Special sessions

!! Please select the desired Special Session in the topics list when submitting an abstract on the submission plateform so that the contribution is directly routed to the session organisers !!

 

 

Special Sessions:

 

 

 

SS1: Damage detectability and effects of environmental and operational variability in structural health monitoring

 

Organisers:

The dynamics of structures under environmental and operational variations (EOVs) represent a significant challenge in the system identification and Structural Health Monitoring (SHM) fields. This challenge is compounded by issues surrounding the successful integration of data across various time scales, and the modeling of evolving system dynamics where the structural integrity is frequently in flux. A burgeoning interest in SHM has catalyzed a focus on addressing the impacts of EOV on damage diagnosis, a continuously growing topic with significant advancements in the field. To further advance our understanding and development of methodologies in this area, this session invites contributions that delve into the latest theoretical and practical developments aimed at identifying, modeling, and compensating for these dynamic systems’ changes. We are particularly keen on papers that explore the use of analytical, data-driven, and/or hybrid models that can adapt to both time and parameter variability, and that employ data-driven models and/or physics-based models to enhance the interpretability and efficacy of long-term structural assessments. Furthermore, research that tackles the normalisation of dynamic features and the integration of explicit and implicit compensation strategies to improve damage detectability under variable operational conditions is crucial. Your insights and scholarly submissions are eagerly anticipated to enrich discussions and contribute to the evolution of this critical area of study. This collaborative and explorative forum is expected to push forward the boundaries of how we monitor and maintain the health of structures under continuously changing
conditions.

 

 

SS2: Economic Impact and Environmental Assessment of Structural Health Monitoring in Engineering Applications

 

Organisers:

Structural Health Monitoring (SHM) has a great potential to improve the safety and reducing the life cycle costs, indeed, it improves the awareness of the structural condition without the need of human intervention. SHM systems, however, require significant investment costs and in some cases, it may affect the functionality of the monitored structure by increasing the weight and the complexity. To enable a large-scale adoption of such technology, a careful cost-benefit analysis is therefore
mandatory. In addition, monitoring is energy demanding in activating transducers and acquiring, communicating and processing data, leading to an intrinsic environmental impact. To assess environmental consequences in adopting SHM solutions, life cycle assessment is likewise crucial. In order to highlight the need for safe, cost effective as well as environment-friendly systems, this special session is aimed at disseminating the tools and case studies concerning the evaluation of economic impact and environmental assessment of SHM in different fields of engineering: aerospace,
civil, mechanical, and energy, with the purpose to:

  • highlighting the most advantageous applications of SHM systems;
  • proposing cost-effective Life Cycle Management strategies of smart structures;
  • providing structural design guidelines to fully exploit the potential of SHM, and
  • highlight potential environmental gains provided by the monitoring over lifetime.

 

 

SS3: Reliability and Quality Assessment of SHM systems

 

Organisers:

Despite intriguing features and promising breakthrough in several fields of application, many SHM systems have so far not achieved widespread industrial acceptance as a continuous monitoring technique. It is indeed of paramount importance understanding the potential effectiveness of an SHM system before transfer into routine applications. A key aspect is that there is still a lack of strategies for performance assessment that take into account the peculiarities of SHM systems. To assess the ability thereof, a variety of prerequisites and contributing factors have to be considered and need to be analysed in the way they affect the system reliability. For guided-wave based systems, e.g. it is not possible to analyse the system performance without looking into the specific structure and the applied SHM system parameters. Therefore, interdependencies of performance assessment and factors, influencing the quality, capability and reliability of an SHM system, are recently discussed and put into relation with state-of-the-art methods for performance analysis of NDE, like Probability of Detection (POD) or Receiver Operating Characteristic Curves (ROC-Curves). In this context, this Special Session aims to represent a forum for researchers and practitioners from industry, academia, and government interested in reliability and performance assessment for SHM.
This session focuses all aspects inherent to reliability and welcomes especially papers which:

  • discuss reliability aspects of any kind of SHM systems,
  • approach quality assessment for any kind of SHM systems, like ROC, POD,
  • discuss approaches on how to make the transition of POD from NDE to SHM,
  • show developments on how to enable simulation-supported quality assessment,
  • introduce new concepts for performance assessment, such as new specific analysis and procedures or artificial-intelligence supported assessment.

Moreover, case studies on defined aspects of reliability and quality assessment for specific SHM systems are very welcome.

