-
公开(公告)号:US08199222B2
公开(公告)日:2012-06-12
申请号:US12485316
申请日:2009-06-16
申请人: Alexandru Drimbarean , Adrian Zamfir , Felix Albu , Vlad Poenaru , Corneliu Florea , Petronel Bigioi , Eran Steinberg , Peter Corcoran
发明人: Alexandru Drimbarean , Adrian Zamfir , Felix Albu , Vlad Poenaru , Corneliu Florea , Petronel Bigioi , Eran Steinberg , Peter Corcoran
IPC分类号: H04N5/225
CPC分类号: H04N5/2355 , G06T5/009 , G06T5/50 , G06T2207/10016 , G06T2207/10024 , G06T2207/10144 , H04N5/235 , H04N9/045
摘要: A method of combining image data from multiple frames to enhance one or more parameters of video image quality includes acquiring a first image at a first exposure duration, as well as acquiring a second image at a second exposure duration shorter than the first exposure duration and at a time just before, just after or overlapping in time with acquiring the first image, such that the first and second images include approximately a same first scene. In this way, the second image is relatively sharp and under-exposed, while the first image is relatively well-exposed and less sharp than the second image. Brightness and/or color information are extracted from the first image and applied to the second image to generate an enhanced version of the second image.
摘要翻译: 一种组合来自多个帧的图像数据以增强视频图像质量的一个或多个参数的方法包括以第一曝光持续时间获取第一图像,以及以比第一曝光持续时间短的第二曝光持续时间获取第二图像,并且 在获取第一图像之前,恰好在或之后重叠的时间,使得第一和第二图像包括大致相同的第一场景。 以这种方式,第二图像相对较锋利且曝光不足,而第一图像相对曝光较好,并且不如第二图像那样锐利。 从第一图像提取亮度和/或颜色信息并将其应用于第二图像以生成第二图像的增强版本。
-
公开(公告)号:US20090303343A1
公开(公告)日:2009-12-10
申请号:US12485316
申请日:2009-06-16
申请人: Alexandru Drimbarean , Petronel Bigioi , Peter Corcoran , Eran Steinberg , Adrian Zamfir , Felix Albu , Vlad Poenaru , Corneliu Florea
发明人: Alexandru Drimbarean , Petronel Bigioi , Peter Corcoran , Eran Steinberg , Adrian Zamfir , Felix Albu , Vlad Poenaru , Corneliu Florea
CPC分类号: H04N5/2355 , G06T5/009 , G06T5/50 , G06T2207/10016 , G06T2207/10024 , G06T2207/10144 , H04N5/235 , H04N9/045
摘要: A method of combining image data from multiple frames to enhance one or more parameters of video image quality includes acquiring a first image at a first exposure duration, as well as acquiring a second image at a second exposure duration shorter than the first exposure duration and at a time just before, just after or overlapping in time with acquiring the first image, such that the first and second images include approximately a same first scene. In this way, the second image is relatively sharp and under-exposed, while the first image is relatively well-exposed and less sharp than the second image. Brightness and/or color information are extracted from the first image and applied to the second image to generate an enhanced version of the second image.
摘要翻译: 一种组合来自多个帧的图像数据以增强视频图像质量的一个或多个参数的方法包括以第一曝光持续时间获取第一图像,以及以比第一曝光持续时间短的第二曝光持续时间获取第二图像,并且 在获取第一图像之前,恰好在或之后重叠的时间,使得第一和第二图像包括大致相同的第一场景。 以这种方式,第二图像相对较锋利且曝光不足,而第一图像相对曝光较好,并且不如第二图像那样锐利。 从第一图像提取亮度和/或颜色信息并将其应用于第二图像以生成第二图像的增强版本。
-
公开(公告)号:US20110205381A1
公开(公告)日:2011-08-25
申请号:US12941983
申请日:2010-11-08
申请人: Ruxandra Vranceanu , Alexandru Drimbarean , Adrian Zamfir , Felix Albu , Vlad Poenaru , Corneliu Florea , Petronel Bigioi , Eran Steinberg , Peter Corcoran
发明人: Ruxandra Vranceanu , Alexandru Drimbarean , Adrian Zamfir , Felix Albu , Vlad Poenaru , Corneliu Florea , Petronel Bigioi , Eran Steinberg , Peter Corcoran
IPC分类号: H04N5/225
CPC分类号: H04N9/646 , G06T5/003 , G06T5/009 , G06T5/40 , G06T5/50 , G06T2207/10016 , G06T2207/10024 , G06T2207/10144 , G06T2207/20008 , H04N5/235 , H04N5/2355 , H04N9/045 , H04N9/68
摘要: A technique is provided for generating sharp, well-exposed, color images from low-light images. A series of under-exposed images is acquired. A mean image is computed and a sum image is generated each based on the series of under-exposed images. Chrominance variables of pixels of the mean image are mapped to chrominance variables of pixels of the sum image. Chrominance values of pixels within the series of under-exposed images are replaced with chrominance values of the sum image. A set of sharp, well-exposed, color images is generated based on the series of under-exposed images with replaced chrominance values.
