Building a Fully-Automatized Active Learning Framework for the Semantic Segmentation of Geospatial 3D Point Clouds

• Published in: Journal of photogrammetry, remote sensing and geoinformation science Vol. 92; no. 2; pp. 131 - 161
• Main Authors: Kölle, Michael, Walter, Volker, Sörgel, Uwe
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.04.2024
• Subjects: Aerospace Technology and Astronautics; Astronomy; Computer Imaging; Earth and Environmental Science; Geographical Information Systems/Cartography; Geography; Observations and Techniques; Original Article; Pattern Recognition and Graphics; Remote Sensing/Photogrammetry; Signal,Image and Speech Processing; Vision; Semantic Segmentation; 3D Point Clouds; Hybrid Intelligence System; Paid Crowdsourcing; Active Learning
• ISSN: 2512-2789; 2512-2819
• DOI: 10.1007/s41064-024-00281-3

In recent years, significant progress has been made in developing supervised Machine Learning (ML) systems like Convolutional Neural Networks. However, it’s crucial to recognize that the performance of these systems heavily relies on the quality of labeled training data. To address this, we propose a shift in focus towards developing sustainable methods of acquiring such data instead of solely building new classifiers in the ever-evolving ML field. Specifically, in the geospatial domain, the process of generating training data for ML systems has been largely neglected in research. Traditionally, experts have been burdened with the laborious task of labeling, which is not only time-consuming but also inefficient. In our system for the semantic interpretation of Airborne Laser Scanning point clouds, we break with this convention and completely remove labeling obligations from domain experts who have completed special training in geosciences and instead adopt a hybrid intelligence approach. This involves active and iterative collaboration between the ML model and humans through Active Learning, which identifies the most critical samples justifying manual inspection. Only these samples (typically ≪ 1 % of Passive Learning training points) are subject to human annotation. To carry out this annotation, we choose to outsource the task to a large group of non-specialists, referred to as the crowd, which comes with the inherent challenge of guiding those inexperienced annotators (i.e., “short-term employees”) to still produce labels of sufficient quality. However, we acknowledge that attracting enough volunteers for crowdsourcing campaigns can be challenging due to the tedious nature of labeling tasks. To address this, we propose employing paid crowdsourcing and providing monetary incentives to crowdworkers. This approach ensures access to a vast pool of prospective workers through respective platforms, ensuring timely completion of jobs. Effectively, crowdworkers become human processing units in our hybrid intelligence system mirroring the functionality of electronic processing units .