arXiv subjects

Zhongwei Chen

Publications and source records attributed to Zhongwei Chen.

12 recordsLinked to original sources

arXiv2026

A Unified Benchmark and Modality-Adaptive Network for Day-and-Night Drone-View Geo-Localization

Most existing drone-view geo-localization (DVGL) benchmarks contain drone imagery captured under a single illumination condition and lack geographically aligned visible drone images, infrared drone images, and satellite images from the same locations. To evaluate the generalization capability of DVGL methods under challenging illumination conditions, some methods train models on a visible benchmark and test them on an independent infrared benchmark. This protocol essentially constitutes transfer between datasets, which makes it difficult to systematically evaluate DVGL across daytime and nighttime conditions within a unified benchmark. To address this limitation, we construct IRCHN,a real-world DVGL benchmark designed for localization across different illumination conditions. IRCHN contains 26,460 images collected from 8,820 geographic locations across four representative scene categories, including farmland, coastline, forest, and urban areas. Each location provides one visible drone image, one infrared drone image, and one corresponding satellite image, which enables unified evaluation of DVGL methods across different illumination conditions and sensing modalities. We further propose the Modality-Adaptive State-Space Transport Relation Network (MASTR-Net), a DVGL framework tailored to localization under varying illumination conditions. MASTR-Net integrates modality-adaptive feature enhancement, bidirectional selective state-space relation modeling, and soft optimal transport relation alignment to jointly reduce modality gaps and view-induced structural discrepancies. Extensive experiments demonstrate that MASTR-Net outperforms existing state-of-the-art methods on IRCHN for localization under varying illumination conditions and achieves competitive performance on two infrared benchmarks, IR-VL328 and CVGL-RGBT. Code: https://github.com/SongtianhaoXu/MASTR-Net

cs.CV↗

arXiv2026

GeoMFD: Continual Drone-View Geo-Localization with Geometry-Aware Adapter and Margin-Field Distillation

Existing drone-view geo-localization (DVGL) methods are mainly developed under a static training paradigm, where models are optimized for fixed environments with all training data available in advance. However, this paradigm is difficult to extend to real-world deployment, where drones may encounter diverse environments and require multiple environment-specific models, resulting in additional storage and model-selection costs. Directly adapting a single model to new environments also risks distorting previously learned cross-view embedding geometry and causing forgetting. To address these challenges, we formalize the continual drone-view geo-localization (C-DVGL) setting and propose GeoMFD, a geometry-aware continual adaptation method for DVGL. GeoMFD combines a cold-start bootstrapping strategy (CBS), a geometry-aware adapter (Geo-Adapter), and margin-field distillation (MFD) to balance adaptation and cross-view geometry preservation. CBS initializes a stable embedding space, Geo-Adapter enables environment adaptation through controlled residual corrections, and MFD preserves similarity margins between positive pairs and hard negatives to alleviate cross-view geometry forgetting. Extensive experiments demonstrate that GeoMFD effectively mitigates forgetting and achieves competitive performance with environment-specific DVGL methods using a single continuously updated model.

cs.CV↗

arXiv2026

From Limited Labels to Open Domains:An Efficient Learning Method for Drone-view Geo-Localization

Traditional supervised drone-view geo-localization (DVGL) methods heavily depend on paired training data and encounter difficulties in learning cross-view correlations from unpaired data. Moreover, when deployed in a new domain, these methods require obtaining the new paired data and subsequent retraining for model adaptation, which significantly increases computational overhead. Existing unsupervised methods have enabled to generate pseudo-labels based on cross-view similarity to infer the pairing relationships. However, geographical similarity and spatial continuity often cause visually analogous features at different geographical locations. The feature confusion compromises the reliability of pseudo-label generation, where incorrect pseudo-labels drive negative optimization. Given these challenges inherent in both supervised and unsupervised DVGL methods, we propose a novel cross-domain invariant knowledge transfer network (CDIKTNet) with limited supervision, whose architecture consists of a cross-domain invariance sub-network (CDIS) and a cross-domain transfer sub-network (CDTS). This architecture facilitates a closed-loop framework for invariance feature learning and knowledge transfer. The CDIS is designed to learn cross-view structural and spatial invariance from a small amount of paired data that serves as prior knowledge. It endows the shared feature space of unpaired data with similar implicit cross-view correlations at initialization, which alleviates feature confusion. Based on this, the CDTS employs dual-path contrastive learning to further optimize each subspace while preserving consistency in a shared feature space. Extensive experiments demonstrate that CDIKTNet achieves state-of-the-art performance under full supervision compared with those supervised methods, and further surpasses existing unsupervised methods in both few-shot and cross-domain initialization.

