WO2021046962A1 - Detection system and detection method for obstacle between shielding door and vehicle body - Google Patents

Detection system and detection method for obstacle between shielding door and vehicle body Download PDF

Info

Publication number
WO2021046962A1
WO2021046962A1 PCT/CN2019/111455 CN2019111455W WO2021046962A1 WO 2021046962 A1 WO2021046962 A1 WO 2021046962A1 CN 2019111455 W CN2019111455 W CN 2019111455W WO 2021046962 A1 WO2021046962 A1 WO 2021046962A1
Authority
WO
WIPO (PCT)
Prior art keywords
corridor
volume
coordinates
wave radar
obstacle
Prior art date
Application number
PCT/CN2019/111455
Other languages
French (fr)
Chinese (zh)
Inventor
孙永才
周杨
吕红强
熊钢
吴强
徐志荣
Original Assignee
中车南京浦镇车辆有限公司
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 中车南京浦镇车辆有限公司 filed Critical 中车南京浦镇车辆有限公司
Publication of WO2021046962A1 publication Critical patent/WO2021046962A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
    • G01S13/867—Combination of radar systems with cameras
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G01S2013/9328—Rail vehicles

Definitions

  • the invention belongs to the field of rail transit, and particularly relates to an obstacle detection system and a detection method between a screen door and a vehicle body.
  • Unmanned driving technology for subway vehicles is one of the goals of subway operation and development.
  • the lines planned to use unmanned operation are: Shanghai Line 14, Suzhou Line 3, Beijing Yagging Line, etc.
  • Unmanned trains have high requirements for the safety, reliability and real-time performance of the whole system. Once passengers or other objects are stuck in the space between the train and the screen door, it will cause major accidents and social impacts. Obstacle detection in the space is a necessary condition to ensure that the vehicle realizes unmanned driving.
  • the current scheme of unmanned vehicles for obstacles on the side of the vehicle is: cameras on both sides of each vehicle (each camera observes the state of 2 doors), the foreign object detection host obtains the camera video through 100M Ethernet, and combines it with the database The pre-stored pictures are compared through algorithms.
  • the vehicle body vibration affects the picture correction, and it is easy to miss the detection; 2.
  • the objects left on the surface of the platform are easy to cause false alarms; 3.
  • the color and texture of the obstacles are close to the environmental background, the miss is easy to occur; 4.
  • there are meteorological conditions such as haze and snow on the elevated platform, it is easy to miss the detection or false alarm; 5.
  • the detection response is slow, etc.
  • the present invention provides an obstacle detection system and a detection method between a screen door and a vehicle body.
  • the present invention provides an obstacle detection system between a screen door and a vehicle body.
  • the passage between the vehicle body and the screen door is a corridor.
  • the system includes a binocular camera, a calibration object, a computer, and a millimeter wave radar;
  • the binocular camera and millimeter wave radar are installed at one end of the corridor, and the calibration object is installed at the other end of the corridor opposite to the binocular camera; both the binocular camera and the millimeter wave radar are connected to a computer;
  • the optical axes of the two cameras of the binocular camera are parallel.
  • the two cameras read the corridor picture information containing the calibration object in real time, and transmit the read information to the computer in real time.
  • the millimeter wave radar transmits radar waves in real time, The radar waves are reflected by the vehicle body, screen doors, and obstacles to generate echoes.
  • the millimeter-wave radar transmits the received echoes to the computer in real time.
  • the computer determines whether the corridor area is based on the received corridor picture information and the echoes. There is an obstacle; if there is an obstacle, the computer sends the information of the obstacle to the driving dispatching system; the driving dispatching system judges whether to detain the car according to the received obstacle information.
  • the frequency of the millimeter wave radar is 77GHZ.
  • the calibration object is a two-dimensional code array.
  • the binocular camera is connected to a computer through Ethernet, and the millimeter wave radar is connected to the computer through a CAN bus.
  • the binocular camera is 1.2 meters away from the platform
  • the millimeter wave radar is 0.9 meters away from the platform.
  • a detection method of the obstacle detection system between the screen door and the vehicle body is specifically as follows:
  • Step 1 Process the corridor picture information containing the calibration objects collected by the binocular camera to filter out the weather factor in the picture information;
  • Step 2 Compare the information collected by the binocular camera with the picture information of the corridor containing the calibration object obscured by obstacles; to obtain the first volume and coordinates; compare the echo generated by the millimeter wave radar with the echo obstructed by the obstacle Compare to get the second volume and coordinates;
  • Step 3 Perform DS fusion calculation on the first volume and coordinates and the second volume and coordinates, and compare the calculated result with the preset threshold. If the calculated result is less than the preset threshold, the corridor is considered There are no obstacles, otherwise it is determined that there are obstacles in the corridor, and whether to detain the car is judged based on the information of the obstacles.
