CN102708694B - Automatic motorcycle type identification system and method based on high-speed pulse laser scanning - Google Patents
Automatic motorcycle type identification system and method based on high-speed pulse laser scanning Download PDFInfo
- Publication number
- CN102708694B CN102708694B CN201210202048.1A CN201210202048A CN102708694B CN 102708694 B CN102708694 B CN 102708694B CN 201210202048 A CN201210202048 A CN 201210202048A CN 102708694 B CN102708694 B CN 102708694B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- unit
- module
- information
- distance parameter
- 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
Images
Landscapes
- Traffic Control Systems (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
本发明涉及一种基于高速脉冲激光扫描的车型自动识别系统及方法,属于智能交通管理设备及方法技术领域。本发明的车型自动识别系统包括高频激光测距模块、车辆轮廓绘制模块和车型识别模块,高频激光测距模块和车辆轮廓绘制模块垂直设置于车道上方。利用本发明的方法,高频激光测距模块进行实时脉冲激光测距并发送距离值至车辆轮廓绘制模块;车辆轮廓绘制模块实时绘制距离参数扫描图并将其发送至车型识别模块;车型识别模块根据距离参数扫描图上的车辆轮廓信息实现车型识别,从而有效克服了现有技术中的缺陷,提供了一种设置及维护简单,成本低廉,车型识别率较高,应用范围广泛的车型自动识别系统及方法。
The invention relates to a vehicle type automatic identification system and method based on high-speed pulsed laser scanning, and belongs to the technical field of intelligent traffic management equipment and methods. The vehicle type automatic identification system of the present invention includes a high-frequency laser ranging module, a vehicle outline drawing module and a vehicle type identification module, and the high-frequency laser ranging module and the vehicle outline drawing module are vertically arranged above the lane. Using the method of the present invention, the high-frequency laser ranging module performs real-time pulse laser ranging and sends the distance value to the vehicle contour drawing module; the vehicle contour drawing module draws the distance parameter scan diagram in real time and sends it to the vehicle type identification module; the vehicle type identification module Car model recognition is realized according to the vehicle profile information on the distance parameter scanning map, thereby effectively overcoming the defects in the prior art, and providing a car model automatic recognition with simple setting and maintenance, low cost, high car model recognition rate and wide application range systems and methods.
Description
技术领域 technical field
本发明涉及智能交通管理设备技术领域,特别涉及车型识别技术领域,具体是指一种基于高速脉冲激光扫描的车型自动识别系统及方法。The invention relates to the technical field of intelligent traffic management equipment, in particular to the technical field of vehicle identification, in particular to a vehicle automatic identification system and method based on high-speed pulsed laser scanning.
背景技术 Background technique
随着交通拥挤和堵塞等各种问题的日益突出,以及计算机技术的不断发展,智能交通系统(Intelligent Transportation System,简称ITS)得到了越来越广泛的应用,并在欧、美等发达国家广泛得到应用,而在我国的应用尚处于探索研究的起步阶段。车辆检测、跟踪和车型识别是ITS应用领域中的重要分支,也是目前相对薄弱的技术环节。With the increasingly prominent problems of traffic congestion and congestion, as well as the continuous development of computer technology, Intelligent Transportation System (ITS) has been more and more widely used, and is widely used in developed countries such as Europe and the United States. It has been applied, but the application in our country is still in the initial stage of exploration and research. Vehicle detection, tracking and vehicle identification are important branches in the application field of ITS, and they are also relatively weak technical links at present.
车型自动识别,是ITS进行车辆分类管理和监控的前提,且与车辆牌照识别功能结合,能够十分全面的掌握道路车辆的行驶信息,为智能化的交通管理提供有力的保障。Vehicle type automatic identification is the premise of ITS for vehicle classification management and monitoring, and combined with the vehicle license plate recognition function, it can fully grasp the driving information of road vehicles and provide a strong guarantee for intelligent traffic management.
目前,车型自动识别方法主要有以下几种:At present, there are mainly the following types of automatic vehicle identification methods:
1、电子标签识别法1. Electronic label identification method
现阶段不停车收费(ETC)采用最多的是基于无线通讯技术。电子标签是用来记录车辆本身的信息包括车辆账号、车辆类型、车主、车牌号等。当车辆通过安装在收费通道内的收费设备时,通过电子标签和阅读器之间的微波通讯,实现信息的交换,并进行CRC校验,最后通过收费系统与车主的银行实行定期清算。因为车辆存在掉换车载电子标签进行作弊的可能,收费站等场所需要额外安装监控设备,增加了基建投入。At this stage, non-stop charging (ETC) is mostly based on wireless communication technology. The electronic tag is used to record the information of the vehicle itself, including the vehicle account number, vehicle type, owner, license plate number, etc. When the vehicle passes through the charging equipment installed in the toll channel, the information exchange is realized through the microwave communication between the electronic tag and the reader, and the CRC check is performed, and finally the regular settlement is carried out with the owner's bank through the charging system. Because there is a possibility of cheating by swapping the on-board electronic tags, toll stations and other places need to install additional monitoring equipment, which increases infrastructure investment.
2、电磁感应线圈识别法2. Electromagnetic induction coil identification method
预先在公路下面铺设一个通有高频电流的线圈,由于车辆的材质大部分是金属,当车辆从感应线圈上面通过时,会在线圈内部产生涡流而使线圈电感量减小。不同车型的底盘结构和铁磁物质分布的有所不同,由于电流变化引起的磁场的变化也不同,因此可以根据感应曲线的不同而区分不同类型的车辆,进而得到具体的车型。该方法的优点是准确率较高、不受气候影响且成本不太高,同时还能检测各车型的车流量及占有率等交通参数。电磁感应线圈法需要把线圈埋入地下,受车辆的挤压容易损坏,寿命较短,维护时需要破坏路面,维护成本较高。Lay a coil with high-frequency current under the road in advance. Since the vehicle is mostly made of metal, when the vehicle passes over the induction coil, eddy current will be generated inside the coil to reduce the inductance of the coil. The chassis structure and ferromagnetic material distribution of different models are different, and the change of the magnetic field caused by the change of current is also different. Therefore, different types of vehicles can be distinguished according to the difference in the induction curve, and then the specific model can be obtained. The advantage of this method is that it has high accuracy, is not affected by the climate, and the cost is not too high. At the same time, it can also detect traffic parameters such as traffic volume and occupancy rate of various models. The electromagnetic induction coil method needs to bury the coil underground, which is easily damaged by the extrusion of the vehicle, has a short life, and needs to destroy the road surface during maintenance, resulting in high maintenance costs.
