CN113124777B - Vehicle size determination method, device and system and storage medium - Google Patents

Vehicle size determination method, device and system and storage medium Download PDF

Info

Publication number
CN113124777B
CN113124777B CN202110425541.9A CN202110425541A CN113124777B CN 113124777 B CN113124777 B CN 113124777B CN 202110425541 A CN202110425541 A CN 202110425541A CN 113124777 B CN113124777 B CN 113124777B
Authority
CN
China
Prior art keywords
vehicle
determining
point
data packet
observation position
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
Application number
CN202110425541.9A
Other languages
Chinese (zh)
Other versions
CN113124777A (en
Inventor
江龙飞
李丰
张佳贺
欧桦楠
刘华伟
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.)
Liaoning Intelly Electronic Information Co ltd
Original Assignee
Liaoning Intelly Electronic Information 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 Liaoning Intelly Electronic Information Co ltd filed Critical Liaoning Intelly Electronic Information Co ltd
Priority to CN202110425541.9A priority Critical patent/CN113124777B/en
Publication of CN113124777A publication Critical patent/CN113124777A/en
Application granted granted Critical
Publication of CN113124777B publication Critical patent/CN113124777B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds

Abstract

The application relates to the field of vehicle outline detection, in particular to a vehicle size determination method, a vehicle size determination device, a vehicle size determination system and a storage medium. The vehicle size determination method includes: acquiring a first point cloud data set of a target vehicle running under an observation position; determining a number of successive flat positions of a plurality of positions on the vehicle profile; determining a vertical distance difference between a maximum vertical coordinate value in a plurality of positions on the vehicle profile and a maximum vertical coordinate value in a continuous flat position; determining the vehicle type of the target vehicle according to the number of the continuous flat positions and the vertical distance difference; and determining the size of the target vehicle according to the determined vehicle type. According to the vehicle size determining method, the vehicle size determining device, the vehicle size determining system and the storage medium, the problem that accuracy of detection results is not high due to the fact that different types of vehicles cannot be classified and detected is solved, the vehicle type of the target vehicle can be determined, and therefore the size of the target vehicle can be determined based on the vehicle type.

