arXiv subjects

Shudong Zhou

Publications and source records attributed to Shudong Zhou.

7 recordsLinked to original sources

arXiv2026

COSTA: A Cluster-Centric Paradigm for Annotation-Free Open-Set Semantic Segmentation of Aerial Point Clouds with Domain Shifts

Semantic segmentation of aerial point cloud is trapped in a generalization crisis under distinct domain shifts. While test-time adaptation offers a privacy-preserving and computationally efficient way to adapt pre-trained models to unlabeled target-domain data during inference, existing methods, bound to closed-set label assumptions and non-scalable point-wise segmentation pipelines, still struggle with semantic shifts. We ask: can we adapt any given pre-trained aerial point cloud segmentation model to a shifted target domain at the inference phase alone, without additional training, while segmenting target-specific categories beyond the source label space on demand? This paper introduces COSTA, which breaks this limitation by shifting from closed-set point-wise adaptation to cluster-centric open-set semantic propagation. Our core discovery is that, once effectively adapted at test time, the rich feature distribution of aerial point clouds can be distilled into a compact set of well-separated semantic centroids that are transferable across label spaces. COSTA leverages this to reformulate open-set semantic segmentation as a cluster-level propagating process: it first bridges the domain gap through proven test-time adaptation, then groups each batch of target-domain points into a small set of semantic clusters based on the similarity distribution in the adapted feature space, and finally propagates high-confidence pseudo labels obtained from an open-vocabulary vision-language model to all points through cluster-level voting. This cluster-centric paradigm enables test-time adaptation of aerial point clouds under significant domain gaps with mixed semantic shifts. With DALES as the source domain, COSTA enables on-demand segmentation across three aerial point cloud benchmarks with distinct domains and heterogeneous category spaces, achieving up to 70.09% mIoU under this new setting.

cs.CV↗

arXiv2026

Semi-Supervised Hyperspectral Image Classification with Edge-Aware Superpixel Label Propagation and Adaptive Pseudo-Labeling

Significant progress has been made in semi-supervised hyperspectral image (HSI) classification regarding feature extraction and classification performance. However, due to high annotation costs and limited sample availability, semi-supervised learning still faces challenges such as boundary label diffusion and pseudo-label instability. To address these issues, this paper proposes a novel semi-supervised hyperspectral classification framework integrating spatial prior information with a dynamic learning mechanism. First, we design an Edge-Aware Superpixel Label Propagation (EASLP) module. By integrating edge intensity penalty with neighborhood correction strategy, it mitigates label diffusion from superpixel segmentation while enhancing classification robustness in boundary regions. Second, we introduce a Dynamic History-Fused Prediction (DHP) method. By maintaining historical predictions and dynamically weighting them with current results, DHP smoothens pseudo-label fluctuations and improves temporal consistency and noise resistance. Concurrently, incorporating condifence and consistency measures, the Adaptive Tripartite Sample Categorization (ATSC) strategy implements hierarchical utilization of easy, ambiguous, and hard samples, leading to enhanced pseudo-label quality and learning efficiency. The Dynamic Reliability-Enhanced Pseudo-Label Framework (DREPL), composed of DHP and ATSC, strengthens pseudo-label stability across temporal and sample domains. Through synergizes operation with EASLP, it achieves spatio-temporal consistency optimization. Evaluations on four benchmark datasets demonstrate its capability to maintain superior classification performance.

cs.CV↗

arXiv2026

AI-enabled Satellite Edge Computing: A Single-Pixel Feature based Shallow Classification Model for Hyperspectral Imaging

As the important component of the Earth observation system, hyperspectral imaging satellites provide high-fidelity and enriched information for the formulation of related policies due to the powerful spectral measurement capabilities. However, the transmission speed of the satellite downlink has become a major bottleneck in certain applications, such as disaster monitoring and emergency mapping, which demand a fast response ability. We propose an efficient AI-enabled Satellite Edge Computing paradigm for hyperspectral image classification, facilitating the satellites to attain autonomous decision-making. To accommodate the resource constraints of satellite platforms, the proposed method adopts a lightweight, non-deep learning framework integrated with a few-shot learning strategy. Moreover, onboard processing on satellites could be faced with sensor failure and scan pattern errors, which result in degraded image quality with bad/misaligned pixels and mixed noise. To address these challenges, we develop a novel two-stage pixel-wise label propagation scheme that utilizes only intrinsic spectral features at the single pixel level without the necessity to consider spatial structural information as requested by deep neural networks. In the first stage, initial pixel labels are obtained by propagating selected anchor labels through the constructed anchor-pixel affinity matrix. Subsequently, a top-k pruned sparse graph is generated by directly computing pixel-level similarities. In the second stage, a closed-form solution derived from the sparse graph is employed to replace iterative computations. Furthermore, we developed a rank constraint-based graph clustering algorithm to determine the anchor labels.

