公开(公告)号：US20220406032A1

公开(公告)日：2022-12-22

申请号：US17777207

申请日：2020-11-13

Applicant: DENSO WAVE INCORPORATED ,  DENSO IT LABORATORY, INC.

Inventor： Yusuke SEKIKAWA ,  Yang SHI

IPC: G06V10/60 ,  G06V10/98 ,  G06T5/00 ,  G06T7/20

Abstract: The image restoration device has an initialization block that initializes the luminance value of each pixel coordinate to an intermediate value in the luminance array list that stores one of a pair of polarity values and intermediate values as the luminance value for each pixel coordinate. The image restoration device also has an update block that updates the initialized luminance array list according to the pixel coordinates and polarity values for each event, and an output block that outputs the luminance array list updated by the update block over the shooting period as a binary image. By the update performed in the update block, the luminance values of the firing coordinates where the event fired in the luminance array list are overwritten by the polarity values of the event. In addition, the update preserves the luminance values of the non-firing coordinates in the luminance array list, excluding the firing coordinates.

公开(公告)号：US11521057B2

公开(公告)日：2022-12-06

申请号：US15795691

申请日：2017-10-27

Applicant: DENSO IT LABORATORY, INC. ,  Tokyo Institute of Technology

Inventor： Ikuro Sato ,  Ryo Fujisaki ,  Akihiro Nomura ,  Yosuke Oyama ,  Satoshi Matsuoka

IPC: G06N3/08 ,  G06F17/10 ,  G06N3/04

Abstract: According to one embodiment of the present disclosure, provided is a learning system that updates a parameter for a neural network, the learning system including: a plurality of differential value calculators; and a parameter update module.

公开(公告)号：US09449505B2

公开(公告)日：2016-09-20

申请号：US13795610

申请日：2013-03-12

Applicant: DENSO IT LABORATORY, INC.

Inventor： Osamu Masutani

IPC: G08G1/00 ,  G08G1/01

CPC classification number: G08G1/00 ,  G08G1/0112 ,  G08G1/0133 ,  G08G1/0141 ,  G08G1/0145

Abstract: Provided is a traffic congestion prediction method which is able to perform a prediction process using floating information with higher accuracy. The traffic congestion prediction method includes: a step of receiving information by a prediction device; a step of predicting a route of each floating car based on the current position information and destination information received; a step of calculating, for the each floating car, a first passing time group which is a set of respective passing times at a plurality of predetermined spots on the route predicted; a step of calculating the number of existing floating cars per link based on the first passing time group, if any of a plurality of floating cars exists on the link at a predetermined time; and a step of calculating a second passing time group by use of the number of existing floating cars and a predetermined calculation technique.

Abstract translation: 提供了能够以更高精度执行使用浮动信息的预测处理的交通拥堵预测方法。 交通拥堵预测方法包括：通过预测装置接收信息的步骤; 基于接收到的当前位置信息和目的地信息来预测每个浮动车辆的路线的步骤; 对于每个浮动车计算作为预测路线上的多个预定点处的各个通过时间的集合的第一通过时间组的步骤; 如果在预定时间内在链路上存在多个浮动车辆中的任何一个，则基于第一通过时间组计算每个链路的现有浮动车辆的数量的步骤; 以及通过使用现有浮动车辆的数量和预定的计算技术来计算第二通过时间组的步骤。

公开(公告)号：US08775080B2

公开(公告)日：2014-07-08

申请号：US13430349

申请日：2012-03-26

Applicant: Nobuhiro Mizuno ,  Yasuhiro Shimizu

Inventor： Nobuhiro Mizuno ,  Yasuhiro Shimizu

IPC: G01C21/26 ,  G01C21/34

CPC classification number: G01C21/3492 ,  G01C21/3617

Abstract: An object of this invention is to improve the accuracy of estimating a destination in a destination estimating apparatus. A destination estimating apparatus 100 includes: a learning data storing unit 9b that stores a history of a location specified as a destination in the past; a destination estimating unit 83 that estimates a destination from among a plurality of destination candidates including a location stored in the learning data storing unit 9b; and a candidate excluding unit 84 that, based on the history stored in the learning data storing unit 9b, excludes a destination candidate for which it is determined that a certainty factor of being a destination is lower than a predetermined threshold value from destination candidates that are estimated as being a destination by the destination estimating unit 83.

