WO2020151560A1 - 一种车辆盲区检测方法、装置和系统 - Google Patents

一种车辆盲区检测方法、装置和系统 Download PDF

Info

Publication number
WO2020151560A1
WO2020151560A1 PCT/CN2020/072406 CN2020072406W WO2020151560A1 WO 2020151560 A1 WO2020151560 A1 WO 2020151560A1 CN 2020072406 W CN2020072406 W CN 2020072406W WO 2020151560 A1 WO2020151560 A1 WO 2020151560A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
information
vehicle
dangerous
dangerous area
Prior art date
Application number
PCT/CN2020/072406
Other languages
English (en)
French (fr)
Inventor
任实
Original Assignee
杭州海康汽车技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 杭州海康汽车技术有限公司 filed Critical 杭州海康汽车技术有限公司
Publication of WO2020151560A1 publication Critical patent/WO2020151560A1/zh

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60QARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
    • B60Q9/00Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
    • B60Q9/008Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling for anti-collision purposes
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60QARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
    • B60Q9/00Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling

Definitions

  • This application relates to the field of intelligent transportation technology, and in particular to a method, device, and system for detecting vehicle blind spots.
  • the blind spot detection method is generally as follows: capture images of blind spots in the visual field that cannot be observed by the side mirrors on both sides of the vehicle through cameras installed on both sides of the vehicle, and send the collected images to the cab for display, so that the driver can Understand the obstacle target in the blind zone of the visual field.
  • the present application provides a vehicle blind spot detection method, device and system.
  • the first aspect of the present application provides a vehicle blind spot detection method, including:
  • a target warning mode is determined, and the target warning mode is executed.
  • a second aspect of the present application provides a vehicle blind spot detection device, the device includes an acquisition module, an identification module, and a processing module; wherein,
  • the acquisition module is used to acquire images collected by image collection devices installed on both sides of the vehicle;
  • the recognition module is used to recognize the image
  • the acquisition module is further configured to acquire steering information of the vehicle when the identification module recognizes that there is a target in the designated detection area;
  • the processing module is configured to determine a target alarm mode according to the identified target information and the steering information of the target, and execute the target alarm mode.
  • the third aspect of the present application provides a vehicle blind spot detection system, including an image acquisition device and a processor, wherein:
  • the image acquisition equipment is installed on both sides of the vehicle and is used to acquire images
  • the processor is used for:
  • a target warning mode is determined, and the target warning mode is executed.
  • the vehicle blind spot detection method, device, and system provided in this application acquire images collected by image acquisition equipment installed on both sides of the vehicle, and recognize the above-mentioned images, and then acquire when a target is identified in a designated detection area
  • the steering information of the vehicle so as to determine the target warning mode based on the recognized target information and the steering information, and execute the target warning mode. In this way, the target in the blind area of the visual field can be autonomously monitored to improve the driver’s experience .
  • FIG. 1 is a flowchart of a vehicle blind spot detection method provided by an embodiment of the application
  • Fig. 2 is a schematic diagram of an installation position of an image acquisition device according to an exemplary embodiment of the application
  • FIG. 3 is a schematic diagram of a designated detection area shown in an exemplary embodiment of this application.
  • FIG. 4 is a flowchart of a method for detecting a vehicle blind spot provided by another embodiment of the application.
  • FIG. 5 is a schematic diagram of a designated dangerous area shown in an embodiment of the application.
  • FIG. 6 is a schematic structural diagram of a vehicle blind spot detection device provided by an embodiment of the application.
  • FIG. 7 is a schematic diagram of a vehicle blind spot detection system provided by an embodiment of the application.
  • first, second, third, etc. may be used in this application to describe various information, the information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other.
  • first information may also be referred to as second information, and similarly, the second information may also be referred to as first information.
  • word “if” as used herein can be interpreted as "when” or “when” or "in response to determination”.
  • This application provides a vehicle blind spot detection method, device and system to improve the driver's experience.
  • Fig. 1 is a flowchart of a vehicle blind spot detection method provided by an embodiment of the application.
  • the vehicle blind spot detection method provided in this embodiment may include:
  • FIG. 2 is a schematic diagram of the installation position of the image capture device shown in an exemplary embodiment of the application.
  • the image capture device is installed under the side mirrors on the left and right sides of the vehicle. ( Figure 2 only shows the image acquisition device installed on the right side of the vehicle), the front right field of view of the image acquisition device and the vehicle body angle are 120°.
  • Fig. 3 is a schematic diagram of a designated detection area shown in an exemplary embodiment of this application. Please refer to Figure 3.
  • the designated detection area is a pentagonal area surrounded by white lines.
  • the image collected by the image acquisition device on the right side of the vehicle is taken as an example to illustrate the designated detection area.
  • the detection area in the image is similar to the detection area in FIG. 3, and will not be repeated here.
  • the target refers to people, motor vehicles, non-motor vehicles, etc.
