公开(公告)号：US08692867B2

公开(公告)日：2014-04-08

申请号：US12959151

申请日：2010-12-02

申请人： Petronel Bigioi ,  Alexandru Drimbarean ,  Mihnea Gangea ,  Piotr Stec ,  Peter Corcoran

发明人： Petronel Bigioi ,  Alexandru Drimbarean ,  Mihnea Gangea ,  Piotr Stec ,  Peter Corcoran

IPC分类号： G02B21/18 ,  H04N7/00 ,  G02B21/22

CPC分类号： G02B21/22 ,  G06K9/6257 ,  G06T5/006 ,  G06T2207/30201 ,  H04N5/23219 ,  H04N5/23238

摘要： An image acquisition device having a wide field of view includes a lens and image sensor configured to capture an original wide field of view (WFoV) image with a field of view of more than 90°. The device has an object detection engine that includes one or more cascades of object classifiers, e.g., face classifiers. A WFoV correction engine may apply rectilinear and/or cylindrical projections to pixels of the WFoV image, and/or non-linear, rectilinear and/or cylindrical lens elements or lens portions serve to prevent and/or correct distortion within the original WFoV image. One or more objects located within the original and/or distortion-corrected WFoV image is/are detectable by the object detection engine upon application of the one or more cascades of object classifiers.

摘要翻译： 具有宽视野的图像采集装置包括：镜头和图像传感器，被配置为捕获具有大于90°的视场的原始宽视野（WFoV）图像。 该装置具有对象检测引擎，其包括一个或多个对象分类器级联，例如面部分类器。 WFoV校正引擎可以对WFoV图像的像素施加直线和/或圆柱形投影，和/或非线性直线和/或柱面透镜元件或透镜部分用于防止和/或校正原始WFoV图像内的失真。 位于原始和/或失真校正的WFoV图像内的一个或多个对象在应用一个或多个对象分类器级联时可由对象检测引擎检测。

公开(公告)号：US08872887B2

公开(公告)日：2014-10-28

申请号：US12959089

申请日：2010-12-02

申请人： Petronel Bigioi ,  Alexandru Drimbarean ,  Mihnea Gangea ,  Piotr Stec ,  Peter Corcoran

发明人： Petronel Bigioi ,  Alexandru Drimbarean ,  Mihnea Gangea ,  Piotr Stec ,  Peter Corcoran

IPC分类号： H04N7/00 ,  G02B21/22 ,  H04N5/232 ,  G06T5/00 ,  G06K9/62

CPC分类号： G02B21/22 ,  G06K9/6257 ,  G06T5/006 ,  G06T2207/30201 ,  H04N5/23219 ,  H04N5/23238

摘要： An image acquisition device having a wide field of view includes a lens and image sensor configured to capture an original wide field of view (WFoV) image with a field of view of more than 90°. The device has an object detection engine that includes one or more cascades of object classifiers, e.g., face classifiers. A WFoV correction engine may apply rectilinear and/or cylindrical projections to pixels of the WFoV image, and/or non-linear, rectilinear and/or cylindrical lens elements or lens portions serve to prevent and/or correct distortion within the original WFoV image. One or more objects located within the original and/or distortion-corrected WFoV image is/are detectable by the object detection engine upon application of the one or more cascades of object classifiers.

公开(公告)号：US20110216158A1

公开(公告)日：2011-09-08

申请号：US12959151

申请日：2010-12-02

申请人： Petronel Bigioi ,  Alexandru Drimbarean ,  Mihnea Gangea ,  Piotr Stec ,  Peter Corcoran

发明人： Petronel Bigioi ,  Alexandru Drimbarean ,  Mihnea Gangea ,  Piotr Stec ,  Peter Corcoran

IPC分类号： H04N5/225 ,  G06K9/00

CPC分类号： G02B21/22 ,  G06K9/6257 ,  G06T5/006 ,  G06T2207/30201 ,  H04N5/23219 ,  H04N5/23238

摘要： An image acquisition device having a wide field of view includes a lens and image sensor configured to capture an original wide field of view (WFoV) image with a field of view of more than 90°. The device has an object detection engine that includes one or more cascades of object classifiers, e.g., face classifiers. A WFoV correction engine may apply rectilinear and/or cylindrical projections to pixels of the WFoV image, and/or non-linear, rectilinear and/or cylindrical lens elements or lens portions serve to prevent and/or correct distortion within the original WFoV image. One or more objects located within the original and/or distortion-corrected WFoV image is/are detectable by the object detection engine upon application of the one or more cascades of object classifiers.