  • the preset threshold includes a volume threshold and a distance threshold between the obstacle and the vehicle body.
  • the specific method for obtaining the first volume and coordinates is: express the calibration object in the form of a digital array, and calculate the difference between the calibration object information collected by the binocular camera and the calibration object information blocked by obstacles, if If the result is 0, the first volume and coordinates are 0. If the result is not 0, it is determined that there is an object in the corridor area; according to the corridor picture information collected by the binocular camera and the corridor picture information blocked by obstacles, use the binocular
  • the distance measurement method calculates the coordinates and volume of the object as the first coordinates and volume.
  • the specific method for obtaining the second volume and coordinates is: calculating the phase difference between the waveform of the echo generated by the millimeter wave radar and the waveform of the echo blocked by no obstacle, if the phase difference is within the phase difference threshold range If there is no object in the corridor area, then the second volume and coordinates are 0. Otherwise, the volume and coordinates of the object are calculated by the transit time method based on the echo generated by the millimeter wave radar, as the second volume and coordinates.
  • the present invention adopts binocular camera and millimeter wave radar to double confirm obstacle information, improves the accuracy of recognition, and uses millimeter wave radar to greatly reduce the influence of weather and other environmental factors on the detection system.
  • Figure 1 is a schematic diagram of the system of the present invention.
  • this embodiment provides an obstacle detection system and a detection method between a screen door and a vehicle body.
  • the system includes a binocular camera 1, a 77GHz millimeter wave radar 2, a calibration object 6, and a computer.
  • the binocular camera and the 77GHz millimeter wave radar are installed at the same end of the corridor, and the binocular camera is about 1.2 meters away from the platform, thus ensuring safe driving and unobstructed observation In the corridor area, the binocular camera is connected to the computer via Gigabit Ethernet.
  • the calibration object of the binocular camera is a two-dimensional code array, installed at the other end of the corridor, opposite to the binocular camera.
  • the millimeter wave radar is installed between the screen door and the train body, about 0.9 meters away from the platform, which ensures safe driving and unobstructed detection of the corridor area.
  • the millimeter wave radar is connected to the computer through the CAN bus, and the vehicle body is filtered and shielded through software algorithms. Fixed targets such as doors, focusing only on the obstacle information in the corridor.
  • the computer compares the information collected by the binocular camera with the picture information of the corridor containing the calibration object obscured by obstacles; thereby obtaining the first volume and coordinates; specifically: the calibration object is expressed in the form of a digital array, and the binocular
  • the calibration object information collected by the camera and the calibration object information obscured by the obstacle are calculated. If the result is 0, the first volume and coordinates are 0. If the result is not 0, it is determined that there is an object in the corridor area;
  • the corridor picture information collected by the eye camera and the corridor picture information blocked by obstacles are used to calculate the coordinates and volume of the object using the binocular distance measurement method as the first coordinates and volume.
  • Comparing the echo generated by the millimeter wave radar with the echo obstructed by no obstacles to obtain the second volume and coordinates specifically: calculate the waveform of the echo generated by the millimeter wave radar and the echo obstructed by the obstacle. If the phase difference is within the phase difference threshold range, it is determined that there is no object in the corridor area, and the second volume and coordinates are 0. Otherwise, the echo generated by the millimeter wave radar is calculated by the transit time method. The volume and coordinates of the object are used as the second volume and coordinates.
  • the preset threshold includes: the volume threshold, the distance between the obstacle and the vehicle body
  • the visual recognition of the binocular camera is affected by factors such as rain, snow, wind, sand, and haze, and can be partially corrected by software.
  • the millimeter wave radar is not affected by rain, snow, and light, but it is more complicated to achieve static obstacle detection. Through coordinate conversion, the camera and millimeter-wave radar are unified, and the size of the obstacle and the position on the platform and whether the obstacle affects the driving safety are determined together, and the data is uploaded to the driving dispatch system.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Radar Systems Or Details Thereof (AREA)
  • Traffic Control Systems (AREA)
  • Geophysics And Detection Of Objects (AREA)

