CN109598947A - A kind of vehicle identification method and system - Google Patents

A kind of vehicle identification method and system Download PDF

Info

Publication number
CN109598947A
CN109598947A CN201811605347.3A CN201811605347A CN109598947A CN 109598947 A CN109598947 A CN 109598947A CN 201811605347 A CN201811605347 A CN 201811605347A CN 109598947 A CN109598947 A CN 109598947A
Authority
CN
China
Prior art keywords
vehicle
laser radar
frame data
data
time
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201811605347.3A
Other languages
Chinese (zh)
Other versions
CN109598947B (en
Inventor
杨勇刚
李康
蔡鄂
胡攀攀
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Wanji Information Technology Co Ltd
Original Assignee
Wuhan Wanji Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Wuhan Wanji Information Technology Co Ltd filed Critical Wuhan Wanji Information Technology Co Ltd
Priority to CN201811605347.3A priority Critical patent/CN109598947B/en
Publication of CN109598947A publication Critical patent/CN109598947A/en
Application granted granted Critical
Publication of CN109598947B publication Critical patent/CN109598947B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/015—Detecting movement of traffic to be counted or controlled with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Optical Radar Systems And Details Thereof (AREA)
  • Traffic Control Systems (AREA)

Abstract

The present invention provides a kind of vehicle identification method and systems, wherein, this method comprises: scanning road section at least through first laser radar and second laser radar with the identical scan period, acquire the data in vehicle travel process, wherein, the scanning surface of the first laser radar and the second laser radar is perpendicular to vehicle heading, the first laser radar and the second laser radar separation preset distance；The speed, length and vehicle of vehicle are determined according to the data and the preset distance, therefore, it can solve in transport investigation in the related technology and the not accurate enough problem of vehicle identification existing for vehicle condition monitored by laser ranging, the related data of vehicle driving is acquired by least two laser radars, the speed, length and vehicle for determining vehicle improve the accuracy of vehicle identification during monitoring.

