CN103955980B - Human body model feature based bus passenger flow statistic device and processing method - Google Patents
Human body model feature based bus passenger flow statistic device and processing method Download PDFInfo
- Publication number
- CN103955980B CN103955980B CN201410200293.8A CN201410200293A CN103955980B CN 103955980 B CN103955980 B CN 103955980B CN 201410200293 A CN201410200293 A CN 201410200293A CN 103955980 B CN103955980 B CN 103955980B
- Authority
- CN
- China
- Prior art keywords
- passenger flow
- lens
- axis
- door
- infrared light
- 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.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims description 8
- 238000001514 detection method Methods 0.000 claims abstract description 56
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000004891 communication Methods 0.000 claims abstract description 7
- JBRZTFJDHDCESZ-UHFFFAOYSA-N AsGa Chemical compound [As]#[Ga] JBRZTFJDHDCESZ-UHFFFAOYSA-N 0.000 claims description 39
- 229910001218 Gallium arsenide Inorganic materials 0.000 claims description 39
- 238000000034 method Methods 0.000 claims description 7
- 239000011347 resin Substances 0.000 claims description 6
- 229920005989 resin Polymers 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000009434 installation Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- GYHNNYVSQQEPJS-UHFFFAOYSA-N Gallium Chemical compound [Ga] GYHNNYVSQQEPJS-UHFFFAOYSA-N 0.000 claims description 2
- 230000009471 action Effects 0.000 claims description 2
- 229910052733 gallium Inorganic materials 0.000 claims description 2
- 238000002347 injection Methods 0.000 claims description 2
- 239000007924 injection Substances 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims 6
- 230000003287 optical effect Effects 0.000 claims 4
- 238000013508 migration Methods 0.000 claims 3
- 230000005012 migration Effects 0.000 claims 3
- 229910052785 arsenic Inorganic materials 0.000 claims 1
- RQNWIZPPADIBDY-UHFFFAOYSA-N arsenic atom Chemical compound [As] RQNWIZPPADIBDY-UHFFFAOYSA-N 0.000 claims 1
- 230000000694 effects Effects 0.000 claims 1
- 239000004744 fabric Substances 0.000 claims 1
- 238000002513 implantation Methods 0.000 claims 1
- 238000009738 saturating Methods 0.000 claims 1
- 238000003384 imaging method Methods 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000003491 array Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000000903 blocking effect Effects 0.000 description 2
- 238000005111 flow chemistry technique Methods 0.000 description 2
- 239000007943 implant Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Landscapes
- Measurement Of Optical Distance (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
本发明公开了一种基于人体模型特征的公交车客流统计装置,包括客流处理器、车门状态检测单元和安装在公交车车门顶部的客流传感器;客流传感器用于对公交车上客门和下客门通行的乘客进行截面轮廓扫描,创建立体三维数据;客流处理器包括车门状态检测输入单元、人体特征信号输入单元、高速数据处理单元、数据缓存单元和一个数据通讯接口,用于对所有连接的所述的客流传感器的立体三维数据进行配对运算,与人体模型特征库进行比对,过滤符合与人体模型特征的物体信号,并结合车门状态信息产生实时的上客门和下客人门上车或下车的客流数据;统计精度高,且统计精度不受环境光线、车辆振动、昼夜分差等因素影响。
The invention discloses a bus passenger flow statistics device based on the characteristics of a human body model, which comprises a passenger flow processor, a door state detection unit and a passenger flow sensor installed on the top of the bus door; Passengers passing through the door scan the cross-sectional profile to create three-dimensional three-dimensional data; the passenger flow processor includes a door state detection input unit, a human body characteristic signal input unit, a high-speed data processing unit, a data cache unit and a data communication interface for all connected The three-dimensional three-dimensional data of the passenger flow sensor is paired and calculated, compared with the human body model feature library, and the object signal conforming to the human body model feature is filtered, and combined with the door state information to generate real-time boarding or exiting the passenger door. The passenger flow data of getting off the bus; the statistical accuracy is high, and the statistical accuracy is not affected by factors such as ambient light, vehicle vibration, and day and night differences.
Description
技术领域technical field
本发明涉及客流量检测设备技术领域,具体涉及一种基于人体模型特征的公交车客流统计装置及处理方法。The invention relates to the technical field of passenger flow detection equipment, in particular to a bus passenger flow statistics device and processing method based on human body model features.
背景技术Background technique
对于公交车的管理者和所有者而言,一种高精度的公交车客流统计系统的使用不仅可杜绝票款流失,还可以为线路规划、车辆调度、营运管理提供精准可靠的数据支持。For bus managers and owners, the use of a high-precision bus passenger flow statistics system can not only prevent the loss of fares, but also provide accurate and reliable data support for route planning, vehicle scheduling, and operation management.
专利申请号为201310688386.5的中国发明专利申请中描述了一种基于乘客多运动行为分析的公交车客流统计方法,采用视频处理技术,通过对提取乘客头部目标分析处理产生客流数据;专利申请号为201310731307.4的中国发明专利申请中描述了一种基于红外测距传感器的公交车客流统计系统,在对乘客计数过程采用红外测距传感器,对通过物体反射信号处理产生客流数据。The Chinese invention patent application with the patent application number 201310688386.5 describes a bus passenger flow statistics method based on passenger multi-movement behavior analysis, using video processing technology to generate passenger flow data by analyzing and processing the extracted passenger head targets; the patent application number is The Chinese invention patent application of 201310731307.4 describes a bus passenger flow statistics system based on infrared ranging sensors. In the process of counting passengers, infrared ranging sensors are used to generate passenger flow data through object reflection signal processing.
