-
公开(公告)号：US09928604B2
公开(公告)日：2018-03-27
申请号：US15209199
申请日：2016-07-13
申请人： THOMSON LICENSING
CPC分类号： G06T7/20 , G06T3/40 , G06T7/11 , G06T7/13 , G06T7/194 , G06T7/60 , G06T7/90 , G06T2207/10024 , G06T2207/20112
摘要： Objects in an image sequence are tracked within a bounding box such that the object is assured to some extent of being contained within the bounding box. The location of the object within the bounding box is less important than knowing with some certainty that the object is within the bounding box, unlike previous methods that attempt to center an object within a bounding box. The approach, which uses histograms of image features such as color indices, is suited to applications such as zooming and is robust to occlusions, out-of-plane rotations, illumination changes and long-term tracking drift.
-
2.发明申请COLOR VIDEO PROCESSING SYSTEM AND METHOD, AND CORRESPONDING COMPUTER PROGRAM 审中-公开彩色视频处理系统和方法，以及相应的计算机程序公开(公告)号：US20150077639A1
公开(公告)日：2015-03-19
申请号：US14484700
申请日：2014-09-12
申请人： Thomson Licensing
发明人： Christel CHAMARET , Yoann Baveye , Fabrice Urban
CPC分类号： H04N9/646 , G06K9/4652 , G06T7/90 , H04N1/6075 , H04N9/643 , H04N9/73
摘要： A color video processing method is disclosed that comprises: marking out an object from a background in each frame of a sequence of frames of a color video, selecting at least two successive frames, determining a global color template from the backgrounds of the selected frames, for each selected frame and for colors of the marked out object, determining an harmonized color according to the global color template, in such a way that the harmonized color is closer to the global color template than the original color.
摘要翻译： 公开了一种彩色视频处理方法，包括：从彩色视频的一系列帧的每帧中的背景中标出一个对象，选择至少两个连续的帧，从所选择的帧的背景中确定全局颜色模板， 对于每个所选择的帧和所标记的对象的颜色，根据全局颜色模板确定协调的颜色，使得协调的颜色比原始颜色更接近全局颜色模板。
-
3.发明申请公开(公告)号：US20140079321A1
公开(公告)日：2014-03-20
申请号：US14028425
申请日：2013-09-16
申请人： THOMSON LICENSING
发明人： Thai Q HUYNH-THU , Fabrice Urban
IPC分类号： G06K9/00
CPC分类号： G06K9/0053 , G06K9/00711 , G06K2209/25
摘要： A method for detecting the presence of a logo in a current picture of a video is disclosed. The method comprises: determining a current candidate logo bounding box in the current picture and a preceding candidate logo bounding box in a picture preceding the current picture; detecting the presence of a logo in the current picture if at least one of the following conditions is fulfilled: the distance between the centers of the current and the preceding candidate logo bounding boxes is below a first threshold or an overlap between the current and the preceding candidate logo bounding boxes is above a second threshold; or an overlap between the current candidate logo bounding box and a saliency mask of the current picture is above a third, wherein the saliency mask identifies regions around saliency peaks.
摘要翻译： 公开了一种在视频的当前照片中检测标识的存在的方法。 该方法包括：确定当前画面中的当前候选标识界限框和当前画面之前的画面中的前一候选标识界限框; 如果满足以下条件中的至少一个条件，则检测当前图片中的徽标的存在：当前和前一个候选徽标界限框的中心之间的距离低于第一阈值或当前和前一个之间的重叠 候选标识界限框高于第二阈值; 或者当前候选标识界限框和当前图片的显着掩模之间的重叠高于三分之一，其中显着掩模识别显着峰值周围的区域。
-
公开(公告)号：US09311533B2
公开(公告)日：2016-04-12
申请号：US14028425
申请日：2013-09-16
申请人： THOMSON LICENSING
发明人： Thai Q Huynh-Thu , Fabrice Urban
CPC分类号： G06K9/0053 , G06K9/00711 , G06K2209/25
摘要： A method for detecting the presence of a logo in a current picture of a video is disclosed. The method comprises: determining a current candidate logo bounding box in the current picture and a preceding candidate logo bounding box in a picture preceding the current picture; detecting the presence of a logo in the current picture if at least one of the following conditions is fulfilled: the distance between the centers of the current and the preceding candidate logo bounding boxes is below a first threshold or an overlap between the current and the preceding candidate logo bounding boxes is above a second threshold; or an overlap between the current candidate logo bounding box and a saliency mask of the current picture is above a third, wherein the saliency mask identifies regions around saliency peaks.
