CN110293993A - Switch detection device and system - Google Patents
Switch detection device and system Download PDFInfo
- Publication number
- CN110293993A CN110293993A CN201910736382.7A CN201910736382A CN110293993A CN 110293993 A CN110293993 A CN 110293993A CN 201910736382 A CN201910736382 A CN 201910736382A CN 110293993 A CN110293993 A CN 110293993A
- Authority
- CN
- China
- Prior art keywords
- turnout
- point
- distance
- laser
- detection device
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 46
- 238000004458 analytical method Methods 0.000 claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 12
- 238000006073 displacement reaction Methods 0.000 claims description 13
- 238000012937 correction Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 6
- 238000001816 cooling Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 14
- 238000012545 processing Methods 0.000 abstract description 5
- 239000000284 extract Substances 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 5
- 238000009434 installation Methods 0.000 description 5
- 230000009193 crawling Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 4
- 230000001681 protective effect Effects 0.000 description 3
- 230000001846 repelling effect Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000001915 proofreading effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
- B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
- B61K9/08—Measuring installations for surveying permanent way
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
Description
技术领域technical field
本发明涉及轨道交通设备领域，具体而言，尤其涉及一种道岔检测装置及系统。The invention relates to the field of rail transit equipment, in particular to a switch detection device and system.
背景技术Background technique
随着全国铁路提速，客运专线和高速铁路的建设，对铁路道岔的有效实时监测检测被提到一个新高度，而换轨时道岔间距的测量是道岔检测的一个重要参数。国外高速铁路对道岔状态的实时监控高度重视，采用相应的道岔监测系统，随着铁路运营速度的提高，结合我国的铁路发展现状和国际经验，对铁路道岔间距进行实时监测检测，是保障铁路安全运营的关键手段。对经过道岔的火车进行经过时间以及重力进行记录，在规定的时间向后台发送数据，运行管理部门可以知道每台道岔运行次数，承载的总重量，确认是否需要更换或维修道岔。现有方法是通过间接统计火车经过时间和重力判断道岔情况，没有采用直接手段判断道岔是否存在安全隐患。With the speeding up of national railways, the construction of passenger dedicated lines and high-speed railways, the effective real-time monitoring and detection of railway turnouts has been raised to a new level, and the measurement of the distance between turnouts when changing tracks is an important parameter for turnout detection. Foreign high-speed railways attach great importance to the real-time monitoring of turnout status. The corresponding turnout monitoring system is adopted. With the increase of railway operation speed, combined with my country's railway development status and international experience, real-time monitoring and detection of railway turnout spacing is the key to ensuring railway safety. key means of operation. Record the elapsed time and gravity of the train passing the turnout, and send the data to the background at the specified time. The operation management department can know the number of times each turnout has been run, the total weight it carries, and confirm whether it needs to be replaced or repaired. The existing method judges the situation of the turnout by indirect statistics of the train elapsed time and gravity, and does not use direct means to judge whether there is a potential safety hazard in the turnout.
发明内容Contents of the invention
根据上述提出的缺少道岔间距直接监控方案的技术问题，而提供一种道岔检测装置。本发明以数字图像处理和机器视觉为基础，从采集图像中提取出道岔状态特征,并对道岔状态进行智能监测检测的功能。通过直接手段对道岔进行监测。提前预警，对保证列车安全运行具有重要的现实意义。According to the above-mentioned technical problem of lack of a direct monitoring solution for the distance between turnouts, a turnout detection device is provided. Based on digital image processing and machine vision, the present invention extracts the state characteristics of the turnout from the collected images, and performs intelligent monitoring and detection on the state of the turnout. Switches are monitored by direct means. Early warning is of great practical significance to ensure the safe operation of trains.
本发明采用的技术手段如下：The technical means adopted in the present invention are as follows:
一种道岔现场检测装置，包括外壳及设置在外壳内部的双目相机及激光器，其特征在于，所述外壳内部中空区域被设定为包括双目相机固定区域、激光发射器固定区域、电源模块固定区域以及工控模块固定区域；An on-site detection device for a turnout, comprising a casing and a binocular camera and a laser arranged inside the casing, characterized in that the hollow area inside the casing is set to include a binocular camera fixing area, a laser transmitter fixing area, a power module Fixed area and fixed area of industrial control module;
所述激光发射器固定区域包括第一侧面及激光发射平面，所述激光发射器的发射口透过设置于所述激光发射平面上的通孔、沿垂直于所述激光发射平面方向发射激光；The laser emitter fixing area includes a first side surface and a laser emitting plane, and the emitting port of the laser emitter emits laser light in a direction perpendicular to the laser emitting plane through a through hole arranged on the laser emitting plane;
所述双目相机固定区域包括第二侧面、第三侧面以及相机拍摄平面，所述双目相机的镜头透过设置于所述相机拍摄平面上的两个并列通孔、沿垂直于所述相机拍摄平面方向拍摄；The fixed area of the binocular camera includes a second side, a third side, and a camera shooting plane, and the lens of the binocular camera passes through two parallel through holes arranged on the camera shooting plane, along a direction perpendicular to the camera. Shooting in the plane direction;
其中，所述激光发射平面与所述第二侧面的夹角大于90°。Wherein, the included angle between the laser emission plane and the second side is larger than 90°.