Description

Vehicle identification method and system
Technical Field
The invention relates to the field of communication, in particular to a vehicle identification method and system.
Background
In recent years, with the rapid development of laser ranging technology, the laser ranging technology is widely used in the field of intelligent transportation, and by means of high-precision measurement of the laser ranging technology, the laser ranging technology has remarkable advantages particularly in the aspects of traffic condition investigation, vehicle contour dimension detection and the like, and is more and more trusted by customers. At present, the laser ranging technology is used for investigating traffic conditions and classifying vehicle types, a plurality of products are available, a good effect is achieved, and some defects exist. The laser scanning device is used for investigating the traffic condition, the error in the aspect of calculating the speed and the length of the vehicle is large, and the classification of the vehicle types with the critical length cannot be well solved; two laser light curtain units, namely point-emission lasers are adopted to investigate traffic conditions, vehicle information which is not collected by scanning lasers is rich, and a relatively large promotion space is provided in the aspect of vehicle type judgment; the vehicle information is acquired by using multiple sensors, and the vehicle type is identified by extracting vehicle characteristics, so that the method is slightly insufficient in the aspects of calculating the vehicle speed and vehicles with critical lengths.
In the existing laser ranging traffic condition investigation method or system, a large lifting space exists in the aspects of vehicle speed, vehicle type and/or vehicle type classification with critical length.
Aiming at the problem that vehicle identification is not accurate enough when the vehicle condition is monitored through laser ranging in traffic condition investigation in the related art, a solution is not provided yet.
Disclosure of Invention
The embodiment of the invention provides a vehicle identification method and a vehicle identification system, which are used for at least solving the problem that the vehicle identification is not accurate enough when the vehicle condition is monitored through laser ranging in traffic condition investigation in the related technology.
According to an embodiment of the present invention, there is provided a vehicle identification method including:
scanning a road section by at least a first laser radar and a second laser radar in the same scanning period, and collecting data in the running process of a vehicle, wherein the scanning surfaces of the first laser radar and the second laser radar are perpendicular to the running direction of the vehicle, and the first laser radar and the second laser radar are separated by a preset distance;
and determining the speed, the length and the model of the vehicle according to the data and the preset distance.
Optionally, determining the speed, the length, and the model of the vehicle according to the data and the predetermined distance comprises:
determining the speed of the vehicle according to the first frame data and time and the last frame data and time of the vehicle acquired by the first laser radar, and the first frame data and time and the last frame data and time and the time of the vehicle acquired by the second laser radar;
determining the length of the vehicle according to the speed of the vehicle, the time difference of different frame data, the preset distance and the scanning period;
and determining the vehicle type of the vehicle according to all frame data of the vehicle collected by the preset distance, the first laser radar and the second laser radar.
Optionally, determining the speed of the vehicle according to the first frame data and time and the last frame data and time of the vehicle collected by the first lidar and the first frame data and time and the last frame data and time of the vehicle collected by the second lidar comprises:
acquiring first frame data and time t of the vehicle acquired by the first laser radar1Last frame data and time t2And the first frame data and the time t of the vehicle collected by the second laser radar3Last frame data and time t4；
Determining similarity gamma of first frame data of the vehicle collected by the first laser radar and first frame data of the vehicle collected by the second laser radar1Similarity gamma between the last frame data of the vehicle collected by the first lidar and the last frame data of the vehicle collected by the second lidar2；
According to the time t1The time t3The predetermined distance, the scanning period, the similarity γ1Determining vehicle speed v1According to said time t2The time t4The predetermined distance, the scanning period, the similarity γ2Determining vehicle speed v2；
According to the vehicle speed v1And the vehicle speed v2Determining a speed of the vehicle.
Optionally, determining a first frame number of the vehicle collected by the first lidar and a first frame number of the vehicle collected by the second lidarAccording to the similarity gamma1Similarity gamma between the last frame data of the vehicle collected by the first lidar and the last frame data of the vehicle collected by the second lidar2The method comprises the following steps:
respectively extracting the following characteristic information from the first frame data of the vehicle collected by the first laser radar and the first frame data of the vehicle collected by the second laser radar: the height of frame data, the width of the frame data, the number of points of a scanning vehicle and the relative position of the vehicle and a laser radar are determined, and the similarity gamma between the first frame data of the vehicle collected by the first laser radar and the first frame data of the vehicle collected by the second laser radar is determined according to the extracted characteristic information1；
Respectively extracting the following characteristic information from the last frame data of the vehicle collected by the first laser radar and the last frame data of the vehicle collected by the second laser radar: frame data height, frame data width, the number of scanning vehicles and the relative positions of the vehicles and the laser radars, and determining the similarity gamma between the last frame data of the vehicles collected by the first laser radar and the last frame data of the vehicles collected by the second laser radar according to the extracted characteristic information2。
Optionally, the time t is determined by the following formula1The time t3The predetermined distance, the scanning period, the similarity γ1Determining the vehicle speed v1：
v1＝S/(t3-t1-k(1-γ1)T)；
According to said time t by the following formula2The time t4The predetermined distance, the scanning period, the similarity γ2Determining vehicle speed v2：
v2＝S/(t4-t2-k(1-γ2)T)，
Wherein S is the predetermined distance, and T is the scanning period;
and when at least one of the characteristic information in the vehicle frame data acquired by the first laser radar is greater than the corresponding characteristic information of the vehicle frame data acquired by the second laser radar, k is a positive number, and otherwise, k is a negative number.
Optionally, the vehicle speed v is determined from the following formula1And the vehicle speed v2Determining a speed v of the vehicle:
v＝α1v1+α2v2，
wherein, α1、α2Is a weight value of α1+α2＝1。
Optionally, the length L of the vehicle is determined according to the speed of the vehicle, the time difference of the different frame data, the predetermined distance, and the scanning period by the following formula:
L1＝v(t2-t1+T)
L2＝v(t4-t3+T)
L3＝v(t4-t1)-S
L＝w1L1+w2L2+w3L3，
wherein, the w1W to2W to3Is a weight value, said w3Greater than said w1W to2，w1+w2+w3＝1。
Optionally, determining the vehicle type of the vehicle according to all frame data of the vehicle collected by the predetermined distance, the first lidar and the second lidar includes:
classifying the vehicle type of the vehicle according to all frame data of the vehicle collected by the preset distance, the first laser radar and the second laser radar;
and determining the vehicle type of the vehicle according to the classification result of the vehicle and all frame data of the vehicle collected by the first laser radar and the second laser radar.
Optionally, classifying the vehicle type of the vehicle according to all frame data of the vehicle collected by the predetermined distance, the first laser radar and the second laser radar includes:
acquiring all frame data of the vehicle acquired by the first laser radar and the second laser radar;
if the first laser radar collects the last frame data of the vehicle, the second laser radar collects the first frame data of the vehicle, and the vehicle is determined to be a vehicle type with a first critical length according to the preset distance;
when the second laser radar collects first frame data of the vehicle, marking the data of the vehicle collected by the first laser radar as ith frame data, and when the first laser radar collects the last frame data of the vehicle, marking the data of the vehicle collected by the second laser radar as jth frame data;
matching the data from the i frame data to the last frame data of the vehicle collected by the first laser radar with the data from the j frame data to the last frame data of the vehicle collected by the second laser radar, and calculating the similarity k1；
Matching the first frame data to the jth frame data of the vehicle collected by the second laser radar with the first frame data to the ith frame data of the vehicle collected by the first laser radar, and calculating the similarity k2；
Calculating the similarity k1With the similarity k2The arithmetic mean of (a);
and when the arithmetic mean value is larger than a preset similarity threshold value, determining that the vehicle is the vehicle type with the second critical length.
Optionally, determining the vehicle type of the vehicle according to the classification result of the vehicle, and all frame data of the vehicle collected by the first lidar and the second lidar includes:
identifying the vehicle type and a first vehicle type confidence coefficient of the vehicle according to the classification result of the vehicle and first contour data information of the vehicle;
identifying a vehicle type and a second vehicle type confidence coefficient of the vehicle according to a classification result of the vehicle and second profile data information of the vehicle, wherein the first profile data information is all frame data of the vehicle collected by the first laser radar, and the second profile data information is all frame data of the vehicle collected by the second laser radar;
and determining the vehicle type of the vehicle according to the first vehicle type confidence coefficient and the second vehicle type confidence coefficient.
Optionally, determining the vehicle type of the vehicle according to the first vehicle type confidence and the second vehicle type confidence comprises:
fusing the first contour data information and the second contour data information by adopting a frame data similarity interpolation method according to a frame data sequence passed by the vehicle to obtain third contour data information;
identifying the vehicle type and the third vehicle type confidence of the vehicle according to the classification result of the vehicle and the third profile data information;
determining the vehicle type of the vehicle according to the first vehicle type confidence degree, the second vehicle type confidence degree and the third vehicle type confidence degree.
According to another embodiment of the present invention, there is also provided a vehicle identification system including at least: a first laser radar, a second laser radar, and a data processing unit, wherein the first laser radar and the second laser radar are respectively connected with the data processing unit, and the first laser radar and the second laser radar are separated by a preset distance,
the first laser radar and the second laser radar are used for scanning road sections in the same scanning period and collecting data in the vehicle running process, wherein the scanning surfaces of the first laser radar and the second laser radar are perpendicular to the vehicle running direction;
and the data processing unit is used for determining the speed, the length and the model of the vehicle according to the data and the preset distance.
Optionally, the data processing unit is further configured to determine the speed of the vehicle according to the first frame data and time of the vehicle and the last frame data and time acquired by the first lidar, and the first frame data and time of the vehicle and the last frame data and time acquired by the second lidar;
determining the length of the vehicle according to the speed of the vehicle, the time difference of different frame data, the preset distance and the scanning period;
and determining the vehicle type of the vehicle according to all frame data of the vehicle collected by the preset distance, the first laser radar and the second laser radar.
Optionally, the data processing unit is further configured to periodically time-calibrate the first lidar and the second lidar.
Optionally, the data processing unit is further configured to send a timing instruction to the first laser radar, where the timing instruction is used to instruct the first laser radar to complete time synchronization with the second laser radar; or,