 

 

SS4: Uses of UltraSonic Embedded Sensors for the Non-Destructive Evaluation and Structural Health Monitoring of Infrastructure
and Human-Built Objects

 

Organisers:

Recent advances, particularly in the context of the Marie Skłodowska-Curie Doctoral Network USES², have enabled the embedding of ultrasonic sensors within structures with minimal intrusiveness, opening new pathways for dense, long-term structural health monitoring (SHM). However, challenges persist due to the stringent power limitations inherent in embedded systems—particularly over decades-long lifespans in environments like concrete—which constrain data acquisition, processing, and transmission capabilities.
Mechanical waves offer powerful diagnostic capabilities due to their scalability and sensitivity to material changes. Embedding sensors directly within materials greatly improves coupling and signal quality, addressing limitations linked to poor accessibility and complex geometries. This embedded configuration is key to enabling reliable monitoring in highly attenuating or structurally complex environments.
Despite this potential, widespread SHM adoption is hindered by the lack of robustness in current systems under varying Environmental and Operational Conditions, which often lead to false alarms or missed detections. Additionally, maintaining consistent data quality and communication with isolated sensors over long durations remains a major challenge.
This session will focus on recent developments in fully embedded sensing solutions, highlighting innovations in sensor front-end design, in-situ data processing, fault detection, and the use of network redundancies to reconstruct missing or corrupted information. Particular emphasis will be placed on sensor systems that are designed from the ground up to be permanently buried within the monitored material, ensuring long-term, autonomous, and resilient structural diagnostics.

 

 

SS5: BRIDGITISE an EU network on the digitalization of bridge integrity management

 

Organisers:

The recently funded EU project BRIDGITISE aims to advance the digitalization of bridge management by developing innovative methods for handling bridge data. It focuses on creating and validating new technologies to improve the management of bridge information, supporting integrity-related decisions throughout the entire lifecycle. The project brings together a consortium of universities, research centers, industry partners, bridge design and assessment firms, and end-users. This Special Session will highlight ongoing research by project partners, covering topics such as cost-effective, large-scale automated data collection technologies, AI and IoT solutions tailored for bridges to process and share information, and digital decision support tools designed for comprehensive lifecycle management.

 

 

SS6: Machine learning and Bayesian methods in rotating machinery diagnostics

 

Organisers:

  • Szymon Gres, Department of Electronic Systems Automation & Control, Aalborg University, sg@es.aau.dk
  • Luis David Avendaño-Valencia, SDU Mechanical Engineering, University of Southern Denmark, ldav@sdu.dk

Diagnosing rotating machinery through vibration response analysis remains a complex and evolving scientific challenge. The intricate dynamics of rotating systems—compounded by friction, fluid-structure interactions, and other nonlinear effects—pose significant hurdles for advanced signal processing and machine learning techniques. These challenges are further amplified by varying operational conditions such as speed and load.
A key enabler for robust condition monitoring is the ability to distinguish early damage signatures from the inherent complexity of machine dynamics. Recent research has focused on integrating sparse, heterogeneous data with physical models, yet difficulties persist in calibrating structural properties while accounting for unmeasured excitations and unmodeled dynamics. To address these issues, modern paradigms such as physics-informed learning and reduced-order modelling are increasingly being embedded into estimation frameworks to enhance diagnostic performance.
This special session invites contributions on machine learning, Bayesian inference, and related methodologies for the identification and fault diagnosis of rotating machinery. Topics of interest include, but are not limited to:

  • Condition monitoring of rotating machinery (e.g., roller, film bearings, gears, reciprocating machine, engines, and pumps)
  • Bayesian filters for input-parameter-state estimation
  • Physics-informed and hybrid (data + physics) modelling approaches
  • Signal preprocessing for harmonic removal and component separation
  • Statistical methods for damage detection, localization, and prognosis
  • Handling disturbances and multi-source data in diagnostics
  • Machine learning techniques tailored to rotating systems

We welcome theoretical developments, numerical simulations, and experimental studies that advance the state of the art in this field. This session aims to foster interdisciplinary dialogue and showcase innovative methodologies that push the boundaries of rotating machinery diagnostics.