  • the target may also include animals such as cats and dogs.
  • the target information is information related to the target, which usually includes location information and category information.
  • the category information is used to characterize which preset category the target belongs to.
  • the preset category is set according to actual needs. For example, in an embodiment , Includes three preset categories, namely pedestrians, motor vehicles and non-motor vehicles.
  • the location information is the information about the location of the target, including the location information of the target in the image and the information about the actual location of the target relative to the vehicle.
  • the steering information of the vehicle can be acquired through the signal line of the vehicle body, and the steering information is transmitted between different components in the vehicle through the signal line of the vehicle.
  • the turning information of the vehicle may indicate that the vehicle has turning intention or no turning intention or is turning.
  • the steering information is operating information or status information of a component related to the steering operation of the vehicle, for example, a turn signal or a steering wheel.
  • the steering information may include that the vehicle turn signal is turned on or the steering wheel of the vehicle is turned and the turning angle exceeds a preset value.
  • the steering information may also include the turn signal is not turned on, the steering wheel is not turned by the driver, or the turning angle does not exceed a preset value (for example, the driver adjusts the position and orientation of the vehicle in the lane by slightly turning the steering wheel).
  • the above-mentioned signals indicating the switch state of the turn signal, the rotation state of the steering wheel, and the like may be transmitted via the signal line.
  • a preset value can indicate that the vehicle has turning intention or is turning, but the turn signal is not turned on, the steering wheel is not turned by the driver or is turned but the turning angle is not exceeded
  • the preset value, etc. may indicate that the vehicle has no intention to turn.
  • S103 Determine a target alarm mode based on the identified target information of the target and the steering information, and execute the target alarm mode.
  • the vehicle itself is provided with warning lights, buzzers, voice alarms, display screens and other devices dedicated to or used for alarm prompts.
  • the alarm modes supported by the vehicle may include the flashing or constant light of the warning light, the buzzer or voice alarm emitting an alarm sound, and the display of the warning text information on the display screen.
  • the target alarm mode is one or more alarm modes determined for the current situation.
  • the target warning mode is determined to be the second warning mode, and if the turning information indicates no turning intention, then Make sure not to call the police.
  • the category information in the above target information is a motor vehicle or a non-motor vehicle
  • the target warning mode is determined to be the first warning mode
  • the turning information indicates that there is no turning intention
  • the target is determined
  • the alarm mode is the second alarm mode.
  • the warning effect of the first alarm mode is higher than that of the second alarm mode.
  • the first alarm mode may be to activate an audible and visual alarm device (for example, the audible and visual alarm device may be a warning lamp and/or a buzzer), and the second alarm mode may be to output a text reminder message.
  • the first alarm mode may be outputting an icon, starting an indicator light, and outputting voice prompt information, and the second alarm mode may output an icon or starting an indicator light.
  • the vehicle blind spot detection method provided in this embodiment acquires images collected by image acquisition devices installed on both sides of the vehicle, and recognizes the above images, and then acquires the steering of the vehicle when the target is identified in the designated detection area. According to the target information of the identified target and the steering information, the target warning mode is determined, and the target warning mode is executed. In this way, the target in the blind zone can be independently monitored and the driver’s experience is improved.
  • FIG. 4 is a flowchart of a method for detecting a vehicle blind spot provided by another embodiment of the application.
  • the method provided in this embodiment determines the target alarm mode based on the identified target information and the turning information of the target, which may include:
  • S401 Determine whether the target is dangerous based on the target information.
  • the specific implementation process of this step may include:
  • the category information in the target information is the first category, determine whether the target is in the designated dangerous area according to the position information in the target information identified from the current frame image, and if so, determine If the target is in danger, if not, it is determined that the target is not in danger.
  • the category information in the target information is the second category, determine whether the target is close to the dangerous area according to the position information in the target information recognized from the current frame image and the previous frame image If yes, it is determined that the target is in danger, if not, it is determined whether the target is in the dangerous area according to the position information in the target information identified from the current frame image, and if so, it is determined that the target exists Danger, if not, it is determined that the target is not in danger.
  • the traveling speed of the first category is lower than the traveling speed of the second category.
  • the second category may be motor vehicles or non-motor vehicles, and the first category is pedestrians.
  • FIG. 5 is a schematic diagram of a designated dangerous area shown in an embodiment.
  • the designated dangerous area is a trapezoidal area surrounded by black lines.
  • the image collected by the image acquisition device on the right side of the vehicle is taken as an example to illustrate the designated dangerous area.
