首页> 外国专利> DEVICE OF CASCADE PROCESSING OF A STREAM OF IMAGES BY MEANS OF CONVOLUTIONAL NEURAL NETWORK

DEVICE OF CASCADE PROCESSING OF A STREAM OF IMAGES BY MEANS OF CONVOLUTIONAL NEURAL NETWORK

机译:卷积神经网络级联图像的级联处理装置

摘要

FIELD: image processing means.;SUBSTANCE: group of inventions relates to the field of automatic image analysis. Device of cascade processing of a stream of images by means of convolutional neural network is offered. Device comprises a motion detection unit connected to a neural network filtering unit that contains generalized feature determination blocks and a decision block, wherein the motion detection unit is connected in parallel with the inputs of the generalized feature determination units whose outputs are connected to the first input of the decision block, second input of which is connected to the output of the motion detection unit. Motion detection unit is configured to receive an image stream at the input, with the possibility of determining the position of image fragments with moving objects on consecutive frames and transfer of information about the position of fragments of images with moving objects to the blocks of definition of generalized features.;EFFECT: technical result is an increase in the reliability of automatic detection of moving objects in the field of view of the video camera due to a combination of a fast method for determining moving objects and a method of neural network processing.;10 cl, 2 dwg
机译:技术领域:组发明涉及自动图像分析领域。提供了借助卷积神经网络对图像流进行级联处理的设备。该装置包括运动检测单元,该运动检测单元连接到神经网络过滤单元,该神经网络过滤单元包含广义特征确定块和决策块,其中,运动检测单元与广义特征确定单元的输入并联,该广义特征确定单元的输出连接到第一输入判决块的第二输入连接到运动检测单元的输出。运动检测单元被配置为在输入端接收图像流,从而可以确定连续帧上具有运动对象的图像片段的位置,并将关于具有运动对象的图像片段的位置的信息传输到图像的定义块。效果:技术结果是通过将确定运动物体的快速方法与神经网络处理方法相结合,提高了摄像机视场中运动物体自动检测的可靠性。 10厘升,2载重吨

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号