4.7 Article

Solving photogrammetric cold cases using AI-based image matching: New potential for monitoring the past with historical aerial images

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Environmental Sciences

Historical Structure from Motion (HSfM): Automated processing of historical aerial photographs for long-term topographic change analysis

Friedrich Knuth et al.

Summary: Archives of historical aerial photographs can be used to augment long-term records of quantitative landscape change, but manual processing tasks hinder efficiency. We developed an automated method to generate high-resolution DEMs and orthoimages from historical images without manual GCP selection. Our method corrects camera position errors and produces accurate georeferenced products, regardless of camera configuration or terrain characteristics.

REMOTE SENSING OF ENVIRONMENT (2023)

Article Environmental Sciences

Giving Historical Photographs a New Perspective: Introducing Camera Orientation Parameters as New Metadata in a Large-Scale 4D Application

Ferdinand Maiwald et al.

Summary: The digitization of historical photographs in archives allows investigating their quality, quantity, and distribution. This paper proposes a method that combines content-based image retrieval (CBIR) and metadata information to filter and process digitized photographs for determining camera parameters. The results show the robustness of the proposed method and its ability to georeference newly digitized images.

REMOTE SENSING (2023)

Proceedings Paper Geography, Physical

PHOTOGRAMMETRY NOW AND THEN - FROM HAND-CRAFTED TO DEEP-LEARNING TIE POINTS -

L. Morelli et al.

Summary: Historical images provide valuable information for applications like city monitoring, building reconstruction, and cultural promotion projects. Finding reliable matches between historical and present images is crucial, and deep learning approaches have shown significant improvement in this area.

7TH INTERNATIONAL WORKSHOP LOWCOST 3D - SENSORS, ALGORITHMS, APPLICATIONS (2022)

Proceedings Paper Geography, Physical

AUTOMATIC ALGORITHM FOR GEOREFERENCING HISTORICAL-TO-NOWADAYS AERIAL IMAGES ACQUIRED IN NATURAL ENVIRONMENTS

Daniela Craciun et al.

Summary: This paper presents an algorithm for automatic georeferencing of historical aerial images. The algorithm extracts and matches image patches and performs local alignment to estimate the pose between historical and modern aerial images. Experimental results demonstrate the effectiveness of the proposed method.

XXIV ISPRS CONGRESS IMAGING TODAY, FORESEEING TOMORROW, COMMISSION II (2022)

Proceedings Paper Geography, Physical

THE EUROSDR TIME BENCHMARK FOR HISTORICAL AERIAL IMAGES

E. M. Farella et al.

Summary: The article introduces the TIME benchmark, which aims to explore the potential of historical aerial images. The benchmark provides multiple historical aerial image datasets and ancillary data to support the photogrammetric processing of the photos.

XXIV ISPRS CONGRESS IMAGING TODAY, FORESEEING TOMORROW, COMMISSION II (2022)

Article Geography, Physical

Feature matching for multi-epoch historical aerial images

Lulin Zhang et al.

Summary: Historical imagery with high resolution and stereoscopic acquisitions is a valuable resource for recovering 3D land-cover information, but accurate geo-referencing remains a challenge. This research presents a fully automatic approach for detecting feature correspondences between historical images taken at different times. By combining rough-to-precise matching and quantifying ground displacement, the method improves image georeferencing accuracy and is robust to scene changes. It is implemented in MicMac, a free, opensource photogrammetric software.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2021)

Article Computer Science, Information Systems

Fully Automated Pose Estimation of Historical Images in the Context of 4D Geographic Information Systems Utilizing Machine Learning Methods

Ferdinand Maiwald et al.

Summary: This paper presents an end-to-end pipeline from utilizing content-based image retrieval to photogrammetric pose estimation of large historical terrestrial image datasets. Research shows that image retrieval approaches outperform metadata search, and photogrammetric techniques enable the selection and pose estimation of historical images.

ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION (2021)

Article Environmental Sciences

Multi-Epoch and Multi-Imagery (MEMI) Photogrammetric Workflow for Enhanced Change Detection Using Time-Lapse Cameras

Xabier Blanch et al.

Summary: This paper presents an enhanced workflow for image-based 3D reconstruction of high-resolution models using fixed time-lapse camera systems, based on multi-epoch multi-images (MEMI) to exploit redundancy. The workflow is capable of obtaining photogrammetric models with a higher quality than the classic Structure from Motion (SfM) time-lapse photogrammetry workflow, reducing the error up to a factor of 2.

REMOTE SENSING (2021)

Article Geosciences, Multidisciplinary

Multi-decadal geomorphic changes of a low-angle valley glacier in the East Kunlun Mountains: remote sensing observations and detachment hazard assessment

Xiaowen Wang et al.

Summary: The study focused on a low-angle valley glacier near the Qinghai-Tibet railway and highway in the East Kunlun Mountains. Observations revealed that the glacier snout has been advancing in the past 40 years, with an increase in advance velocity. Image cross-correlation showed an increase in surface flow velocity, likely influenced by glacier geometry and hydrological factors like ice-dammed lakes and supraglacial ponds.

NATURAL HAZARDS AND EARTH SYSTEM SCIENCES (2021)

Article Green & Sustainable Science & Technology

On the Use of Historical Flights for the Urban Growth Analysis of Cities Through Time: The Case Study of Avila (Spain)

Inmaculada Picon-Cabrera et al.

SUSTAINABILITY (2020)

Article Environmental Sciences

Fluvial and aquatic applications of Structure from Motion photogrammetry and unmanned aerial vehicle/drone technology

Jonathan L. Carrivick et al.

WILEY INTERDISCIPLINARY REVIEWS-WATER (2019)

Article Geography, Physical

Successional stages and their evolution in tropical forests using multi-temporal photogrammetric surface models and superpixels

Adilson Berveglieri et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2018)

Article Geography, Physical

Joining multi-epoch archival aerial images in a single SfM block allows 3-D change detection with almost exclusively image information

D. Feurer et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2018)

Article Forestry

Forest stand age classification using time series of photogrammetrically derived digital surface models

Mikko Vastaranta et al.

SCANDINAVIAN JOURNAL OF FOREST RESEARCH (2016)

Article Geography, Physical

Feature-based registration of historical aerial images by Area Minimization

Sudhagar Nagarajan et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2016)

Article Chemistry, Analytical

Sinusoidal Wave Estimation Using Photogrammetry and Short Video Sequences

Ewelina Rupnik et al.

SENSORS (2015)