公开(公告)号：US08233789B2

公开(公告)日：2012-07-31

申请号：US12755542

申请日：2010-04-07

申请人： Ralph Brunner

发明人： Ralph Brunner

IPC分类号： G03B7/00 ,  G03B3/10 ,  G03B13/34 ,  H04N2/235

CPC分类号： H04N5/23219 ,  H04N5/23216 ,  H04N5/2351

摘要： A system, computer readable medium, and method for dynamically setting a camera's exposure parameters based on face detection are disclosed. When taking a picture or video of a person in front of a bright background, standard exposure algorithms tend to overexpose the background. In one embodiment disclosed herein, a face detection algorithm is run on the current picture or video frame, and the exposure metering region is inset over the detected face. Exposure time, gain, or other exposure parameters may be set based on the pixels within the exposure metering region. In another embodiment, the exposure metering region tracks a moving face according to lag parameters so that the exposure metering region remains substantially over the face. In yet another embodiment, a plurality of faces may be tracked, with the exposure parameters set based on a weighted average of the pixels within the plurality of face-containing exposure metering regions.

摘要翻译： 公开了一种用于基于人脸检测来动态地设置相机的曝光参数的系统，计算机可读介质和方法。 当在明亮的背景前拍摄人物的图片或视频时，标准曝光算法往往会过度曝光背景。 在本文公开的一个实施例中，在当前图片或视频帧上运行面部检测算法，并且将曝光测光区域插入检测到的面部。 可以基于曝光测光区域内的像素来设定曝光时间，增益或其他曝光参数。 在另一个实施例中，曝光测光区域根据滞后参数跟踪移动面，使得曝光测光区域基本上保持在面部上。 在另一个实施例中，可以跟踪多个面部，其中曝光参数是基于多个面部含有曝光测光区域内的像素的加权平均值而设定的。

公开(公告)号：US08305468B2

公开(公告)日：2012-11-06

申请号：US12710421

申请日：2010-02-23

申请人： Masao Sambongi

发明人： Masao Sambongi

IPC分类号： H04N5/217 ,  H04N5/235 ,  H04N9/083 ,  H04N5/222 ,  H04N2/235

CPC分类号： H04N5/217 ,  G06T5/002 ,  G06T5/50 ,  G06T2207/10016 ,  G06T2207/10152 ,  G06T2207/20208 ,  H04N1/3871 ,  H04N1/407 ,  H04N5/2353 ,  H04N5/2355 ,  H04N5/2356 ,  H04N5/243

摘要： A plurality of preliminary image signals is acquired by carrying out preliminary image acquisition of a subject, before actual image acquisition, with different amounts of light received by an image acquisition device. Subsequently, a dynamic range and an amount of noise, or an S/N ratio, for a case in which the plurality of preliminary image signals is combined is calculated, and a received-light-level difference of the image acquisition device among a plurality of actual image signals acquired through the actual image acquisition is calculated on the basis of the dynamic range and the amount of noise, or the S/N ratio. Then, by carrying out the actual image acquisition on the basis of the calculated received-light-level difference, a plurality of actual image signals with different received light level is acquired. These actual image signals are combined to acquire a combined image.

摘要翻译： 通过在图像获取装置接收到的不同光量之前，在实际图像获取之前对被摄体进行初步图像采集来获取多个初步图像信号。 随后，计算多个预备图像信号组合的情况下的动态范围和噪声量或S / N比，以及多个图像获取装置的接收光电平差 基于动态范围和噪声量或S / N比计算通过实际图像获取获取的实际图像信号。 然后，通过基于计算出的接收光水平差进行实际图像采集，获得具有不同接收光电平的多个实际图像信号。 这些实际图像信号被组合以获得组合图像。