Abstract

Disclosed are a detection system and detection method for an obstacle between a shielding door and a vehicle body, wherein a passage between the vehicle body and the shielding door is a corridor. The system comprises: a binocular camera, a calibration object, a computer and a millimeter-wave radar, wherein the binocular camera and the millimeter-wave radar are both mounted at one end of the corridor; two cameras of the binocular camera read, in real time, corridor picture information including the calibration object and transmit the read information to the computer in real time; the millimeter-wave radar emits, in real time, radar waves which are reflected by the vehicle body, the shielding door and an obstacle so as to generate echoes, and the millimeter-wave radar transmits the received echoes to the computer in real time; and the computer performs, by using a D-S algorithm, fusion calculation on a first volume and coordinates calculated by the computer according to the corridor picture information and a second volume and coordinates calculated by the computer according to the echoes, so as to determine whether an obstacle is present. The present invention has a high precision.

Description

一种屏蔽门与车体间的障碍物检测系统及检测方法Obstacle detection system and detection method between screen door and vehicle body 技术领域Technical field
本发明属于轨道交通领域，尤其涉及一种屏蔽门与车体间的障碍物检测系统及检测方法。The invention belongs to the field of rail transit, and particularly relates to an obstacle detection system and a detection method between a screen door and a vehicle body.
背景技术Background technique
地铁车辆无人驾驶技术是地铁运营发展的目标之一，目前计划使用无人驾驶运营的线路有：上海十四号线、苏州三号线、北京燕房线等。无人驾驶列车对全系统的安全性、可靠性和实时性要求较高，一旦有乘客或其它物体被卡在列车与屏蔽门之间的空间内，将造成重大事故和社会影响，所以对特定空间内的障碍物检测是保证车辆实现无人驾驶的必备条件。Unmanned driving technology for subway vehicles is one of the goals of subway operation and development. Currently, the lines planned to use unmanned operation are: Shanghai Line 14, Suzhou Line 3, Beijing Yanfang Line, etc. Unmanned trains have high requirements for the safety, reliability and real-time performance of the whole system. Once passengers or other objects are stuck in the space between the train and the screen door, it will cause major accidents and social impacts. Obstacle detection in the space is a necessary condition to ensure that the vehicle realizes unmanned driving.
目前无人驾驶车辆对车侧障碍物的方案是：在每车的两侧摄像机(每个摄像机观测2个车门的状态)，异物检测主机通过百兆以太网获取摄像机视频，将之与数据库内的预存图片做通过算法比较。The current scheme of unmanned vehicles for obstacles on the side of the vehicle is: cameras on both sides of each vehicle (each camera observes the state of 2 doors), the foreign object detection host obtains the camera video through 100M Ethernet, and combines it with the database The pre-stored pictures are compared through algorithms.
存在如下问题：1、车体振动影响图片校正，易出现漏检现象；2、遗留在站台表面的物体易引起误报；3、障碍物颜色和纹理接近环境背景时，易出现漏检现象；4、在高架站台上出现的雾霾、雪花等气象条件时，易出现漏检或误报现象；5、检测响应慢等。There are the following problems: 1. The vehicle body vibration affects the picture correction, and it is easy to miss the detection; 2. The objects left on the surface of the platform are easy to cause false alarms; 3. When the color and texture of the obstacles are close to the environmental background, the miss is easy to occur; 4. When there are meteorological conditions such as haze and snow on the elevated platform, it is easy to miss the detection or false alarm; 5. The detection response is slow, etc.
发明内容Summary of the invention
发明目的：为解决上述现有技术存在漏检、检查速度慢等问题，本发明提供了一种屏蔽门与车体间的障碍物检测系统及检测方法。Objective of the invention: In order to solve the problems of missed inspection and slow inspection speed in the above-mentioned prior art, the present invention provides an obstacle detection system and a detection method between a screen door and a vehicle body.
技术方案：本发明提供一种屏蔽门与车体间的障碍物检测系统，车体与屏蔽门之间的通道为走廊，该系统包括：双目摄像机、标定物、计算机、毫米波雷达；所述双目摄像机、毫米波雷达均安装在走廊的一端，所述标定物安装在走廊的另外一端与双目摄像机相对；所述双目摄像机与毫米波雷达均与计算机连接；Technical Solution: The present invention provides an obstacle detection system between a screen door and a vehicle body. The passage between the vehicle body and the screen door is a corridor. The system includes a binocular camera, a calibration object, a computer, and a millimeter wave radar; The binocular camera and millimeter wave radar are installed at one end of the corridor, and the calibration object is installed at the other end of the corridor opposite to the binocular camera; both the binocular camera and the millimeter wave radar are connected to a computer;
所述双目摄像机的两个摄像头的光轴平行，该两个摄像头实时读取包含标定物的走廊图片信息，并将读取的信息实时传送至计算机，所述毫米波雷达实时发射雷达波，所述雷达波经过车体、屏蔽门、障碍物反射后产生回波，毫米波雷达将收到的回波实时传送至计算机，所述计算机根据收到的走廊图片信息及回波判定走廊区域是否存在障碍物；若存在障碍，计算机将障碍物的信息发送至行车调度系统；所述行车调度系统根据收到的障碍物信息判断是否扣车。The optical axes of the two cameras of the binocular camera are parallel. The two cameras read the corridor picture information containing the calibration object in real time, and transmit the read information to the computer in real time. The millimeter wave radar transmits radar waves in real time, The radar waves are reflected by the vehicle body, screen doors, and obstacles to generate echoes. The millimeter-wave radar transmits the received echoes to the computer in real time. The computer determines whether the corridor area is based on the received corridor picture information and the echoes. There is an obstacle; if there is an obstacle, the computer sends the information of the obstacle to the driving dispatching system; the driving dispatching system judges whether to detain the car according to the received obstacle information.