Description

Vehicle size determination method, device and system and storage medium
Technical Field
The present application relates to the field of vehicle contour detection, and in particular, to a method, an apparatus, a system, and a storage medium for determining a vehicle size.
Background
Vehicle profile detection can confirm whether a vehicle is refitted or retrofitted, and the like, which is an important means for verifying vehicle safety and ensuring vehicle production consistency.
The existing vehicle outline detection methods include a three-dimensional laser vehicle outline detection method and a two-dimensional laser vehicle outline detection method. However, in the detection process of the existing three-dimensional and two-dimensional laser vehicle contour detection method, due to the influence of the angular resolution of the laser sensor, when the vehicle contour detection is performed remotely, the horizontal distance difference between two adjacent points is large, the influence of the situation on the detection results of different vehicle types is different, and the accuracy of the detection results is not high enough under the condition that different types of vehicles cannot be classified and detected.
Disclosure of Invention
In view of the problem that the accuracy of a detection result is not high enough due to the fact that the existing vehicle outline detection method cannot carry out classification detection on different types of vehicles, the application provides a vehicle size determination method, a vehicle size determination device, a vehicle size determination system and a storage medium.
According to a first aspect of the present application, there is provided a vehicle size determination method including: acquiring a first point cloud data set of a target vehicle passing under an observation position, wherein the first point cloud data set comprises a first data packet collected at the observation position before a first moment when vehicle entering data is detected for the first time under the observation position, and the first data packet comprises horizontal coordinate data and vertical coordinate data of a plurality of positions on a vehicle outline relative to the observation position; determining a number of consecutive flat positions of the plurality of positions on the vehicle contour, wherein a slope between two adjacent ones of the consecutive flat positions is less than a slope threshold, the slope being determined by a ratio of an absolute value of a difference between vertical coordinates and an absolute value of a difference between horizontal coordinates of the two positions; determining a vertical distance difference between a maximum vertical coordinate value in the plurality of positions and a maximum vertical coordinate value in the successive leveling positions on the vehicle profile; determining the vehicle type of the target vehicle according to the number of the continuous flat positions and the vertical distance difference; determining a size of the target vehicle based on the determined vehicle type.
Optionally, the vehicle type includes a hybrid type, and the target vehicle is a hybrid type vehicle, wherein determining the size of the target vehicle according to the determined vehicle type may include: acquiring a second point cloud data set, wherein the second point cloud data set comprises a second data packet acquired at the observation position after a second moment when vehicle driving-away data is first detected under the observation position, and the second data packet comprises horizontal coordinate data and vertical coordinate data of a plurality of positions on the vehicle outline relative to the observation position; judging whether an effective point for the vehicle to enter exists behind the driving direction of the target vehicle in the second data packet or not; determining tail characteristic points in the first data packet according to the judgment result; and determining the size of the target vehicle according to the tail characteristic point.
Optionally, determining the tail feature point in the first data packet according to the determination result may include: determining the last vertical coordinate jumping point in the first data packet as the tail characteristic point in response to the judgment result that the effective point does not exist, and acquiring an observation position data packet in response to the judgment result that the effective point exists, wherein the observation position data packet comprises vertical coordinate data of different positions on the outline of the vehicle from the observation position; and determining the tail characteristic point according to a first vertical coordinate jump point in the first data packet and a second vertical coordinate jump point in the observation position data packet.
Optionally, determining the tail feature point according to the first vertical coordinate trip point in the first data packet and the second vertical coordinate trip point in the observation position data packet includes: determining the number n of the first vertical coordinate trip points and the number m of the second vertical coordinate trip points; comparing the number n of the first vertical coordinate trip points with the number m of the second vertical coordinate trip points, and determining the tail feature point according to a comparison result, wherein if m is greater than or equal to n, the nth first vertical coordinate trip point in the first data packet is determined as the tail feature point; and if m is smaller than n, determining the mth first vertical coordinate jump point in the first data packet as the tail characteristic point.
Optionally, determining the size of the target vehicle according to the tail feature point may include: determining a first horizontal coordinate of the tail feature point in the first data packet relative to the viewing position; determining a tail compensation feature point corresponding to the tail feature point in the second data packet, and determining a second horizontal coordinate of the tail compensation feature point relative to the observation position based on the second data packet; determining a third horizontal coordinate of a first effective point driven by the vehicle in the first data packet relative to the observation position; determining a fourth horizontal coordinate of a last significant point of the second data packet from which the vehicle has traveled relative to the observation location; determining the size of the target vehicle according to the first horizontal coordinate, the second horizontal coordinate, the third horizontal coordinate and the fourth horizontal coordinate.
Optionally, the vehicle type includes a long-compartment type, and the target vehicle is a long-compartment type vehicle, wherein determining the size of the target vehicle according to the determined vehicle type includes: determining the first horizontal distance and the second horizontal distance when a difference between a first horizontal distance of the observation position from a farthest flat position on a vehicle profile on a first side in a horizontal direction and a second horizontal distance of the observation position from a farthest flat position on a vehicle profile on a second side in the horizontal direction is less than a predetermined distance threshold during travel of the target vehicle; determining a fifth horizontal coordinate of the first flat position in the first data packet relative to the viewing position; determining a sixth horizontal coordinate of a first effective point driven by the vehicle in the first data packet relative to the observation position; determining the size of the target vehicle according to the first horizontal distance, the second horizontal distance, the fifth horizontal coordinate and the sixth horizontal coordinate.
Optionally, the vehicle type includes a long-flat type, and the target vehicle is a long-flat type vehicle, wherein determining the size of the target vehicle according to the determined vehicle type includes: determining a seventh horizontal coordinate of the first vertical coordinate maximum point in the first data packet relative to the viewing position; determining an eighth horizontal coordinate of a first effective point driven by the vehicle in the first data packet relative to the observation position; determining a tail compensation feature point corresponding to the first vertical coordinate maximum point in a second data packet acquired at the observation position after a second moment when vehicle departure data is detected for the first time under the observation position, and determining a ninth horizontal coordinate of the tail compensation feature point relative to the observation position based on the second data packet; determining a tenth horizontal coordinate of the last significant point of the vehicle drive-off in the second data packet relative to the observation position; determining the size of the target vehicle according to the seventh horizontal coordinate, the eighth horizontal coordinate, the ninth horizontal coordinate, and the tenth horizontal coordinate.
According to a second aspect of the present application, there is provided a vehicle size determination apparatus. The vehicle size determination apparatus includes: an acquisition unit that acquires a first point cloud data set of a target vehicle that has traveled under an observation position, wherein the first point cloud data set includes a first data packet acquired at the observation position before a first time when vehicle entrance data is first detected directly under the observation position, the first data packet including horizontal coordinate data and vertical coordinate data of a plurality of positions on a vehicle outline with respect to the observation position; a first determination unit that determines the number of consecutive flat positions among the plurality of positions on the vehicle profile, wherein a slope between two adjacent ones of the consecutive flat positions is smaller than a slope threshold, the slope being determined by a ratio of an absolute value of a difference between vertical coordinates of the two positions to an absolute value of a difference between horizontal coordinates; a second determination unit that determines a vertical distance difference between a maximum value of the vertical coordinate in the plurality of positions on the vehicle profile and a maximum value of the vertical coordinate in the successive leveling positions; the type determining unit is used for determining the vehicle type of the target vehicle according to the number of the continuous flat positions and the vertical distance difference; and a size determination unit that determines the size of the target vehicle according to the determined vehicle type.
According to a third aspect of the present application, a vehicle sizing system is provided. The vehicle size determination system includes: the laser sensor is arranged at the observation position and used for measuring the distances from different positions on the outline of the vehicle; a processor; a memory storing a computer program which, when executed by the processor, implements the vehicle size determination method according to the first aspect of the present application.
According to a fourth aspect of the present application, there is provided a computer-readable storage medium storing a computer program which, when executed by a processor, implements the vehicle dimension determination method according to the first aspect of the present application.
According to the vehicle size determination method, device, system and storage medium of the present application, the vehicle type of the target vehicle can be determined from the number of continuous flat positions on the vehicle contour and the vertical distance difference, so that the size of the target vehicle can be determined based on the vehicle type.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