进一步地，所述激光发射器发出的激光照射在所述双目相机两个镜头拍摄区域重合部分的中心。Further, the laser light emitted by the laser emitter is irradiated on the center of the overlapping shooting area of the two lenses of the binocular camera.
进一步地，所述外壳上表面呈点阵式分布有若干散热孔。Further, a number of cooling holes are distributed in a dot matrix on the upper surface of the housing.
进一步地，所述相机拍摄平面与待探测岔尖呈45°夹角，且与基本轨距离为0.2-0.3米。Further, the camera shooting plane forms an included angle of 45° with the fork tip to be detected, and the distance from the basic rail is 0.2-0.3 meters.
本发明还提供了一种道岔检测系统，包括上述任意一项所述的检测装置。The present invention also provides a switch detection system, including the detection device described in any one of the above.
进一步地，系统还包括控制单元以及系统分析单元；Further, the system also includes a control unit and a system analysis unit;
所述控制单元控制所述检测装置以设定频率对轨道运行状态下的道岔结构进行图像采集，并将所采集到的图像信息送至所述系统分析单元进行分析计算，得到道岔形变指标相对变化数值，若所述形变指标数值在安全阈值范围外，系统提示报警。The control unit controls the detection device to collect images of the turnout structure under the track running state at a set frequency, and sends the collected image information to the system analysis unit for analysis and calculation, and obtains the relative change of the turnout deformation index value, if the value of the deformation index is outside the safe threshold range, the system prompts an alarm.
进一步地，所述道岔形变指标包括道岔尖轨与基本轨的密贴度、斥离度和尖轨的纵向位移。Further, the deformation index of the switch includes the degree of closeness and separation between the point rail and the basic rail of the point rail, and the longitudinal displacement of the point rail.
进一步地，所述系统分析单元通过分析计算得到道岔形变指标相对变化数值的步骤包括：Further, the step of obtaining the relative change value of the turnout deformation index by the system analysis unit through analysis and calculation includes:
由所述检测装置采集的岔尖区域3D图像得到岔尖点的真实坐标；The real coordinates of the fork tip point are obtained from the 3D image of the fork tip area collected by the detection device;
将所述岔尖的真实坐标与标定值进行计算转换，得出道岔形变指标相对变化数值，所述标定值为在岔尖密合时通过所述检测装置采集的图像信息中岔尖点的坐标。Calculating and converting the real coordinates of the switch point and the calibration value to obtain the relative change value of the deformation index of the switch point, and the calibration value is the coordinate of the point of the switch point in the image information collected by the detection device when the switch point is close together .
进一步地，所述系统分析单元还用于对检测结果进行校正，具体步骤包括：Further, the system analysis unit is also used to correct the detection result, and the specific steps include:
获取点云数据，并对所述点云数据进行二次极线校正；Obtaining point cloud data, and performing secondary epipolar line correction on the point cloud data;
对二次校正后的点云数据进行滤波处理；Filter the point cloud data after secondary correction;
对滤波后的点云数据进行分割得到岔尖边缘，并利用亚像素技术校正边缘点；Segment the filtered point cloud data to obtain the tip edge, and use sub-pixel technology to correct the edge point;
通过计算多个三维点的相对距离滤波得到三维位移距离；The three-dimensional displacement distance is obtained by calculating the relative distance filtering of multiple three-dimensional points;
对所述三维位移距离对做垂直方向投影得到所述道岔形变指标。The deformation index of the turnout is obtained by vertically projecting the three-dimensional displacement distance pair.
进一步地，所述滤波处理包括：Further, the filtering process includes:
分别以图像中各点为中心点，并统计领域内所有点与中心点的距离值；Take each point in the image as the center point, and count the distance values between all points in the field and the center point;
对得到的所有距离值做平均运算，得到领域内所有点与中心点的平均距离；Perform an average operation on all the obtained distance values to obtain the average distance between all points in the field and the center point;
将与中心点距离大于所述平均距离的点作为噪声点舍弃。Points whose distance from the center point is greater than the average distance are discarded as noise points.
较现有技术相比，本发明具有以下优点：Compared with the prior art, the present invention has the following advantages:
本发明以数字图像处理和机器视觉为基础，从采集图像中提取出道岔状态特征,并对道岔状态进行智能监测检测的功能。通过直接手段对道岔进行监测和预警，对保证列车安全运行具有重要的现实意义。Based on digital image processing and machine vision, the present invention extracts the state characteristics of the turnout from the collected images, and performs intelligent monitoring and detection on the state of the turnout. Monitoring and early warning of turnouts by direct means is of great practical significance to ensure the safe operation of trains.
基于上述理由本发明可在轨道交通安全领域广泛推广。Based on the above reasons, the present invention can be widely promoted in the rail traffic safety field.
附图说明Description of drawings
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图做以简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained according to these drawings without any creative effort.
图1为本发明装置外观图。Fig. 1 is the external view of the device of the present invention.