3、车牌识别法3. License plate recognition method
车牌识别法是一种通过识别车牌间接识别车型的方法。首先从摄像机获取的汽车牌照图像中识别出车牌号和车牌颜色,然后到车辆数据库中去检索与此车牌号相对应的车型,最终得到车辆的类型。该方法对硬件要求不高,安装起来也灵活方便,但需要事先对每一辆车建立包含各种信息的车辆数据库,而且图像必须保证车牌清晰,在实际应用中还受到遮挡、光照等的限制。The license plate recognition method is a method of indirect identification of vehicle types by recognizing license plates. First, identify the license plate number and license plate color from the license plate image captured by the camera, then search the vehicle model corresponding to the license plate number in the vehicle database, and finally get the type of vehicle. This method does not require high hardware and is flexible and convenient to install. However, it is necessary to establish a vehicle database containing various information for each vehicle in advance, and the image must ensure that the license plate is clear. In practical applications, it is also limited by occlusion, lighting, etc. .
4、基于视频图像的车型识别4. Vehicle identification based on video images
国内外利用视频图像进行车型识别的研究很多,因为数字图像能够提供很多有用的信息,利用一定的算法得到许多车辆的信息,然后依据这些车辆特征进而得到具体的车型。相比于其它的车型识别方法,利用图像来识别有其自身的缺点,首先数字图像无法清晰的获取,然后就是很难保证特征提取算法的有效性,这样就无法保证可靠的车型识别率。At home and abroad, there are many researches on the use of video images for car model recognition, because digital images can provide a lot of useful information, using certain algorithms to obtain information about many vehicles, and then get specific car models based on these vehicle features. Compared with other car model recognition methods, image recognition has its own disadvantages. First, the digital image cannot be clearly obtained, and then it is difficult to ensure the effectiveness of the feature extraction algorithm, so that a reliable car model recognition rate cannot be guaranteed.
发明内容 Contents of the invention
本发明的目的是克服了上述现有技术中的缺点,提供一种基于激光高速脉冲扫描技术,对经过车辆的不同部位进行测距扫描,采集车辆的侧面轮廓数据,然后通过这些数据与车型数据库中的数据比较,实现车型判断的,且识别率较高,设置及维护简单,成本低廉,应用范围广泛的基于高速脉冲激光扫描的车型自动识别系统及方法。The purpose of the present invention is to overcome the above-mentioned shortcoming in the prior art, provide a kind of technology based on laser high-speed pulse scanning, carry out ranging scanning to the different parts of passing vehicle, collect the side profile data of vehicle, then pass these data and model database The vehicle type automatic identification system and method based on high-speed pulsed laser scanning can be realized by comparing the data in the vehicle, and the recognition rate is high, the setting and maintenance are simple, the cost is low, and the application range is wide.
为了实现上述的目的,本发明基于高速脉冲激光扫描的车型自动识别系统的具有如下构成:In order to achieve the above-mentioned purpose, the present invention has the following composition based on the vehicle type automatic identification system of high-speed pulsed laser scanning:
该系统包括高频激光测距模块、车辆轮廓绘制模块和车型识别模块,所述的高频激光测距模块和车辆轮廓绘制模块设置于车辆经过的车道上方,所述的高频激光测距模块的激光脉冲发射口垂直于所述的车道,所述的高频激光测距模块的输出端连接所述的车辆轮廓绘制模块的输入端,所述的车辆轮廓绘制模块的输出端连接所述的车型识别模块的输入端。The system includes a high-frequency laser ranging module, a vehicle contour drawing module and a vehicle type identification module. The high-frequency laser ranging module and the vehicle contour drawing module are arranged above the vehicle lane, and the high-frequency laser ranging module The laser pulse emission port is perpendicular to the lane, the output end of the high-frequency laser ranging module is connected to the input end of the vehicle contour drawing module, and the output end of the vehicle contour drawing module is connected to the The input terminal of the vehicle type identification module.
该基于高速脉冲激光扫描的车型自动识别系统中,所述的高频激光测距模块的激光扫描频率为2000Hz,激光波长为904nm。In the vehicle type automatic identification system based on high-speed pulsed laser scanning, the laser scanning frequency of the high-frequency laser ranging module is 2000 Hz, and the laser wavelength is 904 nm.
该基于高速脉冲激光扫描的车型自动识别系统中,所述的高频激光测距模块和车辆轮廓绘制模块均集成于一个高频激光测距仪内,所述的高频激光测距仪固定于所述车道中间上方的道路监控架上。In the vehicle type automatic identification system based on high-speed pulsed laser scanning, the high-frequency laser rangefinder module and the vehicle contour drawing module are integrated in a high-frequency laser rangefinder, and the high-frequency laser rangefinder is fixed on On the road monitoring frame above the middle of the lane.
该基于高速脉冲激光扫描的车型自动识别系统中,所述的高频激光测距模块的测距范围为30米。In the vehicle type automatic identification system based on high-speed pulsed laser scanning, the range of the high-frequency laser ranging module is 30 meters.
该基于高速脉冲激光扫描的车型自动识别系统中,所述的车辆轮廓绘制模块为一距离参数扫描图绘制单元,该距离参数扫描图绘制单元的输入端连接所述的高频激光测距模块的输出端,所述的距离参数扫描图绘制单元的输出端连接所述的车型识别模块。In the vehicle type automatic identification system based on high-speed pulsed laser scanning, the vehicle contour drawing module is a distance parameter scanning map drawing unit, and the input end of the distance parameter scanning map drawing unit is connected to the high-frequency laser ranging module. The output end, the output end of the distance parameter scanning map drawing unit is connected to the vehicle type identification module.
该基于高速脉冲激光扫描的车型自动识别系统中,所述的距离参数扫描图绘制单元通过无线信号连接所述的车型识别模块。In the vehicle type automatic identification system based on high-speed pulsed laser scanning, the distance parameter scanning map drawing unit is connected to the vehicle type identification module through a wireless signal.
该基于高速脉冲激光扫描的车型自动识别系统中,所述的车型识别模块包括预处理单元、图像匹配单元和车型库单元,所述的预处理单元的输入端连接所述的车辆轮廓绘制模块的输出端,所述的预处理单元的输出端分别连接所述的图像匹配单元和车型库单元的输入端,所述的车型库单元的输出端连接所述的图像匹配单元的输出端,所述的图像匹配单元的输出端为车型信息输出端,该车型信息输出端为网络接口或串行接口。In the vehicle type automatic identification system based on high-speed pulsed laser scanning, the vehicle type identification module includes a preprocessing unit, an image matching unit and a vehicle type library unit, and the input end of the preprocessing unit is connected to the vehicle outline drawing module. output terminal, the output terminal of the preprocessing unit is respectively connected to the input terminal of the image matching unit and the model library unit, the output terminal of the vehicle model library unit is connected to the output terminal of the image matching unit, and the The output end of the image matching unit is a vehicle type information output end, and the vehicle type information output end is a network interface or a serial interface.
该基于高速脉冲激光扫描的车型自动识别系统中,所述的预处理单元包括车长识别子单元、车高识别子单元和车辆轮廓线提取子单元,所述的车长识别子单元和车高识别子单元的输出端均连接所述的车型库单元,所述的车辆轮廓线提取子单元连接所述的图像匹配单元。In the vehicle type automatic identification system based on high-speed pulsed laser scanning, the preprocessing unit includes a vehicle length identification subunit, a vehicle height identification subunit, and a vehicle outline extraction subunit, and the vehicle length identification subunit and vehicle height The output ends of the identification subunits are all connected to the vehicle model library unit, and the vehicle outline extraction subunit is connected to the image matching unit.