摘要翻译: 提供了一种用于从低光图像产生锐利,曝光良好的彩色图像的技术。 获得一系列曝光不足的图像。 计算平均图像,并且基于一系列曝光不足的图像来生成和图像。 平均图像的像素的色度变量被映射到和图像的像素的色度变量。 未曝光图像系列中的像素的色度值被和图像的色度值代替。 基于具有替换的色度值的一系列曝光不足的图像产生一组锐利,良好曝光的彩色图像。
-
公开(公告)号:US08698924B2
公开(公告)日:2014-04-15
申请号:US12941983
申请日:2010-11-08
申请人: Alexandru Drimbarean , Adrian Zamfir , Felix Albu , Vlad Poenaru , Corneliu Florea , Petronel Bigioi , Eran Steinberg , Peter Corcoran
发明人: Alexandru Drimbarean , Adrian Zamfir , Felix Albu , Vlad Poenaru , Corneliu Florea , Petronel Bigioi , Eran Steinberg , Peter Corcoran
IPC分类号: H04N9/64
CPC分类号: H04N9/646 , G06T5/003 , G06T5/009 , G06T5/40 , G06T5/50 , G06T2207/10016 , G06T2207/10024 , G06T2207/10144 , G06T2207/20008 , H04N5/235 , H04N5/2355 , H04N9/045 , H04N9/68
摘要: A technique is provided for generating sharp, well-exposed, color images from low-light images. A series of under-exposed images is acquired. A mean image is computed and a sum image is generated each based on the series of under-exposed images. Chrominance variables of pixels of the mean image are mapped to chrominance variables of pixels of the sum image. Chrominance values of pixels within the series of under-exposed images are replaced with chrominance values of the sum image. A set of sharp, well-exposed, color images is generated based on the series of under-exposed images with replaced chrominance values.
摘要翻译: 提供了一种用于从低光图像产生锐利,曝光良好的彩色图像的技术。 获得一系列曝光不足的图像。 计算平均图像,并且基于一系列曝光不足的图像来生成和图像。 平均图像的像素的色度变量被映射到和图像的像素的色度变量。 未曝光图像系列中的像素的色度值被和图像的色度值代替。 基于具有替换的色度值的一系列曝光不足的图像产生一组锐利,良好曝光的彩色图像。
-
公开(公告)号:US20110115928A1
公开(公告)日:2011-05-19
申请号:US12907921
申请日:2010-10-19
申请人: Peter Corcoran , Eran Steinberg , Petronel Bigioi , Alexandru Drimbarean , Adrian Zamfir , Corneliu Florea
发明人: Peter Corcoran , Eran Steinberg , Petronel Bigioi , Alexandru Drimbarean , Adrian Zamfir , Corneliu Florea
IPC分类号: H04N5/228
CPC分类号: H04N5/23251 , H04N5/23248 , H04N5/23258 , H04N5/23277
摘要: An image acquisition sensor of a digital image acquisition apparatus is coupled to imaging optics for acquiring a sequence of images. Images acquired by the sensor are stored. A motion detector causes the sensor to cease capture of an image when the degree of movement in acquiring the image exceeds a threshold. A controller selectively transfers acquired images for storage. A motion extractor determines motion parameters of a selected, stored image. An image re-constructor corrects the selected image with associated motion parameters. A selected plurality of images nominally of the same scene are merged and corrected by the image re-constructor to produce a high quality image of the scene.
