Scale Selection for 3D Point Data

Posted 10 Jan 2005 at 21:14 UTC by steve Share This

The CMU Robotics Institute has released a new technical report titled, "Scale Selection for Classification of Point-Sampled 3D Surfaces" (PDF format). Mobile robots frequently use sensors like the SICK laser scanners or sonar that return a cloud of individual range points when measuring a 3D scene. This paper presents an automated solution to the common problem of figuring out a scale for extracting meaningful features from the point cloud such as determining whether you're looking at a rock or a bush or a man-made structure. The research was done at the Vision and Mobile Robotics Lab and was sponsored by the US Army and the National Science Foundation.

Concept Selection for Sensory Data, posted 11 Jan 2005 at 16:18 UTC by AI4U » (Observer)

Speaking of sensors, I have begun linking from Sensorium Mind- Module webpages to the various robots featured here on as examples of each sense or sensor that a robot may utilize. Therefore users here may find that I am linking down to their particular robots. Since I am mainly interested in robotics from the AI point of view, I offer everybody a theoretical design for forming new concepts from robotic sensory percepts.

See more of the latest robot news!

Recent blogs

30 Sep 2017 evilrobots (Observer)
10 Jun 2017 wedesoft (Master)
9 Jun 2017 mwaibel (Master)
25 May 2017 AI4U (Observer)
25 Feb 2017 steve (Master)
16 Aug 2016 Flanneltron (Journeyer)
27 Jun 2016 Petar.Kormushev (Master)
2 May 2016 motters (Master)
10 Sep 2015 svo (Master)
14 Nov 2014 Sergey Popov (Apprentice)
Share this page