  • the dangerous area in the image is similar to the dangerous area in FIG. 5, and will not be repeated here.
  • the bottom center point of the target frame used to characterize the target can be obtained, and then it is determined whether the bottom center point is in the dangerous area, if so, it is determined that the target is in the dangerous area, otherwise it is determined The target is not in the danger zone.
  • the specific realization process of determining whether the target is close to the dangerous area according to the position information in the target information recognized from the current frame image and the previous frame image may include:
  • the first bottom center point of the target frame used to characterize the target can be obtained according to the position information in the target information of the target recognized from the current frame image, and then the According to the position information in the target information of the target, the second bottom center point of the target frame used to characterize the target is obtained, and then the moving direction of the target is determined according to the first bottom center point and the second bottom center point.
  • the moving direction can be characterized by a vector from the second bottom center point to the first bottom center point.
  • the moving direction of the vector used to characterize the moving direction intersects the dangerous area, it is considered that the moving direction points to the dangerous area, otherwise it is considered that the moving direction does not point to the dangerous area.
  • the target warning mode when the steering information indicates that there is a steering intention or is turning, the target warning mode is determined to be the first warning mode; when the steering information indicates that there is no steering intention, the target warning is determined The mode is the second alarm mode; wherein the warning effect of the first alarm mode is higher than that of the second alarm mode.
  • the method provided in this embodiment provides a method for determining a target alarm mode based on the identified target information and the turning information of the target. In this way, different alarm modes are provided based on different target information and turning information. , Can further improve the driver's experience.
  • the vehicle blind spot detection method provided in this application has been introduced above, and the vehicle blind spot detection device and system provided in this application are introduced below:
  • FIG. 6 is a schematic structural diagram of a vehicle blind spot detection device provided by an embodiment of the application.
  • the vehicle blind spot detection device provided by the present application may include an acquisition module 610, an identification module 620, and a processing module 630; among them,
  • the acquisition module 610 is used to acquire images collected by image acquisition devices installed on both sides of the vehicle;
  • the recognition module 620 is configured to recognize the image
  • the acquiring module 610 is further configured to acquire steering information of the vehicle when the identification module recognizes that there is a target in the designated detection area;
  • the processing module 630 is configured to determine a target alarm mode according to the identified target information and the steering information of the target, and execute the target alarm mode.
  • the device provided in this embodiment can be used to implement the technical solution of the method embodiment shown in FIG. 1, and its implementation principles and technical effects are similar, and will not be repeated here.
  • processing module 630 is specifically configured to:
  • the target information determine whether the target is dangerous
  • processing module 630 is specifically configured to:
  • the category information in the target information is the first category, determine whether the target is in the designated dangerous area according to the position information in the target information recognized from the current frame image, and if so, determine the target There is danger, if not, it is determined that the target is not in danger;
  • the category information in the target information is the second category, determine whether the target is close to the dangerous area according to the position information in the target information recognized from the current frame image and the previous frame image, and if so, It is determined that the target is in danger, if not, it is determined whether the target is in the dangerous area according to the position information in the target information recognized from the current frame image, if it is determined that the target is in danger, if not, Make sure that the target is not dangerous.
  • the traveling speed of the first category is lower than the traveling speed of the second category.
  • the second category may be motor vehicles or non-motor vehicles, and the first category is pedestrians.
  • processing module 630 is specifically configured to:
  • the target alarm mode is the first alarm mode
  • the target alarm mode is a second alarm mode; wherein the warning effect of the first alarm mode is higher than that of the second alarm mode.
  • processing module 630 is specifically configured to:
  • processing module 630 is specifically configured to:
  • FIG. 7 is a schematic diagram of a vehicle blind spot detection system provided by an embodiment of the application.
  • a vehicle blind spot detection system may include an image acquisition device 710 and a processor 720, where:
  • the image acquisition device 710 is installed on both sides of the vehicle for acquiring images
  • the processor 720 is configured to:
  • a target warning mode is determined, and the target warning mode is executed.
  • the image acquisition device 710 may be a camera.
  • the processor 720 may be integrated in the image capture device 710, or may be integrated in other devices independent of the image capture device 710.
  • the processor 720 is integrated in a vehicle blind spot detection device installed in the cab. in. In this embodiment, this is not limited.
  • system of this embodiment can be used to implement the technical solution of the method embodiment shown in FIG.