and sending a timing instruction to the second laser radar, wherein the timing instruction is used for indicating the second laser radar to complete time synchronization with the first laser radar.
Optionally, the first and second lidar comprise at least one of: the system comprises a single-point scanning type laser ranging sensor, a single-line scanning type laser ranging sensor and a multi-line scanning type laser ranging sensor.
Optionally, the scanning angles of the first and second lidar are greater than or equal to 60 degrees, and the scanning areas of the first and second lidar cover all lanes to be monitored.
Optionally, the data processing unit is further configured to establish a connection with a server through an information output interface, and report the identified result to the server.
According to another embodiment of the present invention, there is also provided a vehicle identification device including:
the system comprises an acquisition module, a data acquisition module and a data acquisition module, wherein the acquisition module is used for scanning a road section at the same scanning period at least through a first laser radar and a second laser radar and acquiring data in the running process of a vehicle, the scanning surfaces of the first laser radar and the second laser radar are perpendicular to the running direction of the vehicle, and the first laser radar and the second laser radar are separated by a preset distance;
and the determining module is used for determining the speed, the length and the vehicle type of the vehicle according to the data and the preset distance.
Optionally, the determining module includes:
the first determining unit is used for determining the speed of the vehicle according to the first frame data and time and the last frame data and time of the vehicle acquired by the first laser radar, and the first frame data and time and the last frame data and time of the vehicle acquired by the second laser radar;
the second determining unit is used for determining the length of the vehicle according to the speed of the vehicle, the time difference of different frame data, the preset distance and the scanning period;
and the third determining unit is used for determining the vehicle type of the vehicle according to the preset distance and all frame data of the vehicle acquired by the first laser radar and the second laser radar.
According to a further embodiment of the present invention, there is also provided a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
According to yet another embodiment of the present invention, there is also provided an electronic device, including a memory in which a computer program is stored and a processor configured to execute the computer program to perform the steps in any of the above method embodiments.
According to the invention, at least a first laser radar and a second laser radar are used for scanning the cross section of a road in the same scanning period and collecting data in the running process of a vehicle, wherein the scanning surfaces of the first laser radar and the second laser radar are perpendicular to the running direction of the vehicle, and the first laser radar and the second laser radar are separated by a preset distance; the speed, the length and the vehicle type of the vehicle are determined according to the data and the preset distance, so that the problem that the vehicle identification is not accurate enough when the vehicle condition is monitored through laser ranging in traffic condition investigation in the related technology can be solved, the speed, the length and the vehicle type of the vehicle are determined by collecting the relevant data of vehicle running through at least two laser radars, and the accuracy of vehicle identification in the monitoring process is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a block diagram of a hardware configuration of a mobile terminal of a vehicle identification method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method of vehicle identification according to an embodiment of the present invention;
FIG. 3 is a flow chart of a laser-based vehicle identification method according to an embodiment of the present invention;
FIG. 4 is a first flowchart of a laser-based vehicle identification method according to a preferred embodiment of the present invention;
FIG. 5 is a second flowchart of a laser-based vehicle identification method in accordance with a preferred embodiment of the present invention;
FIG. 6 is a flow chart three of a laser-based vehicle identification method according to a preferred embodiment of the present invention;
FIG. 7 is a schematic diagram of a vehicle identification system according to an embodiment of the invention;
FIG. 8 is a first schematic diagram of a vehicle identification system in accordance with a preferred embodiment of the present invention;
FIG. 9 is a second schematic diagram of a vehicle identification system in accordance with a preferred embodiment of the present invention;
FIG. 10 is a third schematic view of a vehicle identification system in accordance with a preferred embodiment of the present invention;
fig. 11 is a block diagram of a vehicle recognition apparatus according to an embodiment of the present invention.
Detailed Description
The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
Example 1
The method provided by the first embodiment of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. Taking a mobile terminal as an example, fig. 1 is a hardware structure block diagram of a mobile terminal of a vehicle identification method according to an embodiment of the present invention, as shown in fig. 1, a mobile terminal 10 may include one or more processors 102 (only one is shown in fig. 1) (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.), and a memory 104 for storing data, and optionally, the mobile terminal may further include a transmission device 106 for communication function and an input/output device 108. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration, and does not limit the structure of the mobile terminal. For example, the mobile terminal 10 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to the message receiving method in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, so as to implement the method described above. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the mobile terminal 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal 10. In one example, the transmission device 106 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
In the present embodiment, a vehicle identification method operating in the mobile terminal or the network architecture is provided, and fig. 2 is a flowchart of a vehicle identification method according to an embodiment of the present invention, as shown in fig. 2, the flowchart includes the following steps:
step S202, scanning a road section by at least a first laser radar and a second laser radar in the same scanning period, and collecting data in the vehicle running process, wherein the scanning surfaces of the first laser radar and the second laser radar are perpendicular to the vehicle running direction, and the first laser radar and the second laser radar are separated by a preset distance;
and step S204, determining the speed, the length and the model of the vehicle according to the data and the preset distance.
Through the steps, the problem that vehicle identification is not accurate enough when the vehicle condition is monitored through laser ranging in traffic condition investigation in the related technology is solved, the speed, the length and the vehicle type of the vehicle are determined by collecting relevant data of vehicle running through at least two laser radars, and the accuracy of vehicle identification in the monitoring process is improved.
The step S204 may specifically include:
s1, determining the speed of the vehicle according to the first frame data and time and the last frame data and time of the vehicle collected by the first laser radar, and the first frame data and time and the last frame data and time of the vehicle collected by the second laser radar;
s2, determining the length of the vehicle according to the speed of the vehicle, the time difference of different frame data, the preset distance and the scanning period;
and S3, determining the vehicle type of the vehicle according to the preset distance and all the frame data of the vehicle collected by the first laser radar and the second laser radar.
The step S1 may specifically include:
s11, acquiring first frame data and time t of the vehicle collected by the first laser radar1Last frame data and time t2And the first frame data and the time t of the vehicle collected by the second laser radar3Last frame data and time t4；
S12, determining the similarity gamma of the first frame data of the vehicle collected by the first laser radar and the first frame data of the vehicle collected by the second laser radar1Similarity gamma between the last frame data of the vehicle collected by the first lidar and the last frame data of the vehicle collected by the second lidar2；
S13, according to the time t1The time t3The predetermined distance, the scanning period, the similarity γ1Determining vehicle speed v1According to said time t2The time t4The predetermined distance, the scanning period, the similarity γ2Determining vehicle speed v2；
S14, according to the vehicle speed v1And the vehicle speed v2Determining a speed of the vehicle.
Optionally, S12 may specifically include:
respectively extracting the acquired radar points of the first laser radarThe first frame data of the vehicle and the first frame data of the vehicle collected by the second laser radar are characterized by the following information: the height of frame data, the width of the frame data, the number of points of a scanning vehicle and the relative position of the vehicle and a laser radar are determined, and the similarity gamma between the first frame data of the vehicle collected by the first laser radar and the first frame data of the vehicle collected by the second laser radar is determined according to the extracted characteristic information1；
Respectively extracting the following characteristic information from the last frame data of the vehicle collected by the first laser radar and the last frame data of the vehicle collected by the second laser radar: frame data height, frame data width, the number of scanning vehicles and the relative positions of the vehicles and the laser radars, and determining the similarity gamma between the last frame data of the vehicles collected by the first laser radar and the last frame data of the vehicles collected by the second laser radar according to the extracted characteristic information2。
Step S13 is executed according to the time t by the following formula1The time t3The predetermined distance, the scanning period, the similarity γ1Determining the vehicle speed v1：
v1＝S/(t3-t1-k(1-γ1)T)；
According to said time t by the following formula2The time t4The predetermined distance, the scanning period, the similarity γ2Determining vehicle speed v2：
v2＝S/(t4-t2-k(1-γ2)T)，
Wherein S is the predetermined distance, and T is the scanning period;
and when at least one of the characteristic information in the vehicle frame data acquired by the first laser radar is greater than the corresponding characteristic information of the vehicle frame data acquired by the second laser radar, k is a positive number, and otherwise, k is a negative number.
S14, the vehicle speed v is determined by the following formula1And the vehicle speed v2Determining a speed v of the vehicle:
v＝α1v1+α2v2，
wherein, α1、α2Is a weight value of α1+α2＝1。
In the above S2, the length L of the vehicle is determined according to the speed of the vehicle, the time difference of the different frame data, the predetermined distance, and the scanning period by the following formula:
L1＝v(t2-t1+T)
L2＝v(t4-t3+T)
L3＝v(t4-t1)-S
L＝w1L1+w2L2+w3L3，
wherein, the w1W to2W to3Is a weight value, said w3Greater than said w1W to2，w1+w2+w3＝1。
The step S3 may specifically include:
s31, classifying the vehicle type of the vehicle according to the preset distance and all frame data of the vehicle collected by the first laser radar and the second laser radar;
and S32, determining the vehicle type of the vehicle according to the classification result of the vehicle and all frame data of the vehicle collected by the first laser radar and the second laser radar.
Optionally, step S31 may specifically include:
acquiring all frame data of the vehicle acquired by the first laser radar and the second laser radar;
if the first laser radar collects the last frame data of the vehicle, the second laser radar collects the first frame data of the vehicle, and the vehicle is determined to be a vehicle type with a first critical length according to the preset distance;
when the second laser radar collects first frame data of the vehicle, marking the data of the vehicle collected by the first laser radar as ith frame data, and when the first laser radar collects the last frame data of the vehicle, marking the data of the vehicle collected by the second laser radar as jth frame data;
matching the data from the i frame data to the last frame data of the vehicle collected by the first laser radar with the data from the j frame data to the last frame data of the vehicle collected by the second laser radar, and calculating the similarity k1；
Matching the first frame data to the jth frame data of the vehicle collected by the second laser radar with the first frame data to the ith frame data of the vehicle collected by the first laser radar, and calculating the similarity k2；
Calculating the similarity k1With the similarity k2The arithmetic mean of (a);
