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
    • 1. 发明专利
    • 画像処理装置および画像処理方法
    • 图像处理装置和图像处理方法
    • JP2014232439A
    • 2014-12-11
    • JP2013113156
    • 2013-05-29
    • 日産自動車株式会社Nissan Motor Co Ltd
    • ABDELAZIZ KHIATSHIMOMURA TOMOKO
    • G06T7/60G06T1/00G08G1/16
    • 【課題】消失点を適切に検出することが可能な画像処理装置を提供する。【解決手段】自車両の進行方向を撮像し、撮像した像に対応する撮像画像を出力する撮像手段10と、撮像画像内に複数の検出領域を設定し、該検出領域で方向成分を検出するとともに、検出した方向成分に対して所定のカウント値をそれぞれ出力する方向成分検出手段20と、方向成分のカウント値を方向成分の検出方向ごとにカウントすることで、方向成分のヒストグラムを検出領域ごとに生成する生成手段20と、方向成分のヒストグラムがピークとなる方向に沿って、消失点が存在する可能性を評価するため評価領域を設定することで、撮像画像内に複数の評価領域を設定する評価領域設定手段20と、撮像画像内の座標位置のうち評価領域が最も重複している座標位置を消失点として検出する消失点検出手段20と、を備えることを特徴とする画像処理装置。【選択図】図1
    • 要解决的问题:提供一种被配置为适当地检测消失点的图像处理装置。解决方案:图像处理装置包括:成像装置10,其捕获车辆行进方向上的图像,并输出与图像相对应的拾取图像 捕获; 方向分量检测装置20,其设置拾取图像中的多个检测区域,检测检测区域中的方向分量,并输出用于方向分量的预定计数值; 生成装置20,其通过对方向分量的每个检测方向上的方向分量的计数值进行计数来生成每个检测区域的方向分量的直方图; 评估区域设置装置20,其设置用于评估消失点存在的可能性的评估区域沿着方向分量的直方图的峰值方向,以设置拾取图像中的多个评估区域; 以及消除点检测装置20,其检测评估区域最重叠的拾取图像中的坐标位置作为消失点。
    • 2. 发明专利
    • Road surface determination method and road surface determination device
    • 道路表面测定方法和道路表面测定装置
    • JP2008158958A
    • 2008-07-10
    • JP2006349778
    • 2006-12-26
    • Nissan Motor Co Ltd日産自動車株式会社
    • SHIMOMURA TOMOKO
    • G08G1/00B60R1/00G06T1/00G06T7/00H04N7/18
    • PROBLEM TO BE SOLVED: To determine a road surface or a three-dimensional object existing in a pick-up image, even when a segment of high edge intensity is not detected in the pick-up image.
      SOLUTION: A segment retrieval part 21 retrieves a segment whose edge intensity is equal to a prescribed threshold value or more, in the pick-up image, a feature amount calculation part 22 sets an area in obtained by removing the retrieved segment from the pick-up image, as an objective area, calculates a feature amount of the objective area, and specifies a division of the objective area referring to a learning table showing a relation between the feature amount and the prescribed division, based on the calculated feature amount, and a classification determination part 23 determines whether the peripheral road surface state, belongs to a travel road surface, a road surface outside the travel road, or the three-dimensional object.