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)

Abstract

公开了一种车辆盲区检测方法,该检测方法包括:获取安装在车辆两侧的图像采集设备采集到的图像,并对所述图像进行识别;当识别出指定的检测区域中存在目标时,获取车辆的转向信息;然后依据识别出的上述目标的目标信息和上述转向信息,确定目标报警方式,并执行目标报警方式。该检测方法可自主监视视野盲区中的目标,提高驾驶者体验。还公开了一种车辆盲区检测装置和系统。

Description

[根据细则37.2由ISA制定的发明名称] 一种车辆盲区检测方法、装置和系统 技术领域
本申请涉及智能交通技术领域,尤其涉及一种车辆盲区检测方法、装置和系统。
背景技术
随着经济的发展和人民生活水平的提高,越来越多的人选择车辆作为代步工具,然而,由于车辆在进行并线、转弯或调头时,通过侧视镜观察行驶环境时存在视野盲区,驾驶者无法观察到该视野盲区内的障碍目标,例如,无法观察到该视野盲区内的车辆、行人和障碍物等,从而容易造成交通事故。因此,为降低交通事故,盲区检测显得尤为重要。
目前,盲区检测方法一般为:通过设置在车辆两侧的摄像头采集车辆两侧侧视镜无法观察到的视野盲区的影像,并将采集到的影像发送至驾驶室进行显示,以使驾驶者能够了解该视野盲区中障碍目标的情况。
但是,当采用上述方法进行盲区检测时,只能简单的显示影像,驾驶者需要自主监视视野盲区中的障碍目标,容易对驾驶员的正常驾驶造成干扰。
发明内容
有鉴于此,本申请提供一种车辆盲区检测方法、装置和系统。
本申请第一方面提供一种车辆盲区检测方法,包括:
获取安装在车辆两侧的图像采集设备采集到的图像,并对所述图像进行识别;
当识别出指定的检测区域中存在目标时,获取所述车辆的转向信息;
依据识别出的所述目标的目标信息和所述转向信息,确定目标报警方式,并执行所述目标报警方式。
本申请第二方面提供一种车辆盲区检测装置,所述装置包括获取模块、识别模块和处理模块;其中,
所述获取模块,用于获取安装在车辆两侧的图像采集设备采集到的图像;
所述识别模块,用于对所述图像进行识别;
所述获取模块,还用于当所述识别模块识别出指定的检测区域中存在目标时,获取所述车辆的转向信息;
所述处理模块,用于依据识别出的所述目标的目标信息和所述转向信息,确定目标报警方式,并执行所述目标报警方式。
本申请第三方面提供一种车辆盲区检测系统,包括图像采集设备和处理器,其中,
所述图像采集设备安装在车辆两侧,用于采集图像;
所述处理器,用于:
获取所述图像采集设备采集到的图像,并对所述图像进行识别;
当识别出指定的检测区域中存在目标时,获取所述车辆的转向信息;
依据识别出的所述目标的目标信息和所述转向信息,确定目标报警方式,并执行所述目标报警方式。
本申请提供的车辆盲区检测方法、装置和系统,通过获取安装在车辆两侧的图像采集设备采集到的图像,并对上述图像进行识别,进而在识别出指定的检测区域中存在目标时,获取车辆的转向信息,从而依据识别出的所述目标的目标信息和所述转向信息,确定目标报警方式,并执行所述目标报警方式,这样,可自主监视视野盲区中的目标,提高驾驶者体验。
附图说明
图1为本申请一实施例提供的车辆盲区检测方法的流程图;
图2为本申请一示例性实施例示出的图像采集设备的安装位置的示意图;
图3为本申请一示例性实施例示出的指定的检测区域的示意图;
图4为本申请另一实施例提供的车辆盲区检测方法的流程图;
图5为本申请一实施例示出的指定的危险区域的示意图;
图6为本申请一实施例提供的车辆盲区检测装置的结构示意图;
图7为本申请一实施例提供的车辆盲区检测系统的示意图。
具体实施方式
这里将详细地对示例性实施例进行说明,其示例表示在附图中。下面的描述涉及附图时,除非另有表示,不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本申请相一致的所有实施方式。相反,它们仅是与如所附权利要求书中所详述的、本申请的一些方面相一致的装置和方法的例子。
在本申请使用的术语是仅仅出于描述特定实施例的目的,而非旨在限制本申请。在本申请和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式,除非上下文清楚地表示其他含义。还应当理解,本文中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。
应当理解,尽管在本申请可能采用术语第一、第二、第三等来描述各种信息,但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例如,在不脱离本申请范围的情况下,第一信息也可以被称为第二信息,类似地,第二信息也可以被称为第一信息。取决于语境,如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”或“响应于确定”。
本申请提供一种车辆盲区检测方法、装置和系统,以提高驾驶者体验。
下面给出几个具体的实施例,用以详细说明本申请提供的技术方案。下面这几个具体的实施例可以相互结合,对于相同或相似的概念或过程可能在某些实施例中不再赘述。
图1为本申请一实施例提供的车辆盲区检测方法的流程图。请参照图1,本实施例提供的车辆盲区检测方法,可以包括:
S101、获取安装在车辆两侧的图像采集设备采集到的图像,并对上述图像进行识别。
