BENCHMARK "Fisheye Indoor Narrow spaces Evaluation"
Fisheye photogrammetry, low-cost image- and range-based sensors and slam technologies are getting very popular to quickly survey indoor and complex spaces. The different approaches become challenging in narrow environments, such as underground tunnels, stairs, caves, mines, etc. For this purposes, a benchmark dataset was created in order to provide a common playground for the evaluation of the performance of different 3D imaging approaches. Such a benchmark offers the opportunity to tackle one or more topics that influence the final accuracy of the results and to share and challenge your approach over the community. Within the topics that can be studied, we can mention: fisheye distortion models/distortion handling, capturing geometry, pre-calibration, multi-camera constraints, multi-camera synchronization, automated image orientation, point cloud aligment, etc.
More technical information about the benchmark are available here.
If you are willing to participate to the benchmark, please contact Fabio Remondino or Francesco Fassi.