其中,专利申请号201310688386.5的中国发明专利申请中,视频图像受环境光线、照度变化、车辆振动、镜头曲率、摄像头成像质量以及图像处理器处理速度较慢等诸多因素的影响,使其统计精度、重复性精度无法达到高精度使用要求;专利申请号201310731307.4的中国发明专利申请中,在对乘客信息采集采用的是红外测距传感器对通过物体进行高度峰值判断处理,无法进行人物区分,无法过滤手臂动作误差等现实中较为常见的乘客运行动作,极易造成客流统计误差影响客流统计精度。Among them, in the Chinese invention patent application with patent application number 201310688386.5, the video image is affected by many factors such as ambient light, illumination changes, vehicle vibration, lens curvature, camera imaging quality, and slow processing speed of the image processor, making its statistical accuracy, The repeatability accuracy cannot meet the requirements of high-precision use; in the Chinese invention patent application with the patent application number 201310731307.4, the infrared ranging sensor is used for the peak height judgment processing of the passing objects in the collection of passenger information, and it is impossible to distinguish people and filter the arm Action errors and other common passenger movements in reality can easily cause errors in passenger flow statistics and affect the accuracy of passenger flow statistics.
发明内容Contents of the invention
针对现有技术存在的不足,本发明的目的在于提供一种使用红外技术对目标进行截面轮廓扫描,创建空间立体三维数据,通过对人体特征判断实现人、物分离,以及运动轨迹跟踪的统计方法,解决现有技术通过平面或简单的高度检测无法进行人、物区分等,且统计精度易受乘客动作影响的技术问题。Aiming at the deficiencies in the prior art, the object of the present invention is to provide a statistical method that uses infrared technology to scan the cross-sectional profile of the target, create spatial three-dimensional data, realize the separation of people and objects by judging the characteristics of the human body, and track the motion trajectory , to solve the technical problem that the existing technology cannot distinguish between people and objects through plane or simple height detection, and the statistical accuracy is easily affected by passenger movements.
为实现上述目的,本发明提供了如下技术方案:一种基于人体模型特征的公交车客流统计装置,包括一个客流处理器、一个车门状态检测单元和多个安装在公交车车门顶部的客流传感器;所述客流传感器包括两组阵列红外光源、一组CCD检测单元、三个透镜、一个滤光镜、一个数据处理单元和一个信号输出单元,用于对公交车上客门和下客门通行的乘客进行截面轮廓扫描,创建立体三维数据,所述三个透镜分别为第一透镜、第二透镜和第三透镜;所述 的客流处理器包括一个车门状态检测输入单元、多个人体特征信号输入单元、一个高速数据处理单元、一个数据缓存单元和一个数据通讯接口,用于对所有连接的所述的客流传感器的立体三维数据进行配对运算,与人体模型特征库进行比对,过滤符合与人体模型特征的物体信号,并结合车门状态信息产生实时的上客门和下客人门上车或下车的客流数据;所述的客流处理提供了一个通讯接口,为第三方设备提供客流数据支持。To achieve the above object, the present invention provides the following technical solutions: a bus passenger flow counting device based on human body model features, including a passenger flow processor, a door state detection unit and a plurality of passenger flow sensors installed on the top of the bus door; The passenger flow sensor includes two groups of array infrared light sources, a group of CCD detection units, three lenses, a filter mirror, a data processing unit and a signal output unit, which are used to pass through the passenger door and the passenger door of the bus. Passengers scan the cross-sectional profile to create three-dimensional three-dimensional data, the three lenses are the first lens, the second lens and the third lens; the passenger flow processor includes a door state detection input unit, a plurality of human body characteristic signal input unit, a high-speed data processing unit, a data cache unit and a data communication interface, which are used to perform pairing calculations on the three-dimensional and three-dimensional data of all connected passenger flow sensors, compare with the human body model feature library, and filter to match the human body model. The object signal of model characteristics, combined with the door state information, generates real-time passenger flow data of boarding or getting off at the passenger door and passenger door; the passenger flow processing provides a communication interface to provide passenger flow data support for third-party equipment.
本发明进一步设置为:所述客流传感器的两组阵列红外光源包括第一阵列红外光源和第二阵列红外光源,所述第一阵列红外光源由多个方型砷化镓芯片排列组成,由高纯度全透明树脂整体封装,方型砷化镓芯片组间距小于0.2mm,每个方型砷化镓芯片可单独外加带载波的正向偏压向PN结注入电流激发红外光;所述第二阵列红外光源由多个方型砷化镓芯片排列组成,由高纯度全透明树脂整体封装,方型砷化镓芯片组间距小于0.2mm,每个方型砷化镓芯片可单独外加带载波的正向偏压向PN结注入电流激发红外光;所述的第一阵列红外光源固定在第一透镜焦点上,每个方型砷化镓芯片激发红外光通过透镜投射在距离第一透镜一米距离的平面上透射出一个椭圆型Z轴方向长度15cm,X轴长度8cm的椭圆型光斑;所述的第二阵列红外光源固定在第二透镜焦点上,每个方型砷化镓芯片激发红外光通过透镜投射在距离第二透镜一米距离的平面上透射出一个椭圆型Z轴方向长度15cm,X轴长度8cm的椭圆型光斑;所述的CCD检测单元固定在固定在第三透镜焦点上,CCD检测单元和第三透镜之间设置了滤光镜,滤光镜用于过滤95%以上的波长小于780nm光线,允许波长大于780nm的光线通过,减低环境光线对CCD检测单元干扰影响,第三透镜可将入射角度±60度范围的光线聚焦在焦点上。The present invention is further configured as follows: the two sets of array infrared light sources of the passenger flow sensor include a first array infrared light source and a second array infrared light source, the first array infrared light source is composed of a plurality of square gallium arsenide chips arranged, and is composed of a high Purity fully transparent resin overall package, square gallium arsenide chip group spacing is less than 0.2mm, each square gallium arsenide chip can be separately applied with forward bias voltage with carrier to inject current into PN junction to excite infrared light; the second The array infrared light source is composed of a plurality of square gallium arsenide chips, which are packaged by high-purity transparent resin. The distance between the square gallium arsenide chips is less than 0.2mm. Forward bias injects current into the PN junction to excite infrared light; the first array of infrared light sources is fixed on the focal point of the first lens, and each square gallium arsenide chip excites infrared light and projects it through the lens at a distance of one meter from the first lens An elliptical light spot with a length of 15 cm in the Z-axis direction and 8 cm in the X-axis length is transmitted on the plane of the distance; the second array of infrared light sources is fixed on the focal point of the second lens, and each square gallium arsenide chip excites infrared The light is projected through the lens on a plane one meter away from the second lens to transmit an elliptical light spot with a length of 15 cm in the Z-axis direction and an 8 cm length in the X-axis; the CCD detection unit is fixed on the focal point of the third lens , A filter is set between the CCD detection unit and the third lens, the filter is used to filter more than 95% of the light with a wavelength less than 780nm, and allows the light with a wavelength greater than 780nm to pass through, reducing the interference of ambient light on the CCD detection unit. The three lenses can focus the light in the range of ±60 degrees of incident angle on the focal point.