cs.CV↗

arXiv2026

Efficient Spike-driven Transformer for High-performance Drone-View Geo-Localization

Traditional drone-view geo-localization (DVGL) methods based on artificial neural networks (ANNs) have achieved remarkable performance. However, ANNs rely on dense computation, which results in high power consumption. In contrast, spiking neural networks (SNNs), which benefit from spike-driven computation, inherently provide low power consumption. Regrettably, the potential of SNNs for DVGL has yet to be thoroughly investigated. Meanwhile, the inherent sparsity of spike-driven computation for representation learning scenarios also results in loss of critical information and difficulties in learning long-range dependencies when aligning heterogeneous visual data sources. To address these, we propose SpikeViMFormer, the first SNN framework designed for DVGL. In this framework, a lightweight spike-driven transformer backbone is adopted to extract coarse-grained features. To mitigate the loss of critical information, the spike-driven selective attention (SSA) block is designed, which uses a spike-driven gating mechanism to achieve selective feature enhancement and highlight discriminative regions. Furthermore, a spike-driven hybrid state space (SHS) block is introduced to learn long-range dependencies using a hybrid state space. Moreover, only the backbone is utilized during the inference stage to reduce computational cost. To ensure backbone effectiveness, a novel hierarchical re-ranking alignment learning (HRAL) strategy is proposed. It refines features via neighborhood re-ranking and maintains cross-batch consistency to directly optimize the backbone. Experimental results demonstrate that SpikeViMFormer outperforms state-of-the-art SNNs. Compared with advanced ANNs, it also achieves competitive performance.Our code is available at https://github.com/ISChenawei/SpikeViMFormer

cs.CV↗

arXiv2025

Without Paired Labeled Data: End-to-End Self-Supervised Learning for Drone-view Geo-Localization

Drone-view Geo-Localization (DVGL) aims to achieve accurate localization of drones by retrieving the most relevant GPS-tagged satellite images. However, most existing methods heavily rely on strictly pre-paired drone-satellite images for supervised learning. When the target region shifts, new paired samples are typically required to adapt to the distribution changes. The high cost of annotation and the limited transferability of these methods significantly hinder the practical deployment of DVGL in open-world scenarios. To address these limitations, we propose a novel end-to-end self-supervised learning method with a shallow backbone network, called the dynamic memory-driven and neighborhood information learning (DMNIL) method. It employs a clustering algorithm to generate pseudo-labels and adopts a dual-path contrastive learning framework to learn discriminative intra-view representations. Furthermore, DMNIL incorporates two core modules, including the dynamic hierarchical memory learning (DHML) module and the information consistency evolution learning (ICEL) module. The DHML module combines short-term and long-term memory to enhance intra-view feature consistency and discriminability. Meanwhile, the ICEL module utilizes a neighborhood-driven dynamic constraint mechanism to systematically capture implicit cross-view semantic correlations, consequently improving cross-view feature alignment. To further stabilize and strengthen the self-supervised training process, a pseudo-label enhancement strategy is introduced to enhance the quality of pseudo supervision. Extensive experiments on three public benchmark datasets demonstrate that the proposed method consistently outperforms existing self-supervised methods and even surpasses several state-of-the-art supervised methods. Our code is available at https://github.com/ISChenawei/DMNIL.

cs.CV↗

arXiv2025

Multi-Level Embedding and Alignment Network with Consistency and Invariance Learning for Cross-View Geo-Localization

