首页>
外国专利>
Detection of objects in images under equivariance or invariance with respect to the object size
Detection of objects in images under equivariance or invariance with respect to the object size
展开▼
机译:在对象大小上检测标准规范或不变性下的图像中的对象
展开▼
页面导航
摘要
著录项
相似文献
摘要
Method (100) for detecting at least one object (2a-2c) in at least one input image (3) with the steps: • a template image (1) of the object (2a-2c) is processed by a first convolutional neural network, CNN (4a), processed (110) into at least one template feature map (5, 5a-5c); • the input image (3) is processed into at least one input feature map by a second convolutional neural network, CNN (4b). (6, 6a-6c) processed (120);• the at least one template feature map (5, 5a-5c) is compared (130) with the at least one input feature map (6, 6a-6c);• from the result (130a) of the comparison (130) it is evaluated (140) whether, and if so at which position (2a'-2c'), the object (2a-2c) is contained in the input image (3), the convolutional neural Networks (4a, 4b) each contain a plurality of convolution layers (7a, 7b) and wherein at least one of the convolution layers (7a, 7b) is at least partially formed from at least two filters (8a-8c) which can be converted into one another by a scaling operation.
展开▼