专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

JP2014074939A Vehicle detection device 有权
标题翻译：车辆检测装置
公开(公告)号：JP2014074939A
公开(公告)日：2014-04-24
申请号：JP2012220429
申请日：2012-10-02
申请人： Toshiba Corp , 株式会社東芝
发明人： AOKI YASUHIRO , SATO TOSHIO , TAKAHASHI YUSUKE , KARASAWA SHIGERU
IPC分类号： G08G1/04 , G06T1/00 , H04N7/18
CPC分类号： H04N7/18 , G06T7/254 , G06T2207/10021 , G06T2207/10028 , G06T2207/30236 , G08G1/04
摘要： PROBLEM TO BE SOLVED: To provide a vehicle detection device capable of accurately detecting a vehicle entering and exiting from a pickup image without being influenced by a change in optical conditions in a case where a stereo camera is adopted.SOLUTION: A vehicle detection device performs: enhancing edges in vertical directions of a vehicle to obtain parallax data between edge-enhanced pickup images; calculating variance of pixels within the pickup image to selectively discarding parallax data from the result; obtaining distance data from the parallax data to generate a distance image having a distance for each pixel; dividing the distance image into plural zones in a travel direction of the vehicle to generate plural reference sections; calculating a difference between background distance data and distance data for each of the plural reference sections; and calculating a change amount of the difference for each reference section and comparing the change amount of the difference with a threshold for each reference section, to thereby determine a state corresponding to the presence or absence of an article for each clock-time, retain the determination of the state for each clock-time, determine transition of the vehicle, and detect the vehicle entering and exiting.
摘要翻译：要解决的问题：提供一种车辆检测装置，其能够在采用立体照相机的情况下，不会受到光学条件的变化的影响，能够准确地检测进入和离开拾取图像的车辆。解决方案：车辆检测装置执行：增强车辆的垂直方向的边缘，以获得边缘增强的拾取图像之间的视差信息; 计算拾取图像内的像素的方差以选择性地从结果中丢弃视差数据; 从所述视差数据获取距离数据以产生具有每个像素的距离的距离图像; 将距离图像沿车辆的行进方向分割成多个区域以生成多个基准部分; 计算所述多个参考部分中的每一个的背景距离数据和距离数据之间的差; 并且计算每个参考部分的差异的变化量，并且将每个参考部分的差异的变化量与阈值进行比较，从而确定与每个时钟时间有无物品相对应的状态，确定每个时钟时间的状态，确定车辆的过渡，并检测车辆进入和离开。

2. 发明专利

JP2011060024A Apparatus for selecting feature information applied for image recognition processing, and image recognition processing apparatus 有权
标题翻译：用于选择用于图像识别处理的特征信息的装置和图像识别处理装置
公开(公告)号：JP2011060024A
公开(公告)日：2011-03-24
申请号：JP2009209525
申请日：2009-09-10
申请人： Toshiba Corp , 株式会社東芝
发明人： SUZUKI YOSHIHIKO , SAWADA AKIRA , BABA KENJI , TAKAHASHI YUSUKE , NISHIMURA NOBUTAKA , KURATA RYOICHI
IPC分类号： G06T7/00 , G06T1/00 , H04N7/18
摘要： PROBLEM TO BE SOLVED: To provide an apparatus for selecting feature information capable of selecting feature information effective in image recognition processing for achieving of chasing and identifying a person even when there are variations in environmental conditions.
SOLUTION: In an image forming apparatus 10 with the apparatus for selecting the feature information to extract a recognition target from image information photographed by cameras 11A-11C, there is provided a function for selecting the feature information effective in the image recognition processing from a plurality of feature information based on information in importance and reliability.
COPYRIGHT: (C)2011,JPO&INPIT
摘要翻译：要解决的问题：提供一种用于选择能够选择在图像识别处理中有效的特征信息的特征信息的装置，以便即使当环境条件有变化时也可以实现追踪和识别人。解决方案：在具有用于从由照相机11A-11C拍摄的图像信息中提取识别目标的特征信息的设备的图像形成装置10中，提供了用于选择在图像识别处理中有效的特征信息的功能基于重要性和可靠性的信息的多个特征信息。版权所有（C）2011，JPO＆INPIT

