-
公开(公告)号:US20090112287A1
公开(公告)日:2009-04-30
申请号:US12043830
申请日:2008-03-06
申请人: Robert J. Greenberg , Alan Matthew Horsager , Mark S. Humayun , Kelly H. McClure , Matthew J. McMahon , Peter Meilstrup , Neha Jagdish Parikh , Arup Roy , James D. Weiland , Chunhong Zhou
发明人: Robert J. Greenberg , Alan Matthew Horsager , Mark S. Humayun , Kelly H. McClure , Matthew J. McMahon , Peter Meilstrup , Neha Jagdish Parikh , Arup Roy , James D. Weiland , Chunhong Zhou
IPC分类号: A61F9/08
CPC分类号: A61N1/36046 , A61F9/08 , G06K9/4604 , G06K9/4628 , G06K9/605 , G09B21/008
摘要: Saliency-based apparatus and methods for visual prostheses are disclosed. A saliency-based component processes video data output by a digital signal processor before the video data are input to the retinal stimulator. In a saliency-based method, an intensity stream is extracted from an input image, feature maps based on the intensity stream are developed, plural most salient regions of the input image are detected and one of the regions is selected as a highest saliency region.
摘要翻译: 公开了用于视觉假体的基于显着性的装置和方法。 基于显眼的组件在将视频数据输入到视网膜刺激器之前处理由数字信号处理器输出的视频数据。 在基于显着性的方法中,从输入图像中提取强度流,基于强度流形成特征图,检测输入图像的多个最显着区域,并选择其中一个区域作为最高显着区域。
-
公开(公告)号:US09061150B2
公开(公告)日:2015-06-23
申请号:US12043830
申请日:2008-03-06
申请人: Robert J. Greenberg , Alan Matthew Horsager , Mark S. Humayun , Kelly H. McClure , Matthew J. McMahon , Peter Meilstrup , Neha Jagdish Parikh , Arup Roy , James D. Weiland , Chunhong Zhou
发明人: Robert J. Greenberg , Alan Matthew Horsager , Mark S. Humayun , Kelly H. McClure , Matthew J. McMahon , Peter Meilstrup , Neha Jagdish Parikh , Arup Roy , James D. Weiland , Chunhong Zhou
CPC分类号: A61N1/36046 , A61F9/08 , G06K9/4604 , G06K9/4628 , G06K9/605 , G09B21/008
摘要: The present invention is a saliency-based apparatus and methods for visual prostheses. A saliency-based component processes video data output by a digital signal processor before the video data are input to the retinal stimulator. In a saliency-based method, an intensity stream is extracted from an input image, feature maps based on the intensity stream are developed, plural most salient regions of the input image are detected and one of the regions is selected as a highest saliency region.
摘要翻译: 本发明是用于视觉假体的基于显眼的装置和方法。 基于显眼的组件在将视频数据输入到视网膜刺激器之前处理由数字信号处理器输出的视频数据。 在基于显着性的方法中,从输入图像中提取强度流,基于强度流形成特征图,检测输入图像的多个最显着区域,并选择其中一个区域作为最高显着区域。
-