本发明还进一步设置为:构建空间三维坐标,公交车车门包括上客门和下客门,按车身方向即车尾到车头方向定义为X轴;按车高方向即地面到车顶方向定义为Y轴;按上客方向即车外到车内的方向定义为Z轴正方向;按下客方向即车内到车外的方向定义为Z轴负方向,X轴表示CCD检测单元所采集到的当时红外扫描获取的物体截面宽度;Y轴表示当时不同高度反射面反射的红外;Z轴则表示CCD检测单元所采集到的当时物体运动轨迹。The present invention is further set as: building three-dimensional coordinates of the space, the bus door includes the upper passenger door and the lower passenger door, which is defined as the X axis according to the direction of the vehicle body, i.e. the direction from the rear to the front of the vehicle; the direction from the ground to the roof is defined as Y-axis; according to the passenger direction, that is, the direction from the outside to the inside of the car is defined as the positive direction of the Z-axis; the direction of the passenger, that is, the direction from the inside to the outside of the car, is defined as the negative direction of the Z-axis, and the X-axis represents the data collected by the CCD detection unit The cross-sectional width of the object acquired by the infrared scanning at that time; the Y axis indicates the infrared reflected by the reflective surface with different heights at that time; the Z axis indicates the object movement trajectory collected by the CCD detection unit at that time.
本发明还进一步设置为:所述的客流传感器的所述的第一阵列红外光源由所述数据处理单元进行控制,在X轴上从与CCD检测单元最远的方型砷化镓芯片开始依次激发红外光;通过所述的第一透镜的投射,每个砷化镓芯片激发的红外光通过透镜折射具有不同出射角度,覆盖以所述的客流传感器为中心的50cm宽度范围;所述的客流传感器的所述的第二阵列红外光源由所述数据处理单元进行控制,在X轴上从与CCD检测单元最远的方型砷化镓芯片开始依次激发红外光;通过所述的第二透镜的投射,每个砷化镓芯片激发的红外 光通过透镜折射具有不同出射角度,覆盖以所述的客流传感器为中心的50cm宽度范围。The present invention is further set as: the first array of infrared light sources of the passenger flow sensor is controlled by the data processing unit, starting from the square gallium arsenide chip farthest from the CCD detection unit on the X-axis Excite infrared light; through the projection of the first lens, the infrared light excited by each gallium arsenide chip has different exit angles through the lens refraction, covering the 50cm width range centered on the passenger flow sensor; the passenger flow The second array of infrared light sources of the sensor is controlled by the data processing unit, and the infrared light is sequentially excited from the square gallium arsenide chip farthest from the CCD detection unit on the X-axis; through the second lens The infrared light excited by each gallium arsenide chip is refracted by the lens and has different exit angles, covering a 50cm wide range centered on the passenger flow sensor.
本发明还进一步设置为:所述的客流传感器的所述的数据处理单元预先定义了每个位置的砷化镓芯片激发的红外光通过物体反射在所述CCD检测单元的成像偏移量L和物体距离Y关系的运算函数,所述的数据处理单元分别控制分布与CCD检测单元X轴两侧的所述的第一阵列红外光源和所述的第二阵列红外光源的多个砷化镓芯片激发的红外光进行不同区域扫描,同时记录CCD检测单元接收的不同物体表面反射的红外的成像偏移量,通过位置偏移量和物体距离关系的运算函数绘制出物体的空间截面轮廓,并编制成立体三维数据传输给所述客流处理器进行人体模型特征比对。The present invention is further set as: the data processing unit of the passenger flow sensor predefines the imaging offset L and the imaging offset L and The calculation function of the relationship between the object distance Y, the data processing unit respectively controls the multiple gallium arsenide chips of the first array infrared light source and the second array infrared light source distributed on both sides of the X-axis of the CCD detection unit The excited infrared light scans different areas, and at the same time records the imaging offset of the infrared reflected by the surface of different objects received by the CCD detection unit, draws the spatial cross-sectional profile of the object through the calculation function of the position offset and the distance relationship between the object, and compiles The three-dimensional three-dimensional data is transmitted to the passenger flow processor for feature comparison of human body models.