3. 发明专利

JP2010140323A Image processor and image processing method 有权
标题翻译：图像处理器和图像处理方法
公开(公告)号：JP2010140323A
公开(公告)日：2010-06-24
申请号：JP2008317009
申请日：2008-12-12
申请人： Toshiba Corp , 株式会社東芝
发明人： SUZUKI YOSHIHIKO , TAKAHASHI YUSUKE , BABA KENJI , ENOHARA TAKAAKI , SAWADA AKIRA , KINOSHITA HARUKI
IPC分类号： G06T5/00 , G06T1/00 , H04N1/407 , H04N7/18
摘要： PROBLEM TO BE SOLVED: To provide an image processor which can surely detect an object by extracting an edge in an image with high accuracy without relying on brightness or contrast in the image. SOLUTION: The image processor 10 carrying out an image process that extracts the object from an input image photographed by a camera 15 is provided with an image processing section 13 for executing luminance place analysis process by defining the edge by the number of type of luminance having different number of gray scales, analyzing the luminance distribution in the image expressing the dispersion of light and extracting the edge based on the luminance distribution. COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：提供一种通过以高精度提取图像中的边缘而不依赖于图像中的亮度或对比度来确定地检测对象的图像处理器。解决方案：执行从由照相机15拍摄的输入图像提取物体的图像处理器的图像处理器10设置有图像处理部分13，用于通过将边缘数量定义为类型来执行亮度分析处理分析具有不同数目的灰度级的亮度，分析表示光的色散的图像中的亮度分布并基于亮度分布提取边缘。版权所有（C）2010，JPO＆INPIT

4. 发明专利

JP2010068120A Monitoring system 审中-公开
标题翻译：监视系统
公开(公告)号：JP2010068120A
公开(公告)日：2010-03-25
申请号：JP2008231176
申请日：2008-09-09
申请人： Toshiba Corp , 株式会社東芝
发明人： SUZUKI YOSHIHIKO , TAKAHASHI YUSUKE , BABA KENJI , ENOHARA TAKAAKI , KINOSHITA HARUKI , SAWADA AKIRA
IPC分类号： H04N7/18 , G08B25/00 , H04N5/225
摘要： PROBLEM TO BE SOLVED: To improve identification performance of an object to be monitored by using a plurality of monitoring cameras.
SOLUTION: An monitoring system performs the illumination adjustment of light irradiated to a monitoring range by controlling the drive of illumination devices 7 and attached facilities 9 prepared corresponding to an imaging device 3 in order to suppress the black collapse and white halation of an image photographed by one of imaging cameras 3 which becomes a reference among the imaging cameras 3 in each monitoring range. The system controls spectral distribution characteristics of illumination by the illumination devices 7 prepared corresponding to the imaging devices 3 in order to bring a color of the object to be monitored expressed in the photographed image to be close to the actual color. If a color of an image photographed by the reference imaging device 3 and a color of an image photographed by other imaging devices 3 are uniform, an object identification processing unit 53 performs the identification processing of the object to be monitored which pass monitoring ranges of the imaging devices 3 based on images photographed by the imaging devices 3.
COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：通过使用多个监视摄像机来改善待监视对象的识别性能。解决方案：监视系统通过控制对应于成像装置3准备的照明装置7和附属设备9的驱动来执行照射到监视范围的光的照明调节，以便抑制黑色塌陷在每个监视范围内，成像摄像机3中的一个摄像机3拍摄成像照相机3之间的基准。该系统控制与成像装置3相对应地准备的照明装置7的照明的光谱分布特性，以便使拍摄图像中要被监视的被摄体的颜色表达为接近实际颜色。如果由参考成像装置3拍摄的图像的颜色和由其他成像装置3拍摄的图像的颜色是均匀的，则对象识别处理单元53执行通过监视范围的被监视对象的识别处理成像装置3基于由成像装置3拍摄的图像。版权所有：（C）2010，JPO＆INPIT