本发明还提供一种利用所述的系统实现基于高速脉冲激光扫描的车型自动识别的方法,该方法包括以下步骤:The present invention also provides a method for using the system to realize automatic vehicle identification based on high-speed pulsed laser scanning, the method comprising the following steps:
(1)所述的高频激光测距模块进行实时脉冲激光测距,并将测得的距离值发送至所述的车辆轮廓绘制模块;(1) The high-frequency laser ranging module performs real-time pulse laser ranging, and sends the measured distance value to the vehicle contour drawing module;
(2)所述的车辆轮廓绘制模块将接收到距离值实时绘制于距离参数扫描图上;(2) The vehicle contour drawing module draws the received distance value on the distance parameter scanning map in real time;
(3)所述的车辆轮廓绘制模块将所述的距离参数扫描图实时发送至所述的车型识别模块;(3) The vehicle contour drawing module sends the distance parameter scan map to the vehicle type identification module in real time;
(4)所述的车型识别模块根据所述的距离参数扫描图上绘制的车辆轮廓信息识别车型,并输出车型数据信息。(4) The vehicle type identification module identifies the vehicle type according to the vehicle outline information drawn on the distance parameter scan map, and outputs the vehicle type data information.
该实现基于高速脉冲激光扫描的车型自动识别的方法中,所述的车辆轮廓绘制模块为一距离参数扫描图绘制单元,该距离参数扫描图绘制单元的输入端连接所述的高频激光测距模块的输出端,所述的距离参数扫描图绘制单元的输出端连接所述的车型识别模块,所述的车辆轮廓绘制模块将接收到距离值实时绘制于距离参数扫描图上,具体为:所述的距离参数扫描图绘制单元将接收到距离值实时绘制于一坐标系中,形成一距离参数扫描图。In the method for realizing automatic identification of vehicle models based on high-speed pulsed laser scanning, the vehicle contour drawing module is a distance parameter scanning map drawing unit, and the input end of the distance parameter scanning map drawing unit is connected to the high-frequency laser ranging The output end of the module, the output end of the described distance parameter scanning map drawing unit is connected to the described vehicle type identification module, and the described vehicle outline drawing module will receive the distance value and draw it on the distance parameter scanning map in real time, specifically: the The distance parameter scanning map drawing unit draws the received distance value in a coordinate system in real time to form a distance parameter scanning map.
该实现基于高速脉冲激光扫描的车型自动识别的方法中,所述的距离参数扫描图绘制单元通过无线信号连接所述的车型识别模块,所述的车辆轮廓绘制模块将所述的距离参数扫描图实时发送至所述的车型识别模块,具体为:车辆轮廓绘制模块将所述的距离参数扫描图通过无线信号实时发送至所述的车型识别模块。In the method for realizing automatic identification of vehicle types based on high-speed pulsed laser scanning, the distance parameter scanning map drawing unit is connected to the vehicle type identification module through wireless signals, and the vehicle profile drawing module draws the distance parameter scanning map Sending to the vehicle type identification module in real time, specifically: the vehicle outline drawing module sends the distance parameter scan map to the vehicle type identification module in real time through wireless signals.
该实现基于高速脉冲激光扫描的车型自动识别的方法中,所述的车型识别模块包括预处理单元、图像匹配单元和车型库单元,所述的预处理单元的输入端连接所述的车辆轮廓绘制模块的输出端,所述的预处理单元的输出端分别连接所述的图像匹配单元和车型库单元的输入端,所述的车型库单元的输出端连接所述的图像匹配单元的输出端,所述的图像匹配单元的输出端为车型信息输出端,所述的步骤(4)具体包括以下步骤:In the method for realizing the automatic identification of vehicle models based on high-speed pulsed laser scanning, the vehicle vehicle identification module includes a preprocessing unit, an image matching unit and a vehicle vehicle library unit, and the input terminal of the preprocessing unit is connected to the vehicle outline drawing The output end of the module, the output end of the preprocessing unit is respectively connected to the input end of the image matching unit and the car model library unit, the output end of the car model library unit is connected to the output end of the image matching unit, The output end of the image matching unit is the vehicle type information output end, and the step (4) specifically includes the following steps:
(41)所述的预处理单元根据所述的距离参数扫描图获得车型参数信息和车型轮廓信息;(41) The preprocessing unit obtains vehicle model parameter information and vehicle model profile information according to the distance parameter scan map;
(42)所述的预处理单元将所述的车型参数信息发送至所述的车型库单元,并将所述的车型轮廓信息发送至所述的图像匹配单元;(42) The preprocessing unit sends the car model parameter information to the car model library unit, and sends the car model profile information to the image matching unit;
(43)所述的车型库单元根据获得的车型参数信息读取对应的多个车型的图像信息发送至所述的图像匹配单元;(43) The car model library unit reads the image information of multiple car models corresponding to the obtained car model parameter information and sends them to the image matching unit;
(44)所述的图像匹配单元将从所述的预处理单元获得的车型轮廓信息与从所述的车型库单元获得的各个车型的图像信息依次进行对比,并将最接近的图像信息的车型作为匹配车型;(44) The image matching unit sequentially compares the car model profile information obtained from the preprocessing unit with the image information of each car model obtained from the car model library unit, and compares the car model information of the closest image information as a matching model;
(45)所述的车型信息输出端输出所述的匹配车型的数据信息。(45) The vehicle type information output terminal outputs the data information of the matching vehicle type.
该实现基于高速脉冲激光扫描的车型自动识别的方法中,所述的预处理单元包括车长识别子单元、车高识别子单元和车辆轮廓线提取子单元,所述的车长识别子单元和车高识别子单元的输出端均连接所述的车型库单元,所述的车辆轮廓线提取子单元连接所述的图像匹配单元,所述的预处理单元根据所述的距离参数扫描图获得车型参数信息和车型轮廓信息,具体为:所述的车长识别子单元根据所述的距离参数扫描图获得车长信息;所述的车高识别子单元根据所述的距离参数扫描图获得车高信息;所述的车辆轮廓线提取子单元根据所述的距离参数扫描图获得车辆轮廓信息。In the method for realizing the automatic identification of vehicle models based on high-speed pulsed laser scanning, the preprocessing unit includes a vehicle length identification subunit, a vehicle height identification subunit and a vehicle outline extraction subunit, and the vehicle length identification subunit and The output ends of the vehicle height identification subunit are connected to the vehicle model library unit, the vehicle contour extraction subunit is connected to the image matching unit, and the preprocessing unit obtains the vehicle model according to the distance parameter scan image Parameter information and vehicle profile information, specifically: the vehicle length identification subunit obtains vehicle length information according to the distance parameter scanning diagram; the vehicle height identification subunit obtains vehicle height according to the distance parameter scanning diagram Information; the vehicle contour line extraction subunit obtains vehicle contour information according to the distance parameter scan map.
