会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 101. 发明专利
    • Vehicle type discrimination device
    • 车辆类型识别装置
    • JP2013148971A
    • 2013-08-01
    • JP2012007235
    • 2012-01-17
    • Oki Electric Ind Co Ltd沖電気工業株式会社
    • NISHIMURA TADASHIWATANABE TAKAMITSUWATANABE TAKAHIRO
    • G08G1/015G01B11/02G01B11/24G06T1/00
    • G06K9/78G06K9/52G06K2209/23G06T7/62G06T2207/30236G08G1/015
    • PROBLEM TO BE SOLVED: To provide technology for improving accuracy of vehicle type discrimination.SOLUTION: There is provided a vehicle type discrimination device 10A which includes: a detection part 112A which detects a grounding point, a first end point, the lowest ground point, a second endpoint, and an upper endpoint of a vehicle on the imaging surface on the basis of a vehicle area to be extracted from a pick up image; a vehicle width estimation part 113 which estimates vehicle width in a real space on the basis of the grounding point, the first endpoint, and the lowest ground point; a vehicle length estimation part 114A which estimates vehicle length in the real space on the basis of the grounding point, the first endpoint, and the second endpoint; a vehicle height estimation part 115A which estimates vehicle height in the real space on the basis of the grounding point, the first endpoint, and the upper endpoint; and a vehicle type discrimination part 116 which discriminates a type of the vehicle on the basis of the vehicle width, the vehicle length, and the vehicle height.
    • 要解决的问题:提供用于提高车辆识别精度的技术。解决方案:提供一种车辆识别装置10A,其包括:检测部112A,其检测接地点,第一端点,最低接地点, 基于要从拾取图像中提取的车辆区域,在成像表面上的车辆的第二端点和上端点; 基于接地点,第一端点和最低地面点估计实际空间中的车辆宽度的车辆宽度估计部件113; 基于接地点,第一端点和第二端点来估计实际空间中的车辆长度的车辆长度估计部114A; 基于接地点,第一端点和上端点来估计实际空间中的车辆高度的车辆高度估计部分115A; 以及基于车辆宽度,车辆长度和车辆高度来区分车辆的类型的车辆类型识别部分116。
    • 102. 发明专利
    • Vehicle detection device
    • 车辆检测装置
    • JP2013037394A
    • 2013-02-21
    • JP2011170307
    • 2011-08-03
    • Toshiba Corp株式会社東芝
    • AOKI YASUHIROSATO TOSHIOTAKAHASHI YUSUKE
    • G08G1/04G01B11/00G06T1/00
    • G08G1/123G01B11/002G01C11/06G06K9/00201G06K9/00664G06K9/3275G06K2209/23G06T7/593G06T7/75G06T2207/10012G06T2207/30236G08G1/0175
    • PROBLEM TO BE SOLVED: To improve detection precision for a vehicle by determining feature points to be associated among a plurality of images, and making a positioning standard clear.SOLUTION: A vehicle detection device includes segment component extraction means, polygon approximation means, and measurement means. The segment component extraction means extracts a plurality of segment components indicative of a border between a windshield area and a vehicle body of a vehicle included in each of right and left photographed images. The polygon approximation means approximates a polygon forming a closed loop using some of the plurality of extracted segment components for each of the right and left photographed images. The measurement means positions the segment components forming the closed loop for each of the right and left photographed images with each other between the right and left photographed images, and measures the position of the closed loop as a position of the vehicle based upon coordinate information between the positioned segment components and the photographed position where the right and left photographed images are photographed.
    • 要解决的问题:通过确定要在多个图像中相关联的特征点,并且使得定位标准清楚,来提高车辆的检测精度。 解决方案:车辆检测装置包括段分量提取装置,多边形近似装置和测量装置。 段分量提取装置提取表示包含在右拍摄图像和左拍摄图像中的车辆的挡风玻璃区域和车身之间的边界的多个段成分。 多边形近似装置近似于使用左右拍摄图像中的每一个的多个提取的段分量中的一些来形成闭环的多边形。 测量装置将形成闭环的分段成分定位在左和左拍摄图像之间彼此的左右拍摄图像中的每一个,并且基于车辆位置之间的坐标信息来测量闭环的位置 定位的片段成分和拍摄右侧和左侧拍摄的图像的拍摄位置。 版权所有(C)2013,JPO&INPIT
    • 105. 发明专利
    • Image processing device and image processing method
    • 图像处理设备和图像处理方法
    • JP2011170893A
    • 2011-09-01
    • JP2011126246
    • 2011-06-06
    • Panasonic Corpパナソニック株式会社
    • WU GANGRYU IKETSUXIE XIAOHUIGI KYO
    • G06T7/60
    • G06K9/4633G06T7/0004G06T2207/10032G06T2207/30108G06T2207/30184G06T2207/30236
    • PROBLEM TO BE SOLVED: To provide an image processing device capable of high-speed detection of a specific shape from an image.