进一步的，所述毫米波雷达的频率为77GHZ。Further, the frequency of the millimeter wave radar is 77GHZ.
进一步的，所述标定物为二维码阵列。Further, the calibration object is a two-dimensional code array.
进一步的，所述双目摄像机通过以太网与计算机连接,所述毫米波雷达通过CAN总线与计算机连接。Further, the binocular camera is connected to a computer through Ethernet, and the millimeter wave radar is connected to the computer through a CAN bus.
进一步的，所述双目摄像机距离站台1.2米，毫米波雷达距离站台0.9米。Further, the binocular camera is 1.2 meters away from the platform, and the millimeter wave radar is 0.9 meters away from the platform.
一种屏蔽门与车体间的障碍物检测系统的检测方法具体为：A detection method of the obstacle detection system between the screen door and the vehicle body is specifically as follows:
步骤1：对双目摄像机采集的包含标定物的走廊图片信息进行处理，滤除掉图片信息中的天气因素；Step 1: Process the corridor picture information containing the calibration objects collected by the binocular camera to filter out the weather factor in the picture information;
步骤2：将双目摄像机采集的信息与无障碍物遮挡的包含标定物的走廊图片信息进行比较；从而得到第一体积和坐标；将毫米波雷达产生的回波与无障碍物遮挡的回波比较，从而得到第二体积和坐标；Step 2: Compare the information collected by the binocular camera with the picture information of the corridor containing the calibration object obscured by obstacles; to obtain the first volume and coordinates; compare the echo generated by the millimeter wave radar with the echo obstructed by the obstacle Compare to get the second volume and coordinates;
步骤3：将第一体积、坐标和第二体积、坐标进行D-S融合计算，并将计算后的结果与预设好的阈值进行比较，如果计算后的结果小于预设好的阈值，则认定走廊不存在障碍物，否则认定走廊存在障碍物，并根据障碍物的信息判断是否扣车。Step 3: Perform DS fusion calculation on the first volume and coordinates and the second volume and coordinates, and compare the calculated result with the preset threshold. If the calculated result is less than the preset threshold, the corridor is considered There are no obstacles, otherwise it is determined that there are obstacles in the corridor, and whether to detain the car is judged based on the information of the obstacles.
进一步的，所述预设好的阈值包括体积阈值、障碍物与车体之间的距离阈值。Further, the preset threshold includes a volume threshold and a distance threshold between the obstacle and the vehicle body.
进一步的，所述得到第一体积和坐标的具体方法为：将标定物以数字阵列的形式表示，将双目摄像机采集的标定物信息与无障碍物遮挡的标定物信息进行做差计算，如果结果为0则第一体积和坐标为0，若结果不为0，则认定有物体在走廊区域中；根据双目摄像机采集的走廊图片信息，以及无障碍物遮挡的走廊图片信息，利用双目测距法计算出物体的坐标与体积，作为第一坐标与体积。Further, the specific method for obtaining the first volume and coordinates is: express the calibration object in the form of a digital array, and calculate the difference between the calibration object information collected by the binocular camera and the calibration object information blocked by obstacles, if If the result is 0, the first volume and coordinates are 0. If the result is not 0, it is determined that there is an object in the corridor area; according to the corridor picture information collected by the binocular camera and the corridor picture information blocked by obstacles, use the binocular The distance measurement method calculates the coordinates and volume of the object as the first coordinates and volume.
进一步的，所述得到第二体积和坐标的具体方法为：计算毫米波雷达产生的回波的波形与无障碍物遮挡的回波的波形之间的相位差，若相位差在相位差阈值范围内，则判定走廊区域中没有物体，则第二体积和坐标为0，否则，根据毫米波雷达产生的回波，利用渡越时间法计算得到物体的体积和坐标，作为第二体积和坐标。Further, the specific method for obtaining the second volume and coordinates is: calculating the phase difference between the waveform of the echo generated by the millimeter wave radar and the waveform of the echo blocked by no obstacle, if the phase difference is within the phase difference threshold range If there is no object in the corridor area, then the second volume and coordinates are 0. Otherwise, the volume and coordinates of the object are calculated by the transit time method based on the echo generated by the millimeter wave radar, as the second volume and coordinates.
有益效果：本发明采用了双目摄像机和毫米波雷达双重确认障碍物信息，提高了识别的准确度，且利用了毫米波雷达大大减小了天气等环境因素对检测系统的影响。Beneficial effects: The present invention adopts binocular camera and millimeter wave radar to double confirm obstacle information, improves the accuracy of recognition, and uses millimeter wave radar to greatly reduce the influence of weather and other environmental factors on the detection system.
附图说明Description of the drawings
图1为本发明的系统示意图。Figure 1 is a schematic diagram of the system of the present invention.
附图标记说明：1、双目摄像机；2、毫米波雷达；3、屏蔽门；4走廊；5、列车；6、 标定物。Description of reference signs: 1. Binocular camera; 2. Millimeter wave radar; 3. Screen door; 4 Corridor; 5. Train; 6. Calibration object.
具体实施方式detailed description
构成本发明的一部分的附图用来提供对本发明的进一步理解，本发明的示意性实施例及其说明用于解释本发明，并不构成对本发明的不当限定。The drawings constituting a part of the present invention are used to provide a further understanding of the present invention, and the exemplary embodiments of the present invention and the description thereof are used to explain the present invention, and do not constitute an improper limitation of the present invention.
