公开(公告)号：US20150258936A1

公开(公告)日：2015-09-17

申请号：US14643072

申请日：2015-03-10

Applicant: DENSO CORPORATION

Inventor： Masanari TAKAKI

IPC: B60R1/00 ,  H04N5/232 ,  G06K9/00 ,  G06T7/00

CPC classification number: B60R1/00 ,  B60R2300/303 ,  B60R2300/607 ,  G06T3/4038 ,  H04N5/23238

Abstract: In a composite image generation apparatus that is mounted in an own vehicle, each of captured images, which have been captured by a plurality of imaging units, are acquired. A disturbance level for each of the plurality of captured images that have been acquired is determined. The disturbance level indicates: whether or not a disturbance is present in the captured image; or an extent of the disturbance. In an overlapping area in which imaging areas of the plurality of captured images overlap, one or more captured images is selected from the plurality of captured images so that the area occupied by a captured image having a higher disturbance level among the plurality captured images is smaller. A composite image is generated based on the plurality of captured images. In the overlapping area, the composite image is generated by using the captured image selected based on the disturbance level.

Abstract translation: 在安装在本车辆中的复合图像生成装置中，获取已经被多个摄像单元拍摄的拍摄图像。 确定已经获取的多个捕获图像中的每一个的干扰电平。 扰动等级表示：拍摄图像中是否存在干扰; 或干扰程度。 在多个拍摄图像的成像区域重叠的重叠区域中，从多个拍摄图像中选择一个或多个拍摄图像，使得在多个拍摄图像中具有较高干扰电平的拍摄图像占据的面积较小 。 基于多个拍摄图像生成合成图像。 在重叠区域中，通过使用基于干扰电平选择的拍摄图像来生成合成图像。

公开(公告)号：US20240280667A1

公开(公告)日：2024-08-22

申请号：US18421447

申请日：2024-01-24

Applicant: DENSO CORPORATION ,  TOYOTA JIDOSHA KABUSHIKI KAISHA ,  MIRISE Technologies Corporation

Inventor： Masanari TAKAKI

IPC: G01S7/40 ,  G01S13/58 ,  G01S13/931

CPC classification number: G01S7/4021 ,  G01S13/582 ,  G01S13/931 ,  G01S13/589

Abstract: A radar signal processing device includes an acquirer, pre-segment generator, and a segment generator. The acquirer acqu.ires ranging point information including position information and speed information at each of ranging points obtained by irradiating radar waves. The pre-segment generator generates a pre-segment by grouping the ranging points as a set of the ranging points based on the acquired ranging point information from the acquirer. The segment generator generates a composite segment by combining the ranging points from a first pre-segment with the ranging points from a second pre-segment as a set of the ranging points based on a positional relationship between the first pre-segment and the second pre-segment. The first pre-segment is one of pre-segments generated by the pre-segment generator. The second pre-segment is another one of the pre-segments generated by the pre-segment generator.

公开(公告)号：US20150332101A1

公开(公告)日：2015-11-19

申请号：US14698952

申请日：2015-04-29

Applicant: DENSO CORPORATION

Inventor： Masanari TAKAKI ,  Kenji KOBAYASHI

IPC: G06K9/00 ,  B60R1/00 ,  H04N7/18

CPC classification number: B60R1/00 ,  B60R2300/105 ,  B60R2300/301 ,  B60R2300/804 ,  B60T7/22 ,  B60T2201/08 ,  B60T2201/089 ,  G06K9/00798 ,  G08G1/167 ,  H04N7/183

Abstract: A boundary line recognition apparatus receives detection results transmitted from camera devices and a laser radar device performing different optical detection methods. These detection results indicate information regarding a lane boundary line of a vehicle lane on a roadway on which an own vehicle drives. The apparatus further obtains surrounding environmental information of the own vehicle on the roadway, and selects at least one of the camera devices and the laser radar device suitable for correctly recognizing the lane boundary line on the basis of the environmental information. The apparatus finally recognizes the lane boundary line with high accuracy on the basis of the detection result transmitted form one or more devices selected based on the environment information.

Abstract translation: 边界线识别装置接收从相机装置发送的检测结果和执行不同光学检测方法的激光雷达装置。 这些检测结果表示关于本车辆驱动的道路上的车道的车道边界线的信息。 该装置进一步获取道路上的本车辆的周围环境信息，并根据环境信息选择适合于正确识别车道边界线的照相机装置和激光雷达装置中的至少一个。 基于从基于环境信息选择的一个或多个设备发送的检测结果，该设备最终以高精度识别车道边界线。

公开(公告)号：US20150103173A1

公开(公告)日：2015-04-16

申请号：US14499485

申请日：2014-09-29

Applicant: DENSO CORPORATION

Inventor： Masanari TAKAKI

IPC: B60R11/04 ,  G06K9/00

CPC classification number: B60R11/04 ,  B60R1/00 ,  B60R2300/105 ,  B60R2300/303 ,  B60R2300/605 ,  B60R2300/607 ,  G06K9/00798

Abstract: In a synthesized image generation device, an image processing section receives acquired images transmitted from in-vehicle cameras, and selects some of the acquired images having different image acquiring regions which are not overlapped with each other. The image processing section generates synthesized image data on the basis of the selected acquired images. This avoids a process of cutting a predetermined image area from the acquired images during the generation of the synthesized image data as a bird's eye view. It is possible for the image processing section to prevent a part of a clear acquired image from being cut and eliminated even if the clear acquired image and unclear acquired image are selected simultaneously and combined, and extract road markings from the synthesized image data with high accuracy.

Abstract translation: 在合成图像生成装置中，图像处理部接收从车载摄像机发送的获取图像，并且选择具有不相互重叠的不同图像获取区域的一些获取图像。 图像处理部根据所选取得的图像生成合成图像数据。 这避免了在合成图像数据的生成期间将所获取的图像作为鸟瞰图切割预定图像区域的处理。 即使同时选择清晰获取的图像和不清楚的获取图像并且组合，图像处理部分也可以防止清除所获取的图像的一部分被切割和消除，并且从合成图像数据中提取高精度的道路标记 。