      SOLUTION: In the image processing device, a candidate position calculation section (106) obtains a first candidate position of the center point of a first circle in contact at three points with three sides contained in the shape of an object to be detected from a given image. An angle calculation section (106) obtains an angle formed by a normal line drawn from the three sides to the first candidate position and a standard line oriented in a fixed direction and passing a point at which the normal line and each of the three sides cross. A relative relationship calculation section (106) obtains a relationship of the angle relative to the first candidate position. A recognition section (108) recognizes the shape contained in the given image based on the relative relationship of the angle and a relative relationship of a shape stored in advance.
      COPYRIGHT: (C)2011,JPO&INPIT
    • 要解决的问题:提供能够从图像高速检测特定形状的图像处理装置。 解决方案:在图像处理装置中,候选位置计算部(106)在三个点处获得接触的第一圆的中心点的第一候选位置,三个点包含在待检测对象的形状中 从给定的图像。 角度计算部(106)获得由从三面到第一候选位置的法线形成的角度和沿固定方向取向的标准线,并且通过三条线中的每条交叉的法线 。 相对关系计算部(106)获得与第一候选位置的角度的关系。 识别部(108)基于角度的相对关系和预先存储的形状的相对关系来识别包含在给定图像中的形状。 版权所有(C)2011,JPO&INPIT
    • 106. 发明专利
    • Image processor
    • 图像处理器
    • JP2010039634A
    • 2010-02-18
    • JP2008199905
    • 2008-08-01
    • Toyota Motor Corpトヨタ自動車株式会社
    • UCHIDA NAOHIDE
    • G06T7/20G06T1/00
    • G06T7/269G06T2207/10016G06T2207/20012G06T2207/30236
    • PROBLEM TO BE SOLVED: To provide an image processor for improving calculation precision for an optical flow when calculating the optical flow in window units. SOLUTION: The image processor calculates the optical flow based on image information in the window regarding an object to be processed by using a plurality of images which are picked up at different time points. In this case, the image processor is provided with a position acquiring means for acquiring the position information for the object to be processed and a setting means for setting the size of the window for calculating the optical flow based on the position information which is obtained at the position acquiring means. COPYRIGHT: (C)2010,JPO&INPIT
    • 要解决的问题:提供一种用于在计算窗口单位中的光流时提高光流的计算精度的图像处理器。 解决方案:图像处理器通过使用在不同时间点拾取的多个图像,基于窗口中关于待处理对象的图像信息来计算光流。 在这种情况下,图像处理器设置有位置获取装置,用于获取要处理的对象的位置信息,以及设置装置,用于基于位置信息来设置用于计算光流量的窗口的尺寸,该位置信息是 位置获取装置。 版权所有(C)2010,JPO&INPIT
    • 107. 发明专利
    • Device and method for object detection
    • 用于物体检测的装置和方法
    • JP2009198445A
    • 2009-09-03
    • JP2008043109
    • 2008-02-25
    • Toshiba Corp株式会社東芝
    • NAKANO TAKESHIKUBOTA SUSUMUOKAMOTO KYOICHI
    • G01B11/00G01P3/36G06T1/00H04N5/225H04N5/232
    • G06K9/00785G06T7/248G06T2207/10021G06T2207/30236
    • PROBLEM TO BE SOLVED: To detect an object robustly when it has influence of change of lighting or weather, or to detect a motion information, such as position and speed or the like of the object with sufficient accuracy, by the method of calculating three-dimensional coordinate of the object of pedestrian, bicycle or the like and detecting the object from information on height, and asking for parallax image using correlation operation for image acquired from stereo camera attached in pillar or the like which exists in road. SOLUTION: A processing area established according to position and height of the object and arrangement of stereo camera is established plurally for acquired image. The object of pedestrian, bicycle or the like is detected by applying the method using a principle of a plane projection stereo method for every established processing area. The object of whole image is detected by unifying the object detection result for every processing area. The motion information, such as position, speed or the like is detected by tracking the detected object sequentially. COPYRIGHT: (C)2009,JPO&INPIT
    • 要解决的问题:当其受到照明或天气变化的影响时,可以鲁棒地检测物体,或者通过以下方法检测物体的位置和速度等运动信息,即, 计算行人,自行车等的物体的三维坐标,并根据高度信息检测物体,并且使用相关操作对由道路中存在的立柱等附接的立体摄像机获得的图像进行相关操作。 解决方案:根据物体的位置和高度建立的处理区域和立体摄像机的布置被多次建立用于获取的图像。 通过对于每个建立的处理区域应用使用平面投影立体声方法的原理的方法来检测行人,自行车等的对象。 通过统一每个处理区域的对象检测结果来检测整个图像的对象。 通过依次跟踪检测到的物体来检测位置,速度等运动信息。 版权所有(C)2009,JPO&INPIT
    • 108. 发明专利
    • Tracking method and apparatus of the moving object in the image
    • 空值
    • JP4217876B2
    • 2009-02-04
    • JP2002371047
    • 2002-12-20
    • 財団法人生産技術研究奨励会
    • 俊介 上條正夫 坂内
    • H04N7/18G06T7/20
    • G06K9/3241G06K9/00785G06K2209/23G06T7/231G06T2207/10016G06T2207/30236
    • To track moving objects in a smaller number of temporarily stored time-series pictures, regarding N consecutive pictures (N≥2) within the time-series pictures, a method comprises the steps of: (a) by assigning the same ID to adjacent blocks if the absolute value of the difference between motion vectors of the blocks are less than a predetermined value, assigning different IDs to moving objects overlapping in a picture; (b) judging whether or not a first object of a first block group assigned a first ID and a second object of a second block group assigned a second ID are in contact with each other in each of the N consecutive pictures, and further each correlation between the first objects of temporally adjacent pictures in the N consecutive pictures is more than or equal to a predetermined value; and (c) tracking the first and second objects backward in time after the judgment at step (b) is positive.