如图1所示，本实施例提供一种屏蔽门与车体间的障碍物检测系统及检测方法，该系统包括：双目摄像机1、77GHz毫米波雷达2、标定物6、计算机。在障碍物检测过程中，只需要关注宽为列车车体5与屏蔽门之间(走廊4)、长度为列车车头至车尾、从站台起高约为2米的狭长立体区域内有无障碍物即可，不需要检测视野内的所有障碍物，所以把双目摄像机和77GHz毫米波雷达安装在走廊的同一端，且双目摄像机距离站台约1.2米，从而保证了行车安全和无遮蔽观测走廊区域，双目摄像机通过千兆以太网与计算机连接。双目摄像机的标定物是一个二维码阵列，安装于走廊的另一端，与双目摄像机相对。As shown in FIG. 1, this embodiment provides an obstacle detection system and a detection method between a screen door and a vehicle body. The system includes a binocular camera 1, a 77GHz millimeter wave radar 2, a calibration object 6, and a computer. In the obstacle detection process, you only need to pay attention to the obstacles in the narrow and long three-dimensional area with the width between the train body 5 and the screen door (corridor 4), the length from the front to the rear of the train, and the height of about 2 meters from the platform. No need to detect all obstacles in the field of view, so the binocular camera and the 77GHz millimeter wave radar are installed at the same end of the corridor, and the binocular camera is about 1.2 meters away from the platform, thus ensuring safe driving and unobstructed observation In the corridor area, the binocular camera is connected to the computer via Gigabit Ethernet. The calibration object of the binocular camera is a two-dimensional code array, installed at the other end of the corridor, opposite to the binocular camera.
毫米波雷达安装于屏蔽门与列车车体之间，距离站台约0.9米，从而保证了行车安全和无遮蔽探测走廊区域，毫米波雷达通过CAN总线与计算机连接，通过软件算法过滤车体、屏蔽门等固定目标，仅关注走廊内的障碍物信息。The millimeter wave radar is installed between the screen door and the train body, about 0.9 meters away from the platform, which ensures safe driving and unobstructed detection of the corridor area. The millimeter wave radar is connected to the computer through the CAN bus, and the vehicle body is filtered and shielded through software algorithms. Fixed targets such as doors, focusing only on the obstacle information in the corridor.
所述计算机将双目摄像机采集的信息与无障碍物遮挡的包含标定物的走廊图片信息进行比较；从而得到第一体积和坐标；具体为：将标定物以数字阵列的形式表示，将双目摄像机采集的标定物信息与无障碍物遮挡的标定物信息进行做差计算，如果结果为0则第一体积和坐标为0，若结果不为0，则认定有物体在走廊区域中；根据双目摄像机采集的走廊图片信息，以及无障碍物遮挡的走廊图片信息，利用双目测距法计算出物体的坐标与体积，作为第一坐标与体积。The computer compares the information collected by the binocular camera with the picture information of the corridor containing the calibration object obscured by obstacles; thereby obtaining the first volume and coordinates; specifically: the calibration object is expressed in the form of a digital array, and the binocular The calibration object information collected by the camera and the calibration object information obscured by the obstacle are calculated. If the result is 0, the first volume and coordinates are 0. If the result is not 0, it is determined that there is an object in the corridor area; The corridor picture information collected by the eye camera and the corridor picture information blocked by obstacles are used to calculate the coordinates and volume of the object using the binocular distance measurement method as the first coordinates and volume.
将毫米波雷达产生的回波与无障碍物遮挡的回波比较，从而得到第二体积和坐标，具体为：计算毫米波雷达产生的回波的波形与无障碍物遮挡的回波的波形之间的相位差，若相位差在相位差阈值范围内，则判定走廊区域中没有物体，则第二体积和坐标为0，否则，根据毫米波雷达产生的回波，利用渡越时间法计算得到物体的体积和坐标，作为第二体积和坐标。Comparing the echo generated by the millimeter wave radar with the echo obstructed by no obstacles to obtain the second volume and coordinates, specifically: calculate the waveform of the echo generated by the millimeter wave radar and the echo obstructed by the obstacle. If the phase difference is within the phase difference threshold range, it is determined that there is no object in the corridor area, and the second volume and coordinates are 0. Otherwise, the echo generated by the millimeter wave radar is calculated by the transit time method. The volume and coordinates of the object are used as the second volume and coordinates.
将第一体积、坐标和第二体积、坐标进行D-S融合计算，并将计算后的结果与预设好的阈值进行比较，如果计算后的结果小于预设的阈值，则认定走廊不存在障碍物，否则认定走廊存在障碍物，计算机将障碍物信息发送至行车调度系统，行车调度系统根据 障碍物信息判断是否扣车；所述预设的阈值包括：体积阈值、障碍物与车体之间的距离阈值Y，本实施例中Y＝10cm。Perform DS fusion calculation of the first volume, coordinates and second volume and coordinates, and compare the calculated result with the preset threshold. If the calculated result is less than the preset threshold, it is determined that there are no obstacles in the corridor , Otherwise it is determined that there are obstacles in the corridor, and the computer sends the obstacle information to the driving dispatch system, and the driving dispatch system judges whether to detain the car according to the obstacle information; the preset threshold includes: the volume threshold, the distance between the obstacle and the vehicle body The distance threshold Y is Y=10cm in this embodiment.
双目摄像机视觉识别受雨雪、风沙、雾霾等因素影响，通过软件可以得到部分校正，毫米波雷达不受雨雪、光照的影响，但实现静止障碍物探测功能比较复杂。通过坐标转换完成摄像机和毫米波雷达统一，共同完成得到障碍物的大小和在站台位置以及障碍物是否影响行车安全等判定，并将数据上传至行车调度系统。The visual recognition of the binocular camera is affected by factors such as rain, snow, wind, sand, and haze, and can be partially corrected by software. The millimeter wave radar is not affected by rain, snow, and light, but it is more complicated to achieve static obstacle detection. Through coordinate conversion, the camera and millimeter-wave radar are unified, and the size of the obstacle and the position on the platform and whether the obstacle affects the driving safety are determined together, and the data is uploaded to the driving dispatch system.
另外需要说明的是，在上述具体实施方式中所描述的各个具体技术特征，在不矛盾的情况下，可以通过任何合适的方式进行组合。为了避免不必要的重复，本发明对各种可能的组合方式不再另行说明。In addition, it should be noted that the various specific technical features described in the foregoing specific embodiments can be combined in any suitable manner, provided that there is no contradiction. In order to avoid unnecessary repetition, various possible combinations are not described separately in the present invention.

