首页>
外国专利>
Method for producing sample dataset representing an object, for training an object classifier, involves generation of several n sets from sensor data of object or from alternative object by sensor which can be compared with object
Method for producing sample dataset representing an object, for training an object classifier, involves generation of several n sets from sensor data of object or from alternative object by sensor which can be compared with object
The method involves generation of several n sets from sensor data of the object or from an alternative object by sensor which can be compared with object. The n sets are transferred from sensor data in n real-sample data sets suitable to the training of the object classifier, in which an ideal representation of the object is transferred in a ideal-sample dataset corresponding to the real-sample. The training-sample data set representing the new object is produced from the ideal sample on basis of the variation of the parameters of the transformation function considering the probability densities.
展开▼