Feature learning of airborne laser scanning (ALS) point clouds is challenged by both the limited annotated samples and imbalanced class distribution. An intuitive way involves pretraining on a well-annotated source dataset and fine-tuning on a limited target dataset. However, cross-domain challenges such as heterogeneous point cloud density, varying terrain features, and inconsistent object categories complicate transfer learning for 3-D land cover classification. In this article, we address these issues by separating the cross-domain ALS point cloud semantic segmentation into two subsequent subtasks, i.e., the cross-domain transfer learning subtask and the intradomain class-incremental learning subtask, and we use a well-annotated photogrammetric point cloud dataset as the source dataset. To mitigate domain discrepancies, the first subtask employs domain adversarial training to learn from base categories that are shared between source and target datasets. Then, the second subtask incrementally learns new categories that are specific within the target dataset using an incremental feature-semantic distillation module and a semantic adversarial learning module while retaining base category knowledge. Experimental results evaluated on three ALS point cloud datasets (ISPRS, DALES, and H3D) with different semantics show state-of-the-art cross-domain performance with few labeled samples. Compared with few-shot learning methods, our method shows promising generalization ability particularly on domain-specific categories, greatly alleviating the dependence on ALS point cloud annotations.

Existing airborne laser scanning (ALS) point cloud semantic segmentation approaches are limited by their overreliances on sufficient point-wise annotations that further confine their generalization ability to new scenes. To overcome these problems, a novel three-stage multi-prototype relational network (Thr-MPRNet) is proposed for few-shot ALS point cloud semantic segmentation by transferring knowledge from well-annotated photogrammetric point clouds. In MPRNet, a 3D few-shot learning structure containing a feature learner and a relation learner is built to learn meta-knowledge from multiple point-wise tasks, and a multi-prototype generator is designed to represent the semantic distribution of point clouds that can dynamically adapt to large-scale scenarios. Then, to transfer knowledge across different domains, MPRNet is trained in a unified framework with three task-based learning stages. Prior knowledge is first meta-learned from the source photogrammetric point clouds and then transferred to novel target datasets with a few labeled ALS point clouds. Finally, the MPRNet can be flexibly generalized to the unlabeled target ALS point clouds without further retraining from scratch. In the experiments, the SensatUrban dataset is used as the source photogrammetric point clouds, and two ALS point cloud datasets (ISPRS and DALES) are used to evaluate the few-shot semantic segmentation ability of the proposed method. The experiments demonstrate that Thr-MPRNet obtains promising generalization performance on different target datasets. More importantly, it outperforms supervised networks with 10% labeled samples. In summary, the proposed method achieves state-of-the-art cross-domain semantic segmentation performance and greatly alleviates the dependence on ALS point cloud annotations.

The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) equips with a novel photon-counting LiDAR system, which can generate underwater reflections in nearshore environments. However, due to the water reflection, scattering, and absorption, the distribution of bathymetric photons in the nearshore data varies with depth. The existing bathymetric photon extraction algorithms need more adaptability to seafloor topography. The changing density of bathymetric photons and the fluctuation of underwater topography make the noise removal of nearshore data full of challenges. This study proposed a bathymetric photon extraction algorithm using pre-pruning quadtree isolation (PQI). Firstly, the pre-pruning step judges whether to stop the growth of quadtree in advance during quadtree isolation (QI) to avoid excessive division of noise photons. Secondly, the maximum inter-class variance algorithm (also called the Otsu method) obtains the best threshold of isolation depth and extracts bathymetric photons. The algorithm was tested on the Florida coast. The results show that the PQI algorithm can wholly and accurately extract bathymetric photons with different acquisition times from the data. The F1-score of the extracted results is 93.96%. This study provides an intelligent solution to processing bathymetric data in nearshore environments worldwide.

In recent years, deep-learning-based hyperspectral image (HSI) classification methods have achieved significant development and gradually become widely applied. The existing advanced methods can achieve near-saturation performance with sufficient labels in a closed-set environment (CSE), i.e., training set and test set are all known categories of ground objects. However, the real world is usually open because of the diversity of land covers, i.e., test-set exists unknown categories that are not labeled in the training set. Therefore, the prevalent advanced CSE methods still cannot effectively and robustly handle unknown categories of ground objects in an open-set environment (OSE). Therefore, we propose a spectral-spatial MLP-like network with reciprocal points learning (SSMLP-RPL) to improve the performance of open-set HSI classification. First, a feature learning framework based on reciprocal points learning (RPL) is constructed to model the extra-category space and reduce the risk of open space. The learned feature space enables to enlarge the distance between the known and unknown categories. Besides, we further propose to utilize a learnable dynamic threshold of each known category to effectively distinguish the unknown categories and improve open performance of the model. Second, to enhance the capacity of feature learning, a spectral-spatial MLP-like network (SSMLP) is designed to capture the spectral-spatial feature merely with a series of fully-connected (FC) layers, which mainly involve SpeFC and SpaFC two modules. Among them, the SpaFC module enables to model spacial semantics, and the SpeFC module enables to model long-distance spectral dependence. Extensive experiments on three benchmark HSIs show that SSMLP-RPL has a competitive performance both in CSE and OSE and even surpasses currently advanced closed-set and open-set HSI classification methods. As an end-to-end HSI classification framework of MLP-backbone, SSMLP network can compete with the advanced works based on CNN and transformer. The code will be open at: https://github.com/sssssyf/SSMLP-RPL.

The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) is the world’s first satellite-borne photon-counting laser altimeter with unprecedented detection performance. Noise removal is an important process applied to raw data and determines the quality of the end product. Assuming that the sparse spatial distribution of noise photons makes them more easily isolated than signal photons, we propose a noise-removal algorithm without input parameters based on quadtree isolation. MATLAS was used to evaluate the performance of our algorithm. We compare our algorithm to the improved density-based spatial clustering of applications with noise (DBSCAN) algorithm. Experimental results show that our algorithm accurately extracts signal photons from raw data and is superior to the improved DBSCAN in accuracy and time efficiency. This novel algorithm makes it possible to efficiently remove noise from photon-counting light detection and ranging (LiDAR) data.