Cross-View Geo-Localization (CVGL) involves determining the localization of drone images by retrieving the most similar GPS-tagged satellite images. However, the imaging gaps between platforms are often significant and the variations in viewpoints are substantial, which limits the ability of existing methods to effectively associate cross-view features and extract consistent and invariant characteristics. Moreover, existing methods often overlook the problem of increased computational and storage requirements when improving model performance. To handle these limitations, we propose a lightweight enhanced alignment network, called the Multi-Level Embedding and Alignment Network (MEAN). The MEAN network uses a progressive multi-level enhancement strategy, global-to-local associations, and cross-domain alignment, enabling feature communication across levels. This allows MEAN to effectively connect features at different levels and learn robust cross-view consistent mappings and modality-invariant features. Moreover, MEAN adopts a shallow backbone network combined with a lightweight branch design, effectively reducing parameter count and computational complexity. Experimental results on the University-1652 and SUES-200 datasets demonstrate that MEAN reduces parameter count by 62.17% and computational complexity by 70.99% compared to state-of-the-art models, while maintaining competitive or even superior performance. Our code and models will be released on https://github.com/ISChenawei/MEAN.

cs.CV↗

arXiv2025

Coal Strength with Dewatering and Coal Seam Gas Depletion

Understanding the response of coal mechanical properties to dewatering and gas depletion is critical for estimating borehole stability and designing infill coal seam gas (CSG) wells. Despite its importance, the full impact of these processes on coal strength remains little explored. This study aims to quantify these effects through a combination of results from micro-CT imaging, sonic testing, and mechanical testing on coal samples. Micro-CT imaging provides insights into coal's internal structure by focusing on parameters such as fracture porosity and fracture intensity (P32 factor). Sonic testing measures dynamic properties, including P-wave, S-wave velocities (Vp and Vs) and dynamic Young's modulus (Ed), under both dry and wet conditions. Mechanical testing with acoustic emission (AE) monitoring evaluates static properties like Young's modulus (Es) and uniaxial compressive strength (UCS). The key findings are: (i) Micro-CT imaging shows a strong correlation between coal fracture porosity and P32, offering detailed insights into the coal micro-structure; (ii) mechanical testing reveals that dry samples exhibit a 10% higher Es and 31% greater UCS than wet samples, suggesting that dewatering increases coal strength but potentially also promotes embrittlement; and (iii) wet samples show higher Vp and Ed in sonic tests, indicating water saturation significantly influences sonic measurements. These findings improve the understanding of dewatering and gas depletion effects, laying the groundwork for more advanced geomechanical models in coal seam gas (CSG) operations.

physics.geo-ph↗

arXiv2025

A Simple Sonic Mapping Method Verified by CT Scan Images

This study presents a novel sonic mapping method applied to coal samples, verified by CT scan imaging. Cubic coal samples with side lengths of 50-70 mm were subjected to non-destructive sonic tests, measuring both P-wave (Vp) and S-wave (Vs) velocities. Each of the three orthogonal directions (X, Y, and Z) of the cube was divided into 9 regions, resulting in 27 Vp and 27 Vs measurements per sample. From these data, 2D sonic maps were constructed for each direction, and interpolation was employed to refine the mappings. A 3D sonic map was then generated by averaging the 2D maps. The 3D sonic mapping results were compared and validated against high-resolution CT scan images, confirming the reliability of this approach for mapping the internal structure of coal samples.

physics.med-ph↗

arXiv2024

Artificial General Intelligence (AGI) for the oil and gas industry: a review

Artificial General Intelligence (AGI) is set to profoundly impact the oil and gas industry by introducing unprecedented efficiencies and innovations. This paper explores AGI's foundational principles and its transformative applications, particularly focusing on the advancements brought about by large language models (LLMs) and extensive computer vision systems in the upstream sectors of the industry. The integration of Artificial Intelligence (AI) has already begun reshaping the oil and gas landscape, offering enhancements in production optimization, downtime reduction, safety improvements, and advancements in exploration and drilling techniques. These technologies streamline logistics, minimize maintenance costs, automate monotonous tasks, refine decision-making processes, foster team collaboration, and amplify profitability through error reduction and actionable insights extraction. Despite these advancements, the deployment of AI technologies faces challenges, including the necessity for skilled professionals for implementation and the limitations of model training on constrained datasets, which affects the models' adaptability across different contexts. The advent of generative AI, exemplified by innovations like ChatGPT and the Segment Anything Model (SAM), heralds a new era of high-density innovation. These developments highlight a shift towards natural language interfaces and domain-knowledge-driven AI, promising more accessible and tailored solutions for the oil and gas industry. This review articulates the vast potential AGI holds for tackling complex operational challenges within the upstream oil and gas industry, requiring near-human levels of intelligence. We discussed the promising applications, the hurdles of large-scale AGI model deployment, and the necessity for domain-specific knowledge in maximizing the benefits of these technologies.

