New computational method removes moving objects from 3D urban maps
In short: Researchers have developed a new computational approach called ERASOR to clean up 3D point cloud maps. By focusing on how moving objects like cars and pedestrians interact with the ground, the method identifies and removes the 'ghost' traces that dynamic objects often leave behind during the mapping process.
This technique uses a concept called pseudo occupancy to differentiate between occupied spaces and identifies static points through region-wise ground plane fitting. While the method shows promise in datasets like SemanticKITTI, its performance is evaluated through computational simulations rather than real-world physical deployment.
Why it matters: Cleaner 3D maps could significantly improve how autonomous vehicles navigate complex urban environments.
Opens the Intellect+ feed with this card first. Swipe up for the next one.
Sources
- Summary by Intellect · source: Research: Lim et al. (2021). ERASOR: Egocentric Ratio of Pseudo Occupancy-Based Dynamic Object Removal for Static 3D Point Cloud Map Building. IEEE Robotics and Automation Letters.
To cite this card, link to https://intellectplus.co.uk/app/nature-research-new-computational-method-removes-moving-objects-from-3d-urba.
How we source, check and correct cards: Editorial standards.
General information, not professional advice. Spotted an error? Flag the card or see corrections and complaints.
Intellect Plus is a visual educational discovery platform for exploring fascinating facts and ideas. Brain Food, Not Brain Rot. What is Intellect Plus?
Related
More in Nature · Latest · A–Z · All topics