公开(公告)号：US20110216157A1

公开(公告)日：2011-09-08

申请号：US12959137

申请日：2010-12-02

申请人： Petronel Bigioi ,  Alexandru Drimbarean ,  Mihnea Gangea ,  Piotr Stec ,  Peter Corcoran

发明人： Petronel Bigioi ,  Alexandru Drimbarean ,  Mihnea Gangea ,  Piotr Stec ,  Peter Corcoran

IPC分类号： H04N5/225

CPC分类号： G02B21/22 ,  G06K9/6257 ,  G06T5/006 ,  G06T2207/30201 ,  H04N5/23219 ,  H04N5/23238

摘要： An image acquisition device having a wide field of view includes a lens and image sensor configured to capture an original wide field of view (WFoV) image with a field of view of more than 90°. The device has an object detection engine that includes one or more cascades of object classifiers, e.g., face classifiers. A WFoV correction engine may apply rectilinear and/or cylindrical projections to pixels of the WFoV image, and/or non-linear, rectilinear and/or cylindrical lens elements or lens portions serve to prevent and/or correct distortion within the original WFoV image. One or more objects located within the original and/or distortion-corrected WFoV image is/are detectable by the object detection engine upon application of the one or more cascades of object classifiers.

公开(公告)号：US20110216156A1

公开(公告)日：2011-09-08

申请号：US12959089

申请日：2010-12-02

申请人： Petronel Bigioi ,  Alexandru Drimbarean ,  Mihnea Gangea ,  Piotr Stec ,  Peter Corcoran

发明人： Petronel Bigioi ,  Alexandru Drimbarean ,  Mihnea Gangea ,  Piotr Stec ,  Peter Corcoran

IPC分类号： H04N5/225

CPC分类号： G02B21/22 ,  G06K9/6257 ,  G06T5/006 ,  G06T2207/30201 ,  H04N5/23219 ,  H04N5/23238

摘要： An image acquisition device having a wide field of view includes a lens and image sensor configured to capture an original wide field of view (WFoV) image with a field of view of more than 90°. The device has an object detection engine that includes one or more cascades of object classifiers, e.g., face classifiers. A WFoV correction engine may apply rectilinear and/or cylindrical projections to pixels of the WFoV image, and/or non-linear, rectilinear and/or cylindrical lens elements or lens portions serve to prevent and/or correct distortion within the original WFoV image. One or more objects located within the original and/or distortion-corrected WFoV image is/are detectable by the object detection engine upon application of the one or more cascades of object classifiers.

摘要翻译： 具有宽视野的图像采集装置包括：镜头和图像传感器，被配置为捕获具有大于90°的视场的原始宽视野（WFoV）图像。 该装置具有对象检测引擎，其包括一个或多个对象分类器级联，例如面部分类器。 WFoV校正引擎可以对WFoV图像的像素施加直线和/或圆柱形投影，和/或非线性直线和/或柱面透镜元件或透镜部分用于防止和/或校正原始WFoV图像内的失真。 位于原始和/或失真校正的WFoV图像内的一个或多个对象在应用一个或多个对象分类器级联时可由对象检测引擎检测。

公开(公告)号：US20120019614A1

公开(公告)日：2012-01-26

申请号：US13174716

申请日：2011-06-30

申请人： Larry Murray ,  Igor Barcovschi ,  Piotr Stec ,  James Harkin ,  Petronel Bigioi ,  George Susanu ,  Alexandru Drimbarean ,  Peter Corcoran

发明人： Larry Murray ,  Igor Barcovschi ,  Piotr Stec ,  James Harkin ,  Petronel Bigioi ,  George Susanu ,  Alexandru Drimbarean ,  Peter Corcoran

IPC分类号： H04N7/00

CPC分类号： G06T3/4038 ,  H04N13/106

摘要： A technique of generating a stereoscopic panorama image includes panning a portable camera device, and acquiring multiple image frames. Multiple at least partially overlapping image frames are acquired of portions of the scene. The method involves registering the image frames, including determining displacements of the imaging device between acquisitions of image frames. Multiple panorama images are generated including joining image frames of the scene according to spatial relationships and determining stereoscopic counterpart relationships between the multiple panorama images. The multiple panorama images are processed based on the determined stereoscopic counterpart relationships to form a stereoscopic panorama image.

摘要翻译： 产生立体全景图像的技术包括平移便携式相机装置，并获取多个图像帧。 获取场景部分的多个至少部分重叠的图像帧。 该方法包括登记图像帧，包括在获取图像帧之间确定成像装置的位移。 产生多个全景图像，包​​括根据空间关系连接场景的图像帧并确定多个全景图像之间的立体对等关系。 基于确定的立体对等物关系处理多个全景图像以形成立体全景图像。

公开(公告)号：US20120019613A1

公开(公告)日：2012-01-26

申请号：US13174687

申请日：2011-06-30

申请人： Larry Murray ,  Igor Barcovschi ,  Piotr Stec ,  James Harkin ,  Petronel Bigioi ,  George Susanu ,  Alexandru Drimbarean ,  Peter Corcoran

发明人： Larry Murray ,  Igor Barcovschi ,  Piotr Stec ,  James Harkin ,  Petronel Bigioi ,  George Susanu ,  Alexandru Drimbarean ,  Peter Corcoran

IPC分类号： H04N13/02

CPC分类号： G06T3/4038 ,  H04N13/106

摘要： A technique of generating a stereoscopic panorama image includes panning a portable camera device, and acquiring multiple image frames. Multiple at least partially overlapping image frames are acquired of portions of the scene. The method involves registering the image frames, including determining displacements of the imaging device between acquisitions of image frames. Multiple panorama images are generated including joining image frames of the scene according to spatial relationships and dynamically determining stereoscopic counterpart relationships between the multiple panorama images. The multiple panorama images are processed based on the dynamically determined stereoscopic counterpart relationships to form a stereoscopic panorama image.

摘要翻译： 产生立体全景图像的技术包括平移便携式相机装置，并获取多个图像帧。 获取场景部分的多个至少部分重叠的图像帧。 该方法包括登记图像帧，包括在获取图像帧之间确定成像装置的位移。 产生多个全景图像，包​​括根据空间关系连接场景的图像帧并动态地确定多个全景图像之间的立体对等关系。 基于动态确定的立体对等关系来处理多个全景图像以形成立体全景图像。

公开(公告)号：US20110141227A1

公开(公告)日：2011-06-16

申请号：US12879003

申请日：2010-09-09

申请人： Petronel Bigioi ,  George Susanu ,  Igor Barcovschi ,  Piotr Stec ,  Larry Murray ,  Alexandru Drimbarean ,  Peter Corcoran

发明人： Petronel Bigioi ,  George Susanu ,  Igor Barcovschi ,  Piotr Stec ,  Larry Murray ,  Alexandru Drimbarean ,  Peter Corcoran

IPC分类号： H04N13/02

CPC分类号： G06T7/593 ,  G06T2200/32 ,  G06T2207/10016 ,  H04N13/106

摘要： A technique of generating a stereoscopic panorama image includes panning a portable camera device, and acquiring multiple image frames. Multiple at least partially overlapping image frames are acquired of portions of the scene. The method involves registering the image frames, including determining displacements of the imaging device between acquisitions of image frames. Multiple panorama images are generated including joining image frames of the scene according to spatial relationships and determining stereoscopic counterpart relationships between the multiple panorama images. The multiple panorama images are processed based on the stereoscopic counterpart relationships to form a stereoscopic panorama image.

摘要翻译： 产生立体全景图像的技术包括平移便携式相机装置，并获取多个图像帧。 获取场景部分的多个至少部分重叠的图像帧。 该方法包括登记图像帧，包括在获取图像帧之间确定成像装置的位移。 产生多个全景图像，包​​括根据空间关系连接场景的图像帧并确定多个全景图像之间的立体对等关系。 基于立体对等物关系来处理多个全景图像以形成立体全景图像。

公开(公告)号：US10080006B2

公开(公告)日：2018-09-18

申请号：US12879003

申请日：2010-09-09

申请人： Petronel Bigioi ,  George Susanu ,  Igor Barcovschi ,  Piotr Stec ,  Larry Murray ,  Alexandru Drimbarean ,  Peter Corcoran

发明人： Petronel Bigioi ,  George Susanu ,  Igor Barcovschi ,  Piotr Stec ,  Larry Murray ,  Alexandru Drimbarean ,  Peter Corcoran

IPC分类号： H04N13/02 ,  H04N13/00 ,  G06T7/593

CPC分类号： H04N13/106 ,  G06T7/593 ,  G06T2200/32 ,  G06T2207/10016

摘要： A technique of generating a stereoscopic panorama image includes panning a portable camera device, and acquiring multiple image frames. Multiple at least partially overlapping image frames are acquired of portions of the scene. The method involves registering the image frames, including determining displacements of the imaging device between acquisitions of image frames. Multiple panorama images are generated including joining image frames of the scene according to spatial relationships and determining stereoscopic counterpart relationships between the multiple panorama images. The multiple panorama images are processed based on the stereoscopic counterpart relationships to form a stereoscopic panorama image.

公开(公告)号：US08860816B2

公开(公告)日：2014-10-14

申请号：US13077891

申请日：2011-03-31

申请人： Peter Corcoran ,  Petronel Bigioi ,  Piotr Stec

发明人： Peter Corcoran ,  Petronel Bigioi ,  Piotr Stec

IPC分类号： H04N5/225 ,  H04N13/04

CPC分类号： G06T3/0018 ,  H04N5/217 ,  H04N5/23238

摘要： A technique of enhancing a scene containing one or more off-center peripheral regions within an initial distorted image captured with a large field of view includes determining and extracting an off-center region of interest (hereinafter “ROI”) within the image. Geometric correction is applied to reconstruct the off-center ROI into a rectangular or otherwise undistorted or less distorted frame of reference as a reconstructed ROI. A quality of reconstructed pixels is determined within the constructed ROI. Image analysis is selectively applied to the reconstructed ROI based on the quality of the reconstructed pixels.

摘要翻译： 增强在大视野捕获的初始失真图像内包含一个或多个偏心中心外围区域的场景的技术包括确定并提取图像内的偏心偏离区域（以下称为“ROI”）。 应用几何校正来将偏心ROI重建为矩形或其他未失真或较不失真的参考系作为重建的ROI。 在构建的ROI内确定重构像素的质量。 基于重构像素的质量，将图像分析选择性地应用于重建的ROI。