公开(公告)号：US20150117652A1

公开(公告)日：2015-04-30

申请号：US14404500

申请日：2012-05-31

申请人： Jun Sato ,  Ryuji Funayama ,  Tomoya Takatani ,  Toshiki Kindo ,  Hideo Fukamachi

发明人： Jun Sato ,  Ryuji Funayama ,  Tomoya Takatani ,  Toshiki Kindo ,  Hideo Fukamachi

IPC分类号： H04R29/00 ,  G10K11/00

CPC分类号： H04R29/00 ,  G10K11/002 ,  G10L21/0216 ,  G10L21/0232 ,  G10L25/78 ,  G10L2021/02166

摘要： Disclosed is a noise model generation device that generates a noise model suitable for each environment by determining whether an sound source of a detection target is included in sound information collected by an sound collector with high accuracy. The noise model generation device generates a noise model relating to noise information other than the sound source of the detection target included in the sound information collected by the sound collector, which acquires a power spectrum from the sound information; determines whether the sound source of the detection target is included in the sound information collected by evaluating a probability density distribution (histogram) of the power spectrum; and generates a noise model from the collected sound information when it is determined that the sound source of the detection target is not included in the collected sound information.

摘要翻译： 公开了一种噪声模型生成装置，其通过确定检测对象的声源是否被包含在由收集器以高精度收集的声音信息中，从而生成适合于每个环境的噪声模型。 噪声模型生成装置生成与声音收集器收集的声音信息中包含的检测对象的声源以外的噪声信息相关的噪声模型，该声音信息从声音信息获取功率谱; 通过评估功率谱的概率密度分布（直方图）来确定检测对象的声源是否包含在收集的声音信息中; 并且当确定检测目标的声源不包括在所收集的声音信息中时，从所收集的声音信息中产生噪声模型。

公开(公告)号：US20140219505A1

公开(公告)日：2014-08-07

申请号：US14346015

申请日：2011-09-20

申请人： Toshiki Kindo ,  Masahiro Ogawa ,  Ryuji Funayama

发明人： Toshiki Kindo ,  Masahiro Ogawa ,  Ryuji Funayama

IPC分类号： G06K9/00

CPC分类号： G06K9/00369 ,  B60W2420/40 ,  B60W2550/10 ,  G06K9/00342 ,  G06K9/00348 ,  G06K9/00805 ,  G08G1/08 ,  G08G1/166

摘要： According to the present invention, a pedestrian is detected from an imaged image and a partial image including the pedestrian is extracted, shape information of the pedestrian acquired from the extracted partial image is accumulated and the shape information of a predetermined time before and the current shape information are compared using the accumulated shape information to detect change in the movement of the pedestrian, discontinuous movement estimating information indicating a discontinuous movement of the pedestrian that occurs following the change in the movement of the pedestrian is acquired from a storage means at the time the change in the movement of the pedestrian is detected, and a behavior of the pedestrian is predicted using the acquired discontinuous movement estimating information.

摘要翻译： 根据本发明，从拍摄图像中检测行人，并且提取包括行人的部分图像，并且累积从所提取的部分图像获取的行人的形状信息，并且预定时间的形状信息和当前形状 使用累积的形状信息来比较信息，以检测行人的移动的变化，从存储装置获取表示行人的改变之后发生的行人的不连续运动的不连续运动估计信息， 检测到行人的移动的变化，并且使用获取的不连续运动估计信息来预测行人的行为。

公开(公告)号：US09373042B2

公开(公告)日：2016-06-21

申请号：US14346062

申请日：2011-09-20

申请人： Masahiro Ogawa ,  Toshiki Kindo ,  Ryuji Funayama ,  Akio Fukamachi

发明人： Masahiro Ogawa ,  Toshiki Kindo ,  Ryuji Funayama ,  Akio Fukamachi

IPC分类号： G06K9/00 ,  G08G1/16 ,  G06K9/46

CPC分类号： G06K9/00791 ,  B60W2420/40 ,  B60W2550/10 ,  G06K9/00335 ,  G06K9/00348 ,  G06K9/00805 ,  G06K9/4604 ,  G06K9/4671 ,  G08G1/166

摘要： The invention detects a change in a subject by detecting the subject from an image, acquiring a feature quantity distribution that indicates shape information of the detected subject, accumulating the shape information that is indicated by the acquired feature quantity distribution and comparing the shape information a predetermined period of time before with the current shape information by using the accumulated shape information. Here, the invention acquires the feature quantity distribution of the subject from a processing target area extracted from an image area that includes the subject. The invention detects a change in the subject by using accumulated shape change information acquired from the shape information. The invention detects a change in the subject by using averaged shape change information obtained by averaging the shape change information.