cs.IT↗

arXiv2024

Tuning Thermal Conductivity of Hybrid Perovskites through Halide Alloying

Tuning the thermal transport properties of hybrid halide perovskites is critical for their applications in optoelectronics, thermoelectrics, and photovoltaics. Here, we demonstrate an effective strategy to modulate the thermal transport property of hybrid perovskites by halide alloying. A highly tunable thermal conductivity of mixed-halide hybrid perovskites is achieved due to halide-alloying and structural distortion. Our experimental measurements show that the room temperature thermal conductivity of MAPb(BrxI1-x)3 (x = 0-1) can be largely modulated from 0.27 W/mK (x = 0.5) to 0.47 W/mK (x = 1). Molecular dynamics simulations further demonstrate that the thermal conductivity reduction of hybrid halide perovskites results from the suppression of the mean free paths of the low-frequency acoustic and optical phonons. It is found that halide alloying and the induced structural distortion can largely increase the scatterings of optical and acoustic phonons, respectively. The confined diffusion of MA+ cations in the octahedra cage is found to act as an additional thermal transport channel in hybrid perovskites and can contribute around 10-20% of the total thermal conductivity. Our findings provide a strategy for tailoring the thermal transport in hybrid halide perovskites which may largely benefit their related applications.

cond-mat.mtrl-sci↗

arXiv2023

Vision-aided nonlinear control framework for shake table tests

The structural response under the earthquake excitations can be simulated by scaled-down model shake table tests or full-scale model shake table tests. In this paper, adaptive control theory is used as a nonlinear shake table control algorithm which considers the inherent nonlinearity of the shake table system and the Control-Structural Interaction (CSI) effect that the linear controller cannot consider, such as the Proportional-Integral-Derivative (PID) controller. The mass of the specimen can be assumed as an unknown variation and the unknown parameter will be replaced by an estimated value in the proposed control framework. The signal generated by the control law of the adaptive control method will be implemented by a loop-shaping controller. To verify the stability and feasibility of the proposed control framework, a simulation of a bare shake table and experiments with a bare shake table with a two-story frame were carried out. This study randomly selects Earthquake recordings from the Pacific Earthquake Engineering Research Center (PEER) database. The simulation and experimental results show that the proposed control framework can be effectively used in shake table control.

eess.SY↗

arXiv2023

A reinforcement learning based construction material supply strategy using robotic crane and computer vision for building reconstruction after an earthquake

After an earthquake, it is particularly important to provide the necessary resources on site because a large number of infrastructures need to be repaired or newly constructed. Due to the complex construction environment after the disaster, there are potential safety hazards for human labors working in this environment. With the advancement of robotic technology and artificial intelligent (AI) algorithms, smart robotic technology is the potential solution to provide construction resources after an earthquake. In this paper, the robotic crane with advanced AI algorithms is proposed to provide resources for infrastructure reconstruction after an earthquake. The proximal policy optimization (PPO), a reinforcement learning (RL) algorithm, is implemented for 3D lift path planning when transporting the construction materials. The state and reward function are designed in detail for RL model training. Two models are trained through a loading task in different environments by using PPO algorithm, one considering the influence of obstacles and the other not considering obstacles. Then, the two trained models are compared and evaluated through an unloading task and a loading task in simulation environments. For each task, two different cases are considered. One is that there is no obstacle between the initial position where the construction material is lifted and the target position, and the other is that there are obstacles between the initial position and the target position. The results show that the model that considering the obstacles during training can generate proper actions for the robotic crane to execute so that the crane can automatically transport the construction materials to the desired location with swing suppression, short time consumption and collision avoidance.

cs.CV↗