Claims (9)

  1. 一种屏蔽门与车体间的障碍物检测系统，车体与屏蔽门之间的通道为走廊，其特征在于，包括：双目摄像机、标定物、计算机、毫米波雷达；所述双目摄像机、毫米波雷达均安装在走廊的一端，所述标定物安装在走廊的另外一端与双目摄像机相对；所述双目摄像机与毫米波雷达均与计算机连接；An obstacle detection system between a screen door and a vehicle body. The passage between the vehicle body and the screen door is a corridor, which is characterized in that it includes a binocular camera, a calibration object, a computer, and a millimeter wave radar; the binocular camera , The millimeter wave radar is installed at one end of the corridor, and the calibration object is installed at the other end of the corridor opposite to the binocular camera; both the binocular camera and the millimeter wave radar are connected to a computer;
    所述双目摄像机的两个摄像头的光轴平行，该两个摄像头实时读取包含标定物的走廊图片信息，并将读取的信息实时传送至计算机，所述毫米波雷达实时发射雷达波，所述雷达波经过车体、屏蔽门、障碍物反射后产生回波，毫米波雷达将收到的回波实时传送至计算机，所述计算机根据收到的走廊图片信息及回波判定走廊区域是否存在障碍物；若存在障碍，计算机将障碍物的信息发送至行车调度系统；所述行车调度系统根据收到的障碍物信息判断是否扣车。The optical axes of the two cameras of the binocular camera are parallel. The two cameras read the corridor picture information containing the calibration object in real time, and transmit the read information to the computer in real time. The millimeter wave radar transmits radar waves in real time, The radar waves are reflected by the vehicle body, screen doors, and obstacles to generate echoes. The millimeter-wave radar transmits the received echoes to the computer in real time. The computer determines whether the corridor area is based on the received corridor picture information and the echoes. There is an obstacle; if there is an obstacle, the computer sends the information of the obstacle to the driving dispatching system; the driving dispatching system judges whether to detain the car according to the received obstacle information.
  2. 根据权利要求1所述的一种屏蔽门与车体间的障碍物检测系统，其特征在于，所述毫米波雷达的频率为77GHZ。The obstacle detection system between the screen door and the vehicle body according to claim 1, wherein the frequency of the millimeter wave radar is 77GHZ.
  3. 根据权利要求1所述的一种屏蔽门与车体间的障碍物检测系统，其特征在于，所述标定物为二维码阵列。The obstacle detection system between the screen door and the vehicle body according to claim 1, wherein the calibration object is a two-dimensional code array.
  4. 根据权利要求1所述的一种屏蔽门与车体间的障碍物检测系统，其特征在于，所述双目摄像机通过以太网与计算机连接,所述毫米波雷达通过CAN总线与计算机连接。The obstacle detection system between the screen door and the vehicle body according to claim 1, wherein the binocular camera is connected to a computer through an Ethernet, and the millimeter wave radar is connected to a computer through a CAN bus.
  5. 根据权利要求1所述的一种屏蔽门与车体间的障碍物检测系统，其特征在于，所述双目摄像机距离站台1.2米，毫米波雷达距离站台0.9米。The obstacle detection system between the screen door and the vehicle body according to claim 1, wherein the binocular camera is 1.2 meters away from the platform, and the millimeter wave radar is 0.9 meters away from the platform.
  6. 基于权利要求1所述的一种屏蔽门与车体间的障碍物检测系统的检测方法，具体为：The detection method of an obstacle detection system between a screen door and a vehicle body based on claim 1, specifically:
    步骤1：对双目摄像机采集的包含标定物的走廊图片信息进行处理，滤除掉图片信息中的天气因素；Step 1: Process the corridor picture information containing the calibration objects collected by the binocular camera to filter out the weather factor in the picture information;
    步骤2：将双目摄像机采集的信息与无障碍物遮挡的包含标定物的走廊图片信息进行比较；从而得到第一体积和坐标；将毫米波雷达产生的回波与无障碍物遮挡的回波比较，从而得到第二体积和坐标；Step 2: Compare the information collected by the binocular camera with the picture information of the corridor containing the calibration object obscured by obstacles; to obtain the first volume and coordinates; compare the echo generated by the millimeter wave radar with the echo obstructed by the obstacle Compare to get the second volume and coordinates;
    步骤3：将第一体积、坐标和第二体积、坐标进行D-S融合计算，并将计算后的结果与预设好的阈值进行比较，如果计算后的结果小于预设好的阈值，则认定走廊不存在障碍物，否则认定走廊存在障碍物，并根据障碍物的信息判断是否扣车。Step 3: Perform DS fusion calculation on the first volume and coordinates and the second volume and coordinates, and compare the calculated result with the preset threshold. If the calculated result is less than the preset threshold, the corridor is considered There are no obstacles, otherwise it is determined that there are obstacles in the corridor, and whether to detain the car is judged based on the information of the obstacles.
  7. 根据权利要求6所述的方法，其特征在于，所述预设好的阈值包括体积阈值、 障碍物与车体之间的距离阈值。The method according to claim 6, wherein the preset threshold includes a volume threshold and a distance threshold between the obstacle and the vehicle body.
  8. 根据权利要求6所述的方法，其特征在于，所述得到第一体积和坐标的具体方法为：将标定物以数字阵列的形式表示，将双目摄像机采集的标定物信息与无障碍物遮挡的标定物信息做差计算，如果结果为0则第一体积和坐标为0，若结果不为0，则认定有物体在走廊区域中；根据双目摄像机采集的走廊图片信息，以及无障碍物遮挡的走廊图片信息，利用双目测距法计算出物体的坐标与体积，作为第一坐标与体积。The method according to claim 6, characterized in that the specific method for obtaining the first volume and coordinates is: expressing the calibration object in the form of a digital array, and blocking the calibration object information collected by the binocular camera with no obstacles If the result is 0, the first volume and coordinates are 0. If the result is not 0, then it is determined that there is an object in the corridor area; according to the corridor picture information collected by the binocular camera, and the obstacles The picture information of the occluded corridor is calculated using the binocular distance measurement method to calculate the coordinates and volume of the object as the first coordinates and volume.
  9. 根据权利要求6所述的方法，其特征在于，所述得到第二体积和坐标的具体方法为：计算毫米波雷达产生的回波的波形与无障碍物遮挡的回波的波形之间的相位差，若相位差在相位差阈值范围内，则判定走廊区域中没有物体，则第二体积和坐标为0，否则，根据毫米波雷达产生的回波，利用渡越时间法计算得到物体的体积和坐标，作为第二体积和坐标。The method according to claim 6, wherein the specific method for obtaining the second volume and coordinates is: calculating the phase between the waveform of the echo generated by the millimeter wave radar and the waveform of the echo blocked by no obstruction If the phase difference is within the phase difference threshold, it is determined that there is no object in the corridor area, and the second volume and coordinates are 0. Otherwise, the volume of the object is calculated by the transit time method according to the echo generated by the millimeter wave radar And coordinates, as the second volume and coordinates.
PCT/CN2019/111455 2019-09-09 2019-10-16 Detection system and detection method for obstacle between shielding door and vehicle body WO2021046962A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910866213.5A CN110501699A (en) 2019-09-09 2019-09-09 Obstacle detection system and detection method between a kind of shield door and car body
CN201910866213.5 2019-09-09