摘要翻译： 本发明通过从图像中检测对象来检测被摄体的变化，获取表示被检测对象的形状信息的特征量分布，累积由获取的特征量分布指示的形状信息，并将形状信息与规定的 通过使用累积的形状信息与当前形状信息之间的时间段。 这里，本发明从从包括被摄体的图像区域提取的处理目标区域中获取被摄体的特征量分布。 本发明通过使用从形状信息获取的累积形状变化信息来检测被摄体的变化。 本发明通过使用通过对形状变化信息进行平均而获得的平均形状变化信息来检测被摄体的变化。

公开(公告)号：US09904846B2

公开(公告)日：2018-02-27

申请号：US14346015

申请日：2011-09-20

申请人： Toshiki Kindo ,  Masahiro Ogawa ,  Ryuji Funayama

发明人： Toshiki Kindo ,  Masahiro Ogawa ,  Ryuji Funayama

IPC分类号： G06K9/00 ,  G08G1/08 ,  G08G1/16

CPC分类号： G06K9/00369 ,  B60W2420/40 ,  B60W2550/10 ,  G06K9/00342 ,  G06K9/00348 ,  G06K9/00805 ,  G08G1/08 ,  G08G1/166

摘要： According to the present invention, a pedestrian is detected from an imaged image and a partial image including the pedestrian is extracted, shape information of the pedestrian acquired from the extracted partial image is accumulated and the shape information of a predetermined time before and the current shape information are compared using the accumulated shape information to detect change in the movement of the pedestrian, discontinuous movement estimating information indicating a discontinuous movement of the pedestrian that occurs following the change in the movement of the pedestrian is acquired from a storage means at the time the change in the movement of the pedestrian is detected, and a behavior of the pedestrian is predicted using the acquired discontinuous movement estimating information.

公开(公告)号：US09507998B2

公开(公告)日：2016-11-29

申请号：US14125862

申请日：2011-06-13

申请人： Masahiro Ogawa ,  Toshiki Kindo ,  Ryuji Funayama ,  Tadaaki Sakamoto

发明人： Masahiro Ogawa ,  Toshiki Kindo ,  Ryuji Funayama ,  Tadaaki Sakamoto

IPC分类号： G06K9/00 ,  G08G1/16 ,  G06T7/20

CPC分类号： G06K9/00348 ,  G06T7/20 ,  G08G1/166

摘要： A subject is to provide a pedestrian motion predicting device capable of accurately predicting a possibility of a rush out before a pedestrian actually begins to rush out. According to the embodiments, the pedestrian is detected from input image data, a portion in which the detected pedestrian is imaged is cut out from the image data, a shape of the pedestrian imaged in the cut-out partial image data is classified by collating the shape with a learning-finished identifier group or a pedestrian recognition template group, and the rush out of the pedestrian is predicted based on a result of the acquired classification.

摘要翻译： 主题是提供一种行人运动预测装置，其能够在行人实际开始冲出之前准确地预测出车的可能性。 根据实施例，从输入图像数据中检测步行者，从图像数据切出检测到的行人被拍摄的部分，通过将切出的部分图像数据中成像的行人的形状进行分类， 形状与学习完成的标识符组或行人识别模板组，并且基于获取的分类的结果来预测行人的冲出。