 

 

SS7: Damage identification with smart sensor networks: combining physics-based models with data-driven methods

 

Organisers:

The development of Structural Health Monitoring systems has progressed significantly over the past decade. A key factor in this development is the rise of data-driven methods and the accompanying artificial intelligence-based tools to handle the data collected by integrated smart sensor systems. The complexity of real-world systems is too high to rely on physics-based models only, such as high-fidelity numerical simulations. At the same time, interpretation of data without any physical knowledge is a stab in the dark. The solution to this dilemma is using physics informed data driven methods for Structural Health Monitoring Systems. The challenges relate to determining the data and knowledge position: how much is known, which models are available, how much data is available, what is the data quality and how is the data changing under varying operational and environmental conditions etc. The absence of run-to-failure data and limitations in knowledge on fracture mechanics from materials like composites forms another important challenge.
Contributions are welcomed that address how these challenges are tackled: which methods are used and what is their performance, when combining physics-based models with data-driven methods.

 

 

SS8: Satellite-based health monitoring for civil infrastructure

 

Organisers:

In the last decade, the launch of second-generation Synthetic Aperture Radar (SAR) satellites and the parallel evolution of Interferometric SAR (InSAR) processing techniques have made an unprecedented number of high-quality measurements of earth surface displacements available on large areas. Initially exploited to evaluate geophysical phenomena like earthquakes, landslides and volcanoes, these measurements are increasingly applied to monitor building and infrastructure deformations. With a sensitivity to millimetre displacements, high spatial density, and weekly revisit time, SAR satellites are now valuable for supporting structural conditions assessment. This session aims to discuss the most recent challenges and developments in InSAR applications to the health monitoring of structures. Topics cover and are not limited to advances in the processing algorithms and application case studies, including tunnels, bridges, dams, pipelines, etc.

 

 

SS9: Quantum-Enhanced Structural Health Monitoring: A New Frontier in Intelligent Sensing and Diagnostics

 

Organisers:

With the recent advancement of quantum computers, sensors, and the associated algorithms, a new horizon is opening for Structural Health Monitoring (SHM) systems. These developments promise to revolutionize the way we detect, localize, and predict damage in critical structures by offering enhanced sensitivity, ultra-high resolution, and fundamentally new modes of information processing. Quantum-enhanced SHM leverages principles such as quantum entanglement, superposition, and quantum interference to unlock capabilities far beyond the reach of classical sensing and computation.
This transformative approach enables precise monitoring of structural behavior under both operational and extreme conditions, laying the foundation for real-time, high-fidelity diagnostics across diverse engineering domains. When combined with quantum machine learning, these systems can extract subtle patterns from complex structural signals, enhancing predictive maintenance and decision-making in safety-critical applications. From aerospace to civil infrastructure, the integration of quantum technologies into SHM is poised to set a new standard in resilience, efficiency, and sustainability.
The objective of this special session is to bring together leading researchers and practitioners working at the intersection of quantum technology and structural health monitoring. The session will serve as a platform to share theoretical advances, experimental results, and practical implementations that demonstrate the potential of quantum-enhanced SHM.
Researchers are encouraged to contribute to the development of next-generation SHM systems that incorporate quantum sensing and computation. Topics of interest include, but are not limited to:

  • Quantum(-enhanced) Machine Learning for SHM: Quantum-inspired and quantum-enhanced algorithms for pattern recognition, anomaly detection, and system identification in complex structural datasets.
  • Hybrid Quantum-Classical systems: Integration of quantum sensing and ML subsystems with classical SHM platforms, digital twins, and embedded monitoring frameworks.
  • Quantum-Photonic Vibrometry: Development and deployment of quantum-enhanced laser vibrometers for non-contact, non-destructive structural evaluation.
  • Quantum(-enhanced) Sensors: Design and application of quantum sensors (e.g., atom interferometers, quantum-optical sensors) for high-resolution strain, vibration, or displacement measurements.

 

 

SS10: Knowledge transfer and data integration for structural health monitoring and system identification

 

Organisers:

This special session focuses on innovative methodologies and technologies for Structural Health Monitoring (SHM), and structural identification, with a particular focus on knowledge transfer, data integration, and data-driven approaches. Contributions addressing remote, contactless, and cost-effective monitoring solutions are encouraged, especially those capable of dealing with both short- and long-term structural behaviours.
Papers on innovative techniques for processing vibration and environmental signals, aimed at improving the diagnosis and prediction of structural behavior through data-driven, model-based, or hybrid approaches, are welcome. Topics of interest include linear and nonlinear system identification, signal processing, machine learning, transfer learning, model updating, and data analysis from static, dynamic, or remote monitoring systems. Special attention will be given to methods for damage detection, localization, and quantification, including the impact of environmental conditions on the accuracy and robustness of data-driven models. The session aims to promote interdisciplinary dialogue and foster synergy between SHM approaches. Emphasis is placed on approaches that bridge digitalization, machine learning, and large-scale data analysis to improve decision-making.