该实现基于高速脉冲激光扫描的车型自动识别的方法中,所述的预处理单元将所述的车型参数信息发送至所述的车型库单元,具体为:所述的预处理单元将所述的车长信息和车高信息发送至所述的车型库单元。In the method for realizing automatic identification of car models based on high-speed pulsed laser scanning, the preprocessing unit sends the car model parameter information to the car model library unit, specifically: the preprocessing unit sends the The vehicle length information and vehicle height information are sent to the vehicle model library unit.
该实现基于高速脉冲激光扫描的车型自动识别的方法中,所述的车型库单元根据获得的车型参数信息读取对应的多个车型的图像信息发送至所述的图像匹配单元,具体为:车型库单元根据获得的车型车长信息和车高信息读取对应的多个车长及车高相符的车型的图像信息发送至所述的图像匹配单元。In the method for realizing automatic identification of car models based on high-speed pulsed laser scanning, the car model library unit reads the image information of a plurality of car models corresponding to the obtained car model parameter information and sends them to the image matching unit, specifically: car models The library unit reads the corresponding image information of a plurality of vehicle models with matching vehicle lengths and vehicle heights according to the obtained vehicle length information and vehicle height information and sends them to the image matching unit.
该实现基于高速脉冲激光扫描的车型自动识别的方法中,所述的步骤(44)具体包括以下步骤:In the method for realizing the automatic vehicle identification based on high-speed pulsed laser scanning, the step (44) specifically includes the following steps:
(44-1)所述的图像匹配单元利用近似测度方法将所述的车型轮廓信息依次与所述各个车型的图像信息进行对比,获得各个车型的近似度;(44-1) The image matching unit uses an approximate measurement method to compare the profile information of the car model with the image information of each car model in order to obtain the degree of approximation of each car model;
(44-1)所述的图像匹配单元将近似度最高的图像信息对应的车型作为匹配车型。The image matching unit described in (44-1) uses the car model corresponding to the image information with the highest degree of approximation as the matching car model.
采用了该发明的基于高速脉冲激光扫描的车型自动识别系统,其包括高频激光测距模块、车辆轮廓绘制模块和车型识别模块,所述的高频激光测距模块和车辆轮廓绘制模块设置于车辆经过的车道上方,所述的高频激光测距模块的激光脉冲发射口垂直于所述的车道,所述的高频激光测距模块的输出端连接所述的车辆轮廓绘制模块的输入端,所述的车辆轮廓绘制模块的输出端连接所述的车型识别模块的输入端。在车辆经过时,高频激光测距模块进行实时脉冲激光测距,并将测得的距离值发送至所述的车辆轮廓绘制模块;车辆轮廓绘制模块将接收到距离值实时绘制于距离参数扫描图上,并将该距离参数扫描图实时发送至所述的车型识别模块;车型识别模块根据该距离参数扫描图上绘制的车辆轮廓信息实现车型识别。从而有效克服了现有技术中存在的,设备设置及维护成本高,车型识别率低的缺陷,提供了一种设置及维护简单,成本低廉的车型自动识别系统,且该系统的车型识别率较高,应用范围也非常广泛的。The vehicle automatic identification system based on high-speed pulsed laser scanning of the invention is adopted, which includes a high-frequency laser ranging module, a vehicle outline drawing module and a vehicle identification module, and the high-frequency laser ranging module and the vehicle outline drawing module are arranged in Above the lane that the vehicle passes by, the laser pulse emission port of the high-frequency laser ranging module is perpendicular to the lane, and the output end of the high-frequency laser ranging module is connected to the input end of the vehicle contour drawing module , the output end of the vehicle outline drawing module is connected to the input end of the vehicle type identification module. When the vehicle passes by, the high-frequency laser ranging module performs real-time pulse laser ranging, and sends the measured distance value to the vehicle contour drawing module; the vehicle contour drawing module draws the received distance value in real time in the distance parameter scanning on the map, and send the distance parameter scan map to the vehicle type identification module in real time; the vehicle type identification module realizes vehicle type identification according to the vehicle profile information drawn on the distance parameter scan map. Thereby, the defects of high equipment setting and maintenance cost and low vehicle identification rate existing in the prior art are effectively overcome, and a vehicle automatic identification system with simple setting and maintenance and low cost is provided, and the vehicle identification rate of the system is relatively low. High, the application range is also very wide.
附图说明 Description of drawings
图1为本发明的基于高速脉冲激光扫描的车型自动识别系统的结构示意图。Fig. 1 is a structural schematic diagram of the vehicle type automatic identification system based on high-speed pulsed laser scanning of the present invention.
图2为本发明的实现基于高速脉冲激光扫描的车型自动识别的方法的步骤流程图。FIG. 2 is a flow chart of the steps of the method for realizing the automatic vehicle identification based on high-speed pulsed laser scanning of the present invention.
图3为本发明在实际应用中所采用的激光测距仪的原理框图。Fig. 3 is a functional block diagram of the laser rangefinder used in the practical application of the present invention.
图4为本发明在实际应用中激光测距仪架设位置示意图。Fig. 4 is a schematic diagram of the erection position of the laser range finder in the practical application of the present invention.
图5为本发明在实际应用中轮廓扫描数据绘图示意图。Fig. 5 is a schematic diagram of contour scanning data drawing in practical application of the present invention.
图6为本发明在实际应用中车型识别流程示意图。Fig. 6 is a schematic diagram of the vehicle type identification process in practical application of the present invention.
具体实施方式 Detailed ways
为了能够更清楚地理解本发明的技术内容,特举以下实施例详细说明。In order to understand the technical content of the present invention more clearly, the following examples are given in detail.
请参阅图1所示,为本发明的基于高速脉冲激光扫描的车型自动识别系统的结构示意图。Please refer to FIG. 1 , which is a schematic structural diagram of the vehicle type automatic identification system based on high-speed pulsed laser scanning of the present invention.
在一种实施方式中,该系统包括高频激光测距模块、车辆轮廓绘制模块和车型识别模块,所述的高频激光测距模块和车辆轮廓绘制模块设置于车辆经过的车道上方,所述的高频激光测距模块的激光脉冲发射口垂直于所述的车道,所述的高频激光测距模块的输出端连接所述的车辆轮廓绘制模块的输入端,所述的车辆轮廓绘制模块的输出端连接所述的车型识别模块的输入端。In one embodiment, the system includes a high-frequency laser ranging module, a vehicle contour drawing module, and a vehicle type identification module. The high-frequency laser ranging module and the vehicle contour drawing module are arranged above the lane that the vehicle passes through. The laser pulse emission port of the high-frequency laser ranging module is perpendicular to the lane, the output end of the high-frequency laser ranging module is connected to the input end of the vehicle contour drawing module, and the vehicle contour drawing module The output terminal is connected to the input terminal of the vehicle type identification module.
利用该实施方式所述的系统实现基于高速脉冲激光扫描的车型自动识别的方法,如图2所示,包括以下步骤:Using the system described in this embodiment to realize the method for automatic vehicle identification based on high-speed pulsed laser scanning, as shown in Figure 2, includes the following steps:
(1)所述的高频激光测距模块进行实时脉冲激光测距,并将测得的距离值发送至所述的车辆轮廓绘制模块;(1) The high-frequency laser ranging module performs real-time pulse laser ranging, and sends the measured distance value to the vehicle contour drawing module;
(2)所述的车辆轮廓绘制模块将接收到距离值实时绘制于距离参数扫描图上;(2) The vehicle contour drawing module draws the received distance value on the distance parameter scanning map in real time;
(3)所述的车辆轮廓绘制模块将所述的距离参数扫描图实时发送至所述的车型识别模块;(3) The vehicle contour drawing module sends the distance parameter scan map to the vehicle type identification module in real time;
(4)所述的车型识别模块根据所述的距离参数扫描图上绘制的车辆轮廓信息识别车型,并输出车型数据信息。(4) The vehicle type identification module identifies the vehicle type according to the vehicle outline information drawn on the distance parameter scan map, and outputs the vehicle type data information.
在一种较优选的实施方式中,所述的高频激光测距模块和车辆轮廓绘制模块均集成于一个高频激光测距仪内,且该高频激光测距仪固定于所述车道中间上方的道路监控架上,其安装方式十分简便。所述的高频激光测距模块的激光扫描频率可以为2000Hz,激光波长则为904nm。该高频激光测距模块的测距范围为30米。In a more preferred embodiment, the high-frequency laser rangefinder module and the vehicle contour drawing module are integrated into a high-frequency laser rangefinder, and the high-frequency laser rangefinder is fixed in the middle of the lane On the road monitoring frame above, its installation method is very simple. The laser scanning frequency of the high-frequency laser ranging module can be 2000Hz, and the laser wavelength is 904nm. The range of the high-frequency laser ranging module is 30 meters.
在另一种较优选的实施方式中,所述的车辆轮廓绘制模块为一距离参数扫描图绘制单元,该距离参数扫描图绘制单元的输入端连接所述的高频激光测距模块的输出端,所述的距离参数扫描图绘制单元的输出端连接所述的车型识别模块。该距离参数扫描图绘制单元的输出端可以通过数据线或无线信号连接所述的车型识别模块。In another preferred embodiment, the vehicle contour drawing module is a distance parameter scanning map drawing unit, and the input end of the distance parameter scanning map drawing unit is connected to the output end of the high-frequency laser ranging module , the output end of the distance parameter scanning map drawing unit is connected to the vehicle type identification module. The output end of the distance parameter scanning map drawing unit can be connected to the vehicle type identification module through a data line or a wireless signal.
在利用该较优选的实施方式所述的系统实现基于高速脉冲激光扫描的车型自动识别的方法中,所述的步骤(2)车辆轮廓绘制模块将接收到距离值实时绘制于距离参数扫描图上,具体为:所述的距离参数扫描图绘制单元将接收到距离值实时绘制于一坐标系中,形成一距离参数扫描图。且所述的步骤(3)车辆轮廓绘制模块将所述的距离参数扫描图实时发送至所述的车型识别模块,则具体为:车辆轮廓绘制模块将所述的距离参数扫描图通过数据线或无线信号实时发送至所述的车型识别模块。In the method of using the system described in this preferred embodiment to realize the automatic identification of vehicle models based on high-speed pulsed laser scanning, the step (2) the vehicle contour drawing module draws the received distance value on the distance parameter scanning map in real time , specifically: the distance parameter scanning map drawing unit draws the received distance value in a coordinate system in real time to form a distance parameter scanning map. And the step (3) the vehicle contour drawing module sends the distance parameter scanning diagram to the vehicle type identification module in real time, specifically: the vehicle contour drawing module transmits the distance parameter scanning diagram through the data line or The wireless signal is sent to the vehicle identification module in real time.
在一种进一步优选的实施方式中,所述的车型识别模块包括预处理单元、图像匹配单元和车型库单元,所述的预处理单元的输入端连接所述的车辆轮廓绘制模块的输出端,所述的预处理单元的输出端分别连接所述的图像匹配单元和车型库单元的输入端,所述的车型库单元的输出端连接所述的图像匹配单元的输出端,所述的图像匹配单元的输出端为车型信息输出端,该车型信息输出端为网络接口或串行接口。In a further preferred embodiment, the vehicle type identification module includes a preprocessing unit, an image matching unit, and a vehicle type library unit, the input end of the preprocessing unit is connected to the output end of the vehicle outline drawing module, The output of the preprocessing unit is respectively connected to the input of the image matching unit and the car model library unit, the output of the car model library unit is connected to the output of the image matching unit, and the image matching The output end of the unit is the vehicle type information output end, and the vehicle type information output end is a network interface or a serial interface.
在利用该进一步优选的实施方式所述的系统实现基于高速脉冲激光扫描的车型自动识别的方法中,所述的步骤(4)具体包括以下步骤:In the method of using the system described in this further preferred embodiment to realize the automatic vehicle identification method based on high-speed pulsed laser scanning, the step (4) specifically includes the following steps:
(41)所述的预处理单元根据所述的距离参数扫描图获得车型参数信息和车型轮廓信息;(41) The preprocessing unit obtains vehicle model parameter information and vehicle model profile information according to the distance parameter scan map;
(42)所述的预处理单元将所述的车型参数信息发送至所述的车型库单元,并将所述的车型轮廓信息发送至所述的图像匹配单元;(42) The preprocessing unit sends the car model parameter information to the car model library unit, and sends the car model profile information to the image matching unit;
(43)所述的车型库单元根据获得的车型参数信息读取对应的多个车型的图像信息发送至所述的图像匹配单元;(43) The car model library unit reads the image information of multiple car models corresponding to the obtained car model parameter information and sends them to the image matching unit;
(44)所述的图像匹配单元将从所述的预处理单元获得的车型轮廓信息与从所述的车型库单元获得的各个车型的图像信息依次进行对比,并将最接近的图像信息的车型作为匹配车型;(44) The image matching unit sequentially compares the car model profile information obtained from the preprocessing unit with the image information of each car model obtained from the car model library unit, and compares the car model information of the closest image information as a matching model;
(45)所述的车型信息输出端输出所述的匹配车型的数据信息。(45) The vehicle type information output terminal outputs the data information of the matching vehicle type.
在一种更优选的实施方式中,所述的预处理单元包括车长识别子单元、车高识别子单元和车辆轮廓线提取子单元,所述的车长识别子单元和车高识别子单元的输出端均连接所述的车型库单元,所述的车辆轮廓线提取子单元连接所述的图像匹配单元。In a more preferred embodiment, the preprocessing unit includes a vehicle length identification subunit, a vehicle height identification subunit, and a vehicle outline extraction subunit, and the vehicle length identification subunit and vehicle height identification subunit The output ends of each are connected to the car model library unit, and the vehicle outline extraction subunit is connected to the image matching unit.