摘要翻译: 数字图像获取装置的图像采集传感器耦合到成像光学器件,用于获取图像序列。 存储由传感器获取的图像。 当获取图像的移动程度超过阈值时,运动检测器使得传感器停止图像的捕获。 控制器选择性地传送获取的图像以进行存储。 运动提取器确定所选存储的图像的运动参数。 图像重建器使用关联的运动参数校正所选择的图像。 通过图像重构器合并和校正所选择的多个相同场景的图像,以产生高质量的场景图像。
-
公开(公告)号:US08520082B2
公开(公告)日:2013-08-27
申请号:US12907921
申请日:2010-10-19
申请人: Peter Corcoran , Eran Steinberg , Petronel Bigioi , Alexandru Drimbarean , Adrian Zamfir , Corneliu Florea
发明人: Peter Corcoran , Eran Steinberg , Petronel Bigioi , Alexandru Drimbarean , Adrian Zamfir , Corneliu Florea
IPC分类号: H04N5/228
CPC分类号: H04N5/23251 , H04N5/23248 , H04N5/23258 , H04N5/23277
摘要: An image acquisition sensor of a digital image acquisition apparatus is coupled to imaging optics for acquiring a sequence of images. Images acquired by the sensor are stored. A motion detector causes the sensor to cease capture of an image when the degree of movement in acquiring the image exceeds a threshold. A controller selectively transfers acquired images for storage. A motion extractor determines motion parameters of a selected, stored image. An image re-constructor corrects the selected image with associated motion parameters. A selected plurality of images nominally of the same scene are merged and corrected by the image re-constructor to produce a high quality image of the scene.
摘要翻译: 数字图像获取装置的图像采集传感器耦合到成像光学器件,用于获取图像序列。 存储由传感器获取的图像。 当获取图像的移动程度超过阈值时,运动检测器使得传感器停止图像的捕获。 控制器选择性地传送获取的图像以进行存储。 运动提取器确定所选存储的图像的运动参数。 图像重建器使用关联的运动参数校正所选择的图像。 通过图像重构器合并和校正所选择的多个相同场景的图像,以产生高质量的场景图像。
-
公开(公告)号:US08169486B2
公开(公告)日:2012-05-01
申请号:US11753098
申请日:2007-05-24
申请人: Peter Corcoran , Eran Steinberg , Petronel Bigioi , Alexandru Drimbarean , Adrian Zamfir , Corneliu Florea
发明人: Peter Corcoran , Eran Steinberg , Petronel Bigioi , Alexandru Drimbarean , Adrian Zamfir , Corneliu Florea
IPC分类号: H04N5/228
CPC分类号: H04N5/23251 , H04N5/23248 , H04N5/23258 , H04N5/23277
摘要: An image acquisition sensor of a digital image acquisition apparatus is coupled to imaging optics for acquiring a sequence of images. Images acquired by the sensor are stored. A motion detector causes the sensor to cease capture of an image when the degree of movement in acquiring the image exceeds a threshold. A controller selectively transfers acquired images for storage. A motion extractor determines motion parameters of a selected, stored image. An image re-constructor corrects the selected image with associated motion parameters. A selected plurality of images nominally of the same scene are merged and corrected by the image re-constructor to produce a high quality image of the scene.
摘要翻译: 数字图像获取装置的图像采集传感器耦合到成像光学器件,用于获取图像序列。 存储由传感器获取的图像。 当获取图像的移动程度超过阈值时,运动检测器使得传感器停止图像的捕获。 控制器选择性地传送获取的图像以进行存储。 运动提取器确定所选存储的图像的运动参数。 图像重建器使用关联的运动参数校正所选择的图像。 通过图像重构器合并和校正所选择的多个相同场景的图像,以产生高质量的场景图像。
-
公开(公告)号:US20070296833A1
公开(公告)日:2007-12-27
申请号:US11753098
申请日:2007-05-24
申请人: Peter Corcoran , Eran Steinberg , Petronel Bigioi , Alexandru Drimbarean , Adrian Zamfir , Corneliu Florea
发明人: Peter Corcoran , Eran Steinberg , Petronel Bigioi , Alexandru Drimbarean , Adrian Zamfir , Corneliu Florea
CPC分类号: H04N5/23251 , H04N5/23248 , H04N5/23258 , H04N5/23277
摘要: An image acquisition sensor of a digital image acquisition apparatus is coupled to imaging optics for acquiring a sequence of images. Images acquired by the sensor are stored. A motion detector causes the sensor to cease capture of an image when the degree of movement in acquiring the image exceeds a threshold. A controller selectively transfers acquired images for storage. A motion extractor determines motion parameters of a selected, stored image. An image re-constructor corrects the selected image with associated motion parameters. A selected plurality of images nominally of the same scene are merged and corrected by the image re-constructor to produce a high quality image of the scene.