 

 

SS11: AI-powered structural sensing and health monitoring for civil engineering structures

 

Organisers:

Recent advances in artificial intelligence (AI) are transforming structural health monitoring (SHM), enabling more effective sensing, modeling, and decision-making. Despite this progress, reliably deploying AI-based SHM in practice remains challenging. This session will provide a forum to discuss the latest developments in integrating AI into structural sensing and health monitoring, with a focus on strengths, limitations, opportunities, and open challenges. We also welcome discussions on generating large-scale datasets and implementing federated learning to foster community collaboration and unlock AI’s potential in SHM. Our objective is to catalyze interdisciplinary collaboration and exchange of ideas between AI researchers and structural engineers.
The discussion will span diverse sensing technologies and civil infrastructure across multiple spatial and temporal scales—from individual buildings to entire cities. Topics of interest include, but are not limited to:

  • Learning models for interpreting structural sensing data
  • Alignment and fusion of heterogeneous sensing data
  • Domain adaptation and generalization in SHM
  • Advances in population-based SHM
  • Federated learning for SHM

 

 

SS12: Advances in the application of the inverse Finite Element Method (iFEM) for real-time Deformation Reconstruction, Damage Detection,
and Structural Health Monitoring

 

Organisers:

This special session will focus on recent advances and applications of the Inverse Finite Element Method (iFEM) for real-time deformation reconstruction, damage detection, and damage identification across a wide range of engineering fields, including but not limited to aerospace, marine, mechanical and civil structures. Emphasis will be placed on innovative computational models, experimental methodologies, and hybrid physics–data-driven approaches that enable accurate full-field shape sensing from sparse strain measurements. Contributions are invited on topics such as novel algorithms for damage localization and characterization, statistical and nonlinear iFEM formulations, sensor placement optimization, advances in shape sensing performance and integration with Digital Twin frameworks. The session also welcomes studies on the assimilation of diverse sensor technologies—fiber optic, resistive, piezoelectric—into structural systems to provide real-time insight into mechanical behavior. Both numerical and experimental studies are welcome.

 

 

SS13: SHM of Populations and Fleets: Similarity, Transfer and Data-sharing

 

Organisers:

Scarcity of data presents an ongoing dilemma in SHM which has the potential to limit the extent and overall effectiveness of SHM implementations. A key research challenge is finding new methodologies that can harness data from multiple sources (i.e. populations or fleets) to expand the available knowledge of a system. This additional information aims to provide new or further useful insight across a wide variety of decision-making processes.

This special session invites contributions that address the above challenges and may include new techniques and methodologies, advances in existing approaches, and industrial applications. Topics of interest are, but not limited to:

  • Similarity assessment
  • Transfer learning
  • Data-sharing
  • Population-based machine learning
  • Population-based modelling
  • New experimental case studies / datasets

 

 

SS14: Seismic structural health monitoring for civil structures

 

Organisers:

Over the past twenty years, Seismic Structural Health Monitoring (S2HM) has made significant progress, fueled by both increasing demand and growing interest from researchers and practitioners. In many seismically active countries, numerous monitoring systems have been put in place to record real-time or near-real-time structural responses during strong earthquakes. These data are crucial, not only for improving our understanding of how structures behave and perform under seismic loads but also for calibrating accurate and dependable numerical models that can simulate structural behavior and identify potential damage.
This Special Session aims to showcase recent progress and successful applications of seismic SHM for civil structures and infrastructure, including buildings, bridges, historical structures, dams, wind turbines, and pipelines. The session covers both theoretical and computational advances as well as practical implementations. Contributions are invited on a broad range of topics, including but not limited to:

  • Seismic SHM algorithms for structural identification and damage detection
  • Strong motion arrays and real-time monitoring systems
  • Instrumentation, measurement techniques, and tools
  • Optimal sensors placement strategies
  • Experimental testing
  • Integration of seismic SHM with risk assessment and emergency management procedures

This session will serve as a platform for exchanging insights into current developments, evaluating successful applications, and identifying challenges and future directions in the field of seismic SHM.

