홈 › Papers

Unsupervised semantic segmentation of urban high-density multispectral point clouds

2024-10-24 · Oona Oinonen, Lassi Ruoppa, Josef Taher, Matti Lehtomäki, Leena Matikainen, Kirsi Karila, Teemu Hakala, Antero Kukko, Harri Kaartinen, Juha Hyyppä

The availability of highly accurate urban airborne laser scanning (ALS) data will increase rapidly in the future, especially as acquisition costs decrease, for example through the use of drones. Current challenges in data processing are related to the limited spectral information and low point density of most ALS datasets. Another challenge will be the growing need for annotated training data, frequently produced by manual processes, to enable semantic interpretation of point clouds. This study proposes to semantically segment new high-density (1200 points per square metre on average) multispectral ALS data with an unsupervised ground-aware deep clustering method GroupSP inspired by the unsupervised GrowSP algorithm. GroupSP divides the scene into superpoints as a preprocessing step. The neural network is trained iteratively by grouping the superpoints and using the grouping assignments as pseudo-labels. The predictions for the unseen data are given by over-segmenting the test set and mapping the predicted classes into ground truth classes manually or with automated majority voting. GroupSP obtained an overall accuracy (oAcc) of 97% and a mean intersection over union (mIoU) of 80%. When compared to other unsupervised semantic segmentation methods, GroupSP outperformed GrowSP and non-deep K-means. However, a supervised random forest classifier outperformed GroupSP. The labelling efforts in GroupSP can be minimal; it was shown, that the GroupSP can semantically segment seven urban classes (building, high vegetation, low vegetation, asphalt, rock, football field, and gravel) with oAcc of 95% and mIoU of 75% using only 0.004% of the available annotated points in the mapping assignment. Finally, the multispectral information was examined; adding each new spectral channel improved the mIoU. Additionally, echo deviation was valuable, especially when distinguishing ground-level classes.

📄 PDF Abstract BibTeX arXiv:2410.18520

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Clustering Semantic Segmentation Unsupervised Semantic Segmentation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

ALS 설명 없음

HRHD-HK: A benchmark dataset of high-rise and high-density urban scenes for 3D semantic segmentation of photogrammetric point clouds

2023-07-16 · Maosu Li, Yijie Wu, Anthony G. O. Yeh, Fan Xue

Many existing 3D semantic segmentation methods, deep learning in computer vision notably, claimed to achieve desired results on urban point clouds. Thus, it is significant to assess these methods quantitatively in divers…

3D Semantic Segmentation Segmentation Semantic Segmentation

Urban1960SatSeg: Unsupervised Semantic Segmentation of Mid-20$^{th}$ century Urban Landscapes with Satellite Imageries

2025-06-11 · Tianxiang Hao, Lixian Zhang, Yingjia Zhang, Mengxuan Chen 외

Historical satellite imagery, such as mid-20$^{th}$ century Keyhole data, offers rare insights into understanding early urban development and long-term transformation. However, severe quality degradation (e.g., distortio…

Segmentation Self-Supervised Learning Semantic Segmentation Unsupervised Semantic Segmentation

All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes

2023-12-19 · Jose L. Gómez, Manuel Silva, Antonio Seoane, Agnès Borrás 외

We introduce UrbanSyn, a photorealistic dataset acquired through semi-procedurally generated synthetic urban driving scenarios. Developed using high-quality geometry and materials, UrbanSyn provides pixel-level ground tr…

All Domain Adaptation Instance Segmentation Segmentation+2

Semantic Segmentation of Urban Textured Meshes Through Point Sampling

2023-02-21 · Grégoire Grzeczkowicz, Bruno Vallet

Textured meshes are becoming an increasingly popular representation combining the 3D geometry and radiometry of real scenes. However, semantic segmentation algorithms for urban mesh have been little investigated and do n…

3D geometry Segmentation Semantic Segmentation

KLIEP-based Density Ratio Estimation for Semantically Consistent Synthetic to Real Images Adaptation in Urban Traffic Scenes

2021-05-26 · Artem Savkin, Federico Tombari

Synthetic data has been applied in many deep learning based computer vision tasks. Limited performance of algorithms trained solely on synthetic data has been approached with domain adaptation techniques such as the ones…

Autonomous Driving Density Ratio Estimation Domain Adaptation Semantic Segmentation