公开(公告)号：US20170001564A1

公开(公告)日：2017-01-05

申请号：US15197126

申请日：2016-06-29

Applicant: MAGNETI MARELLI S.p.A.

Inventor： Denis BOLLEA ,  Gabriele LINI ,  Paolo PASTERIS ,  Paolo ZANI ,  Marco PATANDER

IPC: B60R1/00 ,  G06K9/00

CPC classification number: B60R1/00 ,  B60R2300/103 ,  B60R2300/301 ,  B60R2300/302 ,  G06K9/00791 ,  G06K9/00805 ,  G06K9/00818 ,  G06K9/00825 ,  G06K9/3233 ,  G08G1/09623 ,  G08G1/165 ,  G08G1/166

Abstract: A system for detection of objects in an environment surrounding the vehicle including: at least one image capture device arranged for acquiring images representative of a region of observation in the environment surrounding the vehicle; a map of a road network; and a device for positioning the vehicle within the road network. A predetermined number of road segments of the road network downstream of the determined position of the vehicle and the attributes associated therewith constitute an electronic horizon of the vehicle. An electronic processing unit is connected to the image capture device and arranged for selecting an area of the image acquired by the image capture device as a function of the electronic horizon of the vehicle. The selected area being representative of a region of interest of the region of observation. The electronic processing unit is arranged for detecting predetermined elements of interest within the region of interest.

Abstract translation: 一种用于在车辆周围的环境中检测物体的系统，包括：至少一个图像捕获装置，被布置成用于获取代表在车辆周围的环境中的观察区域的图像; 道路网的地图; 以及用于将车辆定位在道路网内的装置。 在车辆的确定位置下游的道路网络的预定数量的道路段和与其相关联的属性构成车辆的电子水平线。 电子处理单元连接到图像捕获装置，并且被布置为根据车辆的电子视野来选择由图像捕获装置获取的图像的区域。 所选区域代表观察区域的感兴趣区域。 电子处理单元被布置成用于检测感兴趣区域内的感兴趣的预定元素。

公开(公告)号：US20170116488A1

公开(公告)日：2017-04-27

申请号：US15299518

申请日：2016-10-21

Applicant: Magneti Marelli S.p.A.

Inventor： Marco PATANDER ,  Denis BOLLEA ,  Paolo ZANI

IPC: G06K9/00 ,  B60R11/04 ,  B60R1/00 ,  G06K9/62 ,  G06K9/46

CPC classification number: G06K9/00805 ,  B60R1/00 ,  B60R11/04 ,  B60R2011/004 ,  B60R2300/105 ,  B60R2300/303 ,  B63C9/1255 ,  B63C11/08 ,  B63C11/2245 ,  B63C2009/133 ,  G06K9/00825 ,  G06K9/4604 ,  G06K9/6269

Abstract: Method for identifying an incoming vehicle on the basis of images acquired by one or more video-cameras mounted on a vehicle, comprising processing the images in order to identify light spots corresponding to the vehicle lamps, including performing a multi-scale processing procedure to extract bright spots areas from the images and maximum values of the bright spots areas. The method includes tracking positive regions corresponding to the bright spots and independently tracking the bright spots themselves. The tracking of the positive regions is preceded by a classification procedure including generating candidate regions to be classified, and training multiple classifiers, depending on an aspect ratio of the candidate region.