 

 

SS15: Advancements in Smart Materials and Structures for SHM in Civil Engineering

 

Organisers:

Advancements in smart materials and structural systems are revolutionizing SHM in civil engineering, enabling intelligent infrastructure with real-time monitoring, damage detection, and predictive maintenance capabilities. This session aims to bring together researchers exploring the cutting-edge developments in smart and multifunctional materials and smart structures, including smart sensors and actuators, self-monitoring structural elements, metamaterials and metastructures with self-diagnosing properties, algorithmic strategies for self-sensory systems (including AI) and the integration of adaptive materials such as piezoelectric systems and self-healing composites in civil engineering structures, just to name the main areas of interest. Emphasis is placed on both experimental and practical applications that enhance the safety, resilience, and sustainability of modern infrastructure.

 

 

SS16: Intelligent Digitization and AI-Enabled monitoring for Cultural Heritage Building/cities

 

Organiser:

New digitization technologies are transforming cultural heritage preservation using advanced monitoring and management systems. Cultural heritage organizations across the globe are adopting IoT-enabled sensors, 3D scanning technology, and AI-based analytics to develop end-to-end digital documentation and monitoring systems for artifacts, monuments, and historical sites. Intelligent digitization involves integrating reality capture methods such as photogrammetry, LiDAR scanning, and Building Information Modeling (BIM) to produce accurate digital copies of heritage assets.
Contributions are invited on a broad range of topics, including but not limited to:

  • Application of smart digitization techniques in cultural heritage monitoring and management
  • Maintenance and service life prediction of heritage infrastructure and materials using digital twin and Artificial Intelligence models
  • Data driven monitoring methods for cultural heritage infrastructure
  • Advances in Data Science, Artificial Intelligence, Machine Learning, and Computer Vision for large cultural heritage systems

 

 

SS17: Mobile-sensing prognostics and health management of transportation infrastructure

 

Organisers:

Transportation infrastructure, such as roads and bridges, has become among the most valuable community assets, delivering substantial societal and economic benefits. However, worldwide there is a huge backlog in maintenance needs, and the urgency for effective monitoring, maintenance, and management strategies has never been greater. Recent advances in mobile-sensing technologies, leveraging data from passenger cars, unmanned aerial vehicles (UAVs), autonomous fleets, and trains, offer a transformative pathway for network-level monitoring of transportation infrastructure conditions, modernizing rapid-response capabilities, and enhancing network resilience.

This session invites contributions on novel methods, algorithms, and applications that utilize mobile-sensed data for prognostics and health management (PHM). Topics of interest include, but are not limited to:

  • Combining mobile-sensing technologies with artificial intelligence (AI) to advance health assessment of infrastructure assets;
  • Exploring heterogeneous mobile-sensing systems enabled by artificial intelligence of things (AIoT) technologies;
  • Addressing practical engineering challenges such as data scarcity through transfer learning, data fusion, and generative AI approaches;
  • Developing interpretable and knowledge-guided frameworks (e.g., physics-informed models) for mobile-sensing methods to uncover underlying mechanisms;
  • Integrating mobile-sensed data into digital platforms and decision-support tools to optimize maintenance planning;
  • Large-scale demonstrations, unique application scenarios, and industrial datasets showcasing practical implementations of mobile-sensing PHM.

 

 

SS18: Digital Twins for Structural Health Monitoring of Complex Mechanical Systems

 

Organisers:

Digital twins (DTs) are emerging as a central paradigm for structural health monitoring (SHM) of advanced mechanical systems. They provide a virtual representation that integrates experimental data with high-fidelity models to assess the condition of a structure and predict its future evolution under operating conditions. Mechanical systems of practical interest are increasingly complex, whether due to the use of architected and metamaterials, nonlinear behavior, or multi-physical couplings. Such characteristics make the creation of accurate and efficient DTs particularly challenging. Recent advances in artificial intelligence (AI) and machine learning (ML) provide new avenues for capturing nonlinearities, multi-scale behaviors, and hidden patterns that are difficult to model using physics alone. In this context, both physics-based and data-driven approaches play a complementary role: the former provide interpretability and predictive accuracy, while the latter offer adaptability and efficiency in handling large, uncertain datasets.
Hybridization between physics-based and data-driven approaches open new opportunities for SHM: on the physics-based side, improvements in reduced-order modeling, uncertainty quantification, and nonlinear simulations extend the predictive capability of physics-based models. On the data-driven side, machine learning and statistical inference provide powerful tools to extract damage-sensitive features directly from measurements, and to enhance the adaptability of DTs in uncertain environments. Hybrid strategies which combine the interpretability of physics-based models with the flexibility of data-driven methods are particularly promising to overcome the limitations of each paradigm when used in isolation. In particular, ML approaches such as deep neural operators, graph-based learning, reinforcement learning, and generative models offer unique opportunities to enable self-updating DTs that adapt in real time to streaming SHM data.
This mini-symposium aims to bring together contributions that advance the development of DT technologies for SHM, with a focus on accuracy, computational efficiency, and robustness. Topics of interest include (but are not limited to):