5. 发明专利

JP2009055446A System and device for searching video image 有权
标题翻译：用于搜索视频图像的系统和设备
公开(公告)号：JP2009055446A
公开(公告)日：2009-03-12
申请号：JP2007221399
申请日：2007-08-28
申请人： Toshiba Corp , 株式会社東芝
发明人： SUZUKI YOSHIHIKO , TAKAHASHI YUSUKE , BABA KENJI , ENOHARA TAKAAKI , KINOSHITA HARUKI
IPC分类号： H04N5/76 , G06F17/30 , H04N5/91 , H04N7/18
摘要： PROBLEM TO BE SOLVED: To efficiently search for a video image photographed by a plurality of cameras.
SOLUTION: A video image storage section 53 stores a video image photographed by the plurality of cameras. A search condition input section 54 inputs search conditions for searching an image, containing an object designated by a user. A meta data generating section 55 analyzes an image for compositing a video image stored at the video image storage section 53. A meta data generating section 55 generates meta data indicating attributes characterizing an object contained in the analyzed image. A search processing section 56 searches for the image containing the object designated by the user from the video image storage section 53, based on the input search conditions and the meta data. The search processing section 56 collects meta data indicating attributes characterizing the object contained in each searched image. The search processing section 56 searches for an image containing the object designated by the user from the video image storage section 53, based on the meta data collected.
COPYRIGHT: (C)2009,JPO&INPIT
摘要翻译：要解决的问题：有效地搜索由多个照相机拍摄的视频图像。解决方案：视频图像存储部分53存储由多个照相机拍摄的视频图像。搜索条件输入部分54输入搜索包含由用户指定的对象的图像的搜索条件。元数据生成部55分析用于合成存储在视频图像存储部53中的视频图像的图像。元数据生成部55生成表示分析图像中包含的对象的属性的元数据。搜索处理部56基于输入的搜索条件和元数据，从视频图像存储部53搜索包含用户指定的对象的图像。搜索处理部分56收集指示表征包含在每个搜索图像中的对象的属性的元数据。搜索处理部56基于收集的元数据，从视频图像存储部53搜索包含用户指定的对象的图像。版权所有（C）2009，JPO＆INPIT

6. 发明专利

JP2008227943A Video processing system and video processing method 有权
标题翻译：视频处理系统和视频处理方法
公开(公告)号：JP2008227943A
公开(公告)日：2008-09-25
申请号：JP2007063805
申请日：2007-03-13
申请人： Toshiba Corp , 株式会社東芝
发明人： SUZUKI YOSHIHIKO , TAKAHASHI YUSUKE , BABA KENJI , ENOHARA TAKAAKI , KINOSHITA HARUKI
IPC分类号： H04N5/91 , G11B27/00 , G11B27/034 , G11B27/10 , H04N5/76 , H04N5/765
摘要： PROBLEM TO BE SOLVED: To improve accumulation efficiency and search efficiency of video data by understanding contents of the video data.
SOLUTION: A receiving part 51 receives video data. A video analyzing part 52 analyses video data (object video data) that are received by the receiving part 51. A video accumulation processing part 57 extracts meta data representing contents of an objective video data, based on the analyzing result. The video accumulation processing part 57 attaches the extracted meta data to the objective video data. The video accumulation processing part 57 determines the importance degree of the objective video data, based on the meta data. The video accumulation processing part 57 accumulates the objective video data and the importance degree of it in a video storage 58, based on the accumulation condition determined that is based on the importance degree that has been determined.
COPYRIGHT: (C)2008,JPO&INPIT
摘要翻译：要解决的问题：通过了解视频数据的内容来提高视频数据的累积效率和搜索效率。解决方案：接收部分51接收视频数据。视频分析部分52分析由接收部分51接收的视频数据（对象视频数据）。视频累积处理部分57基于分析结果提取表示目标视频数据的内容的元数据。视频累积处理部57将提取的元数据附加到目标视频数据。视频累积处理部分57基于元数据确定目标视频数据的重要程度。视频累积处理部分57基于根据确定的重要程度确定的累积条件，将目标视频数据及其重要程度累积在视频存储器58中。版权所有（C）2008，JPO＆INPIT