and when the arithmetic mean value is larger than a preset similarity threshold value, determining that the vehicle is the vehicle type with the second critical length.
The step S32 may specifically include:
identifying the vehicle type and a first vehicle type confidence coefficient of the vehicle according to the classification result of the vehicle and first contour data information of the vehicle;
identifying a vehicle type and a second vehicle type confidence coefficient of the vehicle according to a classification result of the vehicle and second profile data information of the vehicle, wherein the first profile data information is all frame data of the vehicle collected by the first laser radar, and the second profile data information is all frame data of the vehicle collected by the second laser radar;
and determining the vehicle type of the vehicle according to the first vehicle type confidence coefficient and the second vehicle type confidence coefficient.
In an optional embodiment, in order to improve accuracy of vehicle type identification, specifically, determining the vehicle type of the vehicle according to the first vehicle type confidence level and the second vehicle type confidence level may further include: fusing the first contour data information and the second contour data information by adopting a frame data similarity interpolation method according to a frame data sequence passed by the vehicle to obtain third contour data information; identifying the vehicle type and the third vehicle type confidence of the vehicle according to the classification result of the vehicle and the third profile data information; determining the vehicle type of the vehicle according to the first vehicle type confidence degree, the second vehicle type confidence degree and the third vehicle type confidence degree.
The following provides a detailed description of embodiments of the invention.
The vehicle identification method provided by the embodiment of the invention can be applied to traffic condition investigation, and fig. 3 is a flow chart of the laser vehicle identification method according to the embodiment of the invention, as shown in fig. 3, the method comprises the following steps:
s301: and at least two laser radars transmit the acquired data to the data processing unit in real time.
Specifically, in the step, scanning surfaces formed by scanning of adjacent laser radars are spaced at a certain distance, the scanning surfaces are parallel to the cross section of the road and are perpendicular to the vehicle running method, the cross section of the road is periodically scanned, and the laser radars transmit acquired data to the data processing unit in real time;
preferably, the method selects two laser radars, namely a first laser radar and a second laser radar, the single scanning periods of the laser radars are the same, and the data processing unit periodically corrects the time of the laser radars.
S302: and the data processing unit calculates the speed and the length of the vehicle according to the fixed distance between the adjacent laser radar scanning surfaces and the time difference of frame data of the collected vehicle.
Specifically, the data processing unit calculates the vehicle speed according to the distance between adjacent laser radar scanning surfaces, the first frame data information and the frame time when the vehicle is detected respectively, and the last frame data information and the frame time, and then calculates the vehicle length according to the vehicle speed and the frame time difference when the adjacent laser radar detects the vehicle respectively.
S303: and the data processing unit classifies the vehicle types with critical lengths according to the fixed distance between the adjacent laser radar scanning surfaces and the acquired contour information of the vehicle.
S304: the data processing unit identifies the vehicle type according to vehicle frame data and contour information collected by adjacent laser radars.
Further, the method further comprises:
fig. 4 is a flowchart of a laser-based vehicle recognition method according to a preferred embodiment of the present invention, wherein, as shown in fig. 4, the specific method for accurately calculating the speed and length of the vehicle shown in step S302 is as follows:
s401: the data processing unit acquires first frame data and time and last frame data and time of two laser radars for respectively detecting the vehicle;
specifically, the data processing unit acquires first frame data and time t of a vehicle collected by a first laser radar1Last frame data and time t2And the first frame data and time t of the vehicle collected by the second laser radar3Last frame data and time t4。
S402: the data processing unit calculates the similarity of first frame data of the detected vehicle and calculates the vehicle speed according to the fixed distance of the two laser radar scanning surfaces and the laser radar period;
specifically, the data processing unit extracts features of the height, width, number of points of the scanned vehicle and relative position of the vehicle and the laser radar from first frame data of a first laser radar detection vehicle and first frame data of a second laser radar detection vehicle, respectively, and calculates similarity γ of the first frame data of the two laser radar detection vehicles1The data processing unit respectively extracts the height and width of frame data, the number of points of a scanned vehicle and the characteristics of the relative positions of the vehicle and the laser radar according to the last frame data of the first laser radar detection vehicle and the last frame data of the second laser radar detection vehicle, and calculates the similarity gamma of the last frame data of the two laser radar detection vehicles2The similarity value range is 0-1, and then the vehicle speed v is respectively calculated according to the space S of the scanning surface of the laser radar and the scanning period T1、v2Finally, the vehicle speed v is calculated by weighting as shown in equation (1):
where k in equation (1) represents a sign, k is preferably a positive sign when the first lidar detects a high, and/or a width, and/or the number of points scanning the vehicle is greater than the corresponding value of the frame data of the second lidar detecting the vehicle, and otherwise is a negative sign α1、α2Is a weight value, and α1+α21, the selection of weighted value is identical to the frame data1、γ2And (4) correlating.
S403: the data processing unit calculates the corresponding vehicle length according to the vehicle speed and the time difference, the fixed interval and the period of different frame data, and then calculates the vehicle length comprehensively according to the corresponding weight;
in particular, the data processing unit is according to step S202, scan period T, first frame data time T for the first lidar to detect the vehicle1Time t of last frame data2Calculating the length L of the vehicle1The second laser radar detects the first frame time t of the vehicle3Time t of last frame data4Calculating the length L of the vehicle2And calculating the time difference L between the frame data of two laser radars3Finally according to different weights w1、w2、w3Calculating the vehicle length L as shown in equation (2):
in the formula (2), preferably, the weight w1、w2、w3The selection rule of (1): w is a1、w2Selecting the same value, w3Greater than w1、w2And w is1+w2+w3Adjusting w to be 1 according to the size relation between the length of the vehicle and the fixed distance of the laser radar1、w2、w3The value of (a).
Further, the method further comprises:
fig. 5 is a second flowchart of a laser-based vehicle recognition method according to a preferred embodiment of the present invention, and as shown in fig. 5, a specific method for classifying the critical vehicle length in step S303 is as follows:
s501: the data processing unit calculates the last frame data of the first laser radar detection vehicle, and meanwhile, the second laser radar detection vehicle first frame data, and then the data processing unit judges that the vehicle is a vehicle type with a first critical length according to the distance between the two laser radar scanning surfaces;
s502: the data processing unit acquires all frame data information of two laser radar detection vehicles, when the second laser radar detects first frame data of the vehicle, the vehicle marked by the first laser radar is ith frame data, and when the first laser radar detects last frame data of the vehicle, the vehicle marked by the second laser radar is jth frame data;
specifically, when the length of the vehicle exceeds the distance between two laser radar scanning surfaces, the second laser radar detects first frame data of the vehicle, meanwhile, the frame data sequence of the first laser radar detected vehicle is the ith frame, and the previous i frame data of the first laser radar detected vehicle is frame data information of which the length of the front section part of the vehicle is the fixed distance between the laser radar scanning surfaces; when the first laser radar detects the last frame data of the vehicle, meanwhile, the frame data sequence of the second laser radar detection vehicle is the jth frame, and after the vehicle completely passes through the second laser scanning area, the second laser radar detects the data of the vehicle from the jth frame data to the last frame data, namely the data information of which the length of the rear section of the vehicle is the fixed distance between the laser radar scanning surfaces.
S503: the data processing unit matches data from ith frame data to last frame data of the first laser radar detection vehicle with data from jth frame data to last frame data of the second laser radar detection vehicle, and calculates similarity k1；
S504: the data processing unit matches first frame data to jth frame data of a second laser radar detection vehicle with first frame data to ith frame data of a first laser radar detection vehicle, and calculates similarity k2；
Specifically, in steps S502 and S503, the data detected by the laser radar in the fixed length of the vehicle part and the data detected by the laser radar in the unknown length of the vehicle part are matched to calculate the similarity k1、k2。
S505: the data processing unit calculates the similarity k1、k2When the value is larger than the set similarity threshold value, the vehicle is judged to be the vehicle type with the second critical length;
specifically, when the last calculated similarity calculation average value is larger than the set similarity threshold value, namely the length of the unknown part of the vehicle and the fixed length of the vehicle detection are within the error allowable range, and the length of the vehicle is 2 times of the fixed distance between the scanning surfaces of the laser radar, the data processing unit judges that the vehicle is the vehicle type with the second type of critical length.
Further, the method further comprises:
fig. 6 is a flowchart three of a laser type vehicle recognition method according to a preferred embodiment of the present invention, and as shown in fig. 6, a specific method of calculating a vehicle type in step S304 is as follows:
s601: the method comprises the steps that a data processing unit obtains all frame number information of two laser radar detection vehicles, namely first contour data information and second contour data information of the vehicles;
s602: the data processing unit respectively identifies the vehicle type and the confidence degree c of the vehicle type according to the vehicle characteristics, the first contour data information and the second contour data information1、c2；
S603: the data processing unit fuses a new vehicle frame data sequence, namely new vehicle contour data information, according to the first contour data information and the second contour data information and the frame data sequence passed by the vehicle by adopting a frame data similarity interpolation method, and identifies the vehicle type and the vehicle type confidence coefficient c3；
Specifically, according to a frame data sequence of a laser radar detection vehicle, similarity between the ith frame data detected by a first laser radar and the ith-1, ith and (i + 1) th frame data detected by a second laser radar is cross-compared from the first frame to the last frame of the frame data, the frame data are combined into a new frame data sequence of the vehicle according to the frame data similarity, the frame data have i + j columns, then machine learning is adopted to identify the vehicle characteristics and the contour information of the new frame data sequence, and the vehicle type confidence coefficient c are calculated3。
S604: comprehensive vehicle type confidence c1、c2、c3And judging the vehicle type.
The data processing unit uploads vehicle type data information including vehicle type, vehicle speed, vehicle length, vehicle height and vehicle width to the data service center in time; and each time of a data uploading period, the data processing unit uploads the vehicle statistical data in the uploading period to the data service center.
Example 2
According to another embodiment of the present invention, there is also provided a vehicle identification system, fig. 7 is a schematic view of a vehicle identification system according to an embodiment of the present invention, as shown in fig. 7, the system including at least: a first lidar 72, a second lidar 74, and a data processing unit 76, wherein the first lidar 72 and the second lidar 74 are respectively connected to the data processing unit 76, the first lidar 72 and the second lidar 74 are spaced apart by a predetermined distance, wherein,