公开(公告)号：US20150049908A1

公开(公告)日：2015-02-19

申请号：US14346062

申请日：2011-09-20

申请人： Masahiro Ogawa ,  Toshiki Kindo ,  Ryuji Funayama ,  Akio Fukamachi

发明人： Masahiro Ogawa ,  Toshiki Kindo ,  Ryuji Funayama ,  Akio Fukamachi

IPC分类号： G06K9/00 ,  G06K9/46

CPC分类号： G06K9/00791 ,  B60W2420/40 ,  B60W2550/10 ,  G06K9/00335 ,  G06K9/00348 ,  G06K9/00805 ,  G06K9/4604 ,  G06K9/4671 ,  G08G1/166

摘要： The invention detects a change in a subject by detecting the subject from an image, acquiring a feature quantity distribution that indicates shape information of the detected subject, accumulating the shape information that is indicated by the acquired feature quantity distribution and comparing the shape information a predetermined period of time before with the current shape information by using the accumulated shape information. Here, the invention acquires the feature quantity distribution of the subject from a processing target area extracted from an image area that includes the subject. The invention detects a change in the subject by using accumulated shape change information acquired from the shape information. The invention detects a change in the subject by using averaged shape change information obtained by averaging the shape change information.

摘要翻译： 本发明通过从图像中检测对象来检测被摄体的变化，获取表示被检测对象的形状信息的特征量分布，累积由获取的特征量分布指示的形状信息，并将形状信息与规定的 通过使用累积的形状信息与当前形状信息之间的时间段。 这里，本发明从从包括被摄体的图像区域提取的处理目标区域中获取被摄体的特征量分布。 本发明通过使用从形状信息获取的累积形状变化信息来检测被摄体的变化。 本发明通过使用通过对形状变化信息进行平均而获得的平均形状变化信息来检测被摄体的变化。

公开(公告)号：US20140112538A1

公开(公告)日：2014-04-24

申请号：US14125862

申请日：2011-06-13

申请人： Masahiro Ogawa ,  Toshiki Kindo ,  Ryuji Funayama ,  Tadaaki Sakamoto

发明人： Masahiro Ogawa ,  Toshiki Kindo ,  Ryuji Funayama ,  Tadaaki Sakamoto

IPC分类号： G06K9/00 ,  G06T7/20

CPC分类号： G06K9/00348 ,  G06T7/20 ,  G08G1/166

摘要： A subject is to provide a pedestrian motion predicting device capable of accurately predicting a possibility of a rush out before a pedestrian actually begins to rush out. According to the embodiments, the pedestrian is detected from input image data, a portion in which the detected pedestrian is imaged is cut out from the image data, a shape of the pedestrian imaged in the cut-out partial image data is classified by collating the shape with a learning-finished identifier group or a pedestrian recognition template group, and the rush out of the pedestrian is predicted based on a result of the acquired classification.

摘要翻译： 主题是提供一种行人运动预测装置，其能够在行人实际开始冲出之前准确地预测冲出的可能性。 根据实施例，从输入图像数据中检测步行者，从图像数据切出检测到的行人被拍摄的部分，通过将切出的部分图像数据中成像的行人的形状进行分类， 形状与学习完成的标识符组或行人识别模板组，并且基于获取的分类的结果来预测行人的冲出。

公开(公告)号：US20120113412A1

公开(公告)日：2012-05-10

申请号：US13322056

申请日：2009-05-29

申请人： Shinya Kawamata ,  Ryuji Funayama ,  Yasuhiro Yoshida ,  Yasukata Yokochi ,  Masato Endo ,  Toshiki Kindo ,  Kenichi Kitahama

发明人： Shinya Kawamata ,  Ryuji Funayama ,  Yasuhiro Yoshida ,  Yasukata Yokochi ,  Masato Endo ,  Toshiki Kindo ,  Kenichi Kitahama

IPC分类号： G01J3/28

CPC分类号： G01J3/2803 ,  G01J1/4204 ,  G01J3/02 ,  G01J3/0289

摘要： Provided is a moveable spectrum measuring apparatus capable of improving discrimination precision of a measuring object on the basis of observation data from a spectrum sensor mounted on a movable apparatus such as a vehicle. A measuring object and a reference body are irradiated with ambient light. A spectrum acquiring device acquires measuring object data indicating the spectrum of the measuring object, and reference body data indicating the spectrum of the reference body to become a reference at the time when the spectrum of the measuring object is corrected. A spectrum converting device has reference body reflectivity data indicating the surface reflectivity of the reference body, and creates ambient light data indicating the spectrum of the ambient light, on the basis of the reference body reflectivity data and the reference body data. By using the ambient light data, the measuring object data is converted into measuring object reflectivity data indicating the surface reflectivity of the measuring object. On the basis of the measuring object reflectivity data, a discrimination device discriminates the measuring object.