图2为本发明装置结构示意图。Fig. 2 is a schematic structural diagram of the device of the present invention.
图3为本发明实施例中装置尺寸示意图。Fig. 3 is a schematic diagram of the size of the device in the embodiment of the present invention.
图4为本发明装置安装位置示意图。Fig. 4 is a schematic diagram of the installation position of the device of the present invention.
图5为本发明系统结构框图。Fig. 5 is a block diagram of the system structure of the present invention.
图6为本发明系统安装示意图。Fig. 6 is a schematic diagram of the installation of the system of the present invention.
图7为本发明系统检测结果校正流程图。Fig. 7 is a flow chart of the correction of the detection result of the system of the present invention.
具体实施方式Detailed ways
需要说明的是，在不冲突的情况下，本发明中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本发明。It should be noted that, in the case of no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and examples.
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。以下对至少一个示例性实施例的描述实际上仅仅是说明性的，决不作为对本发明及其应用或使用的任何限制。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is only some embodiments of the present invention, but not all embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and in no way taken as limiting the invention, its application or uses. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
如图1-4所示，本发明公开一种道岔现场检测装置，包括外壳及设置在外壳内部的双目相机及激光器，所述外壳内部中空区域被设定为包括双目相机固定区域、激光发射器固定区域、电源模块固定区域以及工控模块固定区域；所述激光发射器固定区域包括第一侧面及激光发射平面，所述激光发射器的发射口透过设置于所述激光发射平面上的通孔、沿垂直于所述激光发射平面方向发射激光；所述双目相机固定区域包括第二侧面、第三侧面以及相机拍摄平面，所述双目相机的镜头透过设置于所述相机拍摄平面上的两个并列通孔、沿垂直于所述相机拍摄平面方向拍摄；其中，所述激光发射平面与所述第二侧面的夹角大于90°。为了保证装置拍摄的图像信息的质量，在使用时需保证双目摄像机两个镜头的中垂线与岔尖延伸线的夹角保证45°，且双目摄像机两个镜头的中垂点距离基本轨0.2-0.3米。装置安装位置的准确性直接影响图像信息的质量，进而对岔尖形变指标的分析造成巨大影响。但是双目摄像机与基本轨之间需要辅助工具进行角度和距离的直接测量，后续使用过程中如果要重新布置装置位置，还需要其他辅助设备重新测量角度和距离。为了实现装置的快速定位安装，装置采用激光发射器向基本轨方向发射准直激光，因为双目摄像机镜头拍摄方向与激光发射方向相对角度固定，则确定激光光线照射的相对位置和角度，也就可以间接确定双目摄像机拍摄角度与基本轨间的相对位置和角度。进一步地，所述激光发射器发出的激光照射在所述双目相机两个镜头拍摄区域重合部分的中心。作为一种优选的实施方式，本实施例中，将激光照射平面与第二侧面的夹角设置为100°，各面边长如图4所示，激光发射平面边长70.39mm，相机拍摄平面边长190mm，第一平面边长140mm，第二平面边长68.23mm，第三平面边长59.51mm。此时，外壳呈锯齿状梯形结构，激光发射平面与第三平面夹角25°，双目相机与第三平面夹角135°。这里只需要保证激光照射基本轨的光点对准岔尖位置，即可保证双目相机两个镜头拍摄范围包括岔尖部分。施工人员在安装时，仅需要打开激光发射器，激光在基本轨上投射至岔尖位置，则双目摄像机即可拍摄以岔尖为中心的一定范围内的图像。As shown in Figures 1-4, the present invention discloses an on-site detection device for a turnout, which includes a housing, a binocular camera and a laser installed inside the housing, and the hollow area inside the housing is set to include a fixed area for the binocular camera, a laser The transmitter fixed area, the power module fixed area and the industrial control module fixed area; the laser emitter fixed area includes a first side and a laser emission plane, and the emission port of the laser emitter passes through the laser emission plane arranged on the Through holes, emitting laser light in a direction perpendicular to the laser emitting plane; the fixed area of the binocular camera includes a second side, a third side and a camera shooting plane, and the lens of the binocular camera passes through and is arranged on the camera to shoot The two parallel through holes on the plane are taken along the direction perpendicular to the camera shooting plane; wherein, the angle between the laser emitting plane and the second side is greater than 90°. In order to ensure the quality of the image information captured by the device, it is necessary to ensure that the angle between the vertical line of the two lenses of the binocular camera and the extension line of the fork tip is guaranteed to be 45° during use, and the distance between the vertical points of the two lenses of the binocular camera is basically Rail 0.2-0.3 meters. The accuracy of the installation position of the device directly affects the quality of the image information, which in turn has a huge impact on the analysis of the deformation index of the fork tip. However, auxiliary tools are needed to directly measure the angle and distance between the binocular camera and the basic rail. If the position of the device is to be rearranged during subsequent use, other auxiliary equipment is required to re-measure the angle and distance. In order to realize the rapid positioning and installation of the device, the device uses a laser transmitter to emit collimated laser light in the direction of the basic rail. Because the relative angle between the shooting direction of the binocular camera lens and the laser emitting direction is fixed, the relative position and angle of the laser light irradiation is determined, that is, The relative position and angle between the shooting angle of the binocular camera and the basic rail can be determined indirectly. Further, the laser light emitted by the laser emitter is irradiated on the center of the overlapping shooting area of the two lenses of the binocular camera. As a preferred implementation, in this embodiment, the angle between the laser irradiation plane and the second side is set to 100°, the side lengths of each side are shown in Figure 4, the side length of the laser emission plane is 70.39mm, and the camera shooting plane The side length is 190mm, the side length of the first plane is 140mm, the side length of the second plane is 68.23mm, and the side length of the third plane is 59.51mm. At this time, the casing has a zigzag trapezoidal structure, the angle between the laser emitting plane and the third plane is 25°, and the angle between the binocular camera and the third plane is 135°. Here, it is only necessary to ensure that the light spot of the laser irradiating the basic rail is aligned with the position of the fork tip, and then the shooting range of the two lenses of the binocular camera includes the fork tip. When installing, the construction personnel only need to turn on the laser transmitter, and the laser is projected on the basic rail to the position of the fork tip, and then the binocular camera can capture images within a certain range centered on the fork tip.