在利用该更优选的实施方式所述的系统实现基于高速脉冲激光扫描的车型自动识别的方法中,所述的步骤(41)预处理单元根据所述的距离参数扫描图获得车型参数信息和车型轮廓信息,具体为:所述的车长识别子单元根据所述的距离参数扫描图获得车长信息;所述的车高识别子单元根据所述的距离参数扫描图获得车高信息;所述的车辆轮廓线提取子单元根据所述的距离参数扫描图获得车辆轮廓信息。步骤(42)中所述的预处理单元将所述的车型参数信息发送至所述的车型库单元,具体为:所述的预处理单元将所述的车长信息和车高信息发送至所述的车型库单元。且所述的步骤(43)车型库单元根据获得的车型参数信息读取对应的多个车型的图像信息发送至所述的图像匹配单元,具体为:车型库单元根据获得的车型车长信息和车高信息读取对应的多个车长及车高相符的车型的图像信息发送至所述的图像匹配单元。In the method of using the system described in this more preferred embodiment to realize the automatic recognition of car models based on high-speed pulsed laser scanning, the step (41) preprocessing unit obtains car model parameter information and car model information based on the distance parameter scan map. Outline information, specifically: the vehicle length identification subunit obtains vehicle length information according to the distance parameter scanning diagram; the vehicle height identification subunit obtains vehicle height information according to the distance parameter scanning diagram; The vehicle contour line extraction subunit obtains vehicle contour information according to the distance parameter scan map. The pre-processing unit in step (42) sends the car model parameter information to the car model library unit, specifically: the pre-processing unit sends the car length information and car height information to the car model library unit. The model library unit described above. And in the step (43), the car model library unit reads the image information of the corresponding multiple car models according to the obtained car model parameter information and sends them to the image matching unit, specifically: the car model library unit reads the image information of the corresponding car models according to the obtained model car length information and The vehicle height information reads corresponding image information of a plurality of vehicle models with matching vehicle lengths and vehicle heights and sends them to the image matching unit.
在另一更优选的实施方式中,所述的步骤(44)具体包括以下步骤:In another more preferred embodiment, the step (44) specifically includes the following steps:
(44-1)所述的图像匹配单元利用近似测度方法将所述的车型轮廓信息依次与所述各个车型的图像信息进行对比,获得各个车型的近似度;(44-1) The image matching unit uses an approximate measurement method to compare the profile information of the car model with the image information of each car model in order to obtain the degree of approximation of each car model;
(44-1)所述的图像匹配单元将近似度最高的图像信息对应的车型作为匹配车型。The image matching unit described in (44-1) uses the car model corresponding to the image information with the highest degree of approximation as the matching car model.
在实际应用中,本发明的基于高速脉冲激光扫描的车型自动识别系统具有以下特点:(a)利用高频激光测距仪作为检测器;(b)采用的激光测距仪的扫描频率高达2000Hz,激光发射波长904nm,人眼安全符合GB7247.1-2001I类;(c)测距仪布置在现有的道路监控架上,垂直向下扫描;(d)在激光测距仪上实现车型描绘算法,在PC机器上实现车型识别;(e)系统备有两种传输接口:网络和串口;(f)车型识别算法基于图像模式识别原理,将样本数据与车型数据库中的数据通过计算机比较判断出车型,从而实现车型的自动分类。In practical application, the vehicle type automatic identification system based on high-speed pulsed laser scanning of the present invention has the following characteristics: (a) using a high-frequency laser rangefinder as a detector; (b) the scanning frequency of the laser rangefinder used is as high as 2000Hz , the laser emission wavelength is 904nm, and the safety of human eyes complies with GB7247.1-2001I; (c) The range finder is arranged on the existing road monitoring frame and scans vertically downward; (d) The vehicle model is depicted on the laser range finder (e) The system has two transmission interfaces: network and serial port; (f) The vehicle identification algorithm is based on the principle of image pattern recognition, and the sample data and the data in the vehicle database are compared and judged by the computer Models can be generated, so as to realize the automatic classification of models.
激光扫描技术是利用激光对目标物体进行距离测定(又称激光测距)的技术。它在工作时向目标射出一束激光,由光电元件接收目标反射的激光束,计时器测定激光束从发射到接收的时间,计算出从观测者到目标的距离。LiDAR(Light Laser Detection and Ranging,激光探测及测距系统)的原理和构造与激光测距仪极为相似。系统包括一个单束窄带激光器和一个接收系统。激光器产生并发射一束光脉冲,打在物体上并反射回来,最终被接收器所接收。接收器准确地测量光脉冲从发射到被反射回的传播时间。鉴于光速是已知的,传播时间即可被转换为对距离的测量。本发明所采用的激光测距仪的原理框图如图3所示。Laser scanning technology is a technology that uses laser to measure the distance of the target object (also known as laser ranging). When it works, it shoots a laser beam to the target, and the photoelectric element receives the laser beam reflected by the target. The timer measures the time from the launch to the reception of the laser beam, and calculates the distance from the observer to the target. The principle and structure of LiDAR (Light Laser Detection and Ranging, laser detection and ranging system) are very similar to the laser range finder. The system consists of a single beam narrowband laser and a receiver system. A laser generates and emits a pulse of light that hits an object and bounces back, where it is picked up by a receiver. The receiver accurately measures the travel time of the light pulse from when it is emitted to when it is reflected back. Given that the speed of light is known, travel time can be converted into a measure of distance. The principle block diagram of the laser range finder used in the present invention is shown in FIG. 3 .
激光扫描法是利用布置道路监控架上的激光测距仪器作为检测器,当车辆经过装置时,根据对汽车不同部位的测距扫描,采集车辆的侧面几何数据,然后通过这些数据与车型数据库中的数据比较后判断出车型,从而实现车型的自动分类。在基于激光高速脉冲扫描技术的车型识别系统中,激光测距仪器的频率很高,这就保证了系统可以采集到足够多的数据,这些数据包括车头高度、车长、轴数、轮距等特征数据,这些信息可以比较完整、细致地描绘出车辆的外轮廓及局部典型特征,使系统达到一个很高的识别率。该方法优点是识别率较高,另外硬件安装非常简单,只需在现有的摄像监控支架上安装一台激光测距仪,利用数据传输线和主机相连。并且利用该方法无需破坏路面,维护起来非常方便。The laser scanning method uses the laser ranging instrument arranged on the road monitoring frame as a detector. When the vehicle passes by the device, according to the ranging scanning of different parts of the vehicle, the side geometric data of the vehicle is collected, and then the data is compared with the vehicle model database. The model is judged after comparing the data, so as to realize the automatic classification of the model. In the vehicle identification system based on laser high-speed pulse scanning technology, the frequency of the laser distance measuring instrument is very high, which ensures that the system can collect enough data, including the height of the front of the vehicle, the length of the vehicle, the number of axles, the wheelbase, etc. Feature data, these information can describe the outer contour and local typical features of the vehicle in a relatively complete and detailed manner, so that the system can achieve a high recognition rate. The advantage of this method is that the recognition rate is high. In addition, the hardware installation is very simple. It only needs to install a laser range finder on the existing camera monitoring bracket, and connect it to the host computer with a data transmission line. Moreover, the method does not need to destroy the road surface, and the maintenance is very convenient.
