Prof. Julia Schmale, Extreme Environments Research Laboratory EERL – Ingvar Kamprad Chair
Prof. Alexandre Alahi, Visual Intelligence for Transportation laboratory
Earth system science and autonomous navigation sound unrelated and yet they both share the critical need to scan the world for 3D reasoning. In Earth system science, it is crucial to scan water surfaces in search of small-scale processes (e.g., waves breaking) and objects floating on them (e.g., sea ice) to advance knowledge and model capacity to predict global climate change. For autonomous navigation (e.g., self-driving cars, delivery robots, assisted navigation), it is fundamental to detect and locate objects in 3D (e.g., icebergs/ships on the ocean, or pedestrians/vehicles on the roads) to plan a safe yet efficient navigation.
Therefore, professors Julia Schmale et Alexandre Alahi decided to develop new imaging applications for depth estimation and data processing that cater both fields of science with comparable techniques. The team deployed stereo cameras from a moving icebreaker to detect breaking waves and ice floes on the Arctic Ocean, and developed a new system with two 360° cameras and a lidar to capture high-fidelity 3D data in crowds. Both implementations delivered libraries with more than 1 Million images from which the HELVIPAD image database was released, as well as the extracted numerical oceanographic data. The project led to the creation of 360-IGEVStereo, a new method for omnidirectional stereo depth estimation that extends a previous state-of-the-art approach. New physical relationships of wave breaking and sea spray production based on 3D imaging for implementation in climate models were also developed.
Looking ahead, the outcomes of 3DEarthNavgation have the potential for widespread application in the Earth system sciences, in particular in polar regions, where high quality imaging data is sparse.
