ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume V-2-2022
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-2-2022, 151–158, 2022
https://doi.org/10.5194/isprs-annals-V-2-2022-151-2022
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-2-2022, 151–158, 2022
https://doi.org/10.5194/isprs-annals-V-2-2022-151-2022
 
17 May 2022
17 May 2022

EXPLORING LABEL INITIALIZATION FOR WEAKLY SUPERVISED ALS POINT CLOUD SEMANTIC SEGMENTATION

P. Wang1 and W. Yao1,2 P. Wang and W. Yao
  • 1Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hung Hom, Hong Kong
  • 2The Hong Kong Polytechnic University Shenzhen Research Institute, Shenzhen, China

Keywords: Airborne Laser Scanning, Point clouds, Semantic segmentation, Weakly supervised learning, Data annotation, Feature extraction

Abstract. Although a number of emerging point-cloud semantic segmentation methods achieve state-of-the-art results, acquiring fully interpreted training data is a time-consuming and labor-intensive task. To reduce the burden of data annotation in training, semiand weakly supervised methods are proposed to address the situation of limited supervisory sources, achieving competitive results compared to full supervision schemes. However, given a fixed budget, the effective annotation of a few points is typically ignored, which is referred to as weak-label initialization in this study. In practice, random selection is typically adopted by default. Because weakly supervised methods largely rely on semantic information supplied by initial weak labels, this studies explores the influence of different weak-label initialization strategies. In addition to random initialization, we propose a feature-constrained framework to guide the selection of initial weak labels. A feature space of point clouds is first constructed by feature extraction and embedding. Then, we develop a density-biased strategy to annotate points by locating highly dense clustered regions, as significant information distinguishing semantic classes is often concentrated in such areas. Our method outperforms random initialization on ISPRS Vaihingen 3D data when only using sparse weak labels, achieving an overall accuracy of 78.06% using 1‰ of labels. However, only a minor increase is observed on the LASDU dataset. Additionally, the results show that initialization with category-wise uniformly distributed weak labels is more effective when incorporated using a weakly supervised method.