摘要翻译： 提供了一种可移动的频谱测量装置，其能够基于来自安装在诸如车辆的可移动装置的频谱传感器的观察数据来改善测量对象的辨别精度。 用环境光照射测量对象和参考体。 频谱获取装置获取指示测量对象的频谱的测量对象数据和指示在校正测量对象的频谱时参考的参考体的频谱的参考主体数据。 频谱转换装置具有指示参考体的表面反射率的参考体反射率数据，并且基于参考体反射率数据和参考体数据创建指示环境光的光谱的环境光数据。 通过使用环境光数据，将测量对象数据转换为指示测量对象的表面反射率的测量对象反射率数据。 基于测量对象反射率数据，判别装置鉴别测量对象。

公开(公告)号：US09277339B2

公开(公告)日：2016-03-01

申请号：US14360564

申请日：2011-11-24

申请人： Hideo Fukamachi ,  Toshiki Kindo

发明人： Hideo Fukamachi ,  Toshiki Kindo

IPC分类号： H04R29/00 ,  H04R3/00 ,  G06F17/11 ,  G01S13/93 ,  G01S3/808

CPC分类号： H04R29/00 ,  G01S3/8083 ,  G01S13/93

摘要： In a sound source detection apparatus that detects a sound source of a detection subject on the basis of collected sounds, sounds are collected by at least one sound collector, an autocorrelation between sounds collected in time series by the sound collector is calculated, and a determination as to whether or not the sound source of the detection subject exists is made on the basis of the autocorrelation. More particularly, sounds are preferably collected respectively by two or more sound collectors such that the existence of the sound source of the detection subject is determined by determining whether or not the autocorrelations of the sounds collected by the two or more sound collectors satisfy a predetermined condition. By using the autocorrelation to detect the sound source of the detection subject in this manner, high robustness against an S/N ratio is exhibited, leading to an improved detection performance when detecting the sound source of the detection subject.

摘要翻译： 在根据收集的声音检测检测对象的声源的声源检测装置中，由至少一个声音收集器收集声音，计算由收集器以时间序列收集的声音之间的自相关性，并且确定 关于是否存在检测对象的声源是否基于自相关来进行。 更具体地，声音优选地由两个或更多个收集器分别收集，使得通过确定由两个或更多个收集器收集的声音的自相关是否满足预定条件来确定检测对象的声源的存在 。 通过使用自相关法以这种方式检测检测对象的声源，表现出相对于S / N比的高鲁棒性，导致检测被检测者的声源时的检测性能提高。

公开(公告)号：US09601020B2

公开(公告)日：2017-03-21

申请号：US13877337

申请日：2010-10-05

申请人： Kazuaki Aso ,  Toshiki Kindo ,  Katsuhiro Sakai ,  Masahiro Harada

发明人： Kazuaki Aso ,  Toshiki Kindo ,  Katsuhiro Sakai ,  Masahiro Harada

IPC分类号： G08G1/16 ,  B60W30/095

CPC分类号： G08G1/166 ,  B60W30/0953 ,  B60W30/0956 ,  G08G1/161

摘要： A collision determination device determines the possibility of collision between a host vehicle and the other object on the basis of a shortest arrival time calculated by a shortest arrival time calculation unit and a passage time at each point of the host vehicle acquired by a vehicle route candidate acquisition unit. In this way, even if a locus to be taken by the other object is not generated, the shortest arrival time at which the other object can arrive at each point of the route candidate of the host vehicle with a predetermined first displacement is calculated, thereby determining the possibility of collision between the host vehicle and the other object. Therefore, it is possible to reduce a computational load for determining collision and to accurately determine collision between the host vehicle and the other object.