We dedicated to the research of it. In order to improve its performance, we worked on the selection and training process of classifier, occlusion handling, multiple detection results merging.
本文在对该方法进行研究的基础上,为了提高检测的性能,对分类器的选取、训练方法、遮挡处理、结果融合等方面进行了研究。
The existing occlusion models such as LOS and ROC are all based on the RCC (Region Connection Calculus) theory, which is not suitable for handling multi-dimensional objects.
LOS和ROC等现有的遮蔽关系模型都是基于RCC(区域连接演算)的,因而不能支持混合维空间对象。
应用推荐