A robot-assisted pipeline to rapidly scan 1.7 million historical aerial photographs

TL;DR

The paper addresses the challenge of digitizing vast physical aerial photograph archives, which are costly and slow to digitize manually. It presents a robot-assisted pipeline that couples a preservation pipeline (mould, blocking, cleaning, curling, and emulsion damage remediation) with an automated scanning pipeline using collaborative Sawyer arms and dual scanners at 1200 ppi. In a large-scale test of 1.7 million photos from 65 countries, the system achieves roughly 30-fold higher worker productivity, produces ~425 TB of uncompressed TIFFs plus cropped JPEGs, and maintains archival integrity with minimal damage. The work argues automation is cost-effective only at large scales, creates new skilled roles, and prospects for improved accessibility and georeferencing in global aerial archives.

Abstract

During the 20th Century, aerial surveys captured hundreds of millions of high-resolution photographs of the earth's surface. These images, the precursors to modern satellite imagery, represent an extraordinary visual record of the environmental and social upheavals of the 20th Century. However, most of these images currently languish in physical archives where retrieval is difficult and costly. Digitization could revolutionize access, but manual scanning is slow and expensive. Automated scanning could make at-scale digitization feasible, unlocking this visual record of the 20th Century for the digital era. Here, we describe and validate a novel robot-assisted pipeline that increases worker productivity in scanning 30-fold, applied at scale to digitize an archive of 1.7 million historical aerial photographs from 65 countries.

Figures (18)

• Figure S1: Scanned photograph
• Figure S2: Metadata
• Figure S3: Altitudes
• Figure S4: Scale and ground resolved distance
• Figure S5: Calibration target