7. 发明专利

JP2008225887A Image retrieval system 审中-公开
标题翻译：图像检索系统
公开(公告)号：JP2008225887A
公开(公告)日：2008-09-25
申请号：JP2007063776
申请日：2007-03-13
申请人： Toshiba Corp , 株式会社東芝
发明人： TAKAHASHI YUSUKE , SUZUKI YOSHIHIKO , BABA KENJI , ENOHARA TAKAAKI , KINOSHITA HARUKI
IPC分类号： G06F17/30 , G06T1/00
CPC分类号： G06K9/4652
摘要： PROBLEM TO BE SOLVED: To generate meta information based on color information removing the influence of a photographic environment light source color or the like for every object in an image; and to retrieve the image matched with the request of a user.
SOLUTION: The image retrieval system includes: an image storage device 3 which stores an image; a meta information generation device 4 which recognizes an object existing in the image with respect to the stored image, removes the influence of a photographic environment light source from the object, converts it into color information under a standard light source, and generates meta information; a meta information storage device 5 which stores the generated meta information; an image retrieval UI device 6 which designates and inputs uniquely recognizable color information while taking an interactive format; and an image retrieval device 7 which converts the designated and input color information into color information based on the expression method of color stored in the meta information storage device 5, and which retrieves an image from the image storage device 3 based on the meta information similar to the converted color information from the meta information storage device 5.
COPYRIGHT: (C)2008,JPO&INPIT
摘要翻译：要解决的问题：基于消除图像中的每个对象的摄影环境光源颜色等的影响的颜色信息来生成元信息; 并且检索与用户的请求匹配的图像。图像检索系统包括：存储图像的图像存储装置3; 识别存储在图像中的物体的元信息生成装置4从对象去除摄影环境光源的影响，将其转换为标准光源下的彩色信息，生成元信息; 存储生成的元信息的元信息存储装置5; 图像检索UI装置6，其在采取交互格式的同时指定和输入唯一可识别的颜色信息; 以及图像检索装置7，其基于存储在元信息存储装置5中的颜色的表达方法将指定和输入的颜色信息转换为颜色信息，并且根据元信息类似的方法从图像存储装置3检索图像来自元信息存储装置5的转换颜色信息。（C）2008年，JPO和INPIT

8. 发明专利

JP2014234085A 駅ホーム転落検知装置有权
标题翻译：站台平台检测装置
公开(公告)号：JP2014234085A
公开(公告)日：2014-12-15
申请号：JP2013117057
申请日：2013-06-03
申请人：株式会社東芝 , Toshiba Corp , 西日本旅客鉄道株式会社 , West Japan Railway Co
发明人： TAKAHASHI YUSUKE , KAWAI NOBUYUKI , KURIYAMA OKINORI , MUROYA SHINGO
IPC分类号： B61L23/00 , G06T7/00 , G06T7/60
摘要：【課題】より高い精度で転落事象を検知する駅ホーム転落検知装置を提供する。【解決手段】一実施形態に係る駅ホーム転落検知装置は、ステレオ画像から対象物の基準平面上の位置と前記基準平面からの高さを推定する推定手段と、前記基準平面を前記駅ホームに該当する第1の領域と、前記線路軌道に該当する第2の領域とに分割し、前記対象物が第1の領域に存在すると判別された場合に前記推定された高さが第1の下限閾値以上第1の上限閾値未満であるか否か判別し、前記対象物が第2の領域に存在すると判別された場合に前記推定された高さが第2の下限閾値以上第2の上限閾値未満であるか否か判別する高さ判別手段と、前記推定された高さが下限閾値以上であり上限閾値未満であると判別された場合、転落事象を検知する検知手段と、を具備する。【選択図】図2
摘要翻译：要解决的问题：提供一种能够以更高精度检测坠落事件的车站平台坠落检测装置。解决方案：根据一个实施例的车站平台坠落检测装置包括估计装置，用于估计主平面上的物体的位置平面及其高度与主平面相距立体图像。主平面分为与站平台相关的第一区域和与轨道相关的第二区域。所述检测装置还包括：高度识别装置，当判断出所述对象存在于所述第一区域时，判别所述估计高度是否不小于第一下限阈值且小于第一上限阈值，并且判别是否当判断对象存在于第二区域时，估计高度不小于第二下限阈值且小于第二上限阈值; 以及检测装置，用于当判定所述估计高度不小于所述下限阈值并小于所述上限阈值时，检测所述跌倒事件。

9. 发明专利

JP2014174834A Information processor, cloud platform, information processing method and program thereof 有权
标题翻译：信息处理器，云平台，信息处理方法及其程序
公开(公告)号：JP2014174834A
公开(公告)日：2014-09-22
申请号：JP2013048315
申请日：2013-03-11
申请人： Toshiba Corp , 株式会社東芝
发明人： KIMIYAMA KENJI , SATO TOSHIO , SUZUKI YOSHIHIKO , TAKAHASHI YUSUKE
IPC分类号： G06F9/50 , G06T3/00 , H04N7/01
CPC分类号： G06T3/4053 , G06F3/1446 , G06F3/1454 , G06K9/36 , G06T11/60 , G09G5/001 , G09G2340/0407 , G09G2340/10 , G09G2340/12 , G09G2360/06 , G09G2360/08
摘要： PROBLEM TO BE SOLVED: To provide a technique which allows distributed processing of super-resolution processing at multiple nodes on a cloud platform which has a high affinity with cloud computing and can efficiently process image compressed and coded.SOLUTION: An information processor includes a division point determination part for determining points to divide an input image composed of image frame alignments, a division processing part for dividing the input image composed of image frame alignments at division points for multiple information processors and distributing the divided image frame alignments to the multiple respective corresponding information processors, and a combining processing part for combining results of super-resolution processing executed by the multiple information processor and outputting it.
摘要翻译：要解决的问题：提供一种技术，其允许在与云计算具有高亲和力的云平台上的多个节点上的分辨率处理的分散处理，并且可以有效地处理压缩和编码的图像。解决方案：信息处理器包括：用于确定点分割由图像帧对准组成的输入图像的点确定部分;分割处理部分，用于将由多个信息处理器的分割点处的图像帧排列组成的输入图像分割，并将分割的图像帧排列分配到多个相应的对应信息处理器和用于组合由多个信息处理器执行的超分辨率处理的结果并输出的组合处理部分。

10. 发明专利

JP2014059655A Road situation-monitoring device, and road situation-monitoring method 有权
标题翻译：道路状况监测装置及道路状况监测方法
公开(公告)号：JP2014059655A
公开(公告)日：2014-04-03
申请号：JP2012203499
申请日：2012-09-14
申请人： Toshiba Corp , 株式会社東芝
发明人： HORIE KATSUHIRO , SATO TOSHIO , AOKI YASUHIRO , SUZUKI YOSHIHIKO , KIMIYAMA KENJI , TAKAHASHI YUSUKE
IPC分类号： G06T1/00 , G03B15/00 , G08G1/01 , G08G1/015 , G08G1/04 , H04N5/225 , H04N5/232
摘要： PROBLEM TO BE SOLVED: To provide a road situation-monitoring device and a road-situation monitoring method, in which sampling and tracking of a vehicle can be performed stably even to an image in which a traveling direction of the vehicle changes, and vehicle detection accuracy can be improved.SOLUTION: An image-capturing apparatus captures an image of a monitoring area. An image acquisition section acquires an image of the monitoring area from the image-capturing apparatus. A vehicle detection section detects a vehicle displayed in the monitoring area from the acquired image. A template creating section calculates a position of the detected vehicle in the monitoring area and feature of the vehicle based on the acquired image, and creates a template from a calculation result. A vehicle tracking section detects the same vehicle by sequentially comparing and collating the templates with images to be acquired. A road situation detection section detects road situation based on a detection result obtained through the vehicle detection section and the vehicle tracking section.
摘要翻译：要解决的问题：提供一种道路情况监测装置和道路情况监测方法，其中即使对于车辆的行进方向改变的图像也能够稳定地执行车辆的采样和跟踪，以及车辆检测可以提高精度。解决方案：图像捕获设备捕获监控区域的图像。图像获取部分从图像捕获装置获取监视区域的图像。车辆检测部从所获取的图像检测在监视区域中显示的车辆。模板创建部基于所获取的图像计算车辆的监视区域和特征中检测到的车辆的位置，并根据计算结果创建模板。车辆跟踪部通过顺序地将模板与要获取的图像进行比较和对照来检测相同的车辆。道路状况检测部根据通过车辆检测部和车辆跟踪部获得的检测结果来检测路况。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式