To more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
FIG. 1 shows a schematic flow diagram of a vehicle sizing method according to an exemplary embodiment of the present application;
FIG. 2 shows a schematic structural diagram of a vehicle sizing method according to an exemplary embodiment of the present application;
FIG. 3 shows a graph generated as a target vehicle is scanned at all points at a first time in accordance with an exemplary embodiment of the present application;
FIG. 4 illustrates a laser sensor 90 degree directional point plot of a target vehicle when not parking all of the vehicles from a first time to a second time in accordance with an exemplary embodiment of the present application;
fig. 5 shows a schematic position diagram of a hybrid vehicle according to an exemplary embodiment of the present application at a first instant in time;
fig. 6 shows a schematic position diagram of a hybrid vehicle at a second instant in time according to an exemplary embodiment of the present application;
FIG. 7 illustrates a schematic position diagram of a long-box vehicle at a first time according to an exemplary embodiment of the present application;
fig. 8 shows a position diagram of a long-box vehicle according to an exemplary embodiment of the present application with a middle position directly below the observation position;
FIG. 9 illustrates a schematic position diagram of a long flatbed vehicle at a first time according to an exemplary embodiment of the present application;
FIG. 10 illustrates a position schematic of a long flat panel vehicle at a second time according to an exemplary embodiment of the present application;
fig. 11 shows a schematic block diagram of a vehicle size determination apparatus according to an exemplary embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. Every other embodiment that one skilled in the art can obtain without inventive effort based on the embodiments of the present application falls within the scope of protection of the present application.
It should be noted that in the embodiments of the present application, the term "comprising" is used to indicate the presence of the features stated hereinafter, but does not exclude the addition of further features.
One aspect of the present application relates to a vehicle sizing method. The method can distinguish the types of vehicles, so that the sizes of different types of vehicles can be determined more accurately.
As shown in fig. 1, a vehicle size determination method according to an embodiment of the present application includes the steps of:
s1, a first point cloud data set of a target vehicle running and passing below an observation position is obtained.
In this step, the first set of point cloud data includes a first data packet collected at the observation position before a first time when the vehicle-entering data is first detected directly below the observation position, the first data packet including horizontal coordinate data and vertical coordinate data of a plurality of positions on the vehicle outline with respect to the observation position.
As an example, the vehicle size determination method according to the embodiment of the present application may be implemented by a laser sensor. Specifically, as shown in fig. 2, the vehicle sizing system according to the embodiment of the present application may include a laser sensor 1, and the laser sensor 1 may be disposed at a viewing position for measuring distances from different positions on the vehicle outline. As an example, the laser sensor 1 may be fixed on a cross beam of the gantry 2 across the roadway, which may have a height from the ground of between 6m and 8m, for example 6.5m. The laser sensor 1 may be fixed at a middle position of the cross beam with a scanning direction parallel to a traveling direction of the target vehicle 3 in the lane, the scanning frequency of the laser sensor 1 may be 50Hz, the scanning angle range may be 0 ° to 180 °, the angular resolution may be 0.5 °, and the laser sensor 1 may determine a distance to an irradiated object (e.g., the target vehicle) by emitting laser light and receiving the laser light reflected back from the irradiated object, which may be accurate to a millimeter order. Here, since the scanning area of the laser sensor 1 is distributed in a fan shape as a whole and emits laser light with a constant angular resolution, the farther the distance between adjacent irradiation points irradiated to the ground or the target vehicle is from a scanning angle of 90 °, for example, irradiation points at scanning angles of 0 ° and 180 ° can be considered to fall at positions of infinite distance, and therefore, an effective detection area of the laser sensor 1 can be defined, and for example, a horizontal scanning range and a vertical scanning range of a scanning surface of the laser sensor can be defined with the position where the laser sensor is located as a zero point to form a detection area, where, in the process of collecting data, after data collected by the laser sensor 1 is converted into two-dimensional coordinates, the vehicle is driven off on a positive axis having a horizontal coordinate axis, and a direction vertically downward from an observation position where the laser sensor 1 is mounted on the ground is a positive axis having a vertical coordinate axis. Here, it should be noted that, in the drawings of the present application, the graphs generated by scanning are plotted from data converted based on data recorded on the coordinate axes, specifically, the origin of coordinates shown in fig. 3 and 4 is at a position of the ground surface directly below the observation position in the vertical direction, the positive horizontal axis of fig. 3 and 4 is on the vehicle-off side with respect to the origin of coordinates (i.e., the side of the vehicle that is away from the observation position in the horizontal direction), the negative horizontal axis is on the vehicle-on side with respect to the origin of coordinates (i.e., the side of the vehicle that is near the observation position in the horizontal direction), and the positive vertical axis of fig. 3 and 4 is the direction from the ground surface directly below the observation position where the laser sensor 1 is mounted to the observation position.
Assuming that the predetermined horizontal scanning range may be (Lmin, lmax) and the predetermined vertical scanning range may be (Vmin, vmax), as an example, the maximum value Lmax of the predetermined horizontal scanning range may be 20000mm, the minimum value Lmin may be-20000 mm, the maximum value Vmax of the predetermined vertical scanning range may be 6400mm, and the minimum value Vmin may be 100mm.
By way of example, real-time point cloud data D during vehicle driving is collected, D [ i ] represents a distance value of the ith irradiated point in each first data packet, and Tabcos and Tabsin are respectively data tables generated by a cos value and a sin value with an angular resolution of 0.5 ° in a range of 0 ° -180 °, wherein Tabcos [ i ] represents a cos value of a vehicle driving direction angle of the ith irradiated point, and Tabsin [ i ] represents a sin value of a vehicle driving direction angle of the ith irradiated point. As such, the two-dimensional coordinate data in the first packet may be represented as:
x[i]＝D[i]×Tabcos[i]；
y[i]＝D[i]×Tabsin[i]，
wherein x [ i ] represents the horizontal coordinate of the ith irradiated point, y [ i ] represents the vertical coordinate of the ith irradiated point, x [ i ] is e (Lmin, lmax), and y [ i ] is e (Vmin, vmax).
In the vehicle size determination process in which a target vehicle can travel along a lane passing under an observation position where the laser sensor 1 is located, the laser sensor 1 may scan the outline of the vehicle at a scanning angle in the range of 0 ° to 180 ° with respect to the vehicle traveling direction at a scanning frequency, and from the laser light returned at different scanning angles, determine the distance of an irradiated point irradiated with the laser light at the scanning angle at the present time from the observation position, and may convert into two-dimensional data with respect to the observation position, that is, horizontal coordinate data and vertical coordinate data, thereby determining the horizontal position and the vertical position of the irradiated point. Here, the vertical coordinate may represent the height of the vehicle profile.
In the traveling direction of the target vehicle, a region where the target vehicle travels near the detection position may be referred to as an entry region, and a region where the target vehicle travels away from the detection position may be referred to as a departure region. When a plurality of successive effective points, for example, 5 effective points, appear in the entrance area within the detection area of the laser sensor 1, it is determined that the target vehicle enters. The effective point refers to an irradiated point whose horizontal coordinate is within a predetermined horizontal scanning range and vertical coordinate is within a predetermined vertical scanning range, and taking the detection area of the above laser sensor 1 as an example, the coordinates (x 1, y 1) of the effective point should satisfy x1 ∈ (Lmin, 0) and y1 ∈ (Vmin, vmax).
When it is determined that the target vehicle enters, a predetermined number of packets after the current time point are started to be stored as a point cloud data set, and horizontal coordinate data and vertical coordinate data of a plurality of positions (for example, a plurality of irradiated points) on the vehicle outline with respect to the observation position may be included in the packets. The predetermined number may be arbitrarily set, and may be, for example, 5 packets, that is, the laser sensor 1 emits 5 times of laser light or performs 5 times of scanning, however, the present application is not limited thereto, and the predetermined number may also be, for example, 1. When the predetermined number is 2 or more, the predetermined number of packets may be used to eliminate the detection error, and specifically, all the calculation steps described in the embodiments of the present application may perform one calculation with each of the predetermined number of packets, and the calculation results of the plurality of packets may be compared, the error result may be discarded, or an intermediate value may be taken for the calculation results.
Then, each time a new data packet is detected, the data packet queue in the point cloud data set is shifted backward by one bit, and the new data packet is stored at the forefront of the data packet queue, that is, only a predetermined number of data packets may be stored all the time. When the laser of the laser sensor 90 ° scanning angle detects that the vehicle head reaches directly below the observation position, that is, when it is detected that the coordinates (x 2, y 2) of the irradiated point satisfy x2=0 and y2 ∈ (Vmin, vmax), it may be considered that vehicle data is detected for the first time directly below the observation position, and that the time is determined as a first time, and a point cloud data set collected before the first time is obtained as a first point cloud data set including the predetermined number of packets collected before the first time. The vehicle head outline information curve graph can be drawn based on the first point cloud data set, and the drawing result is shown in fig. 3.
S2, determining the number of continuous flat positions in the plurality of positions on the vehicle outline.
In this step, the slope between two adjacent ones of the successive leveling positions is less than a slope threshold, the slope being determined by the ratio of the absolute value of the difference between the vertical coordinates of the two positions to the absolute value of the difference between the horizontal coordinates.
As an example, the coordinates (x) of two positions as flat positions i ,y i ) And (x) i+1 ,y i+1 ) The following conditional expressions should be satisfied:
Figure BDA0003029396450000101
where k is the slope threshold. Here, the slope threshold may be preset according to actual applications.
When two positions satisfy the above-described conditional expression, the two positions may be regarded as two continuous flat positions, whether the coordinates of each two adjacent positions of the plurality of positions satisfy the above-described conditional expression may be calculated, respectively, and the number of continuously occurring flat positions may be determined.
And S3, determining the vertical distance difference between the maximum value of the vertical coordinate in the plurality of positions on the vehicle outline and the maximum value of the vertical coordinate in the continuous flat position.
In this step, the maximum value y of the vertical coordinate in all the data in the first packet can be determined max And the maximum y of the vertical coordinate in successive leveling positions can be determined pmax And calculates the difference between the two.
And S4, determining the vehicle type of the target vehicle according to the number of the continuous flat positions and the vertical distance difference.
In this step, the number of consecutive leveling positions may be compared with a leveling threshold value, and the vertical distance difference value may be compared with a difference threshold value, and the vehicle type of the target vehicle may be determined according to the comparison result. Here, the flatness threshold may be determined according to the angular resolution of the laser sensor 1, and specifically, the flatness threshold may be in a proportional relationship with the angular resolution of the laser sensor 1, that is, the flatness threshold increases as the angular resolution of the laser sensor 1 increases; as the angular resolution of the laser sensor 1 decreases, the flatness threshold decreases. The difference threshold may be set according to practical applications, and may be 500mm as an example.
And when the number of the continuous leveling positions exceeds the leveling threshold value and the vertical distance difference value is smaller than the difference threshold value, determining that the vehicle type of the target vehicle is a long-compartment type.
And when the number of the continuous leveling positions exceeds the leveling threshold value and the vertical distance difference value is greater than the difference threshold value, determining that the vehicle type of the target vehicle is a long-plate type.
And when the number of the continuous leveling positions is less than or equal to the leveling threshold value, determining that the vehicle type of the target vehicle is a composite type.
As an example, if there are continuous points in the detection area in the horizontal coordinate range between-3000 mm and-20000 mm with a height fluctuation within 100mm up and down, the total number of the continuous points exceeds the set 30 and the horizontal coordinate range between-10000 mm and-20000 mm, the number of the continuous points exceeds the set 10, then the series of points are the leveling points of the vehicle, the starting point (x 3, y 3) of the leveling position is recorded, and the first point (x 4, y 4) of the vehicle head is recorded at the same time. And if the horizontal coordinate range in the curve of the predetermined number of data packets is continuously traversed to be between-10000 mm and-20000 mm, if the horizontal coordinate value continuously exceeds five points and the fluctuation is less than the set 150mm, the target vehicle is determined to be a composite vehicle, otherwise, the target vehicle is a long-compartment vehicle or a long-flat-plate vehicle. And when the difference between the maximum vertical coordinate value of the flat position and the maximum vertical coordinate value of the head is more than 500mm, the target vehicle is determined to be a long-plate type vehicle, and meanwhile, jump point values (x 5 and y 5) from the head to the plate are recorded, otherwise, the target vehicle is a long-compartment type vehicle.
And S5, determining the size of the target vehicle according to the determined vehicle type.
In the case where the target vehicle is a hybrid vehicle, there may be a plurality of vehicles waiting for detection in the detection area, resulting in incorporation of vehicle data behind the target vehicle into the target vehicle when calculating the length, and inaccurate length calculation, and therefore, it may be determined whether there is another vehicle behind the target vehicle first. The hybrid vehicle described herein may refer to a vehicle type other than a long-box type vehicle and a long-flat type vehicle, and also includes a vehicle in which other equipment is provided on a long-box type vehicle or a long-flat type vehicle or a cargo is loaded so that the outer contour thereof is changed, for example, as shown in fig. 5 and 6, an object 6 such as a cargo is placed on a long flat plate portion of a long-flat type vehicle 5 so that the outer contour of the vehicle is a hybrid vehicle type.
Specifically, the step of determining the size of the target vehicle may comprise:
and S511, acquiring a second point cloud data set. Here, the second point cloud data set includes a second data packet acquired at the observation position after a second time instant at which the vehicle-off data is first detected directly below the observation position, the second data packet including horizontal coordinate data and vertical coordinate data of a plurality of positions on the vehicle outline with respect to the observation position.
In this step, when the laser light of the scanning angle of 90 ° of the laser sensor detects that the vehicle tail has passed right below the observation position, that is, when it is detected that the coordinates (x 8, y 8) of the irradiated point satisfy x8=0mm and y8= Vmax, it may be considered that the vehicle-off data is detected for the first time right below the observation position, and that the time is determined as a second time, and the point cloud data set acquired after the second time is obtained as the second point cloud data set.
S512, judging whether the second data packet has a valid point for the vehicle to enter behind the traveling direction of the target vehicle.
In this step, the traveling direction rear may refer to a vehicle entrance area. The effective point refers to an irradiated point whose horizontal coordinate is within a predetermined horizontal scanning range and whose vertical coordinate is within a predetermined vertical scanning range, and as described above, taking the detection area of the above laser sensor 1 as an example, the coordinates (x 1, y 1) of the effective point should satisfy x1 ∈ (Lmin, 0) and y1 ∈ (Vmin, vmax).
And S513, determining the tail characteristic point in the first data packet according to the judgment result.
In one case, it is determined that there is no valid point, and the last vertical coordinate trip point in the first packet is determined as the tail feature point in response to the determination result that there is no valid point.
Specifically, when it is determined that there is no valid point behind the traveling direction of the target vehicle, it may be considered that the data in the first data packet scanned at the first time belongs to the current target vehicle, and there is no interference data of other vehicles behind, and in this case, the last vertical coordinate jumping point in the first data packet may be determined as a tail feature point for use in subsequent vehicle size calculation.
Here, the first vertical coordinate jumping point may refer to an irradiated point: the difference in vertical coordinate between the irradiated point and an adjacent irradiated point on the side away from the observation position in the horizontal direction is greater than the set vertical jump threshold and the difference in horizontal coordinate is greater than the set horizontal jump threshold. Specifically, the first vertical coordinate transition point may be a case where the data points are widely spaced, that is, the vertical coordinate value and the horizontal coordinate value of two adjacent data points are both spaced apart by more than a predetermined transition threshold, for example, as shown in fig. 3, a blank distance without data points occurs between the vehicle head and the vehicle compartment (between about-4500 mm and-3000 mm in the horizontal coordinate), that is, a transition of data points occurs between the vehicle head and the vehicle compartment, where the last data point of the vehicle head portion may be the first vertical transition point. The second vertical coordinate jumping point may refer to an irradiated point: the slope between the irradiated point and the previous irradiated point and the slope between the irradiated point and the next irradiated point have opposite signs (i.e., opposite signs), or one of the slope between the irradiated point and the previous irradiated point and the slope between the irradiated point and the next irradiated point is 0, and the other is positive or negative.
In another case, in response to the determination result that the valid point exists, acquiring an observation position data packet, wherein the observation position data packet includes vertical coordinate data of different positions on the vehicle outline from the observation position; and determining the tail characteristic point according to the first vertical coordinate jump point in the first data packet and the second vertical coordinate jump point in the observation position data packet.
Specifically, when it is determined that there is a valid point behind the traveling direction of the target vehicle, it is considered that part of the data in the first packet scanned at the first time may belong to another vehicle behind the target vehicle, and in this case, the separation process is required.
The step of determining the tail feature point based on the first vertical coordinate trip point in the first packet and the second vertical coordinate trip point in the observation position packet may include:
s5131, determining the number n of the first vertical coordinate jumping points and the number m of the second vertical coordinate jumping points;
s5132, comparing the number n of the first vertical coordinate trip points with the number m of the second vertical coordinate trip points, and determining the last vertical coordinate trip point according to the comparison result.
In the step, if m is larger than or equal to n, determining an nth first vertical coordinate jump point in the first data packet as a tail feature point; and if m is smaller than n, determining the mth first vertical coordinate jump point in the first data packet as the tail characteristic point.
Specifically, if there is a valid point, it is proved that the target vehicle may enter the detection area by another vehicle in the first point cloud data set at the first time, and therefore, as an example, all pieces of data of the 90-degree direction point (directly below the observation position) of the laser sensor when the target vehicle is not parked from the first time to the second time may be acquired as the observation position data packet.
Here, the observation position data packet may be subjected to data processing to filter the interference points. Specifically, the observation position data packet may be processed in the following manner:
out-of-range data point filtering may be performed according to a predetermined vertical scan range. Specifically, data points with vertical coordinates outside of a predetermined vertical scan range of (Vmin, vmax) may be culled such that the vertical coordinates y of all data points i Satisfy Vmin<y i <Vmax。
The smoothness of the vertical coordinate data in the observation position data packet can be optimized by adopting a multipoint mean method so as to search the number n of the vertical coordinate jumping points. Specifically, the vertical coordinate data in the observation position data packet can be reconstructed by the following expression:
