-
1.发明授权公开(公告)号：US10204271B2
公开(公告)日：2019-02-12
申请号：US14448968
申请日：2014-07-31
Applicant: CANON KABUSHIKI KAISHA
Inventor： You Lv , Yong Jiang , Bo Wu , Xian Li
Abstract: In the present invention, an attribution is extracted from each region obtained by segmentation of an image, relationships among the regions are described, and a composition of the image is evaluated based on the attributions and the relationships.
-
公开(公告)号：US20150363649A1
公开(公告)日：2015-12-17
申请号：US14626182
申请日：2015-03-16
Applicant: CANON KABUSHIKI KAISHA
Inventor： Xuyu Zhao , Long Jiang , Yong Jiang
CPC classification number: G06K9/00771 , G06K9/38
Abstract: The present invention relates to the method for updating scene model and video surveillance. A method is provided for updating a scene model in a video which is composed of a plurality of visual elements, comprising: a classifying step for classifying the visual elements in a scene into stationary visual elements and moving visual elements according to their appearance change rates; a border determining step for determining borders from the scene according to a spatial distribution information of the stationary visual elements and the moving visual elements; and an updating step for updating the scene model according to the determined borders in said scene.
Abstract translation: 本发明涉及用于更新场景模型和视频监控的方法。 提供了一种用于更新由多个视觉元素组成的视频中的场景模型的方法，包括：分类步骤，用于根据场景变化率将场景中的视觉元素分类为静态视觉元素和移动视觉元素; 边界确定步骤，用于根据静止视觉元素和移动视觉元素的空间分布信息确定来自场景的边界; 以及更新步骤，用于根据所述场景中确定的边界来更新场景模型。
-
3.发明授权公开(公告)号：US09147169B2
公开(公告)日：2015-09-29
申请号：US13779447
申请日：2013-02-27
Applicant: CANON KABUSHIKI KAISHA
Inventor： Yong Jiang , Long Jiang , Lifeng Xu
CPC classification number: G06N99/005 , G06K9/6217 , G06K9/6267 , G06K9/6285
Abstract: Unlabeled samples are added to existing samples. Candidate samples for new support vectors are extracted from the added unlabeled samples using a plurality of existing support vectors. The new support vectors are selected from the candidate samples using the plurality of existing support vectors.
Abstract translation: 未标记的样品被添加到现有样品中。 使用多个现有的支持向量从添加的未标记的样品中提取新的支持载体的候选样品。 使用多个现有支持向量从候选样本中选择新的支持向量。
-
4.发明申请IMAGE COMPOSITION EVALUATING APPARATUS, INFORMATION PROCESSING APPARATUS AND METHODS THEREOF 审中-公开图像组合物评估装置，信息处理装置及其方法公开(公告)号：US20150036921A1
公开(公告)日：2015-02-05
申请号：US14448968
申请日：2014-07-31
Applicant: CANON KABUSHIKI KAISHA
Inventor： You Lu , Yong Jiang , Bo Wu , Xian Li
CPC classification number: G06K9/00664 , G06T7/0002 , G06T7/11 , G06T7/187 , G06T2207/20021 , G06T2207/20084 , G06T2207/30168
Abstract: The present invention discloses an image composition evaluating apparatus, an information processing apparatus and methods thereof. The image composition evaluating apparatus comprises: a region segmentation unit configured to segment an image into a plurality of regions; a region attribution extraction unit configured to extract at least one attribution from each of the regions; a region relationship description unit configured to describe relationships among the regions based on the extracted attributions; and a composition evaluation unit configured to evaluate the composition of the image based on the extracted attributions, the described relationships and at least one preset criterion. The present invention can evaluate more kinds of images and/or more kinds of composition problems.