摘要翻译: 数字图像获取装置的图像采集传感器耦合到成像光学器件,用于获取图像序列。 存储由传感器获取的图像。 当获取图像的移动程度超过阈值时,运动检测器使得传感器停止图像的捕获。 控制器选择性地传送获取的图像以进行存储。 运动提取器确定所选存储的图像的运动参数。 图像重建器使用关联的运动参数校正所选择的图像。 通过图像重构器合并和校正所选择的多个相同场景的图像,以产生高质量的场景图像。
-
公开(公告)号:US20130010138A1
公开(公告)日:2013-01-10
申请号:US13442721
申请日:2012-04-09
申请人: Petronel Bigioi , Alexei Pososin , Mihnea Gangea , Stefan Petrescu , Peter Corcoran , Alexandru Drimbarean , Adrian Zamfir , Corneliu Florea
发明人: Petronel Bigioi , Alexei Pososin , Mihnea Gangea , Stefan Petrescu , Peter Corcoran , Alexandru Drimbarean , Adrian Zamfir , Corneliu Florea
CPC分类号: G06K9/00261 , G06K9/6257 , H04N5/23219
摘要: A method operable in a digital image acquisition system having no photographic film is provided. The method comprises receiving a relatively low resolution image of a scene from an image stream, wherein the scene potentially includes one or more faces. At least one high quality face classifier is applied to the image to identify relatively large and medium sized face regions and at least one relaxed face classifier is applied to the image to identify relatively small sized face regions. A relatively high resolution image of nominally the same scene is received and at least one high quality face classifier is applied to the identified small sized face regions in the higher resolution version of said image.
摘要翻译: 提供了一种在没有摄影胶片的数字图像采集系统中可操作的方法。 该方法包括从图像流接收场景的相对较低分辨率的图像,其中该场景潜在地包括一个或多个面。 至少一个高质量的脸部分类器被应用于图像以识别相对大的和中等大小的脸部区域,并且至少一个放松的面部分类器被应用于图像以识别相对小的脸部区域。 接收名义上相同的场景的相对高分辨率的图像,并且至少一个高质量的面部分类器应用于所述图像的较高分辨率版本中的所识别的小尺寸的脸部区域。
-
公开(公告)号:US08254674B2
公开(公告)日:2012-08-28
申请号:US12551258
申请日:2009-08-31
申请人: Florin Nanu , Stefan Petrescu , Mihnea Gangea , Adrian Capata , Mihai Ciuc , Adrian Zamfir , Eran Steinberg , Peter Corcoran , Alexei Pososin , Petronel Bigioi , Alexandru Drimbarean
发明人: Florin Nanu , Stefan Petrescu , Mihnea Gangea , Adrian Capata , Mihai Ciuc , Adrian Zamfir , Eran Steinberg , Peter Corcoran , Alexei Pososin , Petronel Bigioi , Alexandru Drimbarean
IPC分类号: G06K9/00
CPC分类号: H04N5/2256 , G06T5/005 , G06T5/008 , G06T7/11 , G06T7/136 , G06T7/90 , G06T2207/10024 , G06T2207/30216 , H04N1/624 , H04N5/23219
摘要: A method for red-eye detection in an acquired digital image includes acquiring a first image, and analyzing one or more partial face regions within the first image. One or more characteristics of the first image are determined. One or more corrective processes are identified including red eye correction that can be beneficially applied to the first image according to the one or more characteristics. The one or more corrective processes are applied to the first image.
-
-
-
-
-
-
-
-
-