Publications (1)

Publication Number Publication Date
WO2021046962A1 true WO2021046962A1 (en) 2021-03-18

Family

ID=68591866

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/111455 WO2021046962A1 (en) 2019-09-09 2019-10-16 Detection system and detection method for obstacle between shielding door and vehicle body

Country Status (2)

Country Link
CN (1) CN110501699A (en)
WO (1) WO2021046962A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113759365A (en) * 2021-10-11 2021-12-07 内蒙古方向图科技有限公司 Binocular vision three-dimensional optical image and ground radar data fusion method and system
CN115657569B (en) * 2022-12-14 2023-04-07 北京七星华创微波电子技术有限公司 Millimeter wave broadband portable calibration source control system and method
CN113759365B (en) * 2021-10-11 2024-05-31 内蒙古方向图科技有限公司 Binocular vision three-dimensional optical image and foundation radar data fusion method and system

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103091724A (en) * 2013-01-31 2013-05-08 华南理工大学 Automatic detection method and device of foreign bodies between linear subway platform shielded gate and train
CN104777522A (en) * 2015-03-24 2015-07-15 广州市地下铁道总公司 Composite-detection-based detection system and detection method for foreign matter between train door and platform shield gate
US9322909B2 (en) * 2012-12-13 2016-04-26 Continental Automotive Systems, Inc. Negative obstacle detection with stereo camera and long range radar
CN108226890A (en) * 2018-01-19 2018-06-29 成都赛英科技有限公司 Based on the time to the airport foreign matter radar detecting method of statistics
CN108490447A (en) * 2018-03-21 2018-09-04 交控科技股份有限公司 The anti-clipping system and method for gate and train
US10228691B1 (en) * 2016-04-01 2019-03-12 Olaeris, Inc. Augmented radar camera view for remotely operated aerial vehicles
CN109572693A (en) * 2019-01-24 2019-04-05 湖北亿咖通科技有限公司 Vehicle obstacle-avoidance householder method, system and vehicle
KR20190040550A (en) * 2017-10-11 2019-04-19 현대모비스 주식회사 Apparatus for detecting obstacle in vehicle and control method thereof
CN109941702A (en) * 2019-03-14 2019-06-28 何山 A kind of X-ray machine vision rays safety detection apparatus double conveyor control system

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3923200B2 (en) * 1998-10-23 2007-05-30 本田技研工業株式会社 Vehicle obstacle detection method
CA2794268A1 (en) * 2010-03-26 2011-09-29 Siemens Sas Safety apparatus for closing and opening a door
CN104049281B (en) * 2014-07-02 2017-07-07 广州市地下铁道总公司 Foreign matter automatic detection device and method between curve metro platform shield door and train
CN104637059A (en) * 2015-02-09 2015-05-20 吉林大学 Night preceding vehicle detection method based on millimeter-wave radar and machine vision
CN105047108B (en) * 2015-08-27 2018-04-06 姜旭东 One kind is used for projection imaging device on subway glass shield door
CN106908783B (en) * 2017-02-23 2019-10-01 苏州大学 Based on obstacle detection method combined of multi-sensor information
CN109572718A (en) * 2017-09-28 2019-04-05 天津天乐泰力科技有限公司 A kind of subway shield door safety system based on two dimensional code
CN108089202A (en) * 2017-12-12 2018-05-29 徐薇 Subway shield door gauge area intelligent anti-clip detection warning device and method
CN110126824A (en) * 2019-05-22 2019-08-16 河南工业大学 A kind of commercial vehicle AEBS system of integrated binocular camera and millimetre-wave radar

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9322909B2 (en) * 2012-12-13 2016-04-26 Continental Automotive Systems, Inc. Negative obstacle detection with stereo camera and long range radar
CN103091724A (en) * 2013-01-31 2013-05-08 华南理工大学 Automatic detection method and device of foreign bodies between linear subway platform shielded gate and train
CN104777522A (en) * 2015-03-24 2015-07-15 广州市地下铁道总公司 Composite-detection-based detection system and detection method for foreign matter between train door and platform shield gate
US10228691B1 (en) * 2016-04-01 2019-03-12 Olaeris, Inc. Augmented radar camera view for remotely operated aerial vehicles
KR20190040550A (en) * 2017-10-11 2019-04-19 현대모비스 주식회사 Apparatus for detecting obstacle in vehicle and control method thereof
CN108226890A (en) * 2018-01-19 2018-06-29 成都赛英科技有限公司 Based on the time to the airport foreign matter radar detecting method of statistics
CN108490447A (en) * 2018-03-21 2018-09-04 交控科技股份有限公司 The anti-clipping system and method for gate and train
CN109572693A (en) * 2019-01-24 2019-04-05 湖北亿咖通科技有限公司 Vehicle obstacle-avoidance householder method, system and vehicle
CN109941702A (en) * 2019-03-14 2019-06-28 何山 A kind of X-ray machine vision rays safety detection apparatus double conveyor control system

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113759365A (en) * 2021-10-11 2021-12-07 内蒙古方向图科技有限公司 Binocular vision three-dimensional optical image and ground radar data fusion method and system
CN113759365B (en) * 2021-10-11 2024-05-31 内蒙古方向图科技有限公司 Binocular vision three-dimensional optical image and foundation radar data fusion method and system
CN115657569B (en) * 2022-12-14 2023-04-07 北京七星华创微波电子技术有限公司 Millimeter wave broadband portable calibration source control system and method

Also Published As

Publication number Publication date
CN110501699A (en) 2019-11-26

Similar Documents

Publication Publication Date Title
EP3885794A1 (en) Track and road obstacle detecting method
WO2019238127A1 (en) Method, apparatus and system for measuring distance
WO2021031469A1 (en) Vehicle obstacle detection method and system
CN104808216B (en) A kind of vehicle collision avoidance early warning system based on laser radar range
CN110329316B (en) Urban rail obstacle detection device and detection method
CN104217590A (en) On-board traffic density estimator
CN104442924A (en) All-weather high speed railway vehicle-mounted obstacle detection system and method
CN113799852B (en) Intelligent active obstacle identification protection method supporting dynamic mode switching
CN105629261B (en) No-raster anti-collision laser radar system of vehicle based on structure light and its working method
Gavrila et al. A multi-sensor approach for the protection of vulnerable traffic participants the PROTECTOR project
CN113850102B (en) Vehicle-mounted vision detection method and system based on millimeter wave radar assistance
CN106585670B (en) To train detection systems and method before a kind of urban track traffic based on video
CN109552366A (en) Locomotive vehicle-mounted railway barrier intelligent detecting alarm system and its method for early warning
CN109367529B (en) Millimeter wave radar combined installation structure and virtual tunnel construction and obstacle judgment method
Wang et al. Vehicle detection and width estimation in rain by fusing radar and vision
CN110596731A (en) Active obstacle detection system and method for metro vehicle
CN109001743A (en) Tramcar anti-collision system
CN109910955A (en) Rail tunnel obstacle detection system and method based on transponder information transmission
CN110816527A (en) Vehicle-mounted night vision safety method and system
CN106740838A (en) A kind of vehicle risk early warning system
WO2023109501A1 (en) Train active obstacle detection method and apparatus based on positioning technology
CN115876198A (en) Target detection and early warning method, device, system and medium based on data fusion
CN113050654A (en) Obstacle detection method, vehicle-mounted obstacle avoidance system and method for inspection robot
WO2021046962A1 (en) Detection system and detection method for obstacle between shielding door and vehicle body
CN208847836U (en) Tramcar anti-collision system

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: 19944945

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: 19944945

Country of ref document: EP

Kind code of ref document: A1