      COPYRIGHT: (C)2008,JPO&INPIT
    • 要解决的问题:即使在拾取图像中没有检测到高边缘强度的段,也可以确定拾取图像中存在的路面或三维物体。 解决方案:段检索部分21检索边缘强度等于或大于预定阈值的段,特征量计算部分22将拾取的段中的区域设置为 拾取图像作为目标区域,计算目标区域的特征量,并且基于计算出的特征来指定表示特征量与规定分割之间的关系的学习表的目标区域的划分 量,分类确定部23判断周边路面状态是属于行驶路面,行驶路外行驶路面还是三维物体。 版权所有(C)2008,JPO&INPIT
    • 4. 发明专利
    • Object detection method and object detector
    • 对象检测方法和对象检测器
    • JP2007255979A
    • 2007-10-04
    • JP2006078486
    • 2006-03-22
    • Nissan Motor Co Ltd日産自動車株式会社
    • SHIMOMURA TOMOKO
    • G01S13/93G01S13/86G08G1/16
    • PROBLEM TO BE SOLVED: To provide an object detector with its object detection accuracy enhanced without using any special device for obtaining external environmental information. SOLUTION: This object detector is equipped with a control unit CU for detecting an object based on information obtained from a camera 1 and a radar 2. The control unit CU includes an external environment detection processing part 13 for detecting an external environment based on image information and detection information. The control unit CU reflects a determination result of the processing part 13 in object detection. COPYRIGHT: (C)2008,JPO&INPIT
    • 要解决的问题:提供一种物体检测器,其物体检测精度提高,而不需要使用任何特殊装置来获得外部环境信息。 解决方案:该对象检测器配备有用于基于从照相机1和雷达2获得的信息来检测物体的控制单元CU。控制单元CU包括用于基于外部环境检测的外部环境检测处理部分13 关于图像信息和检测信息。 控制单元CU在物体检测中反映处理部13的确定结果。 版权所有(C)2008,JPO&INPIT
    • 5. 发明专利
    • Object type determination device and object type determination method
    • 对象类型确定设备和对象类型确定方法
    • JP2007156626A
    • 2007-06-21
    • JP2005348059
    • 2005-12-01
    • Nissan Motor Co Ltd日産自動車株式会社
    • SHIMOMURA TOMOKO
    • G06T7/00B60R21/00G06T1/00G06T7/60G08G1/16
    • PROBLEM TO BE SOLVED: To allow determination of an object including a lot of slant lines or curves to determine the type of the object appearing in an image photographed by a camera with high accuracy. SOLUTION: The image photographed by the camera 1 is taken in an image processor 2, and various types of image processing are performed to determine the type of the object appearing in the photographic image of the camera 1. During the above process, the image processor 2 specifies an area wherein the object is present in the photographic image of the camera 1 as a processing target area by an area specification part 11, finds an edge direction or an edge intensity of each edge component inside the processing target area by an edge component analysis part 12, and determines the type of the object present in the processing target area by use of information such as a distribution of the edge intensity or the edge direction of each the edge component inside the processing target area by a determination part 13. COPYRIGHT: (C)2007,JPO&INPIT
    • 要解决的问题:允许确定包括大量倾斜线或曲线的对象以确定出现在由相机拍摄的图像中的物体的类型高精度。 解决方案:将照相机1拍摄的图像拍摄到图像处理器2中,并且执行各种类型的图像处理以确定出现在相机1的摄影图像中的对象的类型。在上述处理期间, 图像处理器2通过区域指定部分11指定在相机1的摄影图像中存在的物体作为处理目标区域的区域,通过在边缘方向或处理目标区域内的每个边缘分量的边缘强度找到边缘方向或边缘强度 边缘分量分析部分12,并且通过使用诸如处理目标区域内的每个边缘分量的边缘强度或边缘方向的分布的信息由确定部分确定处理对象区域中存在的对象的类型 13.版权所有(C)2007,JPO&INPIT
    • 6. 发明专利
    • Lighting apparatus and method for vehicle
    • 车辆用照明装置及方法
    • JP2007076378A
    • 2007-03-29
    • JP2005262690
    • 2005-09-09
    • Nissan Motor Co Ltd日産自動車株式会社
    • ARAGAKI YOHEISHIMOMURA TOMOKO
    • B60Q1/02
