Photogrammetry

Terms of Reference

• Multi-modal data fusion for photogrammetry
• Stereo / multi-view feature extraction and matching, matching, dense reconstruction and mesh generation.
• Novel 3D Representations for Photogrammetry (e.g., NERF).
• Camera geo-referencing and applications in autonomous platforms.
• Camera calibration.
• Machine learning and artificial intelligence models for photogrammetric applications.
• Photogrammetric pipeline design for virtual and augmented reality applications
• SfM and SLAM.
• Large scale and featureless bundle adjustment.
• Approaches to compute photogrammetric uncertainty and reliability.
• Point cloud extraction, processing, and semantic understanding.
• Integration/fusion across point clouds generated from different sources.
• High definition mobile map-making and map-updates using 2D images and 3D point clouds for spatial information systems (i.e. GIS and BIM).
• Platform autonomy by identification and photogrammetric positioning of objects and obstacles.
• Image sequence analysis and understanding for photogrammetric applications.
• Pixel and region based semantic segmentation under photogrammetric constraints.
• Photogrammetric applications in underground, underwater, space and cultural heritage.

WORKING GROUPS of ISPRS COMMISSION II

• WG II/1 - Image Orientation and Fusion
• WG II/2 - Point Cloud Generation and Processing
• WG II/3 - 3D Scene Reconstruction for Modeling & Mapping
• WG II/4 - AI/ML for Geospatial Data
• WG II/5 - Temporal Geospatial Data Understanding
• WG II/6 - Cultural Heritage Data Acquisition and Processing
• WG II/7 - Underwater Data Acquisition and Processing
• WG II/8 - Environmental & Infrastructure Monitoring
• WG II/9 - Vision Metrology

INTERCOMMISSION WGs of ISPRS COMMISSION II

• ICWG II/Ia - Autonomous Sensing Systems and their Applications
• ICWG II/Ib - Digital Construction: Reality Capture, Automated Inspection, and Integration to BIM

WG II/1 - Image Orientation and Fusion

WG II/1  Terms of Reference

• Orientation of classical and unconventional images including but not limited to oblique images, images from cameras with rolling shutter, RGBD images, crowd-sourced images, historical images, and thermal infrared images
• Multimodal image matching for alignment, registration and fusion of multi-source imagery, e.g. optical and radar images
• Geometric, algebraic and learning-based approaches to multi-view stereo and structure-from-motion (SfM)
• Modern approaches in intrinsic/extrinsic camera calibration and bundle adjustment (BA), e.g. single-image calibration, online calibration, methods for handling ambiguous and degenerate configurations, large-scale BA, and structureless BA
• Vision-based measurement of dynamic processes, e.g. structural deformations
• Evaluation of performance, reliability, robustness, and generality of methods

WG II/2 - Point Cloud Generation and Processing

WG II/2  Terms of Reference

• Point cloud acquisition by terrestrial / mobile / UAV / aerial LiDAR or other scanning technologies or photogrammetry 
• Stereo and Multi-View-Stereo for terrestrial / UAV / aerial / spaceborne imagery 
• Ubiquitous point cloud sensing and mapping, consumer grade 3D sensors, automotive 3D sensors 
• Real-time generation of point clouds using SLAM and related methods 
• Methods for multi-modal mesh generation 
• Integration of point clouds with multi-modal data (e.g., images, InSAR) for change detection/updating 
• Point cloud registration, fusion and integration of point clouds from different data sources or sensors for surface reconstruction
• Development of new methodologies, algorithms and applications for point cloud semantic understanding and analysis
• Explainability and interpretability for DL approaches on point clouds
• Machine learning for point filtering operations
• Information extraction from point clouds, including feature extraction, object detection, segmentation and classification 
• Quality and performance evaluation of point cloud generation with respect to computational complexity, precision, robustness and scalability of methods 

WG II/3 - 3D Scene Reconstruction for Modeling & Mapping

WG II/3  Terms of Reference

• Models and techniques for extracting features, geometrical primitives and objects from data acquired by airborne, spaceborne and/or terrestrial sensors, including object detection and 3D object reconstruction in complex scenes.
• Semantic interpretation of data of various origins and generated by various sensors, including methods for semantic segmentation and panoptic segmentation, potentially involving an interpretation of the entire scene, and considering both outdoor and indoor environments.
• Integration of semantic interpretation and 3D reconstruction of complex scenes, including point-based methods and methods based on object models, e.g. using implicit representations.
• Generation and update of high-resolution 3D city models and road databases, including mesh based, polyhedral, parametric and multi-scale representations possibly with level-of-detail (LOD) and (semantic) attributes, and texturing of the resultant 3D models.
• Object detection, recognition and 3D reconstruction in the context of robotics or autonomous driving.
• Multi-modal data fusion: performing any of the tasks mentioned above by exploiting the complementarity of using different viewpoints (space-borne, nadir/oblique aerial, UAV, fixed/mobile terrestrial), different sensor types (mono-scopic/stereoscopic images, LiDAR, (In)SAR), and existing data (traditional cartographic products, CAD models, urban GIS, data produced by crowd-sourcing).
• Methods addressing any of the tasks mentioned above, while focusing on handling noisy or out-of-distribution input data, including techniques for uncertainty estimation and uncertainty propagation.