Abstract translation: 本发明的目的是提高目的地估计装置中的目的地的估计精度。 目的地估计装置100包括：学习数据存储单元9b，其存储过去指定为目的地的位置的历史; 目的地估计单元83，其从包含存储在学习数据存储单元9b中的位置的多个目的地候选中估计目的地; 候选排除单元84，基于存储在学习数据存储单元9b中的历史，从目的地候选中排除确定作为目的地的确定性因子低于预定阈值的目的地候选， 被估计为目的地估计单元83的目的地。

公开(公告)号：US08352539B2

公开(公告)日：2013-01-08

申请号：US11885471

申请日：2005-03-03

Applicant: Nobuhiro Mizuno

Inventor： Nobuhiro Mizuno

IPC: G06F15/16 ,  G06F7/00

CPC classification number: G06F17/30861 ,  H04N7/17318 ,  H04N21/41422 ,  H04N21/6131 ,  H04N21/6181

Abstract: A technology that makes a program line-up related to contents distributed to a user side, depending on various conditions, preferences, and communication environments of the user side that views and listens to the content is disclosed. According to the technology, an on-board device (content receiving and reproducing device) 1 receives, from a service server 5, potential content list information of contents that can be distributed from a content server 7. The on-board device 1 sorts appropriate content from among the contents in the potential content list information and decide on a reproducing order of the contents, based on conditions of the user side, such as user preferences and vehicle conditions, conditions related to an environment on the user side, such as the communication environment, and conditions related to the contents, such as the genre of the content. The on-board device 1 creates program table information (timetable) and transmits the program table information to the content server. As a result, reception and reproduction of the contents from the content server can be performed in adherence to the program table information.

Abstract translation: 公开了一种技术，其使得与分发给用户侧的内容相关的节目阵容取决于观看和收听内容的用户侧的各种条件，偏好和通信环境。 根据该技术，车载设备（内容接收和再现设备）1从服务服务器5接收可从内容服务器7分发的内容的潜在内容列表信息。车载设备1适当地排序 从潜在内容列表信息中的内容中选择内容，并且基于用户侧的条件（诸如用户偏好和车辆条件），与用户侧的环境相关的条件，诸如 通信环境和与内容相关的条件，如内容的类型。 车载设备1创建节目表信息（时间表），并将节目表信息发送到内容服务器。 结果，可以根据节目表信息来执行来自内容服务器的内容的接收和再现。

公开(公告)号：US20120219212A1

公开(公告)日：2012-08-30

申请号：US13405716

申请日：2012-02-27

Applicant: Mitsuru ANBAI ,  Yuichi YOSHIDA

Inventor： Mitsuru ANBAI ,  Yuichi YOSHIDA

IPC: G06K9/62

CPC classification number: G06F17/30619

Abstract: A bit code converter transforms a learning feature vector using a transformation matrix updated by a transformation matrix update unit, and converts the transformed learning feature vector into a bit code. When the transformation matrix update unit substitutes a substitution candidate for an element of the transformation matrix, a cost function calculator fixes the substitution candidate that minimizes a cost function as the element. The transformation matrix update unit selects the element while sequentially changing the elements, and the cost function calculator fixes the selected element every time the transformation matrix update unit selects the element, thereby finally fixing the optimum transformation matrix. A substitution candidate specifying unit specifies the substitution candidate such that a speed of transformation processing that the bit code converter performs using the transformation matrix using the transformation matrix is enhanced based on a constraint condition stored in a constraint condition storage unit.

Abstract translation: 位代码转换器使用由变换矩阵更新单元更新的变换矩阵来变换学习特征向量，并将变换后的学习特征向量转换为位代码。 当变换矩阵更新单元将替代候选替换为变换矩阵的元素时，成本函数计算器将成本函数最小化的替代候选者固定为元素。 变换矩阵更新单元在顺序地改变元素的同时选择元素，并且每当变换矩阵更新单元选择元素时，成本函数计算器固定所选择的元素，从而最终确定最佳变换矩阵。 替代候选指定单元指定替换候选，使得基于存储在约束条件存储单元中的约束条件来增强使用变换矩阵的比特码转换器使用变换矩阵执行的变换处理的速度。

公开(公告)号：US07734415B2

公开(公告)日：2010-06-08

申请号：US11546566

申请日：2006-10-12

Applicant: Masanori Oumi ,  Takamitsu Suzuki ,  Hirotoshi Iwasaki ,  Kousuke Hara ,  Nobuhiro Mizuno

Inventor： Masanori Oumi ,  Takamitsu Suzuki ,  Hirotoshi Iwasaki ,  Kousuke Hara ,  Nobuhiro Mizuno

IPC: G01C21/30

CPC classification number: G01C21/3641

Abstract: When a vehicle deviates from a guide route at a first branch point, the state of the first branch point is memorized. Afterward, when a second branch point becomes a target for a route guide and the state of the second branch point is similar to the memorized state, a user of the vehicle is provided with a guide for preventing deviation from the guide route at the second branch point with a manner of the guide changed. This procedure allows learning of tendency of the user with respect to a state apt to cause the user to mistake a guide route. A guide to help prevent a user from deviating from a guide route at a branch point can be thus performed appropriately.

