Group items tagged

Marius Muja from University of British Columbia returned to Willow Garage this summer to continue his work object recognition. In addition to working on an object detector that can scale to a large number of objects, he has also been designing a general object recognition infrastructure. One problem that many object detectors have is that they get slower as they learn new objects. Ideally we want a robot that goes into an environment and is capable of collecting data and learning new objects by itself. In doing this, however, we don't want the robot to get progressively slower as it learns new objects. Marius worked on an object detector called Binarized Gradient Grid Pyramid (BiGGPy), which uses the gradient information from an image to match it to a set of learned object templates. The templates are organized into a template pyramid. This tree structure has low resolution templates at the root and higher resolution templates at each lower level. During detection, only a fraction of this tree must be explored. This results in big speedups and allows the detector to scale to a large number of objects.

The main focus for Bastian's work was on the feature-extraction process for 3D data. One of his contributions was a novel interest keypoint extraction method that operates on range images generated from arbitrary 3D point clouds. This method explicitly considers the borders of the objects identified by transitions from foreground to background. Bastian also developed a new feature descriptor type, called NARF (Normal Aligned Radial Features), that takes the same information into account. Based on these feature matches, Bastian then worked on a process to create a set of potential object poses and added spatial verification steps to assure these observations fit the sensor data.

Researchers at MIT’s McGovern Institute for Brain Research are working on a new mathematical model to mimic the human brain's ability to identify objects. The model can predict human performance on certain visual-perception tasks suggesting it’s a good indication of what's actually happening in the brain. Researchers are hoping the new findings will make their way into future object-recognition systems for automation, mobile robotics, and other applications.

NAMO (Novel Articulated MObile platform)  is a humanoid robot built by The Institute of Field Robotics (FIBO) at King Mongkut’s University of Technology Thonburi in Thailand. FIBO is active in the RoboCup scene and have developed a wide range of robot types, including an experimental biped.  NAMO was unveiled on March 29th 2010, serving as FIBO’s mascot as part of the university’s 50 year anniversary celebrations.  NAMO will be used to welcome people to the university and may be deployed at museums.  Given its friendly appearance and functionality, it could be used to research human robot interaction and communication. NAMO is 130cm (4′3″) tall and has 16 degrees of freedom.  It moves on a stable three-wheeled omnidirectional base, and is equipped with a Blackfin camera for its vision system.  It is capable of simple gesture recognition, visually tracks humans or objects of interest automatically, and can speak a few phrases in a child-like voice (in Thai).