cs.CV↗

arXiv2025

Theoretical and experimental studies of energy modulation to demodulation in seeded free-electron lasers

Laser manipulation plays a critical role in precisely tailoring relativistic electron beams through energy modulation, enabling the generation of coherent, intense, and ultrashort radiation in accelerator-based light sources such as synchrotron radiation facilities and free-electron lasers (FELs). However, laser-induced energy modulation inevitably degrades electron beam quality by increasing the energy spread, thereby limiting high-repetition-rate operation. Here, we investigate energy modulation and demodulation in a seeded FEL using two modulators separated by a tunable phase shifter. Analytical analysis and three-dimensional simulations show that a $\pi$ phase delay can nearly reverse the laser-beam interaction and substantially suppress the residual modulation. Diagnostics based on coherent undulator radiation and time-resolved measurements are established to characterize weak residual modulation, and a dedicated demodulation undulator is designed for controlled studies. Preliminary experiments performed at the Shanghai soft X-ray FEL facility using the existing seeding beamline demonstrate laser-induced energy-modulation suppression. Together with the analytical and numerical studies, these results establish a practical framework for investigating the transition from energy modulation to demodulation in seeded FELs, with potential applications in high-repetition-rate, fully coherent X-ray sources with improved preservation of electron beam quality.

physics.acc-ph↗

arXiv2024

A Radiometric Correction based Optical Modeling Approach to Removing Reflection Noise in TLS Point Clouds of Urban Scenes

Point clouds are vital in computer vision tasks such as 3D reconstruction, autonomous driving, and robotics. However, TLS-acquired point clouds often contain virtual points from reflective surfaces, causing disruptions. This study presents a reflection noise elimination algorithm for TLS point clouds. Our innovative reflection plane detection algorithm, based on geometry-optical models and physical properties, identifies and categorizes reflection points per optical reflection theory. We've adapted the LSFH feature descriptor to retain reflection features, mitigating interference from symmetrical architectural structures. By incorporating the Hausdorff feature distance, the algorithm enhances resilience to ghosting and deformation, improving virtual point detection accuracy. Extensive experiments on the 3DRN benchmark dataset, featuring diverse urban environments with virtual TLS reflection noise, show our algorithm improves precision and recall rates for 3D points in reflective regions by 57.03\% and 31.80\%, respectively. Our method achieves a 9.17\% better outlier detection rate and 5.65\% higher accuracy than leading methods. Access the 3DRN dataset at (https://github.com/Tsuiky/3DRN).

cs.CV↗

arXiv1997

New Protostellar Collapse Candidates: An HCO+ Survey of the Class 0 Sources

We have observed 23 Class 0 sources in the HCO+ J=4-3 and 3-2 lines. The mean bolometric temperature of the 16 sources with well-determined values is 44 K and the mean luminosity is 5.7 L_sun, excluding two sources of considerably higher luminosity. Nine sources, including three sources previously suggested to be collapsing, have the correct (blue) spectral line asymmetry for infall in both lines. Three sources have the opposite (red) asymmetry in both lines, and one source, L1157, has a red asymmetry in HCO+ J=4-3 and a blue asymmetry in J=3-2. The rest have no significant or consistent asymmetry. The H13CO+ J=4-3 and 3-2 lines were also observed to find the velocity of the ambient gas, and sources with an interesting line asymmetry were mapped. A Monte Carlo code was used to produce an evolutionary sequence of collapsing cloud models of the HCO+ J=4-3 and 3-2 lines and to compare various diagnostics of the resulting line profiles. The same code was used to compare infall models to the observations in one source, L1527. The results were consistent with previous collapse models. Based on integrated intensity maps of the line peaks and wings, as well as the velocity of the H13CO+ line, we select six of the nine sources with a blue line asymmetry as good candidates for protostellar collapse. Further evidence is needed to establish that infall is taking place. The HCO+ spectra are not conclusive because bipolar outflows produce strong emission, which can confuse the issue in any individual source. However, the predominance of blue asymmetries over red asymmetries is not naturally explained in outflow models, whereas it is expected in collapse models.

astro-ph↗

arXiv1995

Observation of Infrared and Radio Lines of Molecules toward GL2591 and Comparison to Physical and Chemical Models

We have observed rovibrational transitions of acetylene and HCN near 13 microns in absorption toward GL2591. We also observed rotational lines of CS, HCN, H2CO, and HCO+. The combined data are analyzed in terms of models with a cloud envelope with density gradients and discrete regions of hot, dense gas, probably near the infrared source. The abundance of HCN is enhanced by a factor of 400 in the gas producing the infrared absorption, in agreement with chemical models which involve depletion of molecules onto grains and subsequent sublimation when temperatures are raised.

astro-ph↗