轮廓识别系统是采用激光发射和接收垂直地面向下,如下图4所示,对准一条车道的中间位置,当有车辆通行时,激光测距仪能实时输出所测得的距离值的改变,进而描绘出所测车的轮廓。这种测量方式一般使用的激光束发散角度较小,测距范围一般小于30米即可,且要求激光测距速率比较高,一般要求达到几千赫兹。这对于在重要路段监控可以达到很好的效果,能够区分各种车型,对车身扫描的采样率可以达到1厘米一个点。还可用于车流监测、车辆限高等应用。The contour recognition system adopts laser emission and reception vertically downward, as shown in Figure 4 below, aiming at the middle position of a lane. When there is a vehicle passing by, the laser rangefinder can output the change of the measured distance value in real time. Then draw the outline of the car under test. This measurement method generally uses a small laser beam divergence angle, and the ranging range is generally less than 30 meters, and requires a relatively high laser ranging rate, which generally requires several kilohertz. This can achieve very good results for monitoring important road sections, and can distinguish various models, and the sampling rate for body scanning can reach a point of 1 cm. It can also be used in traffic flow monitoring, vehicle height limit and other applications.
本发明的实现基于高速脉冲激光扫描的车型自动识别的方法采用了近似测度法。首先截取激光扫描的数据绘制相关车型,如图5所示。然后作校正处理。校正的主要内容包括轮廓角度和轮廓毛刺,接着就通过相关的模式匹配算法进行识别。其识别过程就是对车型图寻找出一副以它对应的相似车型图片。The method for realizing the automatic vehicle identification based on high-speed pulsed laser scanning of the present invention adopts the approximate measurement method. Firstly, the data of laser scanning is intercepted to draw relevant vehicle models, as shown in Figure 5. Then make corrections. The main content of correction includes contour angle and contour burr, and then it is identified through relevant pattern matching algorithm. The recognition process is to find a picture of a similar car model corresponding to the model map.
一般来说,由于图像在不同时间、不同传感器、不同视角获得的成像条件不同,因此即使是对同一物体,在图像中所表现出来的几何特性、光学特性、空间位置都会有很大的不同,如果考虑到噪声、干扰等影响会使图像发生很大差异,图像匹配就是通过这些不同之处找到它们的相同点。本方法利用图像的物理形状特征(点、线),如边缘,骨架线条,角点等等,需要进行相关计算的像素点数目有了明显的减少,并具有更强的适应能力。这种算法对于一些细微的干扰不太敏感,而是依赖于提取的图像特征。其关键是寻找易于识别和区分的特征,基于特征集之间的相似性度量来找到模板在图像中的匹配位置。因此,本发明所采用识别的流程如图6所示。Generally speaking, due to the different imaging conditions obtained by images at different times, different sensors, and different viewing angles, even for the same object, the geometric characteristics, optical characteristics, and spatial positions shown in the image will be very different. If it is considered that noise, interference and other effects will cause great differences in images, image matching is to find their similarities through these differences. This method utilizes the physical shape features (points, lines) of the image, such as edges, skeleton lines, corners, etc., and the number of pixels that need to be calculated has been significantly reduced, and it has stronger adaptability. This algorithm is less sensitive to some subtle disturbances, but relies on the extracted image features. The key is to find features that are easy to identify and distinguish, and find the matching position of the template in the image based on the similarity measure between feature sets. Therefore, the identification process adopted by the present invention is shown in FIG. 6 .
采用了该发明的基于高速脉冲激光扫描的车型自动识别系统,其包括高频激光测距模块、车辆轮廓绘制模块和车型识别模块,所述的高频激光测距模块和车辆轮廓绘制模块设置于车辆经过的车道上方,所述的高频激光测距模块的激光脉冲发射口垂直于所述的车道,所述的高频激光测距模块的输出端连接所述的车辆轮廓绘制模块的输入端,所述的车辆轮廓绘制模块的输出端连接所述的车型识别模块的输入端。在车辆经过时,高频激光测距模块进行实时脉冲激光测距,并将测得的距离值发送至所述的车辆轮廓绘制模块;车辆轮廓绘制模块将接收到距离值实时绘制于距离参数扫描图上,并将该距离参数扫描图实时发送至所述的车型识别模块;车型识别模块根据该距离参数扫描图上绘制的车辆轮廓信息实现车型识别。从而有效克服了现有技术中存在的,设备设置及维护成本高,车型识别率低的缺陷,提供了一种设置及维护简单,成本低廉的车型自动识别系统,且该系统的车型识别率较高,应用范围也非常广泛的。The vehicle automatic identification system based on high-speed pulsed laser scanning of the invention is adopted, which includes a high-frequency laser ranging module, a vehicle outline drawing module and a vehicle identification module, and the high-frequency laser ranging module and the vehicle outline drawing module are arranged in Above the lane that the vehicle passes by, the laser pulse emission port of the high-frequency laser ranging module is perpendicular to the lane, and the output end of the high-frequency laser ranging module is connected to the input end of the vehicle contour drawing module , the output end of the vehicle outline drawing module is connected to the input end of the vehicle type identification module. When the vehicle passes by, the high-frequency laser ranging module performs real-time pulse laser ranging, and sends the measured distance value to the vehicle contour drawing module; the vehicle contour drawing module draws the received distance value in real time in the distance parameter scanning on the map, and send the distance parameter scan map to the vehicle type identification module in real time; the vehicle type identification module realizes vehicle type identification according to the vehicle profile information drawn on the distance parameter scan map. Thereby, the defects of high equipment setting and maintenance cost and low vehicle identification rate existing in the prior art are effectively overcome, and a vehicle automatic identification system with simple setting and maintenance and low cost is provided, and the vehicle identification rate of the system is relatively low. High, the application range is also very wide.
在此说明书中,本发明已参照其特定的实施例作了描述。但是,很显然仍可以作出各种修改和变换而不背离本发明的精神和范围。因此,说明书和附图应被认为是说明性的而非限制性的。In this specification, the invention has been described with reference to specific embodiments thereof. However, it is obvious that various modifications and changes can be made without departing from the spirit and scope of the invention. Accordingly, the specification and drawings are to be regarded as illustrative rather than restrictive.