具体的,图像采集设备安装在车辆的两侧。例如,图2为本申请一示例性实施例示出的图像采集设备的安装位置的示意图,参照图2,在图2所示示例中,图像采集设备安装在车辆左右两侧的侧视镜的下方(图2中仅示出安装在车辆右侧的图像采集设备),该图像采集设备右前方视野与车身夹角为120°。
需要说明的是,一实施例中,可对整个图像进行识别。当然,另一实施例中,也可对图像中指定的检测区域进行识别。需要说明的是,指定的检测区域是根据实际需要设定的,该指定的检测区域可以为覆盖车身侧面2个车道宽度和120°夹角范围的区域。例 如,图3为本申请一示例性实施例示出的指定的检测区域的示意图。请参照图3,在图3所示示例中,指定的检测区域为白色线围成的五边形区域。需要说明的是,在图3所示示例中,以位于车辆右侧的图像采集设备采集到的图像为例说明指定的检测区域,对于位于车辆左侧的图像采集设备采集到的图像来说,该图像中的检测区域与图3中的检测区域类似,此处不再赘述。
此外,对图像进行识别后,可识别出图像中是否存在目标以及该目标的目标信息。需要说明的是,目标是指人、机动车、非机动车等。在一实施例中,目标还可以包括猫、狗等动物。目标信息是与目标相关的信息,通常可以包括位置信息和类别信息,该类别信息用于表征目标属于哪一预设类别,其中,预设类别是根据实际需要设定的,例如,一实施例中,包括三个预设类别,分别为行人、机动车和非机动车。位置信息为目标所处位置的信息,包括目标在图像中的位置的信息以及由此得出的目标相对于车辆的实际位置的信息。
S102、当识别出指定的检测区域中存在目标时,获取上述车辆的转向信息。
具体的,可通过车身的信号线,获取车辆的转向信息,转向信息通过所述车辆的信号线在车辆内的不同部件之间传输。其中,车辆的转向信息可以指示车辆有转向意图或没有转向意图或正在转向。在一实施例中,转向信息是与车辆的转向操作相关的部件,例如,转向灯或者方向盘,的运行信息或者状态信息。在一实施例中,转向信息可以包括车辆转向灯被打开或者车辆的方向盘被转动且转动角度超过预设值等。此外,转向信息还可以包括转向灯未打开、方向盘未被司机转动或者被转动但转动角度未超过预设值(例如,司机通过略微转动方向盘来调整车辆在车道中的位置以及朝向)等。
上述的指示转向灯的开关状态、方向盘的转动状态等的信号可以经由信号线传输。例如,车辆转向灯被打开或者车辆的方向盘被转动且转动角度超过预设值等可以指示车辆有转向意图或正在转向,而转向灯未打开、方向盘未被司机转动或者被转动但转动角度未超过预设值等可以指示车辆没有转向意图。
S103、依据识别出的上述目标的目标信息和上述转向信息,确定目标报警方式,并执行上述目标报警方式。
车辆本身设置有警示灯、蜂鸣器、语音报警器、显示屏等专用于或者可以用于进行报警提示的装置。相应地,车辆支持的报警方式可以包括警示灯闪动或者常亮、蜂鸣器或语音报警器发出报警音、显示屏显示警示文本信息等。目标报警方式为针对当前情况 确定的一种或多种报警方式。
例如,一实施例中,当上述目标信息中的类别信息为行人时,若转向信息指示有转向意图或正在转向,则确定目标报警方式为第二报警方式,若转向信息指示没有转向意图,则确定不报警。当上述目标信息中的类别信息为机动车或非机动车时,若转向信息指示有转向意图或者正在转向,则确定目标报警方式为第一报警方式,若转向信息指示没有转向意图,则确定目标报警方式为第二报警方式。
需要说明的是,第一报警方式的警示作用高于第二报警方式。例如,一实施例中,第一报警方式可以为启动声光报警装置(例如,该声光报警装置可以为警示灯和/或蜂鸣器),第二报警方式可以为输出文本提醒消息。再例如,另一实施例中,第一报警方式可以为输出图标、启动指示灯并输出语音提示信息,第二报警方式可以输出图标或启动指示灯。
下面将给出详细的实施例,用于详细介绍本步骤的具体实现原理和实现过程,此处不再赘述。
本实施例提供的车辆盲区检测方法,通过获取安装在车辆两侧的图像采集设备采集到的图像,并对上述图像进行识别,进而在识别出指定的检测区域中存在目标时,获取车辆的转向信息,从而依据识别出的所述目标的目标信息和所述转向信息,确定目标报警方式,并执行所述目标报警方式,这样,可自主监视盲区中的目标,提高驾驶者体验。
图4为本申请另一实施例提供的车辆盲区检测方法的流程图。请参照图4,本实施例提供的方法,在上述实施例的基础上,依据识别出的所述目标的目标信息和所述转向信息,确定目标报警方式的步骤,可以包括:
S401、依据上述目标信息,判断上述目标是否存在危险。
具体的,一实施例中,该步骤的具体实现过程,可以包括:
(1)当所述目标信息中的类别信息为第一类别时,依据从当前帧图像中识别出的所述目标信息中的位置信息确定所述目标是否处于指定的危险区域内,若是,确定所述目标存在危险,若否,则确定所述目标不存在危险。
(2)当所述目标信息中的类别信息为第二类别时,依据从当前帧图像和上一帧图像中识别出的所述目标信息中的位置信息确定所述目标是否接近所述危险区域,若是,确定所述目标存在危险,若否,则依据从当前帧图像中识别出的所述目标信息中的位置信息确定所述目标是否处于所述危险区域内,若是,确定所述目标存在危险,若否,则确 定所述目标不存在危险。
需要说明的是,第一类别的行驶速度小于第二类别的行驶速度。例如,一实施例中,第二类别可以为机动车或非机动车,第一类别为行人。
需要说明的是,指定的危险区域是根据实际需要设定的。例如,图5为一实施例示出的指定的危险区域的示意图。在图5所示示例中,指定的危险区域为黑色线围成的梯形区域。需要说明的是,在图5所示示例中,以位于车辆右侧的图像采集设备采集到的图像为例说明指定的危险区域,对于位于车辆左侧的图像采集设备采集到的图像来说,该图像中的危险区域与图5中的危险区域类似,此处不再赘述。
