Speaker Bio & Abstract
CycloMedia Technology
The Netherlands
BiographyBas Boom graduated at the Free University of Amsterdam in Computer Science in 2005. He received his PhD at the University of Twente (2010) in Electrical Engineering, where his thesis was entitled “Face recognition's grand challenge: uncontrolled conditions under control”. From 2011 until 2015 he worked as postdoc at University of Edinburgh on the “Fish4Knowledge” project. His main research is machine learning and computer vision on large scale image and video datasets using supercomputing facilities. He is author and co-author of over 30 scientific publications in journals and international conferences and organized 2 special issues and 2 scientific workshops. Currently within Cyclomedia, he is the expert on computer vision and machine learning, where he created algorithms for automatic blurring of license plates and faces, for traffic sign recognition and building detection from aerial images.AbstractCycloMedia brings the added benefit of the opportunity to capture LiDAR data simultaneously while capturing our GeoCyclorama™ imagery. By this coincident capture method, we ensure the highest levels of both quality and accuracy. We further enhance the LiDAR data by processing it with our proprietary CycloPositioner software to increase its positional accuracy and perfect alignment in 3D space with our imagery. Given precise imagery co-referencing, we are able to extract the RGB values to produce a photo realistic “colorized point cloud”. Customers opting for LiDAR data collection will be able to use CycloMedia’s new Measure Smart ™ tool which takes advantage of a “depth” GeoCyclorama layer produced from the point cloud, and affords users a new measurement tool to achieve significant efficiencies in workflow. Our future vision is to provide customers with semantic point clouds where every point gets besides a color label also a class label (house, trees, road, etc).