    • PROBLEM TO BE SOLVED: To provide a lighting device for a vehicle, lighting the direction of an area detected as having the possibility that a pedestrian may exist or appear therein. SOLUTION: The lighting device for vehicle includes: an infrared ray radiation camera 11 for acquiring a thermal image around a vehicle; a feature amount extracting part 131 which extracts a feature amount in the image from the acquired thermal image; a feature amount distribution calculation part 132 for acquiring distribution of the extracted feature amount; and a moving object presence possibility area extracting part 133 which extracts an area which has a high possibility that the moving object, such as the pedestrian may exist or appear from the distribution of the acquired feature amount, thus irradiating the light from a site lighting part in such a direction of the area in which the moving object may exist or appear. COPYRIGHT: (C)2007,JPO&INPIT
    • 要解决的问题:为了提供一种用于车辆的照明装置,照亮检测到的具有行人可能存在或出现的可能性的区域的方向。 解决方案:车辆照明装置包括:红外线辐射照相机11,用于获取车辆周围的热图像; 特征量提取部131,其从获取的热图像中提取图像中的特征量; 特征量分布计算部132,用于获取提取的特征量的分布; 以及移动对象存在可能性区域提取部133,其从所获取的特征量的分布中提取出可能存在或出现诸如行人的移动物体的可能性高的区域,从而照射来自场地照明部分 在移动物体可能存在或出现的区域的方向上。 版权所有(C)2007,JPO&INPIT
    • 7. 发明专利
    • Image processing apparatus and noise detecting method
    • 图像处理装置和噪声检测方法
    • JP2006314061A
    • 2006-11-16
    • JP2005136636
    • 2005-05-09
    • Nissan Motor Co Ltd日産自動車株式会社
    • SHIMOMURA TOMOKO
    • H04N1/409G06T5/00
    • PROBLEM TO BE SOLVED: To provide a technology for evaluating images and a camera with a simple configuration by evaluating noise included in the images without the need for provision of a particular configuration. SOLUTION: A prescribed image processing is applied to the image imaged by the camera to decide a degree of noise by each image region included in the image, and image regions whose degree of noise is a prescribed threshold or over are detected (steps S3, S4). Then the number of noise detection times in the image regions is summated (step S5), the image regions of which the number of noise detection times is a prescribed value or over are decided to include noise whose reliability at a position in the image is low (step S6), and the processes in the steps S1 to S6 are respectively applied to a plurality of images temporally consecutively imaged. Thus, positions of the noise in the images included in the image regions of which the number of noise detection times counted over a plurality of images is more than the prescribed value are detected (step S7), and the performance of the camera or the images are evaluated on the basis of the positions of the noise in the image (step S8). COPYRIGHT: (C)2007,JPO&INPIT
    • 要解决的问题:通过评估图像中包含的噪声,而不需要提供特定配置,提供用于通过简单配置来评估图像和相机的技术。 解决方案:对由摄像机成像的图像应用规定的图像处理,以确定图像中包括的每个图像区域的噪声程度,并且检测其噪声程度是规定阈值或以上的图像区域(步骤 S3,S4)。 然后,对图像区域中的噪声检测次数进行求和(步骤S5),将噪声检测次数为规定值以上的图像区域确定为包括图像中的位置的可靠性低的噪声 (步骤S6),并且步骤S1至S6中的处理分别应用于时间上连续成像的多个图像。 因此,检测包括在多个图像中计数的噪声检测次数多于其规定值的图像区域中的图像中的噪声位置(步骤S7),以及相机或图像的性能 基于图像中的噪声的位置进行评估(步骤S8)。 版权所有(C)2007,JPO&INPIT
    • 8. 发明专利
    • Image processing apparatus and noise detecting method
    • 图像处理装置和噪声检测方法
    • JP2006314060A
    • 2006-11-16
    • JP2005136628
    • 2005-05-09
    • Nissan Motor Co Ltd日産自動車株式会社
    • SHIMOMURA TOMOKO
    • H04N1/409G06T5/00
