Discrete spatial datasets known as point clouds often lay the groundwork for decision-making applications. But can they become the next big thing?
I am a big point cloud enthusiast. I first discovered their existence 10 years ago, and since then, I have been tweaking my practices through the evolution of Reality Capture to always get sharper datasets. But I still remember my first surveys with terrestrial laser scanners, and quickly getting these amazing (and still amazing) 3D point clouds
But then… the dream is confronted with reality. How does one effectively consider these entities? At that time, the processing — read manual overloaded repetitive digitization — was composed of several heavily manual steps such as filtering, registration, cleaning, segmenting, classifying, meshing, digitizing … It evolved for some parts (mainly registration, filtering, and meshing) but the main bottleneck that I had back then is still unresolved: why do we bother changing the nature of the data (E.g. point cloud to vector) per application?
💡 Dive in the full article freely available at Towards Data Science.
if you want more content like this, follow me on Medium and subscribe to the newsletter 👍