摘要翻译： 公开了一种在视频的当前照片中检测标识的存在的方法。 该方法包括：确定当前画面中的当前候选标识界限框和当前画面之前的画面中的前一候选标识界限框; 如果满足以下条件中的至少一个条件，则检测当前图片中的徽标的存在：当前和前一个候选徽标界限框的中心之间的距离低于第一阈值或当前和前一个之间的重叠 候选标识界限框高于第二阈值; 或者当前候选标识界限框和当前图片的显着掩模之间的重叠高于三分之一，其中显着掩模识别显着峰值周围的区域。
-
公开(公告)号：US10121251B2
公开(公告)日：2018-11-06
申请号：US15206196
申请日：2016-07-08
申请人： THOMSON LICENSING
摘要： A method for controlling tracking using a color model is disclosed. The method includes obtaining a window in a second frame of a video image corresponding to a window in a first frame of the video image using a tracking algorithm in a tracking mode, wherein each pixel in the video image has at least one color component. The method further includes defining a background area around the window in the first frame, assigning a pixel confidence value for each pixel in the second frame according to a color model, assigning a window confidence value for the window in the second frame according to the pixel confidence values of pixels in the window in the second frame, if the window confidence value is greater than a first confidence threshold, selecting the tracking mode, and if the window confidence value is not greater than the first confidence threshold, selecting a mode different from the tracking mode.
-
公开(公告)号：US09930220B2
公开(公告)日：2018-03-27
申请号：US14273727
申请日：2014-05-09
申请人： THOMSON LICENSING
发明人： Fabrice Urban , Christel Chamaret , Yoann Baveye
CPC分类号： H04N1/6077 , G06T7/11 , G06T7/194 , G06T11/001 , G06T2207/10024
摘要： A method for processing a picture is disclosed. The method according to the invention comprises: segmenting the picture into a background layer and at least another layer; selecting a background template of color harmony for the background layer; determining one template of color harmony for each of the at least another layer from the background template of color harmony depending on the distance between the background layer and said at least another layer. processing the picture by mapping the colors of each segmented layer using the corresponding template of color harmony.
-
公开(公告)号：US20170018090A1
公开(公告)日：2017-01-19
申请号：US15209199
申请日：2016-07-13
申请人： THOMSON LICENSING
CPC分类号： G06T7/20 , G06T3/40 , G06T7/11 , G06T7/13 , G06T7/194 , G06T7/60 , G06T7/90 , G06T2207/10024 , G06T2207/20112
摘要： Objects in an image sequence are tracked within a bounding box such that the object is assured to some extent of being contained within the bounding box. The location of the object within the bounding box is less important than knowing with some certainty that the object is within the bounding box, unlike previous methods that attempt to center an object within a bounding box. The approach, which uses histograms of image features such as color indices, is suited to applications such as zooming and is robust to occlusions, out-of-plane rotations, illumination changes and long-term tracking drift.
