|
Mission:
Image sequence analysis is playing an important role in many fields of close-range photogrammetry, computer vision, machine vision and robot vision
for many years. With the development of modern, flexible digital sensors, automatic methods for analyzing and evaluating image sequences are also entering
the fields of aerial photogrammetry and remote sensing. Examples of the application of image sequence analysis in photogrammetry and remote sensing are
2D/3D object tracking, ego-motion determination, detection and characterization of dynamic processes, deformation measurements, monocular or stereoscopic
mapping of the environment of a UAV or an autonomous robot, mobile mapping, biomedical motion analysis, and many others.
However, recent research has shown that a pure transition of methods mainly designed for the analysis of (close-range) video streams to the
aforementioned applications is not possible due to different camera characteristics, varying frame rates, other platforms and, in general, very
challenging environments. Further theoretical and experimental developments accompanied by thorough validations are thus necessary to better exploit
the huge information content of image sequences.
Terms of Reference:
Models, methods and algorithms for:
- Studying camera and camera network calibration from image sequences including cameras with non-standard geometry and variable framerate
- Studying ego-motion determination for navigation, georeferencing and object reconstruction
- Studying detection, reconstruction, classification and tracking of single and multiple objects in image sequences
- Studying event reconstruction from image sequences as well as single and multiple video streams
- Investigating the quality assessment of calibration, orientation and object detection using image sequences
- Benchmarking of calibration, orientation and object detection techniques using image sequences
Technical Commission Officers:
|