进一步地，所述外壳上表面呈点阵式分布有若干散热孔，以保证摄像机和激光发射器在工作过程中产生的热量能够有效散发到空气中。Furthermore, a number of cooling holes are distributed in a dot matrix on the upper surface of the casing to ensure that the heat generated by the camera and the laser transmitter during operation can be effectively dissipated into the air.
本发明还提供了一种道岔检测系统，包括上述任意一项所述的检测装置。The present invention also provides a switch detection system, including the detection device described in any one of the above.
进一步地，系统还包括控制单元以及系统分析单元；Further, the system also includes a control unit and a system analysis unit;
所述控制单元控制所述检测装置以设定频率对轨道运行状态下的道岔结构进行图像采集，并将所采集到的图像信息送至所述系统分析单元进行分析计算，得到道岔形变指标相对变化数值，若所述形变指标数值在安全阈值范围外，系统提示报警。The control unit controls the detection device to collect images of the turnout structure under the track running state at a set frequency, and sends the collected image information to the system analysis unit for analysis and calculation, and obtains the relative change of the turnout deformation index value, if the value of the deformation index is outside the safe threshold range, the system prompts an alarm.
进一步地，所述道岔形变指标包括道岔尖轨与基本轨的密贴度、斥离度和尖轨的纵向位移。Further, the deformation index of the switch includes the degree of closeness and separation between the point rail and the basic rail of the point rail, and the longitudinal displacement of the point rail.
进一步地，所述系统分析单元通过分析计算得到道岔形变指标相对变化数值的步骤包括：Further, the step of obtaining the relative change value of the turnout deformation index by the system analysis unit through analysis and calculation includes:
由所述检测装置采集的岔尖区域3D图像得到岔尖点的真实坐标；The real coordinates of the fork tip point are obtained from the 3D image of the fork tip area collected by the detection device;
将所述岔尖的真实坐标与标定值进行计算转换，得出道岔形变指标相对变化数值，所述标定值为在岔尖密合时通过所述检测装置采集的图像信息中岔尖点的坐标。Calculating and converting the real coordinates of the switch point and the calibration value to obtain the relative change value of the deformation index of the switch point, and the calibration value is the coordinate of the point of the switch point in the image information collected by the detection device when the switch point is close together .
进一步地，所述系统分析单元还用于对检测结果进行校正，具体步骤包括：Further, the system analysis unit is also used to correct the detection result, and the specific steps include:
获取点云数据，并对所述点云数据进行二次极线校正；Obtaining point cloud data, and performing secondary epipolar line correction on the point cloud data;
对二次校正后的点云数据进行滤波处理；Filter the point cloud data after secondary correction;
对滤波后的点云数据进行分割得到岔尖边缘，并利用亚像素技术校正边缘点；Segment the filtered point cloud data to obtain the tip edge, and use sub-pixel technology to correct the edge point;
通过计算多个三维点的相对距离滤波得到三维位移距离；The three-dimensional displacement distance is obtained by calculating the relative distance filtering of multiple three-dimensional points;
对所述三维位移距离对做垂直方向投影得到所述道岔形变指标。The deformation index of the turnout is obtained by vertically projecting the three-dimensional displacement distance pair.
进一步地，所述滤波处理包括：Further, the filtering process includes:
分别以图像中各点为中心点，并统计领域内所有点与中心点的距离值；Take each point in the image as the center point, and count the distance values between all points in the field and the center point;
对得到的所有距离值做平均运算，得到领域内所有点与中心点的平均距离；Perform an average operation on all the obtained distance values to obtain the average distance between all points in the field and the center point;
将与中心点距离大于所述平均距离的点作为噪声点舍弃。Points whose distance from the center point is greater than the average distance are discarded as noise points.