the first laser radar 72 and the second laser radar 74 are used for scanning a road section in the same scanning period and collecting data in the vehicle running process, wherein the scanning surfaces of the first laser radar 72 and the second laser radar 74 are perpendicular to the vehicle running direction;
the data processing unit 76 is used for determining the speed, the length and the type of the vehicle according to the data and the preset distance.
Optionally, the data processing unit 76 is further configured to determine the speed of the vehicle according to the first frame data and time of the vehicle and the last frame data and time acquired by the first lidar 72, and the first frame data and time of the vehicle and the last frame data and time acquired by the second lidar 74;
determining the length of the vehicle according to the speed of the vehicle, the time difference of different frame data, the preset distance and the scanning period;
and determining the vehicle type of the vehicle according to all frame data of the vehicle collected by the predetermined distance and the first laser radar 72 and the second laser radar 74.
Optionally, data processing unit 76 is further configured to periodically time-calibrate first lidar 72 and second lidar 74.
Optionally, the data processing unit 76 is further configured to send a timing instruction to the first lidar 72, where the timing instruction is configured to instruct the first lidar 72 to complete time synchronization with the second lidar 74; or,
sending a timing instruction to second lidar 74, where the timing instruction is used to instruct second lidar 74 to complete time synchronization with first lidar 72.
Optionally, the first lidar 72 and the second lidar 74 comprise at least one of: the system comprises a single-point scanning type laser ranging sensor, a single-line scanning type laser ranging sensor and a multi-line scanning type laser ranging sensor.
Optionally, the scanning angles of the first lidar 72 and the second lidar 74 are greater than or equal to 60 degrees, and the scanning areas of the first lidar 72 and the second lidar 74 cover all lanes to be monitored.
Optionally, the data processing unit 76 is further configured to establish a connection with a server through an information output interface, and report the identified result to the server.
The above system is explained in detail below.
The vehicle identification system provided by the embodiment of the invention can be applied to traffic condition investigation, and comprises the following components: at least two lidar, data processing units 76; the scanning surface of the laser radar is perpendicular to the vehicle running direction, the distance between the scanning surfaces of the adjacent laser radars is 2 meters or integral multiple of 3 meters, and the data processing unit 76 is respectively connected with the laser radars.
When the laser type traffic condition investigation system adopts two laser radars, the distance between the scanning surfaces of the two laser radars is preferably 6 meters, and when the laser type traffic condition investigation system adopts three laser radars, the distance between the scanning surfaces of the adjacent laser radars is preferably 6 meters, namely the distance between the scanning surfaces of the first laser radar 72 and the second laser radar 74 is 6 meters, and the distance between the scanning surfaces of the second laser radar 74 and the third laser radar is 6 meters;
the method comprises the following steps that along the running direction of a vehicle, the laser radar detection areas where the vehicle passes successively are a first laser radar 72 detection area and a second laser radar 74 detection area in sequence, the scanning frequency is not lower than 50 Hz, the point resolution is not more than 0.5 degrees, and the laser radars can be arranged on a vertical rod on the road side and also can be arranged on a gantry;
the scanning included angle of the laser radar is larger than 60 degrees, the scanning area covers all lanes of the investigation road section, in the using process, the included angle range of the scanning surface of the laser radar and the road is 80-100 degrees, and the laser radar adopts a single-point scanning type laser ranging sensor, a single-line scanning type laser ranging sensor or a multi-line scanning type laser ranging sensor;
the time synchronization of the laser radars in the system adopts the data processing unit 76 to periodically correct the time, or selects one laser radar to correct the time of other laser radars, so as to ensure the time synchronization of the laser radars in real time;
the data processing unit 76 is respectively connected with all laser radars in the system, receives data collected by the laser radars for investigating a road surface in real time, and can obtain a frame data sequence and corresponding frame time of a vehicle scanned by the laser radars through calculation, the data processing unit 76 is provided with an I/O information output interface, and when the data processing unit 76 calculates the first frame and/or the last frame of the vehicle to be detected scanned by the laser radars in real time, the information can be transmitted to other devices in time through the I/O information output interface;
the data processing unit 76 is used for processing data information acquired by the laser radar in real time, obtaining vehicle type information passing through a scanning area through calculation, periodically counting road traffic condition information, and uploading the vehicle type information and/or the counted road traffic condition information to a data service center; the data processing unit 76 is also used for processing communication between the equipment units, command operation and information exchange with the data service center, and controlling the normal operation of the whole system.
In the embodiment of the invention, at least two laser radars are adopted to scan the road section at the same period and fixed intervals, the speed and the length of the vehicle are calculated, the vehicle type with the critical length is classified, and the data fusion is adopted to identify the vehicle type, so that the speed and the length precision of the vehicle are improved, the problem of classification of the vehicle type with the critical length is solved, a reliable scheme is provided for traffic condition investigation, and technical support is provided for vehicle speed measurement and law enforcement and more accurate vehicle type subdivision. The system is described in detail below.
As shown in fig. 8, 9, and 10, the system includes: the system comprises a Y-shaped vertical rod or a portal frame or an L-shaped vertical rod 1, a first laser radar 72, a second laser radar 74, a data processing unit 76, a laser radar detection area 2, a scanning surface of the laser radar, a vehicle running direction and a certain distance. Preferably, the horizontal distance between adjacent laser radar scanning surfaces is 6 meters, and the scanning surfaces of the laser radars are vertical to the driving direction of the vehicle.
The laser radar vertically scans the road, the scanning surface of the laser radar is vertical to the driving direction of the vehicle, the area detected by one laser radar through which the vehicle firstly passes is the first laser radar 72, the other laser radar is the second laser radar 74, the laser scanning frequency is not lower than 50 Hz, the horizontal distance between the two laser radar scanning surfaces is 6 m, the angular resolution of laser scanning is not more than 0.5 degrees, and the laser radar collects road data in real time and transmits the road data to the data processing unit 76 in time;
the included angle between the scanning surface of the laser radar and the road surface ranges from 80 degrees to 90 degrees, preferably, the scanning surface of the laser radar is perpendicular to the vehicle running direction, in the running direction, the area detected by the laser radar through which the vehicle passes sequentially is the area scanned by the first laser radar 72, the area scanned by the second laser radar 74 and/or the area scanned by the third laser radar, the distance between the scanning surfaces of the adjacent laser radars is 2 meters or integral multiple of 3 meters, and when the system adopts two laser radars, preferably, the distance between the scanning surface of the first laser radar 72 and the scanning surface of the second laser radar 74 is 6 meters; when the system adopts three laser radars, preferably, the distance between the scanning surface of the first laser radar 72 and the scanning surface of the second laser radar 74 is 6 meters, and the distance between the scanning surface of the second laser radar 74 and the scanning surface of the third laser radar is 6 meters; the scanning angle of the laser radar is larger than 60 degrees, preferably 180 degrees, the scanning area covers all lanes of the investigation road section, preferably, the laser radar is a single-line scanning type laser sensor, the laser scanning frequency is not lower than 50 Hz, the angular resolution of the laser scanning is not larger than 0.5 degree, and the laser radar collects road data in real time and transmits the road data to the data processing unit 76 in time.
The data processing unit 76 is connected with all the laser radars in the system, receives data collected by the laser radars in real time, and preferably, the data processing unit 76 periodically corrects the time of the laser radars to ensure the time synchronization of the laser radars; the system is provided with an I/O signal output interface, preferably, the I/O signal output interface is solidified on the data processing unit 76, and when the data processing unit 76 calculates the first frame and/or the last frame of the laser radar scanning vehicle in real time, the information can be transmitted to other devices in time through the I/O signal output interface; the data processing unit 76 is also used for processing communication between the equipment units, command operation and information exchange with the data service center, and controlling the normal operation of the whole system.
When a vehicle passes through, the laser radar collects vehicle data in real time and transmits the vehicle data to the data processing unit 76, and after the data processing unit 76 performs primary processing, the collected vehicle frame data information is respectively stored in the data storage unit according to the time sequence to form a frame data sequence set A of the first laser radar 72 and a frame data sequence set B of the second laser radar 74;
the data processing unit 76 extracts the first frame data of the detected vehicle and the time t from the frame data sequence set a1Last frame data and time t2Extracting the first frame data of the detected vehicle and the time t from the frame data sequence set B3Last frame data and time t4Calculating the height and width of first frame data and last frame data detected by two laser radars, the number of points of a scanned vehicle, the relative distance from the corresponding laser radar and other characteristics, integrating the characteristics, calculating the similarity of the first frame data and the similarity of the last frame data detected by the two laser radars, and then accurately calculating the vehicle speed according to the conditions of the laser radars such as distance, time, similarity, period of the laser radars, weight and the like; next, the data processing unit 76 processes the frame data according to the frame data time t1、t2、t3、t4Calculating the vehicle length as L1、L2、L3Finally according to the weighted value w1、w2、w3Calculating the length of the vehicle;
when the data processing unit 76 detects that the vehicle is scanned by the last frame of the first laser radar 72 and the vehicle is scanned by the first frame of the second laser radar 74, the vehicle is judged to be the first type of critical-length vehicle according to the distance between the two laser radar scanning surfaces; when the vehicle length of the vehicle is greater than the distance between two laser radars, namely the vehicle length is greater than 6 meters, the data processing unit marks that the second laser radar 74 detects first frame data of the vehicle, at this time, the first laser radar 72 marks that the vehicle is the ith frame data, the first laser radar 72 detects the last frame data of the vehicle, at this time, the second laser radar 74 marks that the vehicle is the jth frame data, the similarity k1 between the ith frame data to the last frame data of the first laser radar 72 and the jth frame data to the last frame data of the second laser radar 74 is calculated, namely, the similarity k between the frame data of 6 meters after the second laser radar 74 scans the vehicle and the frame data of 6 meters after the first laser radar 72 scans is calculated, and the similarity k between the first frame data to the jth frame data of the second laser radar 74 and the first frame data to the ith frame data of the first laser radar 72 are calculated2That is, the similarity between the frame data of the first laser radar 72 scanning 6 meters in front of the vehicle and the frame data of the second laser radar 74 scanning 6 meters behind the vehicle to the head of the vehicle is calculated1、k2When the average value is larger than the set similarity threshold value, the vehicle is judged to be a vehicle type with the second critical length, namely a critical vehicle type with the length of 12 meters;