Figure BDA0003029396450000141
where Y represents the number of mean points, for example, Y may be 20.
The number n of the second vertical coordinate trip points may be determined in the observation position data packet after the data processing, thereby performing the split processing in the free stream state.
As an example, as shown in fig. 4, the number m =2 of the second vertical coordinate transition points (i.e., the vehicle height scanned in the waveform of fig. 4 transits from high to low) may be calculated according to the number of times the slope of the curve formed by the data of the observation position data packet is less than 0.
The number of first vertical coordinate trip points may be determined from the first packet of the first point cloud data set at the first time, as shown in fig. 3, where trip points occur at a position with a horizontal coordinate of-3000 mm and a position with a horizontal coordinate of-16000 mm, respectively, i.e., the number of trip points n =2. Here, the most reliable number of transition points may be obtained by filtering, based on the predetermined number of first packets (e.g., 5 first packets) to generate their corresponding number of transition points, respectively.
If m is larger than or equal to n, the nth first vertical coordinate trip point in the first data packet at the first moment is a vehicle separation point between the target vehicle and the rear vehicle; and if m is less than n, the mth first vertical coordinate jump point in the first data packet at the first moment is the vehicle separation point between the target vehicle and the rear vehicle. The shunting point is the tail characteristic point of the target vehicle.
The existing two-dimensional laser vehicle outline detection method can be divided into a single-rod type and a double-rod type, wherein the existing single-rod type vehicle outline detection scheme is a layout mode that two laser sensors for respectively measuring the width and the height are arranged on the left side and the right side of a portal cross rod, and a laser sensor for measuring the length is arranged in the middle of the portal cross rod; the existing double-rod type vehicle outline detection scheme is a layout of two door frames which are separated by 20 meters, two laser sensors for respectively measuring the width and the height are arranged on the left side and the right side of a front door frame, and a laser sensor for measuring the length is arranged in the middle of a rear door frame. In the single-rod type vehicle and double-rod type vehicle outline detection scheme, the length, the width and the height of the vehicle can be accurately output under a non-free flow state, but when a plurality of vehicles are in a detection area at the same time, the vehicle separation is difficult, the situation that a front vehicle shields a rear vehicle exists, and the accurate value of the length is seriously influenced.
According to the vehicle size determining method, the vehicle separating points can be judged according to the number of the first vertical coordinate jumping points and the second vertical coordinate jumping points, so that a currently detected target vehicle can be distinguished from other vehicles behind the currently detected target vehicle when a plurality of vehicles to be detected are located in the detection area at the same time, and accurate size detection is achieved.
And S514, determining the size of the target vehicle according to the tail characteristic points.
In this step, a first horizontal coordinate of the tail feature point in the first data packet relative to the viewing position may be determined. As shown in fig. 5, the coordinates of the tail feature point are (x 10, y 10).
A tail compensation feature point in the second data packet corresponding to the tail feature point may be determined and, based on the second data packet, a second horizontal coordinate of the tail compensation feature point relative to the observation position may be determined. As shown in fig. 6, the coordinates of the tail compensation feature point are (x 11, y 11).
A third horizontal coordinate of the first significant point in the first data packet, into which the vehicle has entered, relative to the viewing position can be determined. As shown in fig. 5, the coordinates of the first effective point are (x 4, y 4).
A fourth horizontal coordinate of the last significant point in the second data packet from which the vehicle traveled relative to the observation location may be determined. As shown in fig. 6, the coordinates of the last effective point are (x 12, y 12).
The size of the target vehicle may be determined based on the first horizontal coordinate, the second horizontal coordinate, the third horizontal coordinate, and the fourth horizontal coordinate.
Specifically, as shown in fig. 5, based on the first horizontal coordinate and the third horizontal coordinate, an initial vehicle length d from the vehicle head to the tail feature point may be determined 1 ＝|x10|-d 6 = x10-x 4. As shown in fig. 6, according to the second horizontal coordinate and the fourth horizontal coordinate, a tail compensation value d from the tail feature point (or the tail compensation feature point) to the tail feature point can be determined 2 ＝|x12|-d 7 ＝|x12-x11|。
In the above-described size calculation process for a hybrid vehicle, since there may be a scanning blind area in the data in the first packet, for example, a region of the tail of the target vehicle behind the object 6 in which laser light cannot be irradiated due to the presence of the object 6, the tail compensation value needs to be considered in calculating the length of the target vehicle. In determining the tail compensation value, a tail compensation feature point in the second packet corresponding to the tail feature point in the first packet may be determined, for example, an inflection point in the second packet may be compared to a jump point in the first packet to determine the tail compensation feature point. Here, the inflection point may refer to an irradiated point: the slope between the irradiated point and the previous irradiated point and the slope between the irradiated point and the next irradiated point have opposite signs, i.e., opposite signs.
The length of the composite vehicle obtained by the calculation process is the sum of the initial vehicle length and the tail compensation value, namely L = d 1 +d 2 。
In the existing vehicle outline detection scheme, due to the influence of the resolution of a laser sensor, the farther the distance is, the larger the phase difference of converting points generated by two adjacent angles into horizontal coordinate values is, and the accuracy of the length of a vehicle cannot be ensured due to the influence of a scanning blind area of the tail or the head of the vehicle. In the method of the embodiment of the present application, the length of the tail region that is in the blind zone and cannot be detected can be compensated by the tail compensation value, so that the measurement of the length of the vehicle is more accurate.
In the case where the target vehicle is a long-box type vehicle, the step of determining the size of the target vehicle may include:
s521, determining a first horizontal distance and a second horizontal distance when a difference between a first horizontal distance of the observation position from a farthest flat position on the vehicle profile on a first side in the horizontal direction and a second horizontal distance of the observation position from a farthest flat position on the vehicle profile on a second side in the horizontal direction is less than a predetermined distance threshold during the traveling of the target vehicle.
As shown in fig. 8, the first horizontal distance may be the farthest flat position of the observation position from the vehicle outline on the first side in the horizontal direction (e.g., the left side in fig. 8), and the second horizontal distance may be the farthest flat position of the observation position from the vehicle outline on the second side in the horizontal direction (e.g., the right side in fig. 8).
Specifically, when the long-van vehicle enters a 90-degree direction point of the laser sensor, that is, when the long-van vehicle enters a position directly below the observation position, each packet after filtering is started and the absolute values of the last leveling points xl, xr on both sides in the horizontal direction from the observation position in each packet are calculated,as shown in fig. 8, when | (| xl | - | xr |) | is smaller than a set value (e.g., 100 mm), the car length is calculated. I.e. the first horizontal distance d 4 = | xl |, second horizontal distance d 5 ＝|xr|。
S522, determining a fifth horizontal coordinate of the first flat position in the first data packet relative to the observation position.
Specifically, as shown in fig. 7, the coordinates of the first flat position are (x 3, y 3). Here, the first leveling position is a leveling position that is horizontally closest to the observation position among the above-described continuous leveling positions.
And S523, determining a sixth horizontal coordinate of the first effective point, driven by the vehicle, in the first data packet relative to the observation position.
Specifically, as shown in fig. 7, the coordinates of the first effective point are (x 4, y 4). As an example, the first significant point may be a trip point in the first packet that is the closest horizontal distance from the observation location. The first effective point being at a distance d from the observation position in the horizontal direction 12 ＝|x4|。
From the first flat position and the first effective point, it is possible to obtain a distance d from the head foremost end (i.e., the first effective point) of the long-compartment type vehicle 4 (shown in fig. 7 and 8) to the starting position (i.e., the first flat position) of the compartment 3 ＝|x3-x4|。
And S524, determining the size of the target vehicle according to the first horizontal distance, the second horizontal distance, the fifth horizontal coordinate and the sixth horizontal coordinate.
Specifically, the length of the long-compartment type vehicle may be the sum of the length of the compartment and the length of the head, and the length of the compartment may be the first horizontal distance d 4 And a second horizontal distance d 5 The length of the head of the vehicle can be a distance d 3 That is, the length L = d of the long-compartment vehicle 4 +d 5 +d 3 。
In the size calculation process of the existing long-compartment type vehicle, the fact that the compartment part of the long-compartment type vehicle is relatively long is not considered, and the longer the distance is, the larger the horizontal distance between two adjacent angle polar coordinate points is when the two adjacent angle polar coordinate points are converted into two-dimensional coordinates, and the length measurement accuracy is seriously influenced. In contrast, according to the determination method of the embodiment of the present application, it is possible to maximize the accuracy of the length measurement of the car section by acquiring the first horizontal distance and the second horizontal distance when the difference between the first horizontal distance of the observation position from the farthest leveling position on the first side in the horizontal direction and the second horizontal distance of the observation position from the farthest leveling position on the second side in the horizontal direction is smaller than the predetermined distance threshold.
In the case where the target vehicle is a long flatbed vehicle, the determining of the size of the target vehicle may include:
and S531, determining a seventh horizontal coordinate of the first vertical coordinate maximum point in the first data packet relative to the observation position.
Specifically, as shown in fig. 9, the coordinates of the first vertical coordinate maximum point are (x 5, y 5). Here, the first vertical coordinate maximum point may be a point having the maximum vertical coordinate value in the first packet.
S532, determining the eighth horizontal coordinate of the first effective point driven by the vehicle in the first data packet relative to the observation position.
Specifically, as shown in fig. 9, the coordinates of the first effective point are (x 6, y 6). As an example, the first significant point may be a trip point in the first packet that is the closest horizontal distance from the observation location. That is, the distance d in the horizontal direction from the foremost end of the vehicle's nose to the viewing position 9 ＝|x6|。
Based on the first leveling position and the first effective point, the distance d from the head foremost end (i.e., the first effective point) of the long-slab type vehicle 5 (shown in fig. 9 and 10) to the start position (i.e., the first leveling position) of the vehicle slab can be acquired 8 ＝|x5-x6|。
And S533, determining a tail compensation feature point corresponding to the maximum point of the first vertical coordinate in the second data packet, and determining a ninth horizontal coordinate of the tail compensation feature point relative to the observation position based on the second data packet.
In determining the tail compensation feature point, a tail compensation feature point corresponding to the first flat position in the first packet may be determined in the second packet, e.g., an inflection point in the second packet may be compared to a transition point in the first packet to determine the tail compensation feature point. As shown in fig. 10, the coordinates of the tail compensation feature point may be (x 7, y 7).
Specifically, the timing at which the vehicle-off data is detected for the first time by the 90-degree direction point of the laser sensor, that is, the second timing at which the vehicle-off data is detected for the first time directly below the observation position, may be monitored in real time, and a predetermined number of second packets after the second timing may be stored. And calculating the horizontal coordinate of the long-flat-plate type vehicle according to the curve waveform generated by the second data packet, traversing all vertical coordinate values from the position right below the observation position, and searching the point (x 7, y 7) with the maximum vertical coordinate value (when the difference between the two vertical coordinate values is less than 100mm, the maximum vertical coordinate value is not replaced).
And S534, determining the tenth horizontal coordinate of the last effective point, away from which the vehicle drives, in the second data packet relative to the observation position.
Specifically, as shown in fig. 10, the coordinates of the last effective point may be (x 8, y 8).
As shown in fig. 10, according to the tail compensation feature point and the last effective point, the distance d from the tail of the long flat plate type vehicle (i.e., the last effective point) to the first highest point of the head (i.e., the tail compensation feature point) 10 ＝|x7|-d 11 ＝|x7|-|x8|。
And S535, determining the size of the target vehicle according to the seventh horizontal coordinate, the eighth horizontal coordinate, the ninth horizontal coordinate and the tenth horizontal coordinate.
Specifically, as shown in fig. 9 and 10, the length of the long flat type vehicle may be according to the distance d 8 Distance d 10 And a distance d 9 To determine the length L = d of the long flat plate type vehicle 8 +d 10 -d 9 。
On one hand, the farther the scanning blind area of the laser sensor and the distance between two adjacent angles are, the larger the difference between the generated points converted into horizontal coordinate values is; on the other hand, due to high-speed driving, the controller has time errors in capturing the laser sensor key frame, and both aspects can cause inaccurate measurement results of the vehicle size. The method of the embodiment of the application can be used for classifying the vehicle types and calculating the vehicle length, and avoids the error of calculating the vehicle length of the long van type vehicle and the long flat type vehicle which are greatly influenced by the angular resolution.
In addition, in the method of the embodiment of the application, in the processing of the locomotive, the distance from the first effective point of the locomotive to the position right below the observation position is calculated, the problem of key data frame capture delay caused by speed is filtered, and the measurement accuracy is further improved.
Another aspect of the present application provides a vehicle dimension determining apparatus. As shown in fig. 11, the vehicle size determination apparatus includes an acquisition unit 100, a first determination unit 200, a second determination unit 300, a type determination unit 400, and a size determination unit 500.
The acquisition unit 100 may acquire a first point cloud data set of a target vehicle traveling past under an observation position. Here, the first set of point cloud data includes a first data packet collected at the observation position before a first time when the vehicle entrance data is first detected right below the observation position, the first data packet including horizontal coordinate data and vertical coordinate data of a plurality of positions on the vehicle outline with respect to the observation position.
The first determination unit 200 may determine the number of continuous flat positions among a plurality of positions on the vehicle profile. Here, a slope between adjacent two of the consecutive flat positions is smaller than a slope threshold, the slope being determined by a ratio of an absolute value of a difference between vertical coordinates of the two positions to an absolute value of a difference between horizontal coordinates.
The second determination unit 300 may determine a vertical distance difference between a maximum value of the vertical coordinate in a plurality of positions on the vehicle profile and a maximum value of the vertical coordinate in the successive leveling positions.
The type determination unit 400 may determine the vehicle type of the target vehicle based on the number of continuous flat positions and the vertical distance difference.
The size determination unit 500 may determine the size of the target vehicle according to the determined vehicle type.
The obtaining unit 100, the first determining unit 200, the second determining unit 300, the type determining unit 400, and the size determining unit 500 may perform corresponding steps in the method according to the vehicle size determining method in the method embodiment shown in fig. 1 to 10, for example, the obtaining unit 100, the first determining unit 200, the second determining unit 300, the type determining unit 400, and the size determining unit 500 may be implemented by machine readable instructions executable by the obtaining unit 100, the first determining unit 200, the second determining unit 300, the type determining unit 400, and the size determining unit 500, and specific implementation manners of the obtaining unit 100, the first determining unit 200, the second determining unit 300, the type determining unit 400, and the size determining unit 500 may refer to the method embodiment described above, which is not described herein again.
Another aspect of the present application provides a vehicle sizing system that includes a laser sensor, a processor, and a memory. The laser sensor is arranged at the observation position for measuring distances to different positions on the vehicle profile. The memory stores a computer program. When the computer program is executed by the processor, the vehicle size determining system may perform the steps of the vehicle size determining method in the method embodiments shown in fig. 1 to 10, and specific implementation manners may refer to the method embodiments and are not described herein again.
Another aspect of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can perform the steps of the vehicle size determining method in the method embodiments shown in fig. 1 to 10, and specific implementation manners may be referred to the method embodiments and will not be described herein again.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some communication interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in software functional units and sold or used as a stand-alone product, may be stored in a non-transitory computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
According to the vehicle size determination method, device, system and storage medium of the present application, the vehicle type of the target vehicle can be determined from the number of continuous flat positions on the vehicle contour and the vertical distance difference, so that the size of the target vehicle can be determined based on the vehicle type.
In addition, according to the vehicle size determining method, the vehicle size determining device, the vehicle size determining system and the vehicle size determining storage medium, the number of the vertical coordinate jumping points of the vehicle at different positions is compared, the vehicle separation processing is carried out on the composite vehicle, the influence of the vehicle behind the target vehicle on the size measurement of the target vehicle can be avoided, and therefore the length of the vehicle can be accurately measured.
In addition, according to the vehicle size determination method, the vehicle size determination device, the vehicle size determination system and the storage medium, the tail compensation characteristic point is determined, so that the total length of the long-compartment type vehicle is calculated by adopting the sum of the length of the compartment, the length of the head of the vehicle and the tail compensation, the total yard of the long-flat type vehicle is calculated by adopting the sum of the initial length of the vehicle and the tail compensation, and the measurement accuracy is greatly improved.
In addition, according to the vehicle size determining method, the vehicle size determining device, the vehicle size determining system and the storage medium, compared with the existing measuring method, the advantages of low cost, convenience in installation, high detection accuracy and convenience in maintenance exist in the condition of measuring the length of the vehicle in the free-flow driving state, the vehicle size determining method, the device and the system are beneficial to installation and use in multiple application scenes such as toll station entrances and vehicle detection stations, and the universality is high.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the exemplary embodiments of the present application, and are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
While this application includes specific examples, it will be apparent to those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the claims and their equivalents. The examples described herein are to be considered in a descriptive sense only and not for purposes of limitation. The description of features or aspects in each example is to be considered applicable to similar features or aspects of other examples. Suitable results may be achieved if the described techniques are performed in a different order and/or if components in the described systems, architectures, devices or circuits are combined in a different manner and/or replaced or supplemented by other components or their equivalents. Therefore, the scope of the present application is defined not by the detailed description but by the claims and their equivalents, and all changes within the scope of the claims and their equivalents are to be construed as being included in the present application.

Claims (9)

1. A vehicle size determination method, characterized by comprising:
acquiring a first point cloud data set of a target vehicle passing under an observation position, wherein the first point cloud data set comprises a first data packet collected at the observation position before a first moment when vehicle entering data is detected for the first time under the observation position, and the first data packet comprises horizontal coordinate data and vertical coordinate data of a plurality of positions on a vehicle outline relative to the observation position;
determining a number of consecutive flat positions of the plurality of positions on the vehicle contour, wherein a slope between two adjacent ones of the consecutive flat positions is less than a slope threshold, the slope being determined by a ratio of an absolute value of a difference between vertical coordinates and an absolute value of a difference between horizontal coordinates of the two positions;
determining a vertical distance difference between a maximum of a vertical coordinate in the plurality of positions on the vehicle contour and a maximum of a vertical coordinate in the successive leveling positions;
determining the vehicle type of the target vehicle according to the number of the continuous flat positions and the vertical distance difference;
determining the size of the target vehicle according to the determined vehicle type;
the vehicle type comprises a composite type, the target vehicle is a composite type vehicle, wherein the size of the target vehicle is determined according to the determined vehicle type, and the method comprises the following steps:
acquiring a second point cloud data set, wherein the second point cloud data set comprises a second data packet acquired at the observation position after a second moment when vehicle driving-away data is first detected under the observation position, and the second data packet comprises horizontal coordinate data and vertical coordinate data of a plurality of positions on the vehicle outline relative to the observation position;
judging whether an effective point for the vehicle to enter exists behind the driving direction of the target vehicle in the second data packet or not;
determining tail characteristic points in the first data packet according to the judgment result;
and determining the size of the target vehicle according to the tail characteristic point.
2. The vehicle size determination method according to claim 1, wherein determining a tail feature point in the first packet according to the determination result includes:
determining a last vertical coordinate trip point in the first data packet as the tail feature point in response to a determination that the valid point does not exist,
responding to the judgment result that the effective point exists, and acquiring an observation position data packet, wherein the observation position data packet comprises vertical coordinate data of different positions on the outline of the vehicle from the observation position;
and determining the tail characteristic point according to a first vertical coordinate jump point in the first data packet and a second vertical coordinate jump point in the observation position data packet.
3. The vehicle size determination method according to claim 2, wherein determining the tail feature point based on the first vertical coordinate trip point in the first packet and the second vertical coordinate trip point in the observation position packet includes:
determining the number n of the first vertical coordinate trip points and the number m of the second vertical coordinate trip points;
comparing the number n of the first vertical coordinate trip points with the number m of the second vertical coordinate trip points, determining the tail characteristic points according to the comparison result,
if m is larger than or equal to n, determining the nth first vertical coordinate jump point in the first data packet as the tail feature point;
and if m is smaller than n, determining the mth first vertical coordinate jump point in the first data packet as the tail characteristic point.
4. The vehicle size determination method according to any one of claims 1 to 3, wherein determining the size of the target vehicle from the tail feature point includes:
determining a first horizontal coordinate of the tail feature point in the first data packet relative to the viewing position;
determining a tail compensation feature point corresponding to the tail feature point in the second data packet, and determining a second horizontal coordinate of the tail compensation feature point relative to the observation position based on the second data packet;
determining a third horizontal coordinate of a first effective point driven by the vehicle in the first data packet relative to the observation position;
determining a fourth horizontal coordinate of a last significant point of the second data packet from which the vehicle has traveled relative to the observation location;
determining the size of the target vehicle according to the first horizontal coordinate, the second horizontal coordinate, the third horizontal coordinate and the fourth horizontal coordinate.
5. The vehicle size determination method according to claim 1, wherein the vehicle type includes a long-box type, and the target vehicle is a long-box type vehicle, wherein determining the size of the target vehicle according to the determined vehicle type includes:
determining the first horizontal distance and the second horizontal distance when a difference between a first horizontal distance of the observation position from a farthest flat position on a vehicle profile on a first side in a horizontal direction and a second horizontal distance of the observation position from a farthest flat position on a vehicle profile on a second side in the horizontal direction is less than a predetermined distance threshold during travel of the target vehicle;
determining a fifth horizontal coordinate of the first flat position in the first data packet relative to the viewing position;
determining a sixth horizontal coordinate of a first effective point driven by the vehicle in the first data packet relative to the observation position;
determining the size of the target vehicle according to the first horizontal distance, the second horizontal distance, the fifth horizontal coordinate and the sixth horizontal coordinate.
6. The vehicle size determination method according to claim 1, wherein the vehicle type includes a long-flat type, and the target vehicle is a long-flat type vehicle, wherein determining the size of the target vehicle according to the determined vehicle type includes:
determining a seventh horizontal coordinate of the first vertical coordinate maximum point in the first data packet relative to the viewing position;
determining an eighth horizontal coordinate of a first effective point driven by the vehicle in the first data packet relative to the observation position;
determining a tail compensation feature point corresponding to the first vertical coordinate maximum point in a second data packet acquired at the observation position after a second moment when vehicle departure data is detected for the first time under the observation position, and determining a ninth horizontal coordinate of the tail compensation feature point relative to the observation position based on the second data packet;
determining a tenth horizontal coordinate of the last significant point of the vehicle drive-off in the second data packet relative to the observation position;
determining the size of the target vehicle according to the seventh horizontal coordinate, the eighth horizontal coordinate, the ninth horizontal coordinate, and the tenth horizontal coordinate.
7. A vehicle size determination apparatus, characterized by comprising:
an acquisition unit that acquires a first point cloud data set of a target vehicle that has traveled under an observation position, wherein the first point cloud data set includes a first data packet acquired at the observation position before a first time when vehicle entrance data is first detected directly under the observation position, the first data packet including horizontal coordinate data and vertical coordinate data of a plurality of positions on a vehicle outline with respect to the observation position;
a first determination unit that determines the number of consecutive flat positions among the plurality of positions on the vehicle profile, wherein a slope between two adjacent ones of the consecutive flat positions is smaller than a slope threshold, the slope being determined by a ratio of an absolute value of a difference between vertical coordinates of the two positions to an absolute value of a difference between horizontal coordinates;
a second determination unit that determines a vertical distance difference between a maximum value of the vertical coordinate in the plurality of positions on the vehicle profile and a maximum value of the vertical coordinate in the continuous flat position;
the type determining unit is used for determining the vehicle type of the target vehicle according to the number of the continuous flat positions and the vertical distance difference;
a size determination unit that determines the size of the target vehicle according to the determined vehicle type;
the vehicle type comprises a composite type, the target vehicle is a composite type vehicle, wherein the size of the target vehicle is determined according to the determined vehicle type, and the method comprises the following steps:
acquiring a second point cloud data set, wherein the second point cloud data set comprises a second data packet acquired at the observation position after a second moment when vehicle driving-away data is first detected under the observation position, and the second data packet comprises horizontal coordinate data and vertical coordinate data of a plurality of positions on the vehicle outline relative to the observation position;
judging whether an effective point for the vehicle to enter exists behind the driving direction of the target vehicle in the second data packet or not;
determining tail characteristic points in the first data packet according to the judgment result;
and determining the size of the target vehicle according to the tail characteristic point.
8. A vehicle sizing system, characterized in that the vehicle sizing system comprises:
the laser sensor is arranged at the observation position and used for measuring the distances from different positions on the outline of the vehicle;
a processor;
memory storing a computer program which, when executed by a processor, implements a vehicle sizing method according to any of claims 1 to 6.
9. A computer-readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the vehicle dimension determination method according to any one of claims 1 to 6.
CN202110425541.9A 2021-04-20 2021-04-20 Vehicle size determination method, device and system and storage medium Active CN113124777B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110425541.9A CN113124777B (en) 2021-04-20 2021-04-20 Vehicle size determination method, device and system and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110425541.9A CN113124777B (en) 2021-04-20 2021-04-20 Vehicle size determination method, device and system and storage medium

Publications (2)

Publication Number Publication Date
CN113124777A CN113124777A (en) 2021-07-16
CN113124777B true CN113124777B (en) 2023-02-24

Family

ID=76778162

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110425541.9A Active CN113124777B (en) 2021-04-20 2021-04-20 Vehicle size determination method, device and system and storage medium

Country Status (1)

Country Link
CN (1) CN113124777B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113899333A (en) * 2021-09-29 2022-01-07 苏州佳祺仕信息科技有限公司 Distance measuring method and device, electronic equipment and storage medium
CN113932681B (en) * 2021-10-18 2024-04-05 北京京东乾石科技有限公司 Measuring device, automatic guided vehicle detection method, device and storage medium

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001319290A (en) * 2000-05-12 2001-11-16 Hitachi Zosen Corp Method and device for judging vehicle kind
CN101162507A (en) * 2006-10-13 2008-04-16 同方威视技术股份有限公司 Method for recognizing vehicle type of moving care
CN101196979A (en) * 2006-12-22 2008-06-11 四川川大智胜软件股份有限公司 Method for recognizing vehicle type by digital picture processing technology
CN102679889A (en) * 2012-05-30 2012-09-19 北京恒华伟业科技股份有限公司 Vehicle size measurement method and device
CN203489844U (en) * 2013-09-03 2014-03-19 天津大学 System for measuring size of outer profile of vehicle based on machine vision and laser light screen
CN103730011A (en) * 2012-10-12 2014-04-16 博隆建亚科技(北京)有限公司 Vehicle type recognition detection method and system based on laser
CN104714994A (en) * 2013-12-17 2015-06-17 现代自动车株式会社 System and method of recommending type of vehicle based on customer use information and vehicle state
CN105606023A (en) * 2015-12-18 2016-05-25 武汉万集信息技术有限公司 Vehicle profile dimensions measuring method and system
CN108759662A (en) * 2018-04-02 2018-11-06 广州市杜格数控设备有限公司 Vehicle overall dimension measurement method
CN209623627U (en) * 2019-05-06 2019-11-12 辽宁因泰立电子信息有限公司 Vehicle overall dimension check device
CN111928795A (en) * 2020-09-04 2020-11-13 浙江省计量科学研究院 Tractor and trailer overall dimension parameter integrated measurement method
CN112325794A (en) * 2020-10-12 2021-02-05 武汉万集信息技术有限公司 Method, device and system for determining overall dimension of vehicle

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9256803B2 (en) * 2012-09-14 2016-02-09 Palo Alto Research Center Incorporated Automatic detection of persistent changes in naturally varying scenes
CN104391339B (en) * 2014-12-17 2018-02-09 同方威视技术股份有限公司 Model recognizing method and the quick inspection system of vehicle using this method
CN109425365B (en) * 2017-08-23 2022-03-11 腾讯科技（深圳）有限公司 Method, device and equipment for calibrating laser scanning equipment and storage medium
CN112344854B (en) * 2020-10-27 2022-06-03 深圳市航天华拓科技有限公司 Vehicle overrun detection method, system and computer readable storage medium

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001319290A (en) * 2000-05-12 2001-11-16 Hitachi Zosen Corp Method and device for judging vehicle kind
CN101162507A (en) * 2006-10-13 2008-04-16 同方威视技术股份有限公司 Method for recognizing vehicle type of moving care
CN101196979A (en) * 2006-12-22 2008-06-11 四川川大智胜软件股份有限公司 Method for recognizing vehicle type by digital picture processing technology
CN102679889A (en) * 2012-05-30 2012-09-19 北京恒华伟业科技股份有限公司 Vehicle size measurement method and device
CN103730011A (en) * 2012-10-12 2014-04-16 博隆建亚科技(北京)有限公司 Vehicle type recognition detection method and system based on laser
CN203489844U (en) * 2013-09-03 2014-03-19 天津大学 System for measuring size of outer profile of vehicle based on machine vision and laser light screen
CN104714994A (en) * 2013-12-17 2015-06-17 现代自动车株式会社 System and method of recommending type of vehicle based on customer use information and vehicle state
CN105606023A (en) * 2015-12-18 2016-05-25 武汉万集信息技术有限公司 Vehicle profile dimensions measuring method and system
CN108759662A (en) * 2018-04-02 2018-11-06 广州市杜格数控设备有限公司 Vehicle overall dimension measurement method
CN209623627U (en) * 2019-05-06 2019-11-12 辽宁因泰立电子信息有限公司 Vehicle overall dimension check device
CN111928795A (en) * 2020-09-04 2020-11-13 浙江省计量科学研究院 Tractor and trailer overall dimension parameter integrated measurement method
CN112325794A (en) * 2020-10-12 2021-02-05 武汉万集信息技术有限公司 Method, device and system for determining overall dimension of vehicle

Also Published As

Publication number Publication date
CN113124777A (en) 2021-07-16

Similar Documents

Publication Publication Date Title
US10501059B2 (en) Stereo camera device
CN113536883B (en) Obstacle detection method, vehicle, apparatus, and computer storage medium
CN109870223B (en) Bridge dynamic weighing method assisted by visual technology
CN113124777B (en) Vehicle size determination method, device and system and storage medium
WO2019116958A1 (en) Onboard environment recognition device
CN108596058A (en) Running disorder object distance measuring method based on computer vision
KR101925293B1 (en) The vehicle detecting system by converging radar and image
JP4979306B2 (en) Vehicle automatic measurement device, vehicle automatic measurement system, and vehicle automatic measurement method
WO2019088267A1 (en) Obstacle detecting device
CN111198371A (en) Forward-looking obstacle detection system
WO2017145600A1 (en) Image processing device, imaging device, mobile entity apparatus control system, image processing method, and program
CN109839175B (en) Bridge live load optimizing and recognizing system
WO2017145605A1 (en) Image processing device, image pickup device, moving body apparatus control system, image processing method, and program
CN110736999B (en) Railway turnout detection method based on laser radar
WO2014136976A1 (en) Overhead line position measuring device and method
KR20170080481A (en) Multilane vehicle speed detecting system
CN113189583B (en) Time-space synchronization millimeter wave radar and visual information fusion method
CN113689483A (en) Distance measurement method based on monocular camera and laser radar
CN110490342B (en) Contact net static geometrical parameter detection method based on Faster R-CNN
KR101784635B1 (en) METHOD AND SYSTEM FOR DETECTING MULTILINE VECHILE USING 2D LiDAR
CN205991785U (en) A kind of railway tunnel gauge dynamic detection system
JP6602595B2 (en) Vehicle type identification device and vehicle type identification method
CN109801503B (en) Vehicle speed measuring method and system based on laser
JP5952759B2 (en) Overhead wire position measuring apparatus and method
CN111192283A (en) Height limiting rod detection and height calculation method

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