  • Hybridization of model-based and data-driven methods for DTs, including AI-driven model fusion, transfer learning, and multi-fidelity approaches for SHM.
  • Reduced-order and surrogate modeling for SHM and model updating
  • Modeling, computational and identification methods for metamaterials, including AI-based discovery, topology optimization, and inverse design for complex architected materials.
  • Nonlinear and multi-physical identification strategies for dynamical systems.
  • Uncertainty-aware and near-real-time DTs, for instance enabled through Bayesian deep learning and probabilistic graphical models for adaptive SHM.

 

 

SS19: Embedded Signal Processing and AI for Structural Health Monitoring

 

Organisers:

The deployment of Structural Health Monitoring systems in real environments is a complex undertaking, facing significant challenges. Sensors often generate vast amounts of data, which are impractical to transmit and process centrally due to limitations in bandwidth and energy constraints. Many monitoring tasks require low-latency responses and local autonomy, which cannot be achieved with cloud-based solutions alone. These constraints render embedded data processing a vital component of reliable and scalable SHM.
Recent advances in lightweight signal processing and embedded Artificial Intelligence (AI) have created new opportunities to bring intelligence closer to the acquisition systems. Within this paradigm, novel inspection systems can be devised in which diagnostics are performed locally by intelligent monitoring platforms featuring multiple functionalities, from sensing to on-device AI analytics, powered by compact models optimized for resource-constrained hardware (e.g., microcontrollers, field-programmable gate arrays, and system-on-chip platforms). These platforms are capable of inferring the health status of the target facility at the extreme edge of the monitoring chain. This approach reduces communication requirements, accelerates decision-making, and enhances autonomy, thereby enabling long-term deployment of SHM solutions even in challenging environments.
This special session invites contributions that address the latest advances in the field of embedded solutions for SHM, with a particular emphasis on novel algorithmic and methodological developments eventually inspired by AI. The following subjects are of particular interest: efficient signal processing pipelines, energy-aware machine learning models, real-time analytics, and adaptive inference strategies for constrained devices. We also strongly encourage empirical studies and case studies that demonstrate the implementation and validation of embedded algorithms in real-world SHM applications. The objective of this session is to stimulate discourse on the potential of embedded intelligence to transform SHM into a scalable, autonomous, and field-ready technology.
We welcome original contributions, including but not limited to:

  • Embedded signal processing and AI for SHM
  • TinyML and lightweight deep learning models for on-device inference
  • Energy-aware algorithms and adaptive inference strategies for resource-constrained devices
  • Field experiments and validation in real-world SHM scenarios
  • Novel computational platforms supporting embedded SHM diagnostics
  • Small Language Models
  • Analog to Information and In-Sensor Signal Processing
  • HW-SW co-design techniques for SHM system optimization
  • Autonomous and Wireless Sensor Networks powered by on-sensor diagnostics functionalities

 

 

SS20: Vision-Based Techniques for Vibration Assessment and Structural Health Monitoring

 

Organisers:

In recent years, computer vision and optical sensing have emerged as powerful, cost-effective, and non-contact technologies for vibration monitoring and structural health monitoring (SHM). Unlike traditional sensors that provide point-wise data, vision-based methods capture global, full-field measurements of structural response. Techniques such as digital image correlation, optical flow, motion magnification, and UAV-based photogrammetry enable accurate motion extraction, dynamic characterization, and early-stage damage detection, even under operational conditions.

This special session aims to showcase the latest developments and future directions in vision-based vibration assessment and SHM. Contributions are invited on novel methods, hybrid approaches combining video with conventional sensing, and applications to real-world infrastructure such as bridges, buildings, and wind turbines.

Topics of interest include (but are not limited to):

  • Motion extraction and vision-based modal analysis,
  • Damage detection and diagnosis using optical methods,
  • Motion magnification and computational imaging techniques,
  • UAV-based inspection and monitoring of hard-to-reach assets,
  • Robust and efficient processing for real-world environments,
  • Data fusion with conventional sensors,
  • Benchmarking, validation campaigns, and comparisons with traditional sensing approaches.