如图1-7所示，本发明提供了一种道岔检测系统，其特征在于，包括：系统控制单元、图像采集单元以及系统分析单元；所述控制单元控制所述图像采集单元以设定频率对轨道运行状态下的道岔结构进行图像采集，并将所采集到的图像信息送至所述系统分析单元进行分析计算，得到道岔形变指标相对变化数值，若所述形变指标数值在安全阈值范围外，系统提示报警。其中，道岔形变指标包括道岔尖轨与基本轨的密贴度、斥离度和尖轨的纵向位移。As shown in Figures 1-7, the present invention provides a turnout detection system, which is characterized in that it includes: a system control unit, an image acquisition unit, and a system analysis unit; the control unit controls the image acquisition unit to set the frequency Collect images of the turnout structure under the track running state, and send the collected image information to the system analysis unit for analysis and calculation, and obtain the relative change value of the deformation index of the turnout, if the value of the deformation index is outside the safety threshold range , the system prompts an alarm. Among them, the deformation index of the turnout includes the closeness, repulsion and longitudinal displacement of the switch point rail and the basic rail.
图像采集单元采用3D工业相机与激光器协同工作，其视野方向与岔尖成45°夹角，且与基本轨距离为0.2-0.3米。The image acquisition unit uses a 3D industrial camera and a laser to work together. Its field of view forms an angle of 45° with the fork tip, and the distance from the basic rail is 0.2-0.3 meters.
系统分析单元通过分析计算得到道岔形变指标相对变化数值的步骤包括：The steps for the system analysis unit to obtain the relative change value of the turnout deformation index through analysis and calculation include:
a.由所述3D工业相机采集的岔尖区域3D图像得到岔尖点的真实坐标；a. The real coordinates of the fork point are obtained from the 3D image of the fork tip area collected by the 3D industrial camera;
b.将所述岔尖的真实坐标与标定值进行计算转换，得出道岔形变指标相对变化数值。标定值为在岔尖密合时通过所述3D工业相机采集的图像信息中岔尖点的坐标。b. Calculating and converting the real coordinates of the turnout point and the calibration value to obtain the relative change value of the turnout deformation index. The calibration value is the coordinate of the fork tip point in the image information collected by the 3D industrial camera when the fork tip is close together.
此外，系统分析单元还对检测结果进行校正，如图7所示，具体步骤包括：In addition, the system analysis unit also corrects the detection results, as shown in Figure 7, and the specific steps include:
a.获取点云数据，并对所述点云数据进行二次极线校正。图像的每个像素点的灰度值可用于表征场景中某一点距离摄像机的远近。直接反应了景物可见表面的几何形状，经过坐标转换可以计算为点云数据。a. Obtain point cloud data, and perform secondary epipolar line correction on the point cloud data. The gray value of each pixel in the image can be used to represent the distance of a point in the scene from the camera. It directly reflects the geometric shape of the visible surface of the scene, and can be calculated as point cloud data after coordinate conversion.
b.对二次校正后的点云数据进行滤波处理,包括：b. Filter the point cloud data after secondary correction, including:
1)分别以图像中各点为中心点，并统计领域内所有点与中心点的距离值；1) Take each point in the image as the center point, and count the distance values between all points in the field and the center point;
2)对得到的所有距离值做平均运算，得到领域内所有点与中心点的平均距离；2) Perform an average operation on all obtained distance values to obtain the average distance between all points in the field and the center point;
3)将与中心点距离大于所述平均距离的点作为噪声点舍弃。3) The points whose distance from the center point is greater than the average distance are discarded as noise points.
c.对滤波后的点云数据进行分割得到岔尖边缘，并利用亚像素技术校正边缘点。c. Segment the filtered point cloud data to obtain the tip edge, and use sub-pixel technology to correct the edge point.
d.通过计算多个三维点的相对距离滤波得到三维位移距离。d. The three-dimensional displacement distance is obtained by calculating the relative distance filtering of multiple three-dimensional points.
e.对所述三维位移距离对做垂直方向投影得到所述道岔形变指标。e. Perform vertical projection on the three-dimensional displacement distance pair to obtain the turnout deformation index.
下面通过具体的应用实例，对本发明的技术方案做进一步说明：The technical solution of the present invention will be further described below through specific application examples:
本实施例中提供了一种基于3D技术的道岔检测设备，包含系统控制单元、图像采集单元、数据分析单元。系统控制单元主要包括系统控制板、系统存储服务器、声光报警器。图像采集单元由3D相机及激光器组成。数据分析单元由分析识别服务器组成，数据分析单元是整套系统的核心部分，可对所采集到的3D图像进行分析。精准分析所采集的图像。从而判断道岔尖轨与基本轨的密贴度、斥离度和尖轨的纵向位移(尖轨爬行)。尖轨密贴的监控范围为0-20mm，精度为0.1mm。斥离度的监控范围为0-200mm，精度为0.1mm。尖轨爬行的监测范围为±120mm，精度0.1mm。当发现超限情况时，系统立即发出告警指令，控制控制中心内的声光报警器工作，提醒工作人员及时应对。降低列车运行风险。This embodiment provides a turnout detection device based on 3D technology, including a system control unit, an image acquisition unit, and a data analysis unit. The system control unit mainly includes a system control panel, a system storage server, and an audible and visual alarm. The image acquisition unit consists of a 3D camera and a laser. The data analysis unit is composed of an analysis and identification server. The data analysis unit is the core part of the whole system and can analyze the collected 3D images. Accurately analyze the captured images. So as to judge the closeness and repulsion between the point rail and the basic rail, and the longitudinal displacement of the point rail (point rail crawling). The monitoring range of the tip rail close fit is 0-20mm, and the accuracy is 0.1mm. The monitoring range of repulsion is 0-200mm, and the accuracy is 0.1mm. The monitoring range of point rail crawling is ±120mm, and the accuracy is 0.1mm. When an over-limit situation is found, the system immediately sends out an alarm command to control the operation of the sound and light alarm in the control center to remind the staff to respond in time. Reduce the risk of train operation.
