Neural networks and fuzzy logic can conquer control-system challenges that leave conventional systems helpless. Here’s how they work, and how they benefit applications like high-speed image processing.
C.G. Masi, Control Engineering -- Control Engineering, 9/1/2007
Friday, February 29, 2008
Saturday, February 23, 2008
Tracking a Variable Number of Human Groups in Video Using Probability Hypothesis Density
Ya-Dong Wang Jian-Kang Wu Kassim, A.A. Wei-Min Huang
Inst. for Infocomm Res.
This paper appears in: Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
Abstract
We apply a multi-target recursive Bayes filter, the probability hypothesis density (PHD) filter, to a visual tracking problem: tracking a variable number of human groups in video. First, we use background subtraction to detect human groups which appear as foreground blobs. The PHD filter is implemented using sequential Monte Carlo methods; and the centroids of the foreground blobs are used as the measurements to update the PHD filter. Our experimental results show that when human groups appear, merge, split, and disappear in the field of view of a camera, our method can track them correctly. Link
Friday, February 15, 2008
Cooperative Exploration Simulation
Simulates cooperative exploration using 1..n robots. The robots can work independently or employ cooperative localisation where they estimate eachothers' pose. These options are set by the arguements passed to the constructor for the class Simulation.
The robots can employ one or more behaviours, which they switch between based on their potential utility. These can be included/excluded by setting the appropriate flags in the constructor for the class BehaviourData.
The simulation currently works on a single computer with communication between robots and board simulated using shared memory. Will soon be extended to allow execution on different machines with communication via sockets, and eventually over bluetooth.
Weblink
By Declan O'Beirne
The robots can employ one or more behaviours, which they switch between based on their potential utility. These can be included/excluded by setting the appropriate flags in the constructor for the class BehaviourData.
The simulation currently works on a single computer with communication between robots and board simulated using shared memory. Will soon be extended to allow execution on different machines with communication via sockets, and eventually over bluetooth.
Weblink
By Declan O'Beirne
Tuesday, February 12, 2008
A Study of Shopping Cart Robot
Related research are listed as below,
Japan - Hiroshi Takemura
US - Utah State University
Japan - Hiroshi Takemura
- Soh Nishimura, Hiroshi Takemura, Hiroshi Mizoguchi, "Development of Attachable Modules for Robotizing Daily Items -Person Following Shopping Cart Robot-," Proceedings of the 2007 IEEE International Conference on Robotics and Biomimetics,pp.1506-1511, December 15 -18, 2007, Sanya, China.
- Soh Nishimura, Keita Itou, Takashi Kikuchi, Hiroshi Takemura and Hiroshi Mizoguchi, "A Study of Robotizing Daily Items For an Autonomous Carrying System -Development of person following shopping cart robot-," The 9th International Conference on Control, Automation, Robotics and Vision (ICARCV 2006), pp.613-618,2006. (Singapore, 5-8th December 2006)
US - Utah State University
- Kulyukin, V., Gharpure, C., Pentico, C. (2007). Robots as Interfaces to Haptic and Locomotor Spaces. Proceedings of the 2nd ACM Conference on Human-Robot Interaction (HRI 2007), Washington, D.C.
- Kulyukin, V. and Gharpure, C. (2006). Ergonomics-for-One in a Robotic Shopping Cart for the Blind. Proceedings of the 2006 ACM Conference on Human-Robot Interaction (HRI 2006), pp. 142-149. Salt Lake City, Utah.
Subscribe to:
Posts (Atom)