首页>
外国专利>
PYRAMID HISTORY MAP GENERATING METHOD FOR CALCULATING FEATURE MAP IN DEEP LEARNING BASED ON CONVOLUTION NEURAL NETWORK AND FEATURE MAP GENERATING METHOD
PYRAMID HISTORY MAP GENERATING METHOD FOR CALCULATING FEATURE MAP IN DEEP LEARNING BASED ON CONVOLUTION NEURAL NETWORK AND FEATURE MAP GENERATING METHOD
展开▼
机译:基于卷积神经网络和特征图生成方法的深度学习中特征图计算的金字塔历史图生成方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
A method of generating a pyramid history map (B) for a feature map (A) includes a step of determining a reference value corresponding to each convolution value based on whether a pixel value of a first frame is identical to a pixel value of a second frame included in a window area corresponding to each convolution value of the feature map (A), and generating a first layer including a plurality of reference values; a step of dividing the first layer into a plurality of blocks, determining a block value corresponding to each block based on a reference value in each of the divided blocks, and generating a second layer including a plurality of block values; and a step of generating a third layer based on the plurality of block values of the second layer. The feature map for a previous frame can be recycled in a current frame.
展开▼