本发明还进一步设置为:两组阵列红外光源分别布置在CCD检测单元X轴的两侧,其目的在于避免由于目标物体不同高度平面反射的红外信号被遮挡导致CCD检测单元无法获取更多检测信息。The present invention is further set as follows: two sets of array infrared light sources are respectively arranged on both sides of the X-axis of the CCD detection unit, the purpose of which is to prevent the CCD detection unit from being unable to obtain more detection information due to the blocking of the infrared signals reflected by the planes of different heights of the target object .
本发明还进一步设置为:构建人体模型特征库,通过大量实际环境的信息采集,经过数字化处理并整合成人体模型特征库植入所述的客流处理器的高速数据处理单元内,所述的客流处理器实时对所有所述的客流传感器不同时刻不同安装位置的三维数据进行整合配对,配对处理后的立体三维数据与人体模型特征库进行比对,过滤不符合人体特征的数据,保留并对符合人体特征的立体三维数据进行运动轨迹的连续监测,运动轨迹长度大于设置值后,正方向表示上车,负方向表示下车,轨迹长度小于设置值时,则定义为无效动作运动轨迹。The present invention is further set up to: build a human body model feature library, collect a large amount of information from the actual environment, digitally process and integrate it into a human body model feature library and implant it into the high-speed data processing unit of the passenger flow processor, and the passenger flow The processor integrates and matches the three-dimensional data of all the above-mentioned passenger flow sensors in different installation positions at different times in real time, compares the three-dimensional three-dimensional data after pairing processing with the human body model feature database, filters out data that does not conform to human body characteristics, and retains and compares The three-dimensional three-dimensional data of human body characteristics is used for continuous monitoring of the motion track. When the length of the motion track is greater than the set value, the positive direction means getting on the car, and the negative direction means getting off the car. When the track length is less than the set value, it is defined as an invalid motion track.
本发明的优点是:与现有技术相比,本发明通过对人体肩部及头部的轮廓扫描,并根据人体特征进行判断对比,可连续分析乘客上下车动作的完整的运动轨迹,有效过滤乘客随身物体、乘客手臂等非统计目标导致的统计误差,统计精度高,且统计精度不受环境光线、车辆振动、昼夜分差等因素影响。The advantage of the present invention is that compared with the prior art, the present invention can continuously analyze the complete movement trajectory of passengers getting on and off the bus, effectively filter Statistical errors caused by non-statistical objects such as passengers' personal objects and passenger's arms have high statistical accuracy, and the statistical accuracy is not affected by factors such as ambient light, vehicle vibration, and day and night differences.
下面结合说明书附图和具体实施例对本发明作进一步说明The present invention will be further described below in conjunction with accompanying drawing and specific embodiment of description
附图说明Description of drawings
图1为本发明实施例客流传感器工作流程图;Fig. 1 is the working flow chart of the passenger flow sensor of the embodiment of the present invention;
图2为本发明实施例目标物体轮廓扫描示意图;Fig. 2 is a schematic diagram of scanning the outline of a target object according to an embodiment of the present invention;
图3为本发明实施例系统结构框图;Fig. 3 is a system structural block diagram of the embodiment of the present invention;
图4为本发明实施例客流传感器系统结构示意图;Fig. 4 is a schematic structural diagram of a passenger flow sensor system according to an embodiment of the present invention;
图5为本发明实施例目标物体运动轨迹检测示意图。FIG. 5 is a schematic diagram of detection of a moving track of a target object according to an embodiment of the present invention.
具体实施方式detailed description
参见图1、图2、图3、图4、图5,本发明公开的一种基于人体模型特征的公交车客流统计装置,包括一个客流处理器、一个车门状态检测单元和多个安装在公交车车门顶部的客流传感器;所述客流传感器包括两组阵列红外光 源、一组CCD检测单元、三个透镜、一个滤光镜、一个数据处理单元和一个信号输出单元,用于采集公交车上客门和下客门的乘客通行人体特征信息创建立体三维数据,即用于对公交车上客门和下客门通行的乘客进行截面轮廓扫描,创建立体三维数据,所述三个透镜分别为第一透镜、第二透镜和第三透镜;所述的客流处理器包括一个车门状态检测输入单元、多个人体特征信号输入单元、一个高速数据处理单元、一个数据缓存单元和一个数据通讯接口,用于运算对所有连接的所述的客流传感器的立体三维数据进行配对运算,并结合车门状态信息产生实时的上客门和下客人门上车或下车的客流数据;所述的客流处理提供了一个通讯接口,为第三方设备提供客流数据支持。Referring to Fig. 1, Fig. 2, Fig. 3, Fig. 4, and Fig. 5, a bus passenger flow counting device based on human body model features disclosed by the present invention includes a passenger flow processor, a door state detection unit and multiple The passenger flow sensor on the top of the car door; the passenger flow sensor includes two groups of array infrared light sources, a group of CCD detection units, three lenses, a filter mirror, a data processing unit and a signal output unit, used to collect the passenger flow of the bus The body feature information of passengers passing through the passenger door and the passenger door of the bus can be used to create three-dimensional three-dimensional data, which is used to scan the cross-sectional profile of passengers passing through the passenger door and the passenger door of the bus to create three-dimensional three-dimensional data. The three lenses are respectively the first A lens, a second lens and a third lens; the passenger flow processor includes a car door state detection input unit, a plurality of human body characteristic signal input units, a high-speed data processing unit, a data buffer unit and a data communication interface, used The three-dimensional three-dimensional data of all connected passenger flow sensors is paired and calculated, and combined with the door state information to generate real-time passenger flow data of boarding or getting off at the passenger door and the passenger door; the passenger flow processing provides A communication interface that provides passenger flow data support for third-party devices.
