-
公开(公告)号：US09704227B2
公开(公告)日：2017-07-11
申请号：US14784281
申请日：2014-07-28
Applicant: Nokia Technologies Oy
Inventor： Jiangwei Li , He Yan , Kongqiao Wang
CPC classification number: G06T5/20 , G06K9/00624 , G06K9/40 , G06T5/002 , G06T5/004 , G06T5/50 , G06T2207/20224
Abstract: Embodiments of the present invention relate to a method and apparatus for image enhancement. In particular, there is provided a method for image enhancement, the method comprising: estimating unsharpness of the image (S201-S204); determining a protection level of at least one pixel in the image based on the unsharpness (S205); and modifying a value of the at least one pixel to enhance the image, an amount of the modifying being determined at least in part based on the protection level (S206-S210). A corresponding apparatus and user device are disclosed. The invention may be applied to fog or haze removal from images or video without producing over-removal artifacts. In some embodiments, the invention may also be used to remove noise from low-light images.
-
Patent Agency Ranking
公开(公告)号：US20170208234A1
公开(公告)日：2017-07-20
申请号：US15326630
申请日：2015-07-03
Applicant: Nokia Technologies Oy
Inventor： Kongqiao Wang , Jiangwei Li , He Yan
CPC classification number: H04N5/2352 , G06K9/4661 , G06T7/13 , G06T7/49 , H04N5/2258 , H04N5/23232 , H04N5/2351 , H04N5/2355
Abstract: Embodiments of the present invention relate to a method and apparatus for detecting an imaging condition. In one embodiment, there is provided a method for detecting an imaging condition. The method comprises: determining, based on luminance distribution in a first image of a scene, imaging lightness of the first image, the first image being captured by a first camera; determining, based on detection of a highlighted region in a second image of the scene, imaging exposureness of the second image, the second image being captured by a second camera, the first image and the second image being captured under a same or similar imaging condition, an exposure amount of the first camera being lower than an exposure amount of the second camera. There is also disclosed a relevant apparatus, electronic device, and a computer program product.
-
公开(公告)号：US20150348276A1
公开(公告)日：2015-12-03
申请号：US14720074
申请日：2015-05-22
Applicant: Nokia Technologies Oy
Inventor： Kong Qiao Wang , Jiangwei Li , He Yan
CPC classification number: G06T7/0087 , G06K9/38 , G06K9/42 , G06K9/6218 , G06T7/11 , G06T7/136 , G06T7/143 , G06T7/174 , G06T7/187 , G06T7/194 , G06T11/60 , G06T2207/10016 , G06T2207/20076 , H04N5/145 , H04N5/272
Abstract: The present invention provides a method and apparatus for processing a video frame in a video file, the method comprising: for each predetermined numerical value of one or more predetermined numerical values, comparing the video frame with a video frame spaced prior to the video frame by the predetermined numerical value of frames to obtain a first inter-frame difference; comparing the video frame with a video frame spaced after the video frame by the predetermined numerical value of frames to obtain a second inter-frame difference; and for each pixel of the video frame, obtaining a confidence map associating the video frame by the predetermined numerical value based on a smaller value of the first inter-frame difference and the second inter-frame difference; and determining, at least based on a value of each pixel in one or more of the confidence maps associated with a corresponding predetermined numerical value, whether the pixel belongs to a foreground.
Abstract translation: 本发明提供了一种用于处理视频文件中的视频帧的方法和装置，该方法包括：对于一个或多个预定数值的每个预定数值，将视频帧与在视频帧之前间隔开的视频帧进行比较， 帧的预定数值以获得第一帧间差; 将所述视频帧与在所述视频帧之间间隔的视频帧进行比例以预定的数值，以获得第二帧间差; 并且对于所述视频帧的每个像素，获得基于所述第一帧间差和所述第二帧间差的较小值将所述视频帧与所述预定数值相关联的置信图; 以及至少基于与相应的预定数值相关联的一个或多个置信图中的每个像素的值，确定所述像素是否属于前景。
-
公开(公告)号：US09514540B2
公开(公告)日：2016-12-06
申请号：US14720074
申请日：2015-05-22
Applicant: Nokia Technologies Oy
Inventor： Kong Qiao Wang , Jiangwei Li , He Yan
CPC classification number: G06T7/0087 , G06K9/38 , G06K9/42 , G06K9/6218 , G06T7/11 , G06T7/136 , G06T7/143 , G06T7/174 , G06T7/187 , G06T7/194 , G06T11/60 , G06T2207/10016 , G06T2207/20076 , H04N5/145 , H04N5/272
Abstract: The present invention provides a method and apparatus for processing a video frame in a video file, the method comprising: for each predetermined numerical value of one or more predetermined numerical values, comparing the video frame with a video frame spaced prior to the video frame by the predetermined numerical value of frames to obtain a first inter-frame difference; comparing the video frame with a video frame spaced after the video frame by the predetermined numerical value of frames to obtain a second inter-frame difference; and for each pixel of the video frame, obtaining a confidence map associating the video frame by the predetermined numerical value based on a smaller value of the first inter-frame difference and the second inter-frame difference; and determining, at least based on a value of each pixel in one or more of the confidence maps associated with a corresponding predetermined numerical value, whether the pixel belongs to a foreground.
Abstract translation: 本发明提供了一种用于处理视频文件中的视频帧的方法和装置，该方法包括：对于一个或多个预定数值的每个预定数值，将视频帧与在视频帧之前间隔开的视频帧进行比较， 帧的预定数值以获得第一帧间差; 将所述视频帧与在所述视频帧之间间隔的视频帧进行比例以预定的数值，以获得第二帧间差; 并且对于所述视频帧的每个像素，获得基于所述第一帧间差和所述第二帧间差的较小值将所述视频帧与所述预定数值相关联的置信图; 以及至少基于与相应的预定数值相关联的一个或多个置信图中的每个像素的值，确定所述像素是否属于前景。
-
公开(公告)号：US09973706B2
公开(公告)日：2018-05-15
申请号：US15326630
申请日：2015-07-03
Applicant: Nokia Technologies Oy
Inventor： Kongqiao Wang , Jiangwei Li , He Yan
CPC classification number: H04N5/2352 , G06K9/4661 , G06T7/13 , G06T7/49 , H04N5/2258 , H04N5/23232 , H04N5/2351 , H04N5/2355
Abstract: Embodiments of the present invention relate to a method and apparatus for detecting an imaging condition. In one embodiment, there is provided a method for detecting an imaging condition. The method comprises: determining, based on luminance distribution in a first image of a scene, imaging lightness of the first image, the first image being captured by a first camera; determining, based on detection of a highlighted region in a second image of the scene, imaging exposureness of the second image, the second image being captured by a second camera, the first image and the second image being captured under a same or similar imaging condition, an exposure amount of the first camera being lower than an exposure amount of the second camera. There is also disclosed a relevant apparatus, electronic device, and a computer program product.
-
公开(公告)号：US09754153B2
公开(公告)日：2017-09-05
申请号：US14086235
申请日：2013-11-21
Applicant: Nokia Technologies Oy
Inventor： Jiangwei Li , Kongqiao Wang , He Yan
CPC classification number: G06K9/00234 , G06K9/00268 , G06K9/4652 , G06T7/11 , G06T7/13 , G06T7/149 , G06T2207/30201
Abstract: The present invention provides a method for image processing, a corresponding apparatus and a computer program product. The method comprises performing face detection of an image, obtaining a coarse face segmentation region of at least one face and a contour edge of the at least one face based on the face detection; and adjusting the coarse face segmentation region based on the contour edge to obtain a fine face segmentation region. By using the method, corresponding apparatus and computer program product of the present invention, the coarse face region in an image can be precisely segmented, which provides a good basis for the subsequent image processing based on the fine face segmentation region.
-
-
-
-
-
Search Results
6
records
(took 0.012 seconds)
