公开(公告)号：US20250005907A1

公开(公告)日：2025-01-02

申请号：US18734165

申请日：2024-06-05

Applicant: Axis AB

Inventor： Niclas DANIELSSON ,  Amanda NILSSON ,  Christian COLLIANDER ,  Sarah LAROSS

IPC: G06V10/77 ,  G06T3/4038 ,  G06V10/82

Abstract: A method for feature extraction of detected objects, comprising the steps of: receiving a plurality of images, each depicting an object detected by the object detecting application; concatenating the plurality of images into a composite image according to a grid pattern; feeding the composite image through a convolutional neural network (CNN) trained for feature extraction, wherein each convolutional layer of the CNN is configured to, while convolving input data to the convolutional layer using a convolutional filter: determine a currently convolved image of the plurality of images by determining a centre coordinate of a subset of the input data currently covered by the convolutional filter, and mapping the centre coordinate to the grid pattern; and selectively nullifying all weights of the convolutional filter that cover input data derived from any of the plurality of images not being the currently convolved image.