the data processing unit 76 respectively calculates the vehicle type and the confidence c of the vehicle type according to the frame data sequence set A, B1、c2Then, the frame data sequence set A and the frame data sequence B are fused, namely the similarity between the ith frame data in the frame data sequence set A and the ith-1, ith and (i + 1) th frame data in the frame data sequence B is judged, the ith frame in the frame data sequence set A is judged to be in the sequence of the frame data sequence set B, a new frame data sequence set C is formed, the frame data sequence set C is the fusion of the frame data sequence set A and the frame data sequence B, and the vehicle type confidence coefficient C are calculated according to the frame data sequence set C3And finally integrating vehicle type confidence coefficient c1、c2、c3Judging the vehicle type;
after calculating the vehicle type of the vehicle, the data processing unit 76 uploads the vehicle information of the vehicle, such as the vehicle type, speed, length, height, width, and the like, to the data service center, and when each data uploading period comes, the data processing unit 76 uploads the vehicle statistical information in the uploading period to the data service center.
When more than two laser radars are adopted in the system, the working mode or flow of the system is similar to the mode or flow.
The embodiment detects vehicle information on roads by using at least two laser radars and a data processing unit, accurately calculates the vehicle speed and the vehicle length, classifies the vehicle types of critical length, adopts the at least two laser radars to collect the data of the vehicles, fuses and identifies the vehicle types, improves the precision of the vehicle speed and the vehicle length, solves the problem of classification of the vehicles of the critical length, improves the accuracy of the vehicle types, provides a reliable scheme for high-precision traffic condition investigation, and also provides technical support for vehicle speed measurement and more accurate vehicle type subdivision.
Example 3
In this embodiment, a vehicle identification device is further provided, and the device is used to implement the above embodiments and preferred embodiments, and the description of the device is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 11 is a block diagram of a vehicle recognition apparatus according to an embodiment of the present invention, as shown in fig. 11, including:
the acquisition module 112 is configured to scan a road section with the same scanning period at least through a first laser radar and a second laser radar, and acquire data in a vehicle driving process, where scanning surfaces of the first laser radar and the second laser radar are perpendicular to a vehicle driving direction, and the first laser radar and the second laser radar are separated by a predetermined distance;
and the determining module 114 is used for determining the speed, the length and the model of the vehicle according to the data and the preset distance.
Optionally, the determining module 114 includes:
the first determining unit is used for determining the speed of the vehicle according to the first frame data and time and the last frame data and time of the vehicle acquired by the first laser radar, and the first frame data and time and the last frame data and time of the vehicle acquired by the second laser radar;
the second determining unit is used for determining the length of the vehicle according to the speed of the vehicle, the time difference of different frame data, the preset distance and the scanning period;
and the third determining unit is used for determining the vehicle type of the vehicle according to the preset distance and all frame data of the vehicle acquired by the first laser radar and the second laser radar.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
Example 4
Embodiments of the present invention also provide a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
Alternatively, in the present embodiment, the storage medium may be configured to store a computer program for executing the steps of:
s1, scanning a road section by at least a first laser radar and a second laser radar in the same scanning period, and collecting data in the vehicle driving process, wherein the scanning surfaces of the first laser radar and the second laser radar are perpendicular to the vehicle driving direction, and the first laser radar and the second laser radar are separated by a preset distance;
and S2, determining the speed, the length and the model of the vehicle according to the data and the preset distance.
Optionally, in this embodiment, the storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Example 5
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, scanning a road section by at least a first laser radar and a second laser radar in the same scanning period, and collecting data in the vehicle driving process, wherein the scanning surfaces of the first laser radar and the second laser radar are perpendicular to the vehicle driving direction, and the first laser radar and the second laser radar are separated by a preset distance;
and S2, determining the speed, the length and the model of the vehicle according to the data and the preset distance.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A vehicle identification method, characterized by comprising:
scanning a road section by at least a first laser radar and a second laser radar in the same scanning period, and collecting data in the running process of a vehicle, wherein the scanning surfaces of the first laser radar and the second laser radar are perpendicular to the running direction of the vehicle, and the first laser radar and the second laser radar are separated by a preset distance;
and determining the speed, the length and the model of the vehicle according to the data and the preset distance.
2. The method of claim 1, wherein determining the speed, length, and model of the vehicle from the data and the predetermined distance comprises:
determining the speed of the vehicle according to the first frame data and time and the last frame data and time of the vehicle acquired by the first laser radar, and the first frame data and time and the last frame data and time and the time of the vehicle acquired by the second laser radar;
determining the length of the vehicle according to the speed of the vehicle, the time difference of different frame data, the preset distance and the scanning period;
and determining the vehicle type of the vehicle according to all frame data of the vehicle collected by the preset distance, the first laser radar and the second laser radar.
3. The method of claim 2, wherein determining the speed of the vehicle from the first frame of data and time, the last frame of data and time, of the vehicle collected by the first lidar, and the first frame of data and time, the last frame of data and time, of the vehicle collected by the second lidar comprises:
acquiring first frame data and time t of the vehicle acquired by the first laser radar1Last frame data and time t2And the first frame data and the time t of the vehicle collected by the second laser radar3Last frame data and time t4；
Determining similarity gamma of first frame data of the vehicle collected by the first laser radar and first frame data of the vehicle collected by the second laser radar1Similarity gamma between the last frame data of the vehicle collected by the first lidar and the last frame data of the vehicle collected by the second lidar2；
According to the time t1The time t3The predetermined distance, the scanningPeriod, the similarity γ1Determining vehicle speed v1According to said time t2The time t4The predetermined distance, the scanning period, the similarity γ2Determining vehicle speed v2；
According to the vehicle speed v1And the vehicle speed v 2.
4. The method of claim 2, wherein determining the vehicle type of the vehicle from all frame data of the vehicle collected by the predetermined distance, the first lidar and the second lidar comprises:
classifying the vehicle type of the vehicle according to all frame data of the vehicle collected by the preset distance, the first laser radar and the second laser radar;
and determining the vehicle type of the vehicle according to the classification result of the vehicle and all frame data of the vehicle collected by the first laser radar and the second laser radar.
5. The method of claim 4, wherein classifying the vehicle type of the vehicle according to all frame data of the vehicle acquired by the predetermined distance, the first lidar and the second lidar comprises:
acquiring all frame data of the vehicle acquired by the first laser radar and the second laser radar;
if the first laser radar collects the last frame data of the vehicle, the second laser radar collects the first frame data of the vehicle, and the vehicle is determined to be a vehicle type with a first critical length according to the preset distance;
when the second laser radar collects first frame data of the vehicle, marking the data of the vehicle collected by the first laser radar as ith frame data, and when the first laser radar collects the last frame data of the vehicle, marking the data of the vehicle collected by the second laser radar as jth frame data;
matching the data from the i frame data to the last frame data of the vehicle collected by the first laser radar with the data from the j frame data to the last frame data of the vehicle collected by the second laser radar, and calculating the similarity k1；
Matching the first frame data to the jth frame data of the vehicle collected by the second laser radar with the first frame data to the ith frame data of the vehicle collected by the first laser radar, and calculating the similarity k2；
Calculating the similarity k1With the similarity k2The arithmetic mean of (a);
and when the arithmetic mean value is larger than a preset similarity threshold value, determining that the vehicle is the vehicle type with the second critical length.
6. The method of claim 5, wherein determining the vehicle type of the vehicle according to the classification result of the vehicle, the first lidar and the second lidar collecting all frame data of the vehicle comprises:
identifying the vehicle type and a first vehicle type confidence coefficient of the vehicle according to the classification result of the vehicle and first contour data information of the vehicle;
identifying a vehicle type and a second vehicle type confidence coefficient of the vehicle according to a classification result of the vehicle and second profile data information of the vehicle, wherein the first profile data information is all frame data of the vehicle collected by the first laser radar, and the second profile data information is all frame data of the vehicle collected by the second laser radar;
and determining the vehicle type of the vehicle according to the first vehicle type confidence coefficient and the second vehicle type confidence coefficient.
7. The method of claim 6, wherein determining the model of the vehicle from the first vehicle type confidence and the second vehicle type confidence comprises:
fusing the first contour data information and the second contour data information by adopting a frame data similarity interpolation method according to a frame data sequence passed by the vehicle to obtain third contour data information;
identifying the vehicle type and the third vehicle type confidence of the vehicle according to the classification result of the vehicle and the third profile data information;
determining the vehicle type of the vehicle according to the first vehicle type confidence degree, the second vehicle type confidence degree and the third vehicle type confidence degree.
8. A vehicle identification system, characterized in that it comprises at least: a first laser radar, a second laser radar, and a data processing unit, wherein the first laser radar and the second laser radar are respectively connected with the data processing unit, and the first laser radar and the second laser radar are separated by a preset distance,
the first laser radar and the second laser radar are used for scanning road sections in the same scanning period and collecting data in the vehicle running process, wherein the scanning surfaces of the first laser radar and the second laser radar are perpendicular to the vehicle running direction;
and the data processing unit is used for determining the speed, the length and the model of the vehicle according to the data and the preset distance.
9. The system of claim 8,
and the data processing unit is also used for periodically timing the first laser radar and the second laser radar.
The data processing unit is further configured to send a timing instruction to the first laser radar, where the timing instruction is used to instruct the first laser radar to complete time synchronization with the second laser radar; or,
and sending a timing instruction to the second laser radar, wherein the timing instruction is used for indicating the second laser radar to complete time synchronization with the first laser radar.
10. The system of claim 8 or 9,
the scanning angles of the first laser radar and the second laser radar are larger than or equal to 60 degrees, and the scanning areas of the first laser radar and the second laser radar cover all monitored lanes.
The data processing unit is also used for establishing connection with a server through an information output interface and reporting the identified result to the server.
CN201811605347.3A 2018-12-26 2018-12-26 Vehicle identification method and system Active CN109598947B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811605347.3A CN109598947B (en) 2018-12-26 2018-12-26 Vehicle identification method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811605347.3A CN109598947B (en) 2018-12-26 2018-12-26 Vehicle identification method and system

