Object detection system and method

专利名称：Object detection system and method发明人：YURI OWECHKO,NARAYAN

SRINIVASA,SWARUP S.

MEDASANI,RICCARDO BOSCOLO

申请号：AU9507201申请日：20010926公开号：AU9507201A公开日：20020422

摘要：A vision-based system for automatically detecting the type of object within aspecified area, such as the type of occupant within a vehicle. Determination of the type ofoccupant can then be used to determine whether an airbag deployment system shouldbe enabled or not. The system extracts different features from images captured byimage sensors. These features are then processed by classification algorithms to produceoccupant class confidences for various occupant types. The occupant class confidencesare then fused and processed to determine the type of occupant. In a preferredembodiment, image features derived from image edges, motion, and range are used.Classification algorithms may be implemented by using trained C5 decision trees, trainedNonlinear Discriminant Analysis networks, Hausdorff template matching and trainedFuzzy Aggregate Networks. In an exemplary embodiment, class confidences are providedfor a rear-facing infant seat, a front-facing infant seat, an adult out of position, and anadult in a normal or twisted position. Fusion of these class confidences derived frommultiple image features increases the accuracy of the system and provides for correctdetermination of an airbag deployment decision.

申请人：HRL LABORATORIES, LLC

更多信息请下载全文后查看