I am working at the moment on various projects involving 3D Capture and point cloud processing.
Smart Point Cloud Research
The first project concerns my research: how to bring intelligence to point cloud data. Point clouds are a direct source of information physically describing a 3D state of the recorded environment. As such, they are an exhaustive representation of the real world at every scale: a goldmine underexploited. Their generation is increasingly fast but processing routines lack knowledge to reason from information extraction rather than interpretation (i.e. 3D meshes, models). Bridging effective data acquisition and fast rendering through efficient indexing scheme, we developed a new concept: The Smart Point Cloud. It allows to bring intelligence to point clouds and creates a connection between available knowledge and classification procedures that permits semantic injection for information extraction.
For more info about this topic, refer to the following link: Smart Point Cloud
Capturing the world in 3D
The second project is a personal project: while travelling instead of bringing back a 2D photo I bring back a 3D Point Cloud. Then, we can virtual explore the Seychelles islands, Copenhaguen, France, Belgium, Germany, … Naviguate my virtual tour gallery based on Flyvast
Semantic Point Cloud tesserae
The third project concerns the semantization and classification of very high density point clouds from an oratory situated in Germigny-des-prés. Its magnificent mosaic composed of thousands of tessearae hold many secrets over mosaic manufacturing and european influences. The importance of cross-disciplinary understanding is essential to archaeological information extraction based on point clouds. However concepts and tools that simplify this process are rare, which complicates the merging of different experts’ perceptions around cultural heritage applications. Being able to share and exchange contextual knowledge to create a synergy among different actors is needed for planning and analysis of conservation projects. We obtain a tesserae-wise structure where each segment is connected to semantical information. Through data visualisation, we can address visual components that elegantly represent the analytical results while proposing an efficient way to interact with the data. More information: Full workflow
Maastricht Townhall – Tests
Other Reality Capture related projects