Publications (2)

Publication Number Publication Date
CN109598947A true CN109598947A (en) 2019-04-09
CN109598947B CN109598947B (en) 2021-05-11

Family

ID=65962742

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811605347.3A Active CN109598947B (en) 2018-12-26 2018-12-26 Vehicle identification method and system

Country Status (1)

Country Link
CN (1) CN109598947B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110232827A (en) * 2019-05-27 2019-09-13 武汉万集信息技术有限公司 The recognition methods of free flow toll vehicle type, apparatus and system
CN112014855A (en) * 2020-07-20 2020-12-01 江西路通科技有限公司 Vehicle outline detection method and system based on laser radar
CN112099042A (en) * 2020-08-07 2020-12-18 武汉万集信息技术有限公司 Vehicle tracking method and system
CN113514847A (en) * 2020-04-10 2021-10-19 深圳市镭神智能系统有限公司 Vehicle outer contour dimension detection method and system and storage medium
CN113869196A (en) * 2021-09-27 2021-12-31 中远海运科技股份有限公司 Vehicle type classification method and device based on laser point cloud data multi-feature analysis

Citations (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5546188A (en) * 1992-11-23 1996-08-13 Schwartz Electro-Optics, Inc. Intelligent vehicle highway system sensor and method
JPH10307988A (en) * 1997-05-09 1998-11-17 Hitachi Ltd Traffic flow monitoring device
US20020140924A1 (en) * 1999-01-08 2002-10-03 Richard J. Wangler Vehicle classification and axle counting sensor system and method
US20080166023A1 (en) * 2007-01-05 2008-07-10 Jigang Wang Video speed detection system
CN101393687A (en) * 2008-11-18 2009-03-25 河北中交远洲智能交通技术有限公司 Infrared laser traffic information collecting instrument
KR20100104879A (en) * 2009-03-19 2010-09-29 (주)비오비네트웍스 Measurement method of travel time using sequence pattern of vehicles
CN102289938A (en) * 2011-05-23 2011-12-21 辽宁金洋集团信息技术有限公司 Vehicle parting method by using double-row vertical radar wave
CN102663893A (en) * 2012-04-16 2012-09-12 公安部第三研究所 Method for acquiring road information based on laser ranging node system
EP2730945A1 (en) * 2012-11-09 2014-05-14 Nederlandse Organisatie voor toegepast -natuurwetenschappelijk onderzoek TNO Vehicle spacing control
CN103954222A (en) * 2014-04-29 2014-07-30 南京理工大学 Vehicle outline and wheel base automatic measuring system and measuring algorithm
CN104345309A (en) * 2013-08-09 2015-02-11 山推工程机械股份有限公司 Vehicle speed measuring method and device
CN105046968A (en) * 2015-06-19 2015-11-11 武汉万集信息技术有限公司 Motor bus identification and snapshot method, apparatus and system
CN105427614A (en) * 2015-08-28 2016-03-23 北京动视元科技有限公司 Model classification system and method
CN205619890U (en) * 2016-02-16 2016-10-05 武汉万集信息技术有限公司 Long wide high measuring device of vehicle based on laser rangefinder technique
CN106597659A (en) * 2016-11-18 2017-04-26 武汉万集信息技术有限公司 Laser scanning device
CN106683530A (en) * 2017-02-21 2017-05-17 南京多伦科技股份有限公司 Computerized judging system and method based on three-dimensional laser vision and high-precision lane model
CN107437336A (en) * 2016-05-27 2017-12-05 武汉万集信息技术有限公司 Vehicle type recognition device and method
CN107705563A (en) * 2017-11-28 2018-02-16 苏州大学 Continuous vehicle speed detection method based on laser radar
CN107895482A (en) * 2017-11-24 2018-04-10 北京安航达科技有限公司 Transport investigation device and method based on millimetre-wave radar and laser radar
CN107967804A (en) * 2017-12-04 2018-04-27 北京理工大学 A kind of more rotors carry the vehicle cab recognition and vehicle speed measurement device and method of laser radar
CN107990831A (en) * 2017-12-27 2018-05-04 同方威视技术股份有限公司 Vehicle length measuring device and vehicle outer contour measuring system
CN108132025A (en) * 2017-12-24 2018-06-08 上海捷崇科技有限公司 A kind of vehicle three-dimensional outline scans construction method
CN207816198U (en) * 2017-12-27 2018-09-04 同方威视技术股份有限公司 Vehicle length measuring device and vehicle outer profile measuring system
CN108765974A (en) * 2018-06-15 2018-11-06 江西路通科技有限公司 Traffic condition monitoring equipment, monitoring method and system
CN108895968A (en) * 2018-05-15 2018-11-27 天津杰泰高科传感技术有限公司 vehicle measuring device and method

