Fast Color-Independent Ball Detection for Mobile Robots
This paper presents a novel scheme for fast color invariant ball detection in the RoboCup context. Edge ﬁltered camera images serve as an input for an Ada Boost learning procedure that constructs a cascade of classiﬁcation and regression trees (CARTs). Our system is capable to detect different soccer balls in the RoboCup and other environments. The resulting approach for object classiﬁcation is real-time capable and reliable.
- URL: http://citeseer.ist.psu.edu/rd/0%2C717714%2C1%2C0.25%2CDownload/http://citeseer.ist.psu.edu/cache/papers/cs2/534/http:zSzzSzkos.informatik.uni-osnabrueck.dezSzdownloadzSzmechrob2004.pdf/mitri04fast.pdf
Keywords: Evolutionary Robotics
Record created on 2006-10-05, modified on 2016-08-08