    • 为了跟踪在较短数量的临时存储的时间序列图像中的运动对象,关于时间序列图像内的N个连续图像(N≥2),一种方法包括以下步骤:(a)通过将相同的ID分配给相邻块 如果块的运动矢量之间的差的绝对值小于预定值,则向图像中重叠的移动物体分配不同的ID; (b)判断分配有第一ID的第一块组的第一对象和被分配了第二ID的第二块组的第二对象是否在N个连续画面的每一个中彼此接触,并且进一步的每个相关性 在N个连续图像中的时间上相邻的图像的第一对象之间大于或等于预定值; 和(c)在步骤(b)的判断之后,在时间上向后追踪第一和第二物体是正的。
    • 110. 发明专利
    • Method and processor for processing image including moving object
    • 用于处理包含运动对象的图像的方法和处理器
    • JP2003006655A
    • 2003-01-10
    • JP2001187502
    • 2001-06-21
    • Fujitsu LtdKatsushi IkeuchiMasao Sakauchi正夫 坂内富士通株式会社克史 池内
    • KAMIJO SHUNSUKESAKAUCHI MASAOIKEUCHI KATSUSHI
    • G06T1/00G06K9/00G06T7/00G06T7/20G08G1/00G08G1/04G08G1/16H04N5/14H04N7/18H04N9/47H04N9/64
    • G06K9/00785G06K9/00335G06K9/00711G06T7/20G06T7/231G06T2207/10016G06T2207/30236G08G1/04G08G1/164
    • PROBLEM TO BE SOLVED: To more exactly automatically detect a collision accident.
      SOLUTION: In an observation quantity detecting part 26, the feature amount of relative action between moving objects is detected as an observation quantity and the time sequence of such observation quantities is stored in a storage part 27 as an observation sequence. In a classification part 28, the similarity of the observation sequence to a predetermined collision observation sequence is calculated. When the similarity is greater than a setting value, a moving object related to this similarity is stopped in a stop inhibition area set in a storage part 30 and another moving object is moved, a decision part 29 decides a collision accident and when collision decision conditions are satisfied except for the similarity, a moving object fault is decided. By including not only a first scalar resulting from quantizing the vector of relative speed between moving objects but also a second scalar resulting from quantizing the vector of relative position between moving objects as an observation quantity, the relative action between the moving objects is more precisely classified. In a moving object tracking part 25, the moving objects, which are tracked for the unit of a block and overlapped on an image, are identified.
      COPYRIGHT: (C)2003,JPO
    • 要解决的问题:更准确地自动检测碰撞事故。 解决方案:在观察量检测部分26中,检测移动物体之间的相对作用的特征量作为观察量,并且将这种观察量的时间顺序作为观察序列存储在存储部分27中。 在分类部分28中,计算观察序列与预定碰撞观测序列的相似度。 当相似度大于设定值时,与存储部30中设定的停止禁止区域中移动与该相似度有关的移动体停止,另一移动体移动,判定部29判定碰撞事故,碰撞判定条件 除了相似性之外,确定了移动物体故障。 通过不仅包括量化移动物体之间的相对速度的向量而产生的第一标量,而且还包括通过量化移动物体之间的相对位置的矢量作为观察量而产生的第二标量,更精确地分类移动物体之间的相对作用 。 在运动物体跟踪部分25中,识别为块的单位跟踪并重叠在图像上的移动物体。