摘要翻译： 图像序列中的对象在边界框内被跟踪，使得对象在某种程度上被放置在包围框内。 与边界框内的对象的位置不同于先前已经尝试将对象集中在边界框内的方法，这一点与知道对象是否在边界框内的确定性不重要。 使用诸如颜色索引的图像特征的直方图的方法适用于诸如变焦之类的应用，并且对遮挡，面外旋转，照明变化和长期跟踪漂移是鲁棒的。
-
公开(公告)号：US09478044B2
公开(公告)日：2016-10-25
申请号：US14780594
申请日：2014-03-26
申请人： THOMSON LICENSING
发明人： Christel Chamaret , Fabrice Urban , Yoann Baveye
CPC分类号： G06T7/408 , G06T5/005 , G06T7/11 , G06T7/90 , G06T2207/10004 , G06T2207/10024 , G06T2207/30168
摘要： The present invention generally relates to a method and apparatus for creating an harmony map of an image. It also relates to a method and apparatus for assessing the quality of an image. The invention also relates to a method and apparatus for assessing the quality of an image such that an assessment score of the image is obtained from a perceptual map of the image created from the previous method. As an interesting tool for content creator and in the goal of maximizing the artistic effect, the proposed method provides perceptual harmony-guided quality map as well as a score of disharmony of a picture without reference image. The method links two distinct subjects: perceptual quality metric and harmonious hue templates in order to provide new tools to content creator whatever the expertise level.
摘要翻译： 本发明一般涉及一种用于创建图像的和声图的方法和装置。 它还涉及用于评估图像质量的方法和装置。 本发明还涉及一种用于评估图像质量的方法和装置，使得根据从先前方法创建的图像的感知图获得图像的评估分数。 作为内容创作者的有趣工具，为了最大限度地提高艺术效果，本文提出的方法提供了感性和谐指导的质量图以及无参考图像的图像不协调。 该方法链接两个不同的主题：感知质量度量和和谐色调模板，以便为内容创建者提供任何专业知识水平的新工具。
-
公开(公告)号：US20140153651A1
公开(公告)日：2014-06-05
申请号：US14233556
申请日：2012-06-25
申请人： THOMSON LICENSING
CPC分类号： H04N7/01 , H04N19/115 , H04N19/14 , H04N19/154 , H04N19/17 , H04N19/176 , H04N19/196 , H04N19/85
摘要： Reframing is used to re-size an image or video content, e.g. for displaying video signals with a given aspect ratio on a display having a different aspect ratio. Window cropping parameters (position and size over time) are constrained in order to optimise the rate/distortion of the encoded output video signal. Initial reframing is improved by computing a saliency map representing a user attention map which considers the video coding context and by providing a macroblock coding efficiency cost map and then taking the saliency map or a combined saliency/coding cost map into account so that the coding cost for said reframed video signal is smaller than the coding cost for other candidate reframing windows' sizes and positions.
摘要翻译： 重构用于重新调整图像或视频内容的大小，例如 用于在具有不同宽高比的显示器上显示具有给定宽高比的视频信号。 窗口裁剪参数（位置和尺寸随时间）被限制，以便优化编码的输出视频信号的速率/失真。 通过计算表示考虑视频编码上下文的用户注意地图并通过提供宏块编码效率成本图，然后考虑显着图或组合显着/编码成本图来考虑编码成本来改进初始重构 因为所述重构的视频信号小于其他候选重构窗口大小和位置的编码成本。
-
公开(公告)号：US09860502B2
公开(公告)日：2018-01-02
申请号：US14897630
申请日：2014-06-02
申请人： THOMSON LICENSING
发明人： Fabrice Urban , Christel Chamaret , Yoann Baveye
CPC分类号： H04N9/643 , G06K9/4609 , G06K9/4642 , G06K9/4652 , G06T5/40 , G06T7/90 , G06T11/001 , G06T2207/10016 , G06T2207/10024 , G06T2207/20032 , H04N9/646 , H04N9/73
摘要： A method for processing a video is disclosed. The method comprises: obtaining a type and an angle of a template for each picture of the video independently, each template defining a portion of harmonious color values; temporally filtering the types and angles over the video; processing each picture of the video, wherein processing the picture comprises mapping the colors of the picture into the template associated with the picture and defined by the filtered type and the filtered angle.
-
-
-
-
-
-
-
-
-
搜索结果
16 条记录 (耗时 0.018 秒)