Patent Citations (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5546188A (en) * 1992-11-23 1996-08-13 Schwartz Electro-Optics, Inc. Intelligent vehicle highway system sensor and method
JPH10307988A (en) * 1997-05-09 1998-11-17 Hitachi Ltd Traffic flow monitoring device
US20020140924A1 (en) * 1999-01-08 2002-10-03 Richard J. Wangler Vehicle classification and axle counting sensor system and method
US20080166023A1 (en) * 2007-01-05 2008-07-10 Jigang Wang Video speed detection system
CN101393687A (en) * 2008-11-18 2009-03-25 河北中交远洲智能交通技术有限公司 Infrared laser traffic information collecting instrument
KR20100104879A (en) * 2009-03-19 2010-09-29 (주)비오비네트웍스 Measurement method of travel time using sequence pattern of vehicles
CN102289938A (en) * 2011-05-23 2011-12-21 辽宁金洋集团信息技术有限公司 Vehicle parting method by using double-row vertical radar wave
CN102663893A (en) * 2012-04-16 2012-09-12 公安部第三研究所 Method for acquiring road information based on laser ranging node system
EP2730945A1 (en) * 2012-11-09 2014-05-14 Nederlandse Organisatie voor toegepast -natuurwetenschappelijk onderzoek TNO Vehicle spacing control
CN104345309A (en) * 2013-08-09 2015-02-11 山推工程机械股份有限公司 Vehicle speed measuring method and device
CN103954222A (en) * 2014-04-29 2014-07-30 南京理工大学 Vehicle outline and wheel base automatic measuring system and measuring algorithm
CN105046968A (en) * 2015-06-19 2015-11-11 武汉万集信息技术有限公司 Motor bus identification and snapshot method, apparatus and system
CN105427614A (en) * 2015-08-28 2016-03-23 北京动视元科技有限公司 Model classification system and method
CN205619890U (en) * 2016-02-16 2016-10-05 武汉万集信息技术有限公司 Long wide high measuring device of vehicle based on laser rangefinder technique
CN107437336A (en) * 2016-05-27 2017-12-05 武汉万集信息技术有限公司 Vehicle type recognition device and method
CN106597659A (en) * 2016-11-18 2017-04-26 武汉万集信息技术有限公司 Laser scanning device
CN106683530A (en) * 2017-02-21 2017-05-17 南京多伦科技股份有限公司 Computerized judging system and method based on three-dimensional laser vision and high-precision lane model
CN107895482A (en) * 2017-11-24 2018-04-10 北京安航达科技有限公司 Transport investigation device and method based on millimetre-wave radar and laser radar
CN107705563A (en) * 2017-11-28 2018-02-16 苏州大学 Continuous vehicle speed detection method based on laser radar
CN107967804A (en) * 2017-12-04 2018-04-27 北京理工大学 A kind of more rotors carry the vehicle cab recognition and vehicle speed measurement device and method of laser radar
CN108132025A (en) * 2017-12-24 2018-06-08 上海捷崇科技有限公司 A kind of vehicle three-dimensional outline scans construction method
CN107990831A (en) * 2017-12-27 2018-05-04 同方威视技术股份有限公司 Vehicle length measuring device and vehicle outer contour measuring system
CN207816198U (en) * 2017-12-27 2018-09-04 同方威视技术股份有限公司 Vehicle length measuring device and vehicle outer profile measuring system
CN108895968A (en) * 2018-05-15 2018-11-27 天津杰泰高科传感技术有限公司 vehicle measuring device and method
CN108765974A (en) * 2018-06-15 2018-11-06 江西路通科技有限公司 Traffic condition monitoring equipment, monitoring method and system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
秦小明，喻全红，陈景诚: "基于激光扫描的交通情况调查系统", 《中国交通信息化》 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110232827A (en) * 2019-05-27 2019-09-13 武汉万集信息技术有限公司 The recognition methods of free flow toll vehicle type, apparatus and system
CN113514847A (en) * 2020-04-10 2021-10-19 深圳市镭神智能系统有限公司 Vehicle outer contour dimension detection method and system and storage medium
CN112014855A (en) * 2020-07-20 2020-12-01 江西路通科技有限公司 Vehicle outline detection method and system based on laser radar
CN112099042A (en) * 2020-08-07 2020-12-18 武汉万集信息技术有限公司 Vehicle tracking method and system
CN112099042B (en) * 2020-08-07 2024-04-12 武汉万集信息技术有限公司 Vehicle tracking method and system
CN113869196A (en) * 2021-09-27 2021-12-31 中远海运科技股份有限公司 Vehicle type classification method and device based on laser point cloud data multi-feature analysis

Also Published As

Publication number Publication date
CN109598947B (en) 2021-05-11

Similar Documents

Publication Publication Date Title
CN109598947B (en) Vehicle identification method and system
CN112816954B (en) Road side perception system evaluation method and system based on true value
CN111275960A (en) Traffic road condition analysis method, system and camera
KR101446546B1 (en) Display system of vehicle information based on the position
CN112309108B (en) Truck-mounted overrun detection system and method
US11270581B1 (en) Vehicle queue length and traffic delay measurement using sensor data for traffic management in a transportation network
US11500055B2 (en) Detection method and detection apparatus
CN109410584B (en) Road condition detection method and device
CN106327880B (en) A kind of speed recognition methods and its system based on monitor video
CN101408937A (en) Method and apparatus for locating character row
CN111830470B (en) Combined calibration method and device, target object detection method, system and device
Sochor et al. Brnocompspeed: Review of traffic camera calibration and comprehensive dataset for monocular speed measurement
CN117058600B (en) Regional bridge group traffic load identification method and system
CN110136186A (en) A kind of detection target matching method for mobile robot object ranging
CN111062285A (en) Parking lot intelligent monitoring and recognizing system based on deep learning algorithm
CN112133085B (en) Vehicle information matching method, device and system, storage medium and electronic device
CN115201218A (en) Vehicle-mounted pavement disease intelligent detection method and system
CN116128360A (en) Road traffic congestion level evaluation method and device, electronic equipment and storage medium
CN117746346B (en) Heavy vehicle load identification method
CN107978151A (en) A kind of vehicle checking method and system
KR20210055940A (en) system and method for monitoring floating population and traffic device and method
CN114677843B (en) Road condition information processing method, device, system and electronic equipment
CN116645612A (en) Forest resource asset determination method and system
CN114783181B (en) Traffic flow statistics method and device based on road side perception
CN115131423B (en) Distance measurement method and device integrating millimeter wave radar and vision

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant