专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明专利

JP2014059646A Object detection device and object detection method 有权
标题翻译：对象检测装置和对象检测方法
公开(公告)号：JP2014059646A
公开(公告)日：2014-04-03
申请号：JP2012203408
申请日：2012-09-14
申请人： Toshiba Corp , 株式会社東芝
发明人： TAKAHASHI YUSUKE , SATO TOSHIO , AOKI YASUHIRO , SUZUKI YOSHIHIKO , KIMIYAMA KENJI , HORIE KATSUHIRO
IPC分类号： G06T1/00 , G06T7/00
摘要： PROBLEM TO BE SOLVED: To provide an object detection device and an object detection method for calculating the attribute information of an object without requiring the installation conditions of a camera or the like.SOLUTION: A plurality of camera images in which the detection area of an object are photographed are acquired, and the image photographed by one camera is converted such that the position of a pattern on a reference plane projected on the reference image of a monitoring area is coincident with the position of the pattern on the reference plane projected on the reference image of the monitoring area photographed by the other camera to generate a projection image, and the coordinates of the arbitrary point of the reference image and the coordinates of the corresponding point of the projection image are calculated, and a difference between the coordinate values of the arbitrary point of the reference image and the corresponding point of the projection image is calculated, and the position of an object on the reference plane is calculated, and whether or not there exists an object in the monitoring area is determined from the position of the object on the reference plane, and when there exists the object, the object is detected.
摘要翻译：要解决的问题：提供一种物体检测装置和物体检测方法，用于在不需要相机等的安装条件的情况下计算物体的属性信息。解决方案：多个摄像机图像，其中检测区域拍摄对象，并且通过一个照相机拍摄的图像被转换，使得投影在监视区域的参考图像上的参考平面上的图案的位置与投影在监视区域上的参考平面上的图案的位置一致由其他相机拍摄的监视区域的参考图像生成投影图像，并且计算参考图像的任意点的坐标和投影图像的对应点的坐标，并且计算坐标值之间的差计算参考图像的任意点和投影图像的对应点，并且计算对象在参考平面上的位置，并且根据对象在参考平面上的位置确定监视区域中是否存在对象，并且当存在对象时，检测对象。

32. 发明专利

JP2013134667A Vehicle detection device 有权
标题翻译：车辆检测装置
公开(公告)号：JP2013134667A
公开(公告)日：2013-07-08
申请号：JP2011285473
申请日：2011-12-27
申请人： Toshiba Corp , 株式会社東芝
发明人： AOKI YASUHIRO , SATO TOSHIO , TAKAHASHI YUSUKE
IPC分类号： G08G1/04 , G01B11/02 , G01V8/10 , G06T1/00 , G06T7/00 , G06T7/60
摘要： PROBLEM TO BE SOLVED: To detect a vehicle which has entered or left without being affected by the change of optical conditions.SOLUTION: A vehicle detection device acquires each photographic image obtained by photographing a road on which a vehicle is traveling with a stereo-camera, and acquires distance data measured by scanning a distance between a laser sensor and the road on which the vehicle is traveling with the laser sensor disposed adjacently to the stereo-camera, and detects the vehicle which has entered or left the visual field of the stereo-camera on the basis of the scan image obtained by connecting the distance data and each photographic image.
摘要翻译：要解决的问题：检测进入或离开而不受光学条件变化影响的车辆。解决方案：车辆检测装置获取通过立体摄像机拍摄车辆行驶的道路获得的每个摄影图像并且通过使用与立体照相机相邻设置的激光传感器扫描激光传感器与车辆行驶的道路之间的距离而测量的距离数据，并且检测已经进入或离开立体摄像机的视场的车辆基于通过连接距离数据和每个摄影图像而获得的扫描图像。

33. 发明专利

JP2012195880A Image processing apparatus, image processing method, and program 有权
标题翻译：图像处理设备，图像处理方法和程序
公开(公告)号：JP2012195880A
公开(公告)日：2012-10-11
申请号：JP2011059828
申请日：2011-03-17
申请人： Toshiba Corp , 株式会社東芝
发明人： KIMIYAMA KENJI , SATO TOSHIO
IPC分类号： H04N7/173 , G06T3/00 , G06T3/40 , H04N7/01 , H04N19/00 , H04N19/117 , H04N19/132 , H04N19/136 , H04N19/137 , H04N19/154 , H04N19/46 , H04N19/587 , H04N19/59 , H04N19/70 , H04N19/80 , H04N21/234 , H04N21/2343 , H04N21/235 , H04N21/431 , H04N21/435 , H04N21/436 , H04N21/4402 , H04N21/84
摘要： PROBLEM TO BE SOLVED: To provide an apparatus which when performing improvement of resolution on an input image signal, is capable of sufficiently extracting performance for improvement of resolution by increasing reference information needed for improvement of resolution.SOLUTION: According to the embodiment, an image conversion apparatus generates a converted image signal and transmits the converted image signal to a receiving apparatus via a repeating apparatus. The receiving apparatus performs restoration processing and super-resolution processing on the received converted image signal, thereby obtaining a high resolution image signal having improved resolution. In order to reduce the capacity of the repeating apparatus, the image conversion apparatus obtains the converted image signal by processing an original image signal. In order to improve the performance of the super-resolution processing by the receiving apparatus, a conversion property extraction apparatus generates image conversion associated information to support the super-resolution processing. Then, a connection apparatus transmits the converted image signal and the image conversion associated information to the receiving apparatus.
摘要翻译：要解决的问题：提供一种在输入图像信号上进行分辨率提高时能够通过增加分辨率提高所需的参考信息而充分提取用于提高分辨率的性能的装置。解决方案：根据实施例，图像转换装置生成转换的图像信号，并且经由重复装置将转换的图像信号发送到接收装置。接收装置对所接收的转换图像信号进行恢复处理和超分辨率处理，从而获得具有改善的分辨率的高分辨率图像信号。为了降低重复装置的容量，图像转换装置通过处理原始图像信号来获得转换的图像信号。为了提高接收装置的超分辨率处理的性能，转换特性提取装置生成图像转换相关信息以支持超分辨率处理。然后，连接装置将转换的图像信号和图像转换相关信息发送到接收装置。版权所有（C）2013，JPO＆INPIT

34. 发明专利

JP2011258144A Image photographing device, image correction processing method and image correction processing program 审中-公开
标题翻译：图像摄影装置，图像校正处理方法和图像校正处理程序
公开(公告)号：JP2011258144A
公开(公告)日：2011-12-22
申请号：JP2010134440
申请日：2010-06-11
申请人： Toshiba Corp , 株式会社東芝
发明人： SATO TOSHIO , AOKI YASUHIRO , YAMAGUCHI OSAMU
IPC分类号： G06T5/00 , H04N5/225
摘要： PROBLEM TO BE SOLVED: To photograph an image to be photographed clearly through a polarization filter.SOLUTION: An image photographing device comprises a polarization filter 11 for passing only predetermined light of a polarization direction, an image input part 12 for photographing a person in a vehicle through the polarization filter 11 and a windshield 3 by setting the windshield part of the vehicle as a visual field range, a luminance measurement part 14 for determining at least an average luminance from a distribution of a luminance value measured from a photographic image photographed, a correction parameter calculation part 15 for calculating an image correction parameter based on the average luminance determined by the luminance measurement part 14 and an image correction processing part 16 for converting the luminance value of the image data photographed at the image input part based on the image correction parameter.
摘要翻译：要解决的问题：通过偏振过滤器清晰地拍摄要拍摄的图像。解决方案：图像拍摄装置包括仅偏振方向的预定光的偏振滤光器11，用于通过偏振滤光器11和挡风玻璃3拍摄车辆中的人物的图像输入部12，通过将挡风玻璃部分作为视场范围的亮度测量部14，用于根据从拍摄的照片图像测量的亮度值的分布来确定至少平均亮度的亮度测量部14，用于基于所述图像校正参数计算图像校正参数的校正参数计算部15 由亮度测量部分14确定的平均亮度和用于基于图像校正参数转换在图像输入部分拍摄的图像数据的亮度值的图像校正处理部分16。版权所有（C）2012，JPO＆INPIT

35. 发明专利

JP2011103696A Image compressing method and image compressing apparatus 审中-公开
标题翻译：图像压缩方法和图像压缩装置
公开(公告)号：JP2011103696A
公开(公告)日：2011-05-26
申请号：JP2011028605
申请日：2011-02-14
申请人： Toshiba Corp , 株式会社東芝
发明人： HASEBE KOI , IRIE BUNPEI , AKAGI TAKUMA , SATO TOSHIO , SUKEGAWA HIROSHI
IPC分类号： H04N1/41
摘要： PROBLEM TO BE SOLVED: To provide an image compressing method and apparatus, improving compression efficiency in encoding processing while having redundancy.
SOLUTION: An image compressing method for performing compression processing on an image including a recognition object, inputs the image including the recognition object, performs predetermined filter processing on the input image to acquire an intermediate value within a filter, compares the acquired intermediate value with a current pixel-of-interest value, performs smoothing processing by performing no processing on a pixel of interest if a difference between both values is equal to or more than a predetermined threshold, or implementing processing for replacing the current pixel-of-interest value with the acquired intermediate value repeatedly until the pixel of interest targets all pixels if the difference is less than the threshold, and also performs variable-length coding on the smoothed image in accordance with a frequency of occurrence.
COPYRIGHT: (C)2011,JPO&INPIT
摘要翻译：要解决的问题：提供一种图像压缩方法和装置，提高编码处理的压缩效率，同时具有冗余性。解决方案：一种用于对包括识别对象的图像执行压缩处理的图像压缩方法，输入包括识别对象的图像，对输入图像执行预定的滤波处理以获取滤波器内的中间值，将获取的中间值具有当前像素的值的值，如果两个值之间的差等于或大于预定阈值，则执行对感兴趣的像素的处理，或者执行用于替换当前像素的值的处理，利用所获取的中间值的重要值直到感兴趣像素针对所有像素为止，如果差小于阈值，并且还根据发生频率对平滑图像执行可变长度编码。版权所有（C）2011，JPO＆INPIT

36. 发明专利

JP2010086403A Facial recognition device, facial recognition method, and passage controller 审中-公开
标题翻译：面部识别装置，面部识别方法和通话控制器
公开(公告)号：JP2010086403A
公开(公告)日：2010-04-15
申请号：JP2008256487
申请日：2008-10-01
申请人： Toshiba Corp , 株式会社東芝
发明人： SUKEGAWA HIROSHI , SATO TOSHIO
IPC分类号： G06T7/00 , G06F21/20 , G06T1/00
摘要： PROBLEM TO BE SOLVED: To provide a facial recognition device, a facial recognition method and a passage controller, capable of recognizing a person with high accuracy, in a short time. SOLUTION: This facial recognition device 100 is provided with a registration information storage means 108 for preliminarily storing registration information, and an image input means 102A for consecutively enterinh images, including at least the face of the person. The facial recognition device detects a facial area of the person from among the consecutive images entered from the image input means, in each image. The facial recognition device determines the presence of a recognition intention of the person, based on the position and the size of the face area detected in each image. The facial recognition device selects either of the first collation system for conducting collation, based on the plurality of detected facial area images and the registration information stored by the registration information storage means, or the second collation system for conducting collation based on at least one of the detected facial area images and the registration information stored by the registration information storage means, and determines whether the person is one who has registered in advance. COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：提供能够在短时间内高精度地识别人的面部识别装置，面部识别方法和通过控制器。解决方案：该面部识别装置100设置有用于预先存储登记信息的登记信息存储装置108，以及用于连续地输入至少包含人脸的图像输入装置102A。面部识别装置从每个图像中从图像输入装置输入的连续图像中检测人的面部区域。面部识别装置基于在每个图像中检测到的面部区域的位置和大小来确定人的识别意图的存在。面部识别装置基于多个检测到的面部区域图像和由登记信息存储装置存储的登记信息或第二对照系统，基于以下各项中的至少一个来选择第一对照系统进行排序：检测到的面部区域图像和由登记信息存储装置存储的登记信息，并且确定该人是否是预先登记的人。版权所有（C）2010，JPO＆INPIT

37. 发明专利

JP2006202209A Image compression method and image compression device 审中-公开
标题翻译：图像压缩方法和图像压缩装置
公开(公告)号：JP2006202209A
公开(公告)日：2006-08-03
申请号：JP2005015629
申请日：2005-01-24
申请人： Toshiba Corp , 株式会社東芝
发明人： HASEBE KOI , IRIE BUNPEI , AKAGI TAKUMA , SATO TOSHIO , SUKEGAWA HIROSHI
IPC分类号： G06T5/20 , G06T5/00 , G06T7/00 , H04N1/41 , H04N19/102 , H04N19/136 , H04N19/167 , H04N19/172 , H04N19/182 , H04N19/196 , H04N19/20 , H04N19/50 , H04N19/503 , H04N19/593 , H04N19/80 , H04N19/91
CPC分类号： H04N19/80 , G06K9/00234 , H04N1/40062 , H04N19/85
摘要： PROBLEM TO BE SOLVED: To provide an image compression method and an image compression device that can increase compression efficiency by coding by ensuring redundancy. SOLUTION: The image compression method for compressing an image including a recognition object inputs an image including a recognition object, applies predetermined filtering to the input image to acquire a median in the filter, compares the acquired median and a pixel value of current interest and, if their difference is not smaller than a predetermined threshold, keeps the pixel of interest unprocessed, or if not, replaces the pixel value of current interest with the acquired median as smoothing, and applies variable length coding depending on the frequency of appearance to the smoothed image. COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：提供一种图像压缩方法和图像压缩装置，其可以通过确保冗余来编码来提高压缩效率。解决方案：用于压缩包括识别对象的图像的图像压缩方法输入包括识别对象的图像，对输入图像应用预定滤波以获取滤波器中的中值，将获取的中值和当前的像素值进行比较并且如果它们的差异不小于预定阈值，则保持感兴趣的像素未被处理，或者如果不是，则将所获取的中值的当前兴趣的像素值替换为平滑，并且根据外观的频率应用可变长度编码到平滑的图像。版权所有（C）2006，JPO＆NCIPI

38. 发明专利

JP2004265231A Face picture recording system and method 审中-公开
公开(公告)号：JP2004265231A
公开(公告)日：2004-09-24
申请号：JP2003056188
申请日：2003-03-03
申请人： Toshiba Corp , 株式会社東芝
发明人： OKAZAKI AKIO , SATO TOSHIO , YOKOI KENTAROU , SUKEGAWA HIROSHI , OGATA ATSUSHI
IPC分类号： G06T7/00 , G06F15/00 , G06F21/20 , G06T1/00
摘要： PROBLEM TO BE SOLVED: To allow a monitor to determine "pretending" in each input terminal in real time, and a guard can report it. SOLUTION: This system is provided to photograph the face image of a user identified by ID identification based on ID information inputted by the user in an input terminal 2, and to verify the identity of the user by a face recording server 3 according to face collation using the face image. COPYRIGHT: (C)2004,JPO&NCIPI

39. 发明专利

JP2000182115A PAPER SHEETS STATE IDENTIFYING DEVICE, PAPER SHEETS STAIN STATE IDENTIFYING DEVICE, PAPER SHEETS PRINT STATE IDENTIFYING DEVICE AND PAPER SHEETS SURFACE AND REAR IDENTIFYING DEVICE 失效
公开(公告)号：JP2000182115A
公开(公告)日：2000-06-30
申请号：JP36278798
申请日：1998-12-21
申请人： TOSHIBA CORP
发明人： YUGE AKIO , TAKAHASHI HISASHI , SUDA MASATO , SAITO TSUTOMU , SATO TOSHIO , NAGAAI KAZUMICHI , WATANABE SATOSHI , TAKIZAWA KEI , HASHIYA KAZUYO , MIURA JUNJI
IPC分类号： G06T1/00 , G06T7/00 , G07D7/00
摘要： PROBLEM TO BE SOLVED: To consider even the deterioration of a print state when the state of paper sheets on which a prescribed image is printed is identified by deciding the whole stain condition except the stain condition of printed area based on the mean value of density values of each pixel in density data except the printed area extracted by an extracting means. SOLUTION: A printed area extracting part 3 extracts the density data of an object stored in an image memory 2 and outputs it to a printing ink quantity measuring part 5. Also, an unprinted area extracting part 4 extracts image data in the area other than preliminarily decided printed area from the density data stored in the memory 2 and outputs it to a doodle measuring part 8 and a whole stain measuring part 10. The part 5 measures printing ink quantity according to image data in a printed area, and a printed state deterioration condition deciding part 6 decides the deterioration level of a printed state based on the printing ink quantity. Also, stain condition deciding parts 9 and 11 decide respective stain condition levels according to measured results by the parts 8 and 10.

40. 发明专利

JPH07198626A PRINTING APPARATUS 失效
公开(公告)号：JPH07198626A
公开(公告)日：1995-08-01
申请号：JP35418093
申请日：1993-12-28
申请人： TOSHIBA CORP
发明人： SATO TOSHIO , KUBOTA HIROAKI
IPC分类号： G01N21/89 , B41J29/393 , G01N21/88 , G01N21/892 , G01N21/93 , G06K15/00 , G06T1/00 , G07D7/00 , G07D7/06 , G07D7/20 , H04N1/00 , G06T7/00
摘要： PURPOSE:To perform printing while good prints are selected correctly and without lowering the processing time by collecting determiner's final determination oven on prints containing a very small defect or a light defect, the test processing of which can not be determined. CONSTITUTION:A paper sheet P is taken out to a transport mechanism 123, and a pattern is printed on the paper sheet P in a printing part 102. In printing, image data is input in an image input part 103 to be compared with standard data in a print testing part 109. The compared image data is sent to data display parts 116, 117, 118 at need to determine whether it is good or bad through a determination input parts 119, 120, 121. The determination resulti s sent to a select mechanism 106 for selecting a print, and a bad print P is removed.

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