    • PROBLEM TO BE SOLVED: To provide an image processing apparatus and a noise detecting method capable of eliminating noise appearing at fixed positions with respect to a camera. SOLUTION: In the case of using an image imaged by the camera and detecting an object imaged by the camera, a prescribed image processing is applied to the image imaged by the camera to decide a degree of noise by each image region included in the image, and image regions whose degree of noise is a prescribed threshold or over are detected (steps S3, S4). Then the number of noise detection times in the image regions is summated (step S5), the image regions of which the number of noise detection times is a prescribed value or over are decided to include noise whose reliability at a position in the image is low (step S6). Then the processes in the steps S1 to S6 are respectively applied to a plurality of images temporally consecutively imaged. Thus, in a step S7, positions of the noise in the images included in the image regions of which the number of noise detection times counted over a plurality of images is more than the prescribed value can be detected. COPYRIGHT: (C)2007,JPO&INPIT
    • 要解决的问题:提供能够消除相对于照相机在固定位置出现的噪声的图像处理装置和噪声检测方法。 解决方案:在使用由相机成像的图像并检测由相机拍摄的物体的情况下,将规定的图像处理应用于由相机成像的图像,以通过包括在相机中的每个图像区域来确定噪声的程度 检测图像和噪声程度为规定阈值以上的图像区域(步骤S3,S4)。 然后,对图像区域中的噪声检测次数进行求和(步骤S5),将噪声检测次数为规定值以上的图像区域确定为包括图像中的位置的可靠性低的噪声 (步骤S6)。 然后,将步骤S1至S6中的处理分别应用于时间上连续成像的多个图像。 因此,在步骤S7中,可以检测在多个图像中计数的噪声检测次数多于规定值的图像区域中包含的图像中的噪声位置。 版权所有(C)2007,JPO&INPIT
    • 10. 发明专利
    • Threshold value setting device and method
    • 阈值设置装置和方法
    • JP2005128776A
    • 2005-05-19
    • JP2003363468
    • 2003-10-23
    • Nissan Motor Co Ltd日産自動車株式会社
    • ARAGAKI YOHEISHIMOMURA TOMOKO
    • B60R1/00G08G1/16
    • PROBLEM TO BE SOLVED: To provide a threshold setting device and a threshold value setting method, capable of more accurately extracting a person area.
      SOLUTION: This threshold setting device 1 has: a camera 10 for acquiring a thermal image A having a state amount data value around a vehicle; a histogram generation part 12 for generating a histogram showing relation between a thermal data value and a degree of the thermal data value on the basis of the thermal image A acquired by the camera 10; a characteristic amount calculation part 13 for calculating a characteristic amount including a maximum point and an inflection pint of the histogram on the basis of the histogram generated by the histogram generation part 12; a threshold value setting part 15 for setting a threshold value showing a range of the thermal data value of a person on the basis of peripheral environment of the vehicle, and the characteristic amount calculated by the characteristic amount calculation part 13; and an area extraction part 17 for extracting the person area having the thermal data value within the range shown by the threshold value set by the threshold value setting part 15, from the thermal image A acquired by the camera 10.
      COPYRIGHT: (C)2005,JPO&NCIPI
    • 要解决的问题:提供能够更准确地提取人员区域的阈值设定装置和阈值设定方法。

      解决方案:该阈值设定装置1具有:摄像机10,用于获取具有车辆周围的状态量数据值的热图像A; 直方图生成部分12,用于基于由照相机10获取的热图像A生成表示热数据值与热数据值的关系的直方图; 特征量计算部13,用于基于由直方图生成部12生成的直方图来计算包括直方图的最大点和拐点的特征量; 阈值设定部15,其基于车辆的周边环境设定表示人物的热量数据值的范围的阈值和由特征量计算部13计算出的特征量; 以及区域提取部17,用于从由照相机10获取的热图像A中提取具有由阈值设定部15设定的阈值所示的范围内的热量数据值的人物区域。

      COPYRIGHT :(( C)2005,JPO&NCIPI