首页> 外国专利> Using neural networks for object detection in scenes with widespread light intensity

Using neural networks for object detection in scenes with widespread light intensity

机译:利用神经网络在具有广泛光强度的场景中进行对象检测

摘要

Problem to be solved: to provide a method of detecting an object in a high dynamic range image, a system and a non temporary computer readable storage medium.The method is a step 102 for inspecting a set of images including a long exposure image and a short exposure image of a scene recorded by the camera and training to perform one or more of the object detection, object classification and object recognition in the image data A step 104 for processing an image set by a predefined neural network.Long exposure images and short exposure images are recorded by a camera at a very close or overlapping time.The neural network uses image data from both the long exposure image and the short exposure image to detect an object in the set of images.Diagram
机译:要解决的问题:提供一种在高动态范围图像中检测对象的方法,系统和非临时计算机可读存储介质。该方法是用于检查一组图像的步骤102,包括长曝光图像和a 摄像机和训练记录的场景的短曝光图像,以在图像数据中执行一个或多个对象检测,对象分类和对象识别,步骤104,用于处理由预定义的神经网络设置的图像.Long曝光图像和短 曝光图像在非常接近或重叠的时间内被相机记录。神经网络使用来自长曝光图像和短曝光图像的图像数据来检测该组图像中的对象.diagram

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