different neural networks and experimenting on different source datasets, mimicking realistic conditions for historical archives. The scoring of suitable metrics based on time intervals demonstrates high savings in terms of human effort while achieving high-quality results.View this paper.
- Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
- You may sign up for e-mail alerts to receive table of contents of newly released issues.
- PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.