具体安装位置为：1套3D工业相机安置于定制化一体防护罩内，防护罩安装于轨道中央。距离基本轨0.2-0.3米，3D工业相机视野方向与岔尖成45°夹角。实时对道岔状态进行监测。系统控制单元和数据分析单元安装在铁路沿线防护箱内。通过地下穿线管进行布线完成信息通信。The specific installation location is: 1 set of 3D industrial cameras is placed in a customized integrated protective cover, and the protective cover is installed in the center of the track. The distance from the basic rail is 0.2-0.3 meters, and the field of view of the 3D industrial camera forms an angle of 45° with the tip of the fork. Real-time monitoring of turnout status. The system control unit and data analysis unit are installed in protective boxes along the railway. Wiring through underground conduits completes information communication.
通过3D相机对道岔结构进行图像采集，生成3D图像。基于图像识别算法对图像进行识别，具体方法如下：The 3D camera is used to collect images of the turnout structure to generate a 3D image. The image is recognized based on the image recognition algorithm, the specific method is as follows:
方法概述：由图像采集单元对岔尖区域进行图像采集，得到岔尖的三维尺寸。密贴、斥离度监测方案为在岔尖密合时做图像标定，并记录岔尖点的坐标，求得的岔尖点坐标与标定值进行计算转换，得到密贴、斥离距离。爬行距离方案与斥离检测方案一致，需要先标定岔尖位置，然后根据三维坐标转换得到相对与标定点的爬行距离。Method overview: The image acquisition unit collects images of the fork tip area to obtain the three-dimensional size of the fork tip. The close-fitting and repelling degree monitoring scheme is to perform image calibration when the fork tips are close together, and record the coordinates of the fork-tip points, and calculate and convert the obtained fork-tip point coordinates with the calibration value to obtain the close-fitting and repelling distances. The creeping distance scheme is consistent with the repulsion detection scheme. It is necessary to calibrate the position of the fork tip first, and then obtain the crawling distance relative to the calibration point according to the three-dimensional coordinate conversion.
为保证系统检测精度，本项目组提出一种校对方法，与上述检测结果进行误差矫正，以得到更准确值。具体方法为：对3D图像进行算法分析，直接得到主轨的三维平面方程，然后求得岔尖点三维坐标，得到点到平面的垂直距离作为斥离距离。与检测结果进行对比，求平均值作为检测结果。In order to ensure the detection accuracy of the system, the project team proposed a proofreading method to correct the errors with the above detection results to obtain more accurate values. The specific method is: carry out algorithm analysis on the 3D image, directly obtain the three-dimensional plane equation of the main rail, then obtain the three-dimensional coordinates of the fork point, and obtain the vertical distance from the point to the plane as the repelling distance. Compared with the test results, the average value is taken as the test result.
具体方法：对得到的双目图像进行图像立体校正，并加以二次极线校正，保证三维重建的精确度。获取点云数据时，由于设备精度、电磁波的衍射特性、被测物体表面性质变化和点云拼接配准操作过程的影响，点云数据中讲不可避免的出现一些噪声。在点云处理流程中滤波处理作为预处理的第一步，对后续的影响比较大。每个点的邻域进行一个统计分析，并修剪掉一些不符合一定标准的点，基于在输入数据中对点到临近点的距离分布的计算，对每一个点，计算它到它的所有临近点的平均距离，假设得到的结果是一个高斯分布，其形状是由均值和标准差决定，平均距离在标准范围之外的点，可以被定义为噪声点并可从数据中去除。对三维点云数据进行滤波并分割后，可得到岔尖边缘。Specific method: Carry out image stereo correction on the obtained binocular image, and add secondary epipolar line correction to ensure the accuracy of three-dimensional reconstruction. When acquiring point cloud data, due to the influence of equipment accuracy, diffraction characteristics of electromagnetic waves, changes in the surface properties of the measured object, and the operation process of point cloud splicing and registration, some noise will inevitably appear in the point cloud data. As the first step of preprocessing in the point cloud processing flow, filtering processing has a relatively large impact on the follow-up. A statistical analysis is performed on the neighborhood of each point, and some points that do not meet certain criteria are pruned. Based on the calculation of the distance distribution from the point to the adjacent point in the input data, for each point, calculate it to all its neighbors The average distance of points, assuming that the obtained result is a Gaussian distribution, its shape is determined by the mean and standard deviation, and the points whose average distance is outside the standard range can be defined as noise points and can be removed from the data. After filtering and segmenting the 3D point cloud data, the tip edge can be obtained.