Abstract translation: 本发明公开了一种图像构图评估装置，信息处理装置及其方法。 该图像合成评估装置包括：区域分割单元，被配置为将图像分割成多个区域; 区域属性提取单元，被配置为从每个区域提取至少一个归属; 区域关系描述单元，被配置为基于所提取的属性来描述区域之间的关系; 以及构图评估单元，被配置为基于所提取的属性，所描述的关系和至少一个预设标准来评估图像的构图。 本发明可以评估更多种类的图像和/或更多种类的构图问题。
-
公开(公告)号：US09704069B2
公开(公告)日：2017-07-11
申请号：US14642321
申请日：2015-03-09
Applicant: CANON KABUSHIKI KAISHA
Inventor： You Lv , Yong Jiang , Bo Wu
CPC classification number: G06K9/72 , G06K9/00671
Abstract: The present invention discloses an image processing evaluating apparatus and image processing method. The processing apparatus comprising: a confidence generation means for generating a classification confidence for each region in the image, the classification confidence represents the probability of an region belonging to a predefined class; and a classification means for classifying the regions in the image, which are obvious to be classified by their classification confidences, to respective classes based on the calculated confidences. The image processing apparatus further comprising: a fuzzy region extraction means for extracting one or more regions, which are not obvious to be classified by their classification confidences, as fuzzy regions; and a confidence update means for updating the classification confidence for each fuzzy region based on the classification confidences of adjacent regions thereof, wherein the classification means further classifies the fuzzy regions to respective classes based on the updated classification confidences.
-
Patent Agency Ranking
公开(公告)号：US09600884B2
公开(公告)日：2017-03-21
申请号：US14857669
申请日：2015-09-17
Applicant: CANON KABUSHIKI KAISHA
Inventor： Fuguo Zhu , Yong Jiang , Xian Li , Lifeng Xu , Dongchao Wen
CPC classification number: G06T7/33 , G06K9/00281 , G06K9/4671 , G06K9/621 , G06K9/6244 , G06T2207/30196
Abstract: An apparatus includes a unit configured to acquire an object shape regression model, which comprises an average object shape, a plurality of regression functions and a plurality of feature selection maps; a unit configured to set an initial object shape for the object image based on the average object shape; a unit configured to calculate at least one feature vector with respect to a plurality of feature points; a unit configured, for each coordinate of the plurality of feature points, to select feature fragments from the calculated feature vector based on a corresponding one of the plurality of feature selection maps and assemble the feature fragments into a sub feature vector; and a unit configured, for at least one coordinate of at least one feature point, to predict a coordinate increment based on the corresponding sub feature vector and a corresponding one of the plurality of regression functions.
-
7.发明授权Method and apparatus for generating image description vector, image detection method and apparatus 有权用于生成图像描述矢量的方法和装置，图像检测方法和装置公开(公告)号：US09275300B2
公开(公告)日：2016-03-01
申请号：US13774281
申请日：2013-02-22
Applicant: CANON KABUSHIKI KAISHA
Inventor： Yong Jiang , Wenwen Zhang , Lifeng Xu
CPC classification number: G06K9/481 , G06K9/4638 , G06K9/4671
Abstract: This invention relates to a method and an apparatus for generating an image description vector, an image detection method and apparatus. The method for generating an image description vector comprising: an encoding step of encoding each of a plurality of pixel regions of an image into M pieces of N-bit binary codes, wherein each bit of an N-bit binary code represents a neighboring pixel region which is in neighborhood of a corresponding pixel region; and a generating step of generating an image description vector of the image based on matching at least one of the M pieces of N-bit binary code of each pixel region of the plurality of pixel regions with a particular code pattern, where M is an integer of 3 or larger, and N is an integer of 3 or larger.
Abstract translation: 本发明涉及一种用于生成图像描述向量的方法和装置，图像检测方法和装置。 一种用于生成图像描述向量的方法，包括：编码步骤，将图像的多个像素区域中的每一个编码为M个N位二进制码，其中N位二进制码的每个位表示相邻像素区域 其位于相应的像素区域附近; 以及生成步骤，基于将所述多个像素区域的每个像素区域的M个N位二进制码中的至少一个与特定码型匹配来生成图像的图像描述向量，其中M是整数 3以上，N为3以上的整数。
-
8.发明授权Object detection method, object detection apparatus and image pickup apparatus 有权物体检测方法，物体检测装置和摄像装置公开(公告)号：US09171230B2
公开(公告)日：2015-10-27
申请号：US14107436
申请日：2013-12-16
Applicant: CANON KABUSHIKI KAISHA
Inventor： Yong Jiang , Lifeng Xu
CPC classification number: G06K9/6217 , G06K9/00281 , G06K9/00362 , G06K9/628 , G06K9/6857
Abstract: An object detection method performed by an apparatus which stores a general model for a specific object type in advance, the general model describing a plurality of components which are expected to co-exist in objects of the specific object type, the method including: a sample image receiving step of receiving one or more sample images, the one or more sample images each include a same query object of the specific object type; an object detector creating step of creating, using the general model and the one or more sample images, a detector specific to said query object; and an object detecting step of detecting, using the created detector specific to the query object, the query object from a destination image. According to the object detection method mentioned above, various objects of a specific object type can be precisely detected with high flexibility.
Abstract translation: 一种由预先存储特定对象类型的一般模型的装置执行的对象检测方法，描述预期在特定对象类型的对象中共存的多个组件的一般模型，该方法包括：样本 图像接收步骤，接收一个或多个样本图像，所述一个或多个样本图像各自包括特定对象类型的相同查询对象; 对象检测器创建步骤，使用所述一般模型和所述一个或多个样本图像来创建特定于所述查询对象的检测器; 以及对象检测步骤，用于从目的地图像中检测对所述查询对象特有的创建检测器的查询对象。 根据上述对象检测方法，可以高度灵活地精确地检测特定对象类型的各种对象。
-
公开(公告)号：US09659220B2
公开(公告)日：2017-05-23
申请号：US14626182
申请日：2015-03-16
Applicant: CANON KABUSHIKI KAISHA
Inventor： Xuyu Zhao , Long Jiang , Yong Jiang
CPC classification number: G06K9/00771 , G06K9/38
Abstract: The present invention relates to the method for updating scene model and video surveillance. A method is provided for updating a scene model in a video which is composed of a plurality of visual elements, comprising: a classifying step for classifying the visual elements in a scene into stationary visual elements and moving visual elements according to their appearance change rates; a border determining step for determining borders from the scene according to a spatial distribution information of the stationary visual elements and the moving visual elements; and an updating step for updating the scene model according to the determined borders in said scene.
-
10.发明申请OBJECT SHAPE ALIGNING APPARATUS, OBJECT PROCESSING APPARATUS AND METHODS THEREOF 有权对象形状对准装置，对象处理装置及其方法公开(公告)号：US20160086053A1
公开(公告)日：2016-03-24
申请号：US14857669
申请日：2015-09-17
Applicant: CANON KABUSHIKI KAISHA
Inventor： Fuguo Zhu , Yong Jiang , Xian Li , Lifeng Xu , Dongchao Wen
CPC classification number: G06T7/33 , G06K9/00281 , G06K9/4671 , G06K9/621 , G06K9/6244 , G06T2207/30196
Abstract: An apparatus includes a unit configured to acquire an object shape regression model, which comprises an average object shape, a plurality of regression functions and a plurality of feature selection maps; a unit configured to set an initial object shape for the object image based on the average object shape; a unit configured to calculate at least one feature vector with respect to a plurality of feature points; a unit configured, for each coordinate of the plurality of feature points, to select feature fragments from the calculated feature vector based on a corresponding one of the plurality of feature selection maps and assemble the feature fragments into a sub feature vector; and a unit configured, for at least one coordinate of at least one feature point, to predict a coordinate increment based on the corresponding sub feature vector and a corresponding one of the plurality of regression functions.
Abstract translation: 一种装置包括：被配置为获取对象形状回归模型的单元，其包括平均对象形状，多个回归函数和多个特征选择图; 被配置为基于平均对象形状来设置对象图像的初始对象形状的单元; 被配置为针对多个特征点计算至少一个特征向量的单元; 针对所述多个特征点的每个坐标配置的单元，基于所述多个特征选择图中的相应一个，从所计算的特征向量中选择特征片段，并将所述特征片段组合成子特征向量; 以及针对至少一个特征点的至少一个坐标配置的单元，用于基于所述对应的子特征向量和所述多个回归函数中的相应的一个来预测坐标增量。
-
-
-
-
-
-
-
-
-
Search Results
22
records
(took 0.022 seconds)