具体的,依据目标信息中的位置信息,可获取用于表征目标的目标框的底部中心点,进而判断该底部中心点是否处于危险区域内,若是,确定目标处于所述危险区域内,否则确定所述目标不处于所述危险区域内。
进一步地,依据从当前帧图像和上一帧图像中识别出的所述目标信息中的位置信息确定所述目标是否接近所述危险区域的具体实现过程可以包括:
(1)依据从当前帧图像和上一帧图像中识别出的所述目标信息中的位置信息,确定所述目标的移动方向。
具体的,可依据从当前帧图像识别出的所述目标的目标信息中的位置信息,获取用于表征该目标的目标框的第一底部中心点,进而依据从上一帧图像中识别出的所述目标的目标信息中的位置信息,获取用于表征该目标的目标框的第二底部中心点,然后依据第一底部中心点和第二底部中心点,确定所述目标的移动方向,该移动方向可以用第二底部中心点指向第一底部中心点的向量表征。
(2)判断所述移动方向是否指向所述危险区域。
具体的,一实施例中,若用于表征移动方向的向量的方向与危险区域相交,则认为所述移动方向指向所述危险区域,否则认为所述移动方向不指向所述危险区域。
(3)若是,确定所述目标接近所述危险区域。
(4)若否,确定所述目标不接近所述危险区域。
S402、若是,确定上述目标报警方式为与上述转向信息匹配的报警方式。
具体的,一实施例中,当所述转向信息指示有转向意图或正在转向时,确定所述目标报警方式为第一报警方式;当所述转向信息指示没有转向意图时,确定所述目标报警 方式为第二报警方式;其中,所述第一报警方式的警示作用高于所述第二报警方式的警示作用。
S403、若否,确定上述目标报警方式为不进行报警。
本实施例提供的方法,给出了一种依据识别出的所述目标的目标信息和所述转向信息确定目标报警方式的方法,这样,基于不同的目标信息和转向信息,提供不同的报警方式,可进一步提高驾驶员的体验。
以上对本申请提供的车辆盲区检测方法进行了介绍,下面对本申请提供的车辆盲区检测装置和系统进行介绍:
图6为本申请一实施例提供的车辆盲区检测装置的结构示意图。请参照图6,本申请提供的车辆盲区检测装置,可以包括获取模块610、识别模块620和处理模块630;其中,
所述获取模块610,用于获取安装在车辆两侧的图像采集设备采集到的图像;
所述识别模块620,用于对所述图像进行识别;
所述获取模块610,还用于当所述识别模块识别出指定的检测区域中存在目标时,获取所述车辆的转向信息;
所述处理模块630,用于依据识别出的所述目标的目标信息和所述转向信息,确定目标报警方式,并执行所述目标报警方式。
具体的,本实施例提供的装置,可用于执行图1所示方法实施例的技术方案,其实现原理和技术效果类似,此处不再赘述。
进一步地,所述处理模块630,具体用于:
依据所述目标信息,判断所述目标是否存在危险;
若是,确定所述目标报警方式为与所述转向信息匹配的报警方式;
若否,确定所述目标报警方式为不进行报警。
进一步地,所述处理模块630,具体用于:
当所述目标信息中的类别信息为第一类别时,依据从当前帧图像中识别出的所述目标信息中的位置信息确定所述目标是否处于指定的危险区域内,若是,确定所述目标存在危险,若否,则确定所述目标不存在危险;
当所述目标信息中的类别信息为第二类别时,依据从当前帧图像和上一帧图像中识别出的所述目标信息中的位置信息确定所述目标是否接近所述危险区域,若是,确定所述目标存在危险,若否,则依据从当前帧图像中识别出的所述目标信息中的位置信息确定所述目标是否处于所述危险区域内,若是确定所述目标存在危险,若否则确定所述目标不存在危险。
需要说明的是,第一类别的行驶速度小于第二类别的行驶速度。例如,一实施例中,第二类别可以为机动车或非机动车,第一类别为行人。
进一步地,所述处理模块630,具体用于:
当所述转向信息指示有转向意图或者正在转向时,确定所述目标报警方式为第一报警方式;
当所述转向信息指示没有转向意图时,确定所述目标报警方式为第二报警方式;其中,所述第一报警方式的警示作用高于所述第二报警方式的警示作用。
进一步地,所述处理模块630,具体用于:
判断用于表征所述目标的目标框的底部中心点是否处于所述危险区域内;
若是,确定所述目标处于所述危险区域内;
若否,确定所述目标不处于所述危险区域内。
进一步地,所述处理模块630,具体用于:
依据从当前帧图像和上一帧图像中识别出的所述目标信息中的位置信息,确定所述目标的移动方向;
判断所述移动方向是否指向所述危险区域;
若是,确定所述目标接近所述危险区域;
若否,确定所述目标不接近所述危险区域。
图7为本申请一实施例提供的车辆盲区检测系统的示意图。请参照图7,车辆盲区检测系统,可以包括图像采集设备710和处理器720,其中,
所述图像采集设备710安装在车辆两侧,用于采集图像;
所述处理器720,用于:
获取所述图像采集设备采集到的图像,并对所述图像进行识别;
当识别出指定的检测区域中存在目标时,获取所述车辆的转向信息;
依据识别出的所述目标的目标信息和所述转向信息,确定目标报警方式,并执行所述目标报警方式。
具体的,图像采集设备710可以为摄像机。此外,处理器720可以集成在图像采集设备710中,也可以集成在独立于图像采集设备710的其他设备中,例如,一实施例中,处理器720集成在安装在驾驶室内的车辆盲区检测设备中。本实施例中,不对此进行限定。
此外,本实施例的系统,可用于执行图1所示方法实施例的技术方案,其实现原理和技术效果类似,此处不再赘述。
以上所述仅为本申请的较佳实施例而已,并不用以限制本申请,凡在本申请的精神和原则之内,所做的任何修改、等同替换、改进等,均应包含在本申请保护的范围之内。