Claims (14)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210202048.1A CN102708694B (en) | 2012-06-19 | 2012-06-19 | Automatic motorcycle type identification system and method based on high-speed pulse laser scanning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210202048.1A CN102708694B (en) | 2012-06-19 | 2012-06-19 | Automatic motorcycle type identification system and method based on high-speed pulse laser scanning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102708694A CN102708694A (en) | 2012-10-03 |
CN102708694B true CN102708694B (en) | 2014-07-09 |
Family
ID=46901406
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210202048.1A Active CN102708694B (en) | 2012-06-19 | 2012-06-19 | Automatic motorcycle type identification system and method based on high-speed pulse laser scanning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102708694B (en) |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103021035A (en) * | 2012-10-20 | 2013-04-03 | 山东易构软件技术有限公司 | Electronic toll collection system using laser radar in long communication area |
CN103208203A (en) * | 2012-11-29 | 2013-07-17 | 柏淞耀 | View display system of parking place condition of parking lot |
CN103035038B (en) * | 2012-12-17 | 2016-12-07 | 山东易构软件技术股份有限公司 | A kind of electronic non-parking weight and charge system |
CN103106398A (en) * | 2013-01-28 | 2013-05-15 | 芜湖德力自动化装备科技有限公司 | Vehicle type recognition device |
CN103197323B (en) * | 2013-04-17 | 2014-11-26 | 清华大学 | Scanning data matching method and device for laser distance measuring machine |
CN104361752A (en) * | 2014-10-27 | 2015-02-18 | 北京握奇智能科技有限公司 | Laser scanning based vehicle type recognition method for free flow charging |
CN104574996A (en) * | 2015-01-22 | 2015-04-29 | 青岛大学 | Scanning-type intelligent detection method and device for road traffic vehicles |
CN106772419B (en) * | 2015-11-23 | 2021-02-12 | 北京万集科技股份有限公司 | Vehicle positioning method and device |
CN105575133B (en) * | 2015-12-24 | 2018-07-31 | 北京万集科技股份有限公司 | A kind of moving vehicle detection method, apparatus and system |
CN105447528B (en) | 2015-12-29 | 2018-11-27 | 同方威视技术股份有限公司 | Train license number and model recognizing method and system and safety detection method and system |
CN107437336B (en) * | 2016-05-27 | 2019-12-10 | 武汉万集信息技术有限公司 | vehicle type recognition device and method |
CN110307809B (en) * | 2018-03-20 | 2021-08-06 | 中移(苏州)软件技术有限公司 | A vehicle type identification method and device |
CN109480628A (en) * | 2019-01-07 | 2019-03-19 | 上海万沣环保科技有限公司 | A kind of child intelligence protection drinking-water system |
CN109754610A (en) * | 2019-03-01 | 2019-05-14 | 北京数字智通科技有限公司 | vehicle monitoring method and device |
CN112009490A (en) * | 2019-05-30 | 2020-12-01 | 博世汽车部件(苏州)有限公司 | Method and system for determining the shape of an object or vehicle, and driving assistance system |
CN111783638B (en) * | 2020-06-30 | 2023-09-01 | 山东鼎高信息技术有限公司 | System and method for detecting number of wheel axles of vehicle and identifying vehicle type |
CN116216344B (en) * | 2022-10-21 | 2023-11-07 | 中电投锦州港口有限责任公司 | Double-car dumper system and double-car dumper method |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101451833A (en) * | 2007-11-30 | 2009-06-10 | 佛山普立华科技有限公司 | Laser ranging apparatus and method |
CN101859491A (en) * | 2009-04-10 | 2010-10-13 | 张高军 | Method for obtaining longitudinal profile pattern of mobile vehicle and device thereof |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3015876B2 (en) * | 1998-06-30 | 2000-03-06 | 建設省土木研究所長 | Traveling vehicle grasping device using pulse laser |
-
2012
- 2012-06-19 CN CN201210202048.1A patent/CN102708694B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101451833A (en) * | 2007-11-30 | 2009-06-10 | 佛山普立华科技有限公司 | Laser ranging apparatus and method |
CN101859491A (en) * | 2009-04-10 | 2010-10-13 | 张高军 | Method for obtaining longitudinal profile pattern of mobile vehicle and device thereof |
Non-Patent Citations (5)
Title |
---|
JP特开2000-20876A 2000.01.21 |
一种开放式全自动电子收费系统的研究;关双城;《黑龙江工程学院学报》;20030331;第17卷(第1期);第51-54页 * |
关双城.一种开放式全自动电子收费系统的研究.《黑龙江工程学院学报》.2003,第17卷(第1期),第51-54页. |
激光测距技术在智能交通中的应用;陈建勇;《中国安防》;20101030(第10期);第96页第1列倒数第1-6行,第2-3列、第97页第1列倒数第1-6行、第2列第1-21行、图2-3 * |
陈建勇.激光测距技术在智能交通中的应用.《中国安防》.2010,(第10期),第96页第1列倒数第1-6行,第2-3列、第97页第1列倒数第1-6行、第2列第1-21行、图2-3. |
Also Published As
Publication number | Publication date |
---|---|
CN102708694A (en) | 2012-10-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102708694B (en) | Automatic motorcycle type identification system and method based on high-speed pulse laser scanning | |
CN104064031B (en) | The vehicle peccancy monitoring of a kind of applying electronic car plate and tracking location system | |
CN102737247B (en) | Identification system of smoke intensity image of tail gas of diesel vehicle | |
CN102663893B (en) | A method of road information collection based on laser ranging node system | |
CN101777263B (en) | Traffic vehicle flow detection method based on video | |
CN105046968B (en) | A kind of motor bus identification and grasp shoot method, apparatus and system | |
CN102509089B (en) | Method for recognizing zebra crossing and measuring zebra crossing distance based on line-by-line scanning | |
CN103954222B (en) | A kind of vehicle's contour and wheelbase automatic measurement system and Measurement Algorithm | |
CN103714603B (en) | Based on the bus passenger flow statistical system of infrared distance sensor | |
CN108510734A (en) | A kind of information of vehicles matching process of roadside unit and a kind of roadside unit | |
CN204632107U (en) | A kind of combined model recognition system based on scanning type laser stadimeter | |
CN102426785B (en) | Traffic flow information perception method and system based on contour and local feature points | |
CN208422108U (en) | Transport investigation device based on millimetre-wave radar and laser radar | |
CN110751788A (en) | System and method for identifying whether vehicle direction and angle and distance of road are correct | |
CN104361752A (en) | Laser scanning based vehicle type recognition method for free flow charging | |
CN106448189A (en) | Multilane speed measuring and block port triggering method and device based on microwaves | |
CN104183133A (en) | Method for acquiring and transmitting road traffic flow dynamic information | |
CN112232139B (en) | An obstacle avoidance method based on the combination of Yolo v4 and Tof algorithm | |
CN102914290A (en) | Metro gauge detecting system and detecting method thereof | |
CN110346295B (en) | Defect composite positioning method and device, equipment and storage medium | |
KR102093237B1 (en) | Vehicle classification system using non-contact automatic vehicle detectior | |
CN104361751A (en) | Laser scanning based vehicle type recognition system for free flow charging | |
CN103714604B (en) | Based on the bus passenger flow statistical system of ultrasonic sensor | |
CN107796373A (en) | A kind of distance-finding method of the front vehicles monocular vision based on track plane geometry model-driven | |
CN102141372A (en) | Measuring grating-based device and method for detecting illegal loading of transport vehicles |
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 |