Abstract translation: 当车辆在第一分支点处偏离引导路线时，存储第一分支点的状态。 之后，当第二分支点成为路线导向件的目标物体并且第二分支点的状态与存储状态相似时，车辆用户设置有用于防止在第二分支处与引导路线偏离的引导件 指导方式改变了。 该过程允许学习用户相对于易于导致用户错误引导路线的状态的倾向。 因此可以适当地执行帮助防止用户在分支点偏离引导路线的指南。

公开(公告)号：US20080077321A1

公开(公告)日：2008-03-27

申请号：US11902785

申请日：2007-09-25

Applicant: Ari Widodo ,  Akira Yoshizawa ,  Yasutaka Yamauchi ,  Takeshi Matsui

Inventor： Ari Widodo ,  Akira Yoshizawa ,  Yasutaka Yamauchi ,  Takeshi Matsui

IPC: G01C21/30

CPC classification number: G01C21/32 ,  G01C21/3644

Abstract: An information provision apparatus (1) comprises an observed-object detection apparatus (11) and an information output unit (41), and outputs from the information output unit (41) information on an observed object detected by the observed-object detection apparatus (11). The observed-object detection apparatus (11) comprises: a line-of-sight detector (21) for detecting a line of sight of a driver; an object detector (22) for detecting an object which is on a line of sight of a driver, based on the direction of the line of sight detected by the line-of-sight detector (21), on a current position of a vehicle, and on map information; and an observed-object calculator (23) for determining from objects detected by the object detector (22) an observed object observed by a driver, based on time for which the object is on a line of sight. This allows an object observed by a driver to be detected even if there is no trigger from the driver.

Abstract translation: 信息提供装置（1）包括观察对象检测装置（11）和信息输出部（41），并且从信息输出部（41）输出由观察对象检测装置检测出的观察对象的信息（ 11）。 观察对象检测装置（11）包括：用于检测驾驶员的视线的视线检测器（21）; 用于基于由视线检测器（21）检测到的视线的方向，在车辆的当前位置上检测在驾驶员的视线上的物体的物体检测器（22） ，和地图信息; 以及观察对象计算器（23），用于基于对象检测器（22）检测到的对象，根据对象在视线上的时间来确定由驾驶员观察到的观察对象。 这允许即使没有来自驾驶员的触发来检测驾驶员观察到的物体。

公开(公告)号：US20070088502A1

公开(公告)日：2007-04-19

申请号：US11546566

申请日：2006-10-12

Applicant: Masanori Oumi ,  Takamitsu Suzuki ,  Hirotoshi Iwasaki ,  Kousuke Hara ,  Nobuhiro Mizuno

Inventor： Masanori Oumi ,  Takamitsu Suzuki ,  Hirotoshi Iwasaki ,  Kousuke Hara ,  Nobuhiro Mizuno

IPC: G01C21/32

CPC classification number: G01C21/3641

Abstract: When a vehicle deviates from a guide route at a first branch point, the state of the first branch point is memorized. Afterward, when a second branch point becomes a target for a route guide and the state of the second branch point is similar to the memorized state, a user of the vehicle is provided with a guide for preventing deviation from the guide route at the second branch point with a manner of the guide changed. This procedure allows learning of tendency of the user with respect to a state apt to cause the user to mistake a guide route. A guide to help prevent a user from deviating from a guide route at a branch point can be thus performed appropriately.

Abstract translation: 当车辆在第一分支点处偏离引导路线时，存储第一分支点的状态。 之后，当第二分支点成为路线导向件的目标物体并且第二分支点的状态与存储状态相似时，车辆用户设置有用于防止在第二分支处与引导路线偏离的引导件 指导方式改变了。 该过程允许学习用户相对于易于导致用户错误引导路线的状态的倾向。 因此可以适当地执行帮助防止用户在分支点偏离引导路线的指南。

公开(公告)号：US12136032B2

公开(公告)日：2024-11-05

申请号：US15812118

申请日：2017-11-14

Applicant: DENSO IT LABORATORY, INC.

Inventor： Jingo Adachi

IPC: G06N3/04 ,  G06F7/50 ,  G06N3/045 ,  G06N3/08 ,  G06N3/082 ,  G06N7/01 ,  G06F7/02

Abstract: A technique for stable and fast computation of a variance representing a confidence interval for an estimation result in an estimation apparatus using a neural network including an integrated layer that combines a dropout layer for dropping out part of input data and an FC layer for computing a weight is provided. When input data having a multivariate distribution is supplied to the integrated layer, a data analysis unit 30 determines, based on a numerical distribution of terms formed by respective products of each vector element of the input data and the weight, a data type of each vector element of output data from the integrated layer. An estimated confidence interval computation unit 20 applies an approximate computation method associated with the data type, to analytically compute a variance of each vector element of the output data from the integrated layer based on the input data to the integrated layer.