news    views    podcast    learn    |    about    contribute     republish    

Combining monocular video and SLAM to improve object recognition | MIT News


curated by | July 26, 2015

“John Leonard’s group in the MIT Department of Mechanical Engineering specializes in SLAM, or simultaneous localization and mapping… Last week, at the Robotics Science and Systems conference, members of Leonard’s group presented a new paper demonstrating how SLAM can be used to improve object-recognition systems… The system uses SLAM information to augment existing object-recognition algorithms. … Despite working with existing SLAM and object-recognition algorithms, however, and despite using only the output of an ordinary video camera, the system’s performance is already comparable to that of special-purpose robotic object-recognition systems that factor in depth measurements as well as visual information.”

John Payne’s insight:
The paper: "Monocular SLAM Supported Object Recognition" http://people.csail.mit.edu/spillai/projects/vslam-object-recognition/pillai_rss15.pdf
Via Slashdot: http://hardware.slashdot.org/story/15/07/26/1211220/mit-is-improving-object-recognition-for-robots



comments powered by Disqus


Halodi Robotics’ EVEr3: A Full-size Humanoid Robot
May 13, 2019

Are you planning to crowdfund your robot startup?

Need help spreading the word?

Join the Robohub crowdfunding page and increase the visibility of your campaign