WG II/4 - AI/ML for Geospatial Data

WG II/4  Terms of Reference

• Machine learning, deep learning
• Analysis and interpretation of geospatial data
• Scene classification, semantic (instance) segmentation, object detection
• Unsupervised, supervised, weakly supervised, transfer, self-supervised learning
• Human-in-the-loop learning
• Multi-view, multi-modal learning
• Precision agriculture, environmental/urban monitoring
• Biases analysis, interpretability and explainability of machine learning models

WG II/5 - Temporal Geospatial Data Understanding

WG II/5  Terms of Reference

• Classification and change detection in image time-series and/or 3D point clouds
• Dynamic scene understanding from image sequences
• Detection, reconstruction, classification and tracking of objects in image/lidar sequences
• Event reconstruction and scene analysis from single and multiple image/lidar streams
• Multi-source, multi-view, multi-temporal, multi-modal image analysis
• Machine learning and deep learning for time-series data

WG II/6 - Cultural Heritage Data Acquisition and Processing

WG II/6  Terms of Reference

• Innovative strategies and solutions in the collection and processing of data for the documentation of cultural heritage
• Automation strategies in data processing
• Multi-source data fusion
• Remote sensing in cultural heritage
• Cultural heritage monitoring
• Metrics and accuracy in cultural heritage
• Cultural heritage modelling towards HBIM
• Virtual and augmented reality
• Open-source promotion
• Low-cost merging strategies
• Cultural heritage data acquisition standards
• Establishment of good practice protocols

ICWG II/Ia - Autonomous Sensing Systems and their Applications

ICWG II/Ia  Terms of Reference

• Drones, ground and underwater autonomous systems
• Autonomous path planning, SLAM, navigation and VLOS/BVLOS exploration
• Edge, fog and cloud computing for real-time scene understanding
• Collaborative and swarm platforms for Geospatial applications
• Heterogenous data collection from drones (e.g. climate sensors)
• Next-generation autonomous platform applications
• Innovative active and passive sensors embedded on autonomous platforms
• Dissemination of learning and teaching material on the use of Autonomous Sensing Systems and their Applications in Academia
• Collaboration with other scientific communities and associations involved in Autonomous Sensing Systems and their Applications (EuroSDR, robotics, computer vision, electronics, etc.)
• Cooperation and involvement of industrial partners in ISPRS activities

ICWG II/Ib - Digital Construction: Reality Capture, Automated Inspection, and Integration to BIM

ICWG II/Ib  Terms of Reference

• Tackling opportunities and challenges that digital construction and various 3D printing methods (contour crafting, shotcrete, particle-bed, etc.) bring to the current data capturing and inspection methodologies
• Analysis and selection of sensors and systems for the purpose of reality capture and automated inspection in digital construction (from component to building scale)
• Progress monitoring of large construction projects (buildings, bridges, etc.)
• Data exchange between inspection systems and BIM/FIM
• Augmented Reality and Mixed Reality in digital construction
• As-built vs. as-designed and evaluation of geometric conformity in 3D printing (co-registration, inspection metrics, etc.)
• Computer vision in digital construction: Co-registration, detection, localization, and tracking of the moving robots and sensors
• Automated risk assessment and safety hazard identification
• Increasing automation (IoT, Industry 4.0, etc.) and remote inspection

WG II/7 - Underwater Data Acquisition and Processing

WG II/7  Terms of Reference

• Geometric and stochastic modelling of multimedia geometry for underwater image and range measurements
• Definition of best practice for geometric calibration, colour correction and restoration, validation of systems for underwater 3D measurements
• Combined above-water, through-water and underwater techniques for 3D modelling and mapping of coastal habitat
• Lidar and photo bathymetry for seafloor and water surface measurement
• AI-driven solutions for through-water, underwater and habitat mapping applications
• Algorithms and methods for underwater localization, navigation and mapping, including augmented and virtual reality applications
• Sensors’ integration and performance evaluation of UUVs (ROVs and AUVs), towed vehicles and diver operated systems
• Underwater applications and methods in archaeology, habitat mapping and monitoring, industrial metrology and inspections, volumetric reconstruction for flow tracking

WG II/8 - Environmental & Infrastructure Monitoring

WG II/8  Terms of Reference

• Promote the use of highly accurate tools and efficient technology to achieve geometric deformation tracking in the urban and natural environment as well as infrastructure.
• Promote the study, development, and application of algorithms to solve problems in environmental (natural and urban) as well as infrastructure monitoring accurately and precisely, respectively.
• Evaluate the performance and robustness of methods through the processing of different 2D-3D geospatial datasets to achieve a better description, mapping, and monitoring of the environment.
• Study and analyze optimal and precise solutions according to the capabilities and challenges of the various remote sensing platforms. Address errors and their impact on the resulting processing.
• Promote the development of new approaches and methods for biomedical data processing and analysis to improve monitoring and diagnostics and provide valuable results in biometry and biomedicine.

WG II/9 - Vision Metrology

WG II/9  Terms of Reference

• Geometrical 2D, 3D, and 4D measurements
• Consideration and assessment of uncertainty
• Benchmarking
• Modeling and calibration of vision sensors and lenses
• Performance evaluation of active and passive sensor systems
• Machine learning for vision metrology
• Geometrical object inspection
• Sensor and object pose determination
• Vision-guided industrial robots
• Close-range photogrammetry
• Vision metrology for objects/scenes with complex optical material appearance
• Large-volume measurement applications
• Innovative industrial applications
• Machine Vision