所述客流传感器的两组阵列红外光源包括第一阵列红外光源和第二阵列红外光源,所述第一阵列红外光源由多个方型砷化镓芯片排列组成,由高纯度全透明树脂整体封装,方型砷化镓芯片组间距小于0.2mm,每个方型砷化镓芯片可单独外加带载波的正向偏压向PN结注入电流激发红外光;所述第二阵列红外光源由多个方型砷化镓芯片排列组成,由高纯度全透明树脂整体封装,方型砷化镓芯片组间距小于0.2mm,每个方型砷化镓芯片可单独外加带载波的正向偏压向PN结注入电流激发红外光;所述的第一阵列红外光源固定在第一透镜焦点上,每个方型砷化镓芯片激发红外光通过透镜投射在距离第一透镜一米距离的平面上透射出一个椭圆型Z轴方向长度15cm,X轴长度8cm的椭圆形光斑;所述的第二阵列红外光源固定在第二透镜焦点上,每个方型砷化镓芯片激发红外光通过透镜投射在距离第二透镜一米距离的平面上透射出一个椭圆型Z轴方向长度15cm,X轴长度8cm的椭圆形光斑;所述的CCD检测单元固定在固定在第三透镜焦点上,CCD检测单元和第三透镜之间设置了滤光镜,滤光镜用于过滤95%以上的波长小于780nm光线,允许波长大于780nm的光线通过,减低环境光线对CCD检测单元干扰影响,第三透镜可将入射角度±60度范围的光线聚焦在焦点上。The two arrays of infrared light sources of the passenger flow sensor include a first array of infrared light sources and a second array of infrared light sources. The first array of infrared light sources is composed of a plurality of square gallium arsenide chips arranged and packaged as a whole by high-purity fully transparent resin , the distance between the square gallium arsenide chipset is less than 0.2mm, and each square gallium arsenide chip can be separately applied with a forward bias voltage with a carrier to inject current into the PN junction to excite infrared light; the second array of infrared light sources consists of multiple Composed of square gallium arsenide chip arrays, which are integrally packaged by high-purity fully transparent resin, the spacing between square gallium arsenide chips is less than 0.2mm, and each square gallium arsenide chip can be individually applied with forward bias with carrier to PN The junction injection current excites infrared light; the first array of infrared light sources is fixed on the focal point of the first lens, and each square gallium arsenide chip excites infrared light through the lens and is projected on a plane one meter away from the first lens and transmitted An elliptical spot with a length of 15 cm in the Z-axis direction and 8 cm in the X-axis length; the second array of infrared light sources is fixed on the focal point of the second lens, and each square gallium arsenide chip excites infrared light and projects it through the lens at a distance of An elliptical Z-axis direction length of 15 cm and an elliptical spot of X-axis length of 8 cm are transmitted on the plane of the second lens at a distance of one meter; the CCD detection unit is fixed on the focal point of the third lens, and the CCD detection unit and the first A filter is set between the three lenses. The filter is used to filter more than 95% of the light with a wavelength less than 780nm, and allows the light with a wavelength greater than 780nm to pass through, reducing the interference of ambient light on the CCD detection unit. The third lens can adjust the incident angle The light in the range of ±60 degrees is focused on the focal point.
一种基于人体模型特征的公交车客流统计装置的处理方法:构建空间三维坐标,公交车车门包括上客门和下客门,按车身方向即车尾到车头方向定义为X轴;按车高方向即地面到车顶方向定义为Y轴;按上客方向即车外到车内的方向定义为Z轴正方向;按下客方向即车内到车外的方向定义为Z轴负方向,X轴表示CCD检测单元所采集到的当时红外扫描获取的物体截面宽度;Y轴表示当时不同高度反射面反射的红外;Z轴则表示CCD检测单元所采集到的当时物体运动轨迹。A processing method for a bus passenger flow statistics device based on human body model features: constructing a three-dimensional space coordinate, the bus door includes the upper passenger door and the lower passenger door, and the X axis is defined according to the direction of the vehicle body, that is, the direction from the rear to the front of the vehicle; The direction from the ground to the roof of the car is defined as the Y axis; the direction of getting on the passenger, that is, the direction from the outside to the inside of the car, is defined as the positive direction of the Z axis; the direction of the passenger, that is, the direction from the inside to the outside of the car is defined as the negative direction of the Z axis. The X-axis represents the cross-sectional width of the object collected by the CCD detection unit at that time through infrared scanning; the Y-axis represents the infrared reflected by reflective surfaces of different heights at that time; the Z-axis represents the movement trajectory of the object at that time collected by the CCD detection unit.
所述的客流传感器的所述的第一阵列红外光源由所述数据处理单元进行控制,在X轴上从与CCD检测单元最远的方型砷化镓芯片开始依次激发红外光;通过所述的第一透镜的投射,每个砷化镓芯片激发的红外光通过透镜折射具有不同出射角度,覆盖以所述的客流传感器为中心的50cm宽度范围;所 述的客流传感器的所述的第二阵列红外光源由所述数据处理单元进行控制,在X轴上从与CCD检测单元最远的方型砷化镓芯片开始依次激发红外光;通过所述的第二透镜的投射,每个砷化镓芯片激发的红外光通过透镜折射具有不同出射角度,覆盖以所述的客流传感器为中心的50cm宽度范围。The first array of infrared light sources of the passenger flow sensor is controlled by the data processing unit, and the infrared light is sequentially excited from the square gallium arsenide chip farthest from the CCD detection unit on the X-axis; through the The projection of the first lens, the infrared light excited by each gallium arsenide chip has different exit angles through the lens refraction, covering the 50cm width range centered on the passenger flow sensor; the second passenger flow sensor The array infrared light source is controlled by the data processing unit, and sequentially excites infrared light from the square gallium arsenide chip farthest from the CCD detection unit on the X axis; through the projection of the second lens, each arsenide The infrared light excited by the gallium chip is refracted by the lens and has different exit angles, covering a 50cm wide range centered on the passenger flow sensor.
