Color segmentation is a challenging subtask in computer vision. Most popular approaches are computationally expensive, involve an extensive off-line training phase and/or rely on a stationary camera. This paper presents an approach for color learning on-board a legged robot with limited computational and memory resources. A key defining feature of the approach is that it works without any labeled training data. Rather, it trains autonomously from a color-coded model of its environment. The process is fully implemented, completely autonomous, and provides high degree of segmentation accuracy.
JUDY WOODRUFF: As we reported earlier, President Trump visited the African American Museum of History and Culture today, spending time considering the struggle to overcome racism in the United States. Tonight, another installment in our series Race Matters, focused on finding solutions to racism. CHARLAYNE HUNTER-GAULT: This is one of Lemuel LaRoche's day jobs, teaching graduate students in the University of Georgia's School of Social Work. But LaRoche is a man of many parts, one who doesn't separate town from gown, especially the parts of town populated by troubled youth. LEMUEL LAROCHE, University of Georgia School of Social Work: These kids are looking for opportunities, looking for a way out, bouncing from foster home to foster homes.
The St. Louis Chess Club and Scholastic Center has a pretty humble beginning. After retiring and moving back to his Missouri home, financier (and Forbes contributor) Rex Sinquefield had settled into the St. Louis area. A lifelong chess player, Sinquefield told me his motivation for creating his club was pretty simple, "I just wanted a chess club. It thought it'd be nice to have a chess club in St. Louis." Nearly a decade later, the simple desire of a guy who just wanted to play chess in his retirement has turned a neighborhood in St. Louis into a virtual chess campus - complete with a club, a museum, a home for grandmasters, and a chess-themed diner.
Chess Dominion - Great chess site for learning how to play. Has interactive tutorials, chess problems and chess computers that will play you in different games so that you can practice playing with just one piece at a time. Also features an interactive section where you can enter your games for analysis or share in the analysis of someone else's game. Includes a lesson plan for teacher's interested in teaching chess in their classrooms.
James Bruce Tucker Balch Manuela Veloso School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Abstract Vision systems employing region segmentation by color are crucial in applications such as object tracking, automated manufacturing and mobile robotics. Traditionally, systems employing realtime color-based segmentation are either implemented in hardware, or as very specific software systems that take advantage of domain knowledge to attain the necessary efficiency. However, we have found that with careful attention to algorithm efficiency fast color image segmentation can be accomplished using commodity image capture and CPU hardware. This paper describes a system capable of tracking several hundred regions of up to 32 colors at 30 Hertz on general purpose commodity hardware. The software system is composed of three main parts; a color threshold classifier, a region merger to calculate connected components, and a separation and sorting system to gather various region features and sort them by size. The algorithms and representations will be described, as well as descriptions of three applications in which it has been used.