Claims (13)

  1. 一种车辆盲区检测方法,包括:
    获取安装在车辆两侧的图像采集设备采集到的图像,并对所述图像进行识别;
    当识别出指定的检测区域中存在目标时,获取所述车辆的转向信息;
    依据识别出的所述目标的目标信息和所述转向信息,确定目标报警方式,并执行所述目标报警方式。
  2. 根据权利要求1所述的方法,其特征在于,所述依据识别出的所述目标的目标信息和所述转向信息,确定目标报警方式,包括:
    依据所述目标信息,判断所述目标是否存在危险;
    若是,确定所述目标报警方式为与所述转向信息匹配的报警方式;
    若否,确定所述目标报警方式为不进行报警。
  3. 根据权利要求2所述的方法,其特征在于,所述依据所述目标信息,判断所述目标是否存在危险,包括:
    当所述目标信息中的类别信息为第一类别时,依据从当前帧图像中识别出的所述目标信息中的位置信息确定所述目标是否处于指定的危险区域内,
    若是,确定所述目标存在危险,
    若否,则确定所述目标不存在危险;
    当所述目标信息中的类别信息为第二类别时,依据从所述当前帧图像和上一帧图像中识别出的所述目标信息中的位置信息确定所述目标是否接近所述危险区域,
    若是,确定所述目标存在危险,
    若否,则依据从所述当前帧图像中识别出的所述目标信息中的位置信息确定所述目标是否处于所述危险区域内,
    若是,则确定所述目标存在危险,
    若否,则确定所述目标不存在危险。
  4. 根据权利要求2所述的方法,其特征在于,所述确定所述目标报警方式为与所述转向信息匹配的报警方式,包括:
    当所述转向信息指示所述车辆有转向意图或者正在转向时,确定所述目标报警方式为第一报警方式;
    当所述转向信息指示所述车辆没有转向意图时,确定所述目标报警方式为第二报警方式;
    其中,所述第一报警方式的警示作用高于所述第二报警方式的警示作用。
  5. 根据权利要求3所述的方法,其特征在于,依据从所述当前帧图像中识别出的所述目标信息中的位置信息确定所述目标是否处于所述危险区域内,包括:
    判断用于表征所述目标的目标框的底部中心点是否处于所述危险区域内;
    若是,确定所述目标处于所述危险区域内;
    若否,确定所述目标不处于所述危险区域内。
  6. 根据权利要求3所述的方法,其特征在于,所述依据从所述当前帧图像和所述上一帧图像中识别出的所述目标信息中的位置信息确定所述目标是否接近所述危险区域,包括:
    依据从所述当前帧图像和所述上一帧图像中识别出的所述目标信息中的位置信息,确定所述目标的移动方向;
    判断所述移动方向是否指向所述危险区域;
    若是,确定所述目标接近所述危险区域;
    若否,确定所述目标不接近所述危险区域。
  7. 一种车辆盲区检测装置,包括获取模块、识别模块和处理模块;其中,
    所述获取模块,用于获取安装在车辆两侧的图像采集设备采集到的图像;
    所述识别模块,用于对所述图像进行识别;
    所述获取模块,还用于当所述识别模块识别出指定的检测区域中存在目标时,获取所述车辆的转向信息;
    所述处理模块,用于依据识别出的所述目标的目标信息和所述转向信息,确定目标报警方式,并执行所述目标报警方式。
  8. 根据权利要求7所述的装置,其特征在于,所述处理模块,具体用于:
    依据所述目标信息,判断所述目标是否存在危险;
    若是,确定所述目标报警方式为与所述转向信息匹配的报警方式;
    若否,确定所述目标报警方式为不进行报警。
  9. 根据权利要求8所述的装置,其特征在于,所述处理模块,具体用于:
    当所述目标信息中的类别信息为第一类别时,依据从当前帧图像中识别出的所述目标信息中的位置信息确定所述目标是否处于指定的危险区域内,
    若是,确定所述目标存在危险,
    若否,则确定所述目标不存在危险;
    当所述目标信息中的类别信息为第二类别时,依据从所述当前帧图像和上一帧图像中识别出的所述目标信息中的位置信息确定所述目标是否接近所述危险区域,
    若是,确定所述目标存在危险,
    若否,则依据从所述当前帧图像中识别出的所述目标信息中的位置信息确定所述目标是否处于所述危险区域内,
    若是,确定所述目标存在危险,
    若否,则确定所述目标不存在危险。
  10. 根据权利要求8所述的装置,其特征在于,所述处理模块,具体用于:
    当所述转向信息指示所述车辆有转向意图或正在转向时,确定所述目标报警方式为第一报警方式;
    当所述转向信息指示所述车辆没有转向意图时,确定所述目标报警方式为第二报警方式;
    其中,所述第一报警方式的警示作用高于所述第二报警方式的警示作用。
  11. 根据权利要求9所述的装置,其特征在于,所述处理模块,具体用于:
    判断用于表征所述目标的目标框的底部中心点是否处于所述危险区域内;
    若是,确定所述目标处于所述危险区域内;
    若否,确定所述目标不处于所述危险区域内。
  12. 根据权利要求9所述的装置,其特征在于,所述处理模块,具体用于:
    依据从所述当前帧图像和所述上一帧图像中识别出的所述目标信息中的位置信息,确定所述目标的移动方向;
    判断所述移动方向是否指向所述危险区域;
    若是,确定所述目标接近所述危险区域;
    若否,确定所述目标不接近所述危险区域。
  13. 一种车辆盲区检测系统,包括图像采集设备和处理器,其中,
    所述图像采集设备安装在车辆两侧,用于采集图像;
    所述处理器,用于:
    获取所述图像采集设备采集到的图像,并对所述图像进行识别;
    当识别出指定的检测区域中存在目标时,获取所述车辆的转向信息;
    依据识别出的所述目标的目标信息和所述转向信息,确定目标报警方式,并执行所述目标报警方式。
PCT/CN2020/072406 2019-01-24 2020-01-16 一种车辆盲区检测方法、装置和系统 WO2020151560A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910069181.6 2019-01-24
CN201910069181 2019-01-24

Publications (1)

Publication Number Publication Date
WO2020151560A1 true WO2020151560A1 (zh) 2020-07-30

Family

ID=71736445

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/072406 WO2020151560A1 (zh) 2019-01-24 2020-01-16 一种车辆盲区检测方法、装置和系统

Country Status (2)

Country Link
CN (1) CN111469760A (zh)
WO (1) WO2020151560A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112277799A (zh) * 2020-10-30 2021-01-29 重庆长安汽车股份有限公司 一种汽车盲区检测报警方法及系统

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112061030A (zh) * 2020-10-13 2020-12-11 深圳市全守安行科技有限公司 一种商用车盲区监测装置及其检测方法
CN113103957B (zh) * 2021-04-28 2023-07-28 上海商汤临港智能科技有限公司 一种盲区监测方法、装置、电子设备及存储介质

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5680123A (en) * 1996-08-06 1997-10-21 Lee; Gul Nam Vehicle monitoring system
US6115651A (en) * 1998-01-15 2000-09-05 Cruz; Diogenes J. Large vehicle blindspot monitor
JP2006260217A (ja) * 2005-03-17 2006-09-28 Advics:Kk 車両用走行支援装置
CN102632839A (zh) * 2011-02-15 2012-08-15 汽车零部件研究及发展中心有限公司 一种基于后视图像认知的车载盲区预警系统及方法
CN105459907A (zh) * 2015-12-15 2016-04-06 小米科技有限责任公司 车辆安全系统、盲区监测方法及装置
CN107031623A (zh) * 2017-03-16 2017-08-11 浙江零跑科技有限公司 一种基于车载盲区相机的道路预警方法
CN108407720A (zh) * 2018-03-26 2018-08-17 宁夏大学 用于大型货车的安全距离报警及防护装置
CN108583432A (zh) * 2018-07-05 2018-09-28 广东机电职业技术学院 一种基于图像识别技术的智能a柱盲区预警装置与方法
CN109153359A (zh) * 2018-08-23 2019-01-04 深圳市锐明技术股份有限公司 一种汽车盲区的监测方法及系统

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103832380A (zh) * 2012-11-23 2014-06-04 深圳华一汽车科技有限公司 一种基于机器视觉的盲区车辆检测及警告系统及方法
CN103723143B (zh) * 2013-11-29 2016-06-29 天津博信汽车零部件有限公司 车辆零胎压安全行驶的控制方法和控制系统
CN107953827A (zh) * 2016-10-18 2018-04-24 杭州海康威视数字技术股份有限公司 一种车辆盲区预警方法及装置
CN107472128A (zh) * 2017-04-11 2017-12-15 宝沃汽车(中国)有限公司 车辆盲区的监控方法、系统及车辆
CN107458306B (zh) * 2017-07-28 2021-02-02 奇瑞汽车股份有限公司 车辆安全预警方法及装置

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5680123A (en) * 1996-08-06 1997-10-21 Lee; Gul Nam Vehicle monitoring system
US6115651A (en) * 1998-01-15 2000-09-05 Cruz; Diogenes J. Large vehicle blindspot monitor
JP2006260217A (ja) * 2005-03-17 2006-09-28 Advics:Kk 車両用走行支援装置
CN102632839A (zh) * 2011-02-15 2012-08-15 汽车零部件研究及发展中心有限公司 一种基于后视图像认知的车载盲区预警系统及方法
CN105459907A (zh) * 2015-12-15 2016-04-06 小米科技有限责任公司 车辆安全系统、盲区监测方法及装置
CN107031623A (zh) * 2017-03-16 2017-08-11 浙江零跑科技有限公司 一种基于车载盲区相机的道路预警方法
CN108407720A (zh) * 2018-03-26 2018-08-17 宁夏大学 用于大型货车的安全距离报警及防护装置
CN108583432A (zh) * 2018-07-05 2018-09-28 广东机电职业技术学院 一种基于图像识别技术的智能a柱盲区预警装置与方法
CN109153359A (zh) * 2018-08-23 2019-01-04 深圳市锐明技术股份有限公司 一种汽车盲区的监测方法及系统

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112277799A (zh) * 2020-10-30 2021-01-29 重庆长安汽车股份有限公司 一种汽车盲区检测报警方法及系统

Also Published As

Publication number Publication date
CN111469760A (zh) 2020-07-31

Similar Documents

Publication Publication Date Title
US11012666B2 (en) Surround camera system for autonomous driving
US11518401B2 (en) Vehicular driving assist with driver monitoring
WO2020151560A1 (zh) 一种车辆盲区检测方法、装置和系统
US6281806B1 (en) Driver road hazard warning and illumination system
JP5345350B2 (ja) 車両の運転支援装置
JP3390289B2 (ja) 警報装置
JP4134891B2 (ja) 衝突可能性判定装置
TWI458653B (zh) 盲區偵測系統及其盲區偵測方法
CN104786933A (zh) 一种全景影像驾驶辅助装置及方法
JPH08248128A (ja) 車両の衝突回避方法及びこれを遂行するための装置
KR101405398B1 (ko) 보행자친화형 안전 알림장치 및 방법
WO2013115241A1 (ja) 車両の運転手の注意を喚起する装置及びその方法
JP2010113601A (ja) 車両用警告装置
CN110126717B (zh) 一种用于车辆的转向示警系统及转向示警方法
KR20180065527A (ko) 차량 후측방 경고 장치 및 이를 이용한 경고 방법
EP2487505B1 (en) Blind area warning for vehicles
CN112498343A (zh) 车辆转向控制系统及方法
CN113602276A (zh) 基于LiFi信号交互的汽车智能辅助驾驶方法及系统
WO2020241485A1 (ja) 運転支援システム、運転支援方法及びプログラム
CN113173160A (zh) 车辆用防碰撞装置及车辆用防碰撞方法
JP2024105001A (ja) 表示システム
JP2003030799A (ja) 障害物情報呈示装置
JP2005327177A (ja) 車両間衝突防止支援システムおよび車両間衝突防止支援装置
CN113415236A (zh) 重型车盲区监测及预警系统
JP2008250453A (ja) 運転支援装置および運転支援方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20745924

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20745924

Country of ref document: EP

Kind code of ref document: A1