所述的客流传感器的所述的数据处理单元预先定义了每个位置的砷化镓芯片激发的红外光通过物体反射在所述CCD检测单元的成像偏移量L和物体距离Y关系的运算函数,所述的数据处理单元分别控制分布与CCD检测单元X轴两侧的所述的第一阵列红外光源和所述的第二阵列红外光源的多个砷化镓芯片激发的红外光进行不同区域扫描,同时记录CCD检测单元接收的不同物体表面反射的红外的成像偏移量,通过位置偏移量和物体距离关系的运算函数绘制出物体的空间截面轮廓,并编制成立体三维数据传输给所述客流处理器进行人体模型特征比对。The data processing unit of the passenger flow sensor pre-defines the calculation function of the relationship between the imaging offset L and the object distance Y of the infrared light excited by the gallium arsenide chip at each position reflected by the object on the CCD detection unit , the data processing unit respectively controls the infrared light excited by the plurality of gallium arsenide chips distributed on both sides of the X-axis of the CCD detection unit and the first array infrared light source and the second array infrared light source to carry out different regions Scan and record the infrared imaging offset of different object surfaces received by the CCD detection unit at the same time, draw the spatial cross-sectional profile of the object through the calculation function of the position offset and the object distance relationship, and compile it into three-dimensional data and transmit it to the institute The passenger flow processor is used to compare the characteristics of the human body model.
参见图1,本发明公开的客流传感器工作流程,两组阵列红外光源包括了8个方型砷化镓芯片的红外光源,所有红外光源采用扫描方式依次发送带载波的红外光,同时采集每个载波的红外光通过目标物体反射在CCD检测单元的成像位置,并计算该位置与基准位置的偏移量,通过三角测距原理计算物体表面与CCD检测单元的距离,结合8个扫描点的空间位置信息可获得检测目标在客流传感器有效检测区域内的空间轮廓立体三维数据;完成一个扫描周期所需的时间为3ms,即每3ms可更新更新一次立体三维数据,通过对上一次三维数据的保存可获得检测目标在客流传感器有效检测区域内的连续的运动轨迹。Referring to Fig. 1, the working process of the passenger flow sensor disclosed by the present invention, two sets of array infrared light sources include infrared light sources of 8 square gallium arsenide chips, and all infrared light sources use scanning mode to sequentially send infrared light with a carrier wave, and simultaneously collect each The infrared light of the carrier is reflected on the imaging position of the CCD detection unit by the target object, and the offset between the position and the reference position is calculated, and the distance between the object surface and the CCD detection unit is calculated by the principle of triangulation ranging, combined with the space of 8 scanning points The position information can obtain the three-dimensional three-dimensional data of the spatial outline of the detection target in the effective detection area of the passenger flow sensor; the time required to complete a scanning cycle is 3ms, that is, the three-dimensional three-dimensional data can be updated every 3ms, and the last three-dimensional data can be saved The continuous motion trajectory of the detection target in the effective detection area of the passenger flow sensor can be obtained.
两组阵列红外光源分别布置在CCD检测单元X轴的两侧,其目的在于避免由于目标物体不同高度平面反射的红外信号被遮挡导致CCD检测单元无法获取更多检测信息。Two arrays of infrared light sources are respectively arranged on both sides of the X-axis of the CCD detection unit, the purpose of which is to prevent the CCD detection unit from being unable to obtain more detection information due to the blocking of infrared signals reflected by different height planes of the target object.
构建人体模型特征库,通过大量实际环境的信息采集,经过数字化处理并整合成人体模型特征库植入所述的客流处理器的高速数据处理单元内,所述的客流处理器实时对所有所述的客流传感器不同时刻不同安装位置的三维数据进行整合配对,配对处理后的立体三维数据与人体模型特征库进行比对,过滤不符合人体特征的数据保留并对符合人体特征的立体三维数据进行运动轨迹的连续监测,运动轨迹长度大于设置值后,正方向表示上车,负方向表示下车,轨迹长度小于设置值时,则定义为无效动作运动轨迹。Build a human body model feature library, collect a large amount of information from the actual environment, digitally process and integrate it into a human body model feature library and implant it into the high-speed data processing unit of the passenger flow processor, and the passenger flow processor performs real-time processing of all the The three-dimensional data of the passenger flow sensor at different times and different installation locations are integrated and paired, and the three-dimensional three-dimensional data after pairing processing are compared with the human body model feature database, and the data that does not conform to the human body characteristics are filtered and retained, and the three-dimensional three-dimensional data that conforms to the human body characteristics are moved. Continuous monitoring of the trajectory. When the length of the trajectory is greater than the set value, the positive direction means getting on the car, and the negative direction means getting off the car. When the trajectory length is less than the set value, it is defined as an invalid motion trajectory.
参见图2,本发明公开的目标物体轮廓扫描原理,客流传感器的两组阵列红外光源分别布置在CCD检测单元X轴的两侧,其目的在于避免由于目标物体不同高度平面反射的红外信号被遮挡导致CCD检测单元无法获取更多检测信息;这样设置后,乘客进入客流传感器检测区域内时,根据CCD检测单元的L1或L4成像偏移量,通过三角测距原理计算扫描点物体表面与CCD检测单元之间的距离,从而获得乘客肩部与客流传感器的距离Y2;根据CCD检测单元 的L2或L3成像偏移量,通过三角测距原理计算扫描点物体表面与CCD检测单元之间的距离,从而获得乘客头部与客流传感器的距离Y1;根据CCD检测单元的L1和L4成像偏移量,通过三角测距原理和三角函数关系,可计算出乘客头部宽度XT,完成创建完整的立体三维数据。Referring to Fig. 2, the target object contour scanning principle disclosed in the present invention, the two sets of array infrared light sources of the passenger flow sensor are respectively arranged on both sides of the X-axis of the CCD detection unit, the purpose of which is to prevent the infrared signals reflected by the different height planes of the target object from being blocked As a result, the CCD detection unit cannot obtain more detection information; after this setting, when passengers enter the detection area of the passenger flow sensor, according to the L1 or L4 imaging offset of the CCD detection unit, the object surface of the scanning point and the CCD detection are calculated by the principle of triangulation distance measurement. The distance between the units, so as to obtain the distance Y2 between the shoulder of the passenger and the passenger flow sensor; according to the L2 or L3 imaging offset of the CCD detection unit, the distance between the object surface of the scanning point and the CCD detection unit is calculated by the principle of triangulation ranging, In order to obtain the distance Y1 between the head of the passenger and the passenger flow sensor; according to the L1 and L4 imaging offsets of the CCD detection unit, the width XT of the head of the passenger can be calculated through the principle of triangular distance measurement and the relationship of trigonometric functions, and the creation of a complete three-dimensional three-dimensional data.
按车门宽度多个客流传感器在X轴上以间距20cm平均分布安装,相邻两个客流传感器检测区域重叠设置;若乘客从其中一个客流传感器正下方通过时,则该客流传感器可采集到乘客完整的立体三维数据,通过客流处理器的人体模型特征比对即可产生客流数据;若乘客从两个客流传感器中间通过,两个客流传感器分别采集到乘客一左一右的不完整立体三维数据,通过客流处理器的配对运算即可将两个客流传感器分别采集到乘客一左一右的不完整立体三维数据整合成一个完整的立体三维数据在通过人体模型特征比对即可产生客流数据。According to the width of the car door, multiple passenger flow sensors are evenly distributed on the X-axis with a distance of 20cm, and the detection areas of two adjacent passenger flow sensors are overlapped; Passenger flow data can be generated by comparing the human body model features of the passenger flow processor; if passengers pass between the two passenger flow sensors, the two passenger flow sensors collect incomplete three-dimensional 3D data of the passengers, one left and one right, respectively. Through the pairing operation of the passenger flow processor, the incomplete three-dimensional three-dimensional data collected by the two passenger flow sensors, one left and one right, respectively, can be integrated into a complete three-dimensional three-dimensional data, and the passenger flow data can be generated by comparing the characteristics of the human body model.
参见图5,本发明公开的目标物体运动轨迹检测原理,客流传感器的第一阵列红外光源和第一阵列红外光源通过第一透镜和第二透镜扫描投射后,在距离一米距离的平面上相当于投射出一个Z轴上长度15cm,X轴上长度50cm的方形光斑,乘客在上下车动作时需要以Z轴方向穿过该光斑,行程距离为ZL;从进入光斑区域的起始位置到离开光斑区域的终止位置,反射光线在CCD检测单元在Z轴方向产生了距离为LZ的成像偏移,通过对LZ偏移方向可获得乘客运行方向及上客方向或下客方向。Referring to Fig. 5 , according to the detection principle of the target object movement trajectory disclosed by the present invention, after the first array infrared light source and the first array infrared light source of the passenger flow sensor scan and project through the first lens and the second lens, they are equivalent on a plane with a distance of one meter. To project a square light spot with a length of 15cm on the Z axis and a length of 50cm on the X axis, passengers need to pass through the light spot in the direction of the Z axis when getting on and off the bus, and the travel distance is ZL; from the starting position of entering the light spot area to leaving At the end position of the spot area, the reflected light produces an imaging offset with a distance of LZ in the Z-axis direction of the CCD detection unit. By offsetting the direction of LZ, the passenger running direction and the direction of boarding or disembarking can be obtained.
上述实施例对本发明的具体描述,只用于对本发明进行进一步说明,不能理解为对本发明保护范围的限定,本领域的技术工程师根据上述发明的内容对本发明作出一些非本质的改进和调整均落入本发明的保护范围之内。The specific description of the present invention in the above-mentioned embodiments is only used to further illustrate the present invention, and can not be interpreted as limiting the protection scope of the present invention. Technical engineers in the field make some non-essential improvements and adjustments to the present invention according to the content of the above-mentioned invention. Into the protection scope of the present invention.
Claims (7)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410200293.8A CN103955980B (en) | 2014-05-13 | 2014-05-13 | Human body model feature based bus passenger flow statistic device and processing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410200293.8A CN103955980B (en) | 2014-05-13 | 2014-05-13 | Human body model feature based bus passenger flow statistic device and processing method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103955980A CN103955980A (en) | 2014-07-30 |
CN103955980B true CN103955980B (en) | 2017-02-15 |
Family
ID=51333249
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410200293.8A Active CN103955980B (en) | 2014-05-13 | 2014-05-13 | Human body model feature based bus passenger flow statistic device and processing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103955980B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104183040B (en) * | 2014-08-21 | 2016-04-20 | 成都易默生汽车技术有限公司 | Passenger carriage overloading detection system and detection method thereof |
CN105869388B (en) * | 2016-05-31 | 2018-09-04 | 苏州朗捷通智能科技有限公司 | The analysis method and system of a kind of acquisition of bus passenger flow data and origin and destination |
CN106600777B (en) * | 2016-12-09 | 2019-02-22 | 济南赛英立德电子信息股份有限公司 | Method of counting and device based on infrared array number sensor |
CN107704870B (en) * | 2017-09-07 | 2021-04-20 | 武汉大学 | Reliable human-vehicle proximity sensing device and method based on fusion of BLE fingerprint positioning and IMU action recognition |
CN108509914B (en) * | 2018-04-03 | 2022-03-11 | 华录智达科技有限公司 | Statistical analysis system and method of bus passenger flow based on TOF camera |
CN108875701A (en) * | 2018-07-11 | 2018-11-23 | 温州亿通自动化设备有限公司 | A kind of inlet/outlet passenger number automatic statistics method |
CN110490110B (en) * | 2019-01-29 | 2024-07-16 | 王馨悦 | Passenger flow counting device and method based on human engineering feature detection |
CN112158705B (en) * | 2020-08-31 | 2021-06-29 | 猫岐智能科技(上海)有限公司 | Light curtain imaging method and system, light curtain identification method and system, light curtain device and elevator equipment |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2721126A1 (en) * | 1994-06-08 | 1995-12-15 | Brime Sa | Device for detecting the presence and direction of passage of mobiles and people for the purpose of counting. |
CN1393005A (en) * | 2000-07-13 | 2003-01-22 | 埃里斯红外线高智力传感器有限责任公司 | Detection device |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2354821A (en) * | 1999-09-29 | 2001-04-04 | Dine O Quick | Threshold crossing counter |
CN100442315C (en) * | 2006-11-28 | 2008-12-10 | 天津大学 | Infrared photoelectric passenger flow statistics method based on human body model |
EP2541506A1 (en) * | 2011-06-27 | 2013-01-02 | Siemens S.A.S. | Method and system for managing a flow of passengers on a platform |
CN103714603B (en) * | 2013-12-26 | 2016-03-30 | 苏州清研微视电子科技有限公司 | Based on the bus passenger flow statistical system of infrared distance sensor |
-
2014
- 2014-05-13 CN CN201410200293.8A patent/CN103955980B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2721126A1 (en) * | 1994-06-08 | 1995-12-15 | Brime Sa | Device for detecting the presence and direction of passage of mobiles and people for the purpose of counting. |
CN1393005A (en) * | 2000-07-13 | 2003-01-22 | 埃里斯红外线高智力传感器有限责任公司 | Detection device |
Also Published As
Publication number | Publication date |
---|---|
CN103955980A (en) | 2014-07-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103955980B (en) | Human body model feature based bus passenger flow statistic device and processing method | |
US20240036207A1 (en) | Multiple Resolution, Simultaneous Localization And Mapping Based On 3-D Lidar Measurements | |
JP2022546591A (en) | Processing LIDAR images | |
CN203489844U (en) | System for measuring size of outer profile of vehicle based on machine vision and laser light screen | |
CN1815258B (en) | Photoelectric imaging tracking system based on scanning galvanometer | |
CN103453836A (en) | System and method for measuring vehicle outline dimensions based on machine vision and laser light curtain | |
CN102840825B (en) | Particle locating system and method | |
CN108919294A (en) | Ranging camera system and solid-state imager | |
CN106175780A (en) | Facial muscle motion-captured analysis system and the method for analysis thereof | |
CN110047111B (en) | Parking apron corridor bridge butt joint error measuring method based on stereoscopic vision | |
CN103419944A (en) | Air bridge and automatic abutting method therefor | |
CN105014675B (en) | A kind of narrow space intelligent mobile robot vision navigation system and method | |
CN110926417B (en) | Vehicle-mounted railway tunnel inspection system based on machine vision | |
WO2021154037A1 (en) | 3d lidar-based target object recognition method, device, and moving body using same | |
CN103247074A (en) | 3D (three dimensional) photographing method combining depth information and human face analyzing technology | |
CN104103077A (en) | Human head detecting method and human head detecting device | |
CN109976339B (en) | Vehicle-mounted distribution network inspection data acquisition method and inspection system | |
CN102661746B (en) | Sensor main mounting boxes and passive optical sensor | |
CN102887155A (en) | Freight train transfinite computer vision inspection system | |
CN103196393A (en) | Geometrical shape and surface color real time imaging device | |
CN102435142B (en) | Active infrared action identifying method | |
CN104570147B (en) | A kind of obstacle detection method based on monocular camera and initiating structure light | |
CN111811776A (en) | A method and system for measuring spray flow field | |
CN104296679A (en) | Mirror image type three-dimensional information acquisition device and method | |
CN104228874A (en) | Rail vehicle exterior outline noncontact detection system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
EE01 | Entry into force of recordation of patent licensing contract | ||
EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20140730 Assignee: Wenzhou Dongtou Yiwei Automation Equipment Factory Assignor: WENZHOU YITONG AUTOMATION EQUIPMENT Co.,Ltd. Contract record no.: X2023980047233 Denomination of invention: A Bus Passenger Flow Statistics Device and Processing Method Based on Human Model Features Granted publication date: 20170215 License type: Common License Record date: 20231116 |
|
PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Bus Passenger Flow Statistics Device and Processing Method Based on Human Body Model Features Granted publication date: 20170215 Pledgee: Wenzhou Dongtou Branch of Agricultural Bank of China Ltd. Pledgor: WENZHOU YITONG AUTOMATION EQUIPMENT Co.,Ltd. Registration number: Y2024330001939 |