对二维图像求canny边缘，得到岔尖边缘图。二维图像得到的边缘图会对三维分割得到的边缘进行二次校准，并利用亚像素技术进一步优化边缘点，以保证测量点的准确性。距离的计算由多个三维点的相对距离滤波而得到。其中两点间的距离根据一下公式求得：Calculate the canny edge on the two-dimensional image to obtain the fork tip edge map. The edge map obtained from the 2D image will recalibrate the edge obtained from the 3D segmentation, and further optimize the edge points by using sub-pixel technology to ensure the accuracy of the measurement points. The calculation of the distance is obtained by filtering the relative distance of multiple three-dimensional points. The distance between two points is calculated according to the following formula:
其中，(x1,y1,z1)与(x2,y2,z2)为三维空间中的两点。对得到的距离做X方向与Z方向的投影，得到密贴、斥离度与爬行距离。Wherein, (x 1 , y 1 , z 1 ) and (x 2 , y 2 , z 2 ) are two points in the three-dimensional space. Project the obtained distance in the X direction and Z direction to obtain close adhesion, repulsion and crawling distance.
最后应说明的是：以上各实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述各实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the various embodiments of the present invention. scope.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910736382.7A CN110293993B (en) | 2019-08-09 | 2019-08-09 | A turnout detection device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910736382.7A CN110293993B (en) | 2019-08-09 | 2019-08-09 | A turnout detection device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110293993A true CN110293993A (en) | 2019-10-01 |
| CN110293993B CN110293993B (en) | 2024-07-26 |
Family
ID=68032921
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910736382.7A Active CN110293993B (en) | 2019-08-09 | 2019-08-09 | A turnout detection device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110293993B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111127436A (en) * | 2019-12-25 | 2020-05-08 | 北京深测科技有限公司 | Displacement detection early warning method for bridge |
| CN111311590A (en) * | 2020-03-06 | 2020-06-19 | 通控研究院(安徽)有限公司 | Turnout switch point tightness detection method based on image detection technology |
| CN112342852A (en) * | 2020-11-27 | 2021-02-09 | 上海邦诚电信技术股份有限公司 | Turnout working condition comprehensive inspection device, and turnout working condition comprehensive monitoring system and method |
| CN112580465A (en) * | 2020-12-08 | 2021-03-30 | 卡斯柯信号有限公司 | Switch overhaul evaluation method and system |
| CN113753094A (en) * | 2021-09-24 | 2021-12-07 | 北京杰迈科技股份有限公司 | Switch detection system and method |
| CN113970354A (en) * | 2021-09-24 | 2022-01-25 | 西安铁路信号有限责任公司 | Method for controlling normal start and stop of push rod of test board of seal inspection device |
| CN114179866A (en) * | 2021-12-10 | 2022-03-15 | 青岛地铁集团有限公司运营分公司 | Track turnout opening direction safety detection system and detection method |
| CN114179865A (en) * | 2021-11-15 | 2022-03-15 | 通号城市轨道交通技术有限公司 | Turnout motion monitoring method, device and system based on optical flow method |
| CN114666550A (en) * | 2022-04-02 | 2022-06-24 | 南京理工大学 | Contact point parameter detection device and method of close contact checker based on image processing |
| CN114987564A (en) * | 2022-06-16 | 2022-09-02 | 西南交通大学 | A portable high-speed switch detection car and detection method based on binocular recognition |
| CN115131377A (en) * | 2021-03-26 | 2022-09-30 | 北京理工大学 | Railway turnout spacing detection method, device and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105526882A (en) * | 2015-12-28 | 2016-04-27 | 西南交通大学 | Turnout wear detection system and detection method based on structured light measurement |
| US20170066459A1 (en) * | 2015-09-03 | 2017-03-09 | Sameer Singh | Rail track asset survey system |
| WO2018049818A1 (en) * | 2016-08-16 | 2018-03-22 | 上海汇像信息技术有限公司 | Three-dimensional measurement technology-based system and method for measuring surface area of object |
| CN208411752U (en) * | 2018-07-11 | 2019-01-22 | 廊坊英博电气有限公司 | Track detecting device and detection device |
| CN210391171U (en) * | 2019-08-09 | 2020-04-24 | 大连维德集成电路有限公司 | Switch detection device |
-
2019
- 2019-08-09 CN CN201910736382.7A patent/CN110293993B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170066459A1 (en) * | 2015-09-03 | 2017-03-09 | Sameer Singh | Rail track asset survey system |
| CN105526882A (en) * | 2015-12-28 | 2016-04-27 | 西南交通大学 | Turnout wear detection system and detection method based on structured light measurement |
| WO2018049818A1 (en) * | 2016-08-16 | 2018-03-22 | 上海汇像信息技术有限公司 | Three-dimensional measurement technology-based system and method for measuring surface area of object |
| CN208411752U (en) * | 2018-07-11 | 2019-01-22 | 廊坊英博电气有限公司 | Track detecting device and detection device |
| CN210391171U (en) * | 2019-08-09 | 2020-04-24 | 大连维德集成电路有限公司 | Switch detection device |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111127436A (en) * | 2019-12-25 | 2020-05-08 | 北京深测科技有限公司 | Displacement detection early warning method for bridge |
| CN111127436B (en) * | 2019-12-25 | 2023-10-20 | 北京深测科技有限公司 | Displacement detection early warning method for bridge |
| CN111311590A (en) * | 2020-03-06 | 2020-06-19 | 通控研究院(安徽)有限公司 | Turnout switch point tightness detection method based on image detection technology |
| CN111311590B (en) * | 2020-03-06 | 2023-11-21 | 通控研究院(安徽)有限公司 | Switch point contact degree detection method based on image detection technology |
| CN112342852A (en) * | 2020-11-27 | 2021-02-09 | 上海邦诚电信技术股份有限公司 | Turnout working condition comprehensive inspection device, and turnout working condition comprehensive monitoring system and method |
| CN112580465A (en) * | 2020-12-08 | 2021-03-30 | 卡斯柯信号有限公司 | Switch overhaul evaluation method and system |
| CN115131377A (en) * | 2021-03-26 | 2022-09-30 | 北京理工大学 | Railway turnout spacing detection method, device and system |
| CN113753094A (en) * | 2021-09-24 | 2021-12-07 | 北京杰迈科技股份有限公司 | Switch detection system and method |
| CN113970354B (en) * | 2021-09-24 | 2022-08-09 | 西安铁路信号有限责任公司 | Method for controlling normal start and stop of push rod of test board of seal inspection device |
| CN113970354A (en) * | 2021-09-24 | 2022-01-25 | 西安铁路信号有限责任公司 | Method for controlling normal start and stop of push rod of test board of seal inspection device |
| CN114179865A (en) * | 2021-11-15 | 2022-03-15 | 通号城市轨道交通技术有限公司 | Turnout motion monitoring method, device and system based on optical flow method |
| CN114179866A (en) * | 2021-12-10 | 2022-03-15 | 青岛地铁集团有限公司运营分公司 | Track turnout opening direction safety detection system and detection method |
| CN114666550A (en) * | 2022-04-02 | 2022-06-24 | 南京理工大学 | Contact point parameter detection device and method of close contact checker based on image processing |
| CN114666550B (en) * | 2022-04-02 | 2024-09-20 | 南京理工大学 | Device and method for detecting contact point parameters of close-fit inspector based on image processing |
| CN114987564A (en) * | 2022-06-16 | 2022-09-02 | 西南交通大学 | A portable high-speed switch detection car and detection method based on binocular recognition |
| CN114987564B (en) * | 2022-06-16 | 2023-10-20 | 西南交通大学 | Portable high-speed turnout detection trolley based on binocular identification and detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110293993B (en) | 2024-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110293993B (en) | A turnout detection device and system | |
| CN113536883B (en) | Obstacle detection method, vehicle, apparatus, and computer storage medium | |
| EP3138754B1 (en) | Rail track asset survey system | |
| KR101602376B1 (en) | A train faulty monitoring system | |
| CN109489584B (en) | Tunnel clearance detection system and tunnel clearance identification method based on 3D technology | |
| CN109633674A (en) | Three-dimensional Track automatic planning is maked an inspection tour in transmission of electricity based on laser point cloud data | |
| CN110986820B (en) | Track intrusion detection method, device and electronic equipment | |
| KR102017870B1 (en) | Real-time line defect detection system | |
| CN105115605A (en) | Track train infrared detection system and detection method | |
| CN112539704B (en) | A method for measuring the distance between hidden dangers and conductors in transmission line channels | |
| CN110133669A (en) | A three-dimensional laser foreign body invasion monitoring method and system | |
| CN112960014B (en) | Rail transit operation safety online real-time monitoring and early warning management cloud platform based on artificial intelligence | |
| AU2017232220B2 (en) | Railroadtrack asset survey system | |
| CN115035087B (en) | A new railway line image detection method and system | |
| CN114572273B (en) | Railway vehicle wheel set tread 3D image detection method | |
| CN114148378B (en) | Audible and visual alarm for railway section operation protection | |
| ES2394902A1 (en) | SYSTEM AND PROCEDURE FOR MEASURING THE THICKNESS OF PANTOGRAPH SCRAPERS. | |
| CN115503788A (en) | A ballasted track bed section scanning detection system | |
| KR20150034860A (en) | Pole position detection system through number recognition | |
| CN118898892A (en) | A parallel monitoring and early warning method for highway slopes | |
| CN105292179A (en) | Wheel rim size detection method | |
| Rikhotso et al. | 3D rail modelling and measurement for rail profile condition assessment | |
| CN205157057U (en) | Infrared detecting system of rail train | |
| CN117842130A (en) | Rapid continuous profile detection method based on line structured laser | |
| CN112001971A (en) | Object identification method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |