On-road parking behavior judgment method and system

Abstract

The invention discloses a curb parking behavior judgment method. The curb parking behavior judgment method comprises the steps that an outer side parking space reference line and an inner side parking space reference line in a picture are recognized, and a mark point of each parking space is marked on the outer side parking space reference line and the inner side parking space reference line; detecting a plurality of vehicle frames in the picture and calculating coordinates, width and height of a target vehicle frame; searching a reference parking space corresponding to the target vehicle frame according to the coordinate and the height of the target vehicle frame and the mark point of each parking space; and judging whether the vehicle is parked on the reference parking space according to the coordinate, width and height of the target vehicle frame and the coordinate of the reference parking space. Whether the vehicle is parked on the berth or not is accurately judged by analyzing the line segment defined by the vehicle frame and the berth reference line and the ratio relation of the reference berth and the line segment defined by the berth reference line, and the judgment method is simple; under the condition that the inclination angle of the parking space recognized by the picture is too large, as the proportional relation of the line segments does not change, whether the vehicle is parked on the parking space or not can still be accurately recognized, and therefore adaptability is high.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a method, system, device and computer-readable storage medium for judging on-street parking behavior. Background Art

[0002] On-street parking solutions are an important part of urban traffic management. Through reasonable planning and efficient management of on-street parking resources, the utilization rate of urban space can be effectively improved and the parking problem can be alleviated. This solution has been successfully implemented in many cities, showing obvious social and economic benefits.

[0003] The mainstream parking behavior recognition solution is still the video solution, which uses the YOLO algorithm to identify the vehicle rectangular frame, and then determines the overlap ratio between the vehicle frame and the parking area. However, YOLO detects a projection of a three-dimensional vehicle on a two-dimensional plane, while the parking frame is another plane space perpendicular to the two-dimensional plane. When the parking space is tilted too much, that is, when the slope of the reference line on the side close to the center of the road is small, its area ratio will change significantly, and this method cannot solve and adapt to such changes.

[0004] Based on this, a new solution is needed. Summary of the invention

[0005] The main purpose of the present invention is to provide a method and system for determining on-street parking behavior.

[0006] To achieve the above object, the present invention provides a method for determining on-street parking behavior, comprising the following steps: Identify an outer berth reference line and an inner berth reference line in the picture, and mark a mark point of each berth on the outer berth reference line and the inner berth reference line, wherein the outer berth reference line is a reference line on a side close to the center of the road; Detect multiple vehicle frames in the image, and calculate the coordinates, width, and height of the target vehicle frame; According to the coordinates and height of the target vehicle frame and the marking points of each berth, searching for a reference berth corresponding to the target vehicle frame; and According to the coordinates, width, height of the target vehicle frame and the coordinates of the reference parking space, it is determined whether the vehicle is parked at the reference parking space.

[0007] In the on-street parking behavior judgment method provided by the present invention, the YOLO algorithm is used to detect the multiple vehicle frames in the picture.

[0008] In the on-street parking behavior judgment method provided by the present invention, in the step of searching for a reference berth corresponding to the target vehicle frame based on the coordinates, height and marking points of each berth of the target vehicle frame, if the sum of the ordinate and height of the target vehicle frame is less than the ordinate of the marking point of the berth on the outer berth reference line, the berth is determined to be a reference berth.

[0009] In the on-street parking behavior judgment method provided by the present invention, the step of judging whether the vehicle is parked in the reference parking space according to the coordinates, width, height of the target vehicle frame and the coordinates of the reference parking space includes: Calculating a first ratio of a first length between a bottom edge of a target vehicle frame and a first intersection point to a length of the bottom edge of the vehicle frame, wherein the first intersection point is an intersection point between the bottom edge of the target vehicle frame and the outer berth reference line; calculating a second ratio of a second length between a third vertex and a second intersection of the reference berth and a third length between the third vertex and a third intersection of the reference berth, wherein the third vertex is a point of the reference berth located below the inner berth reference line, the second intersection is an intersection of a horizontal line passing through the third vertex on the X axis and the outer berth reference line, the third intersection is an intersection of a horizontal line passing through the third vertex on the X axis and a vertical line passing through a first vertex on the Y axis of the reference berth, and the first vertex is a point of the reference berth located above the outer berth reference line; and When the difference between the first ratio and the second ratio is smaller than a preset threshold, it is determined that the vehicle is in the reference parking space.

[0010] In addition, to achieve the above-mentioned purpose, the present invention also provides an on-street parking behavior judgment system, comprising: A berth reference line identification and marking module is used to identify an outer berth reference line and an inner berth reference line in the picture, and mark a mark point of each berth on the outer berth reference line and the inner berth reference line, wherein the outer berth reference line is a reference line on the side close to the center of the road; A vehicle frame detection module, used to detect multiple vehicle frames in the picture and calculate the coordinates, width and height of the target vehicle frame; A reference berth search module, used to search for a reference berth corresponding to the target vehicle frame according to the coordinates and height of the target vehicle frame and the marking points of each berth; and The determination module is used to determine whether the vehicle is parked at the reference parking space according to the coordinates, width, height of the target vehicle frame and the coordinates of the reference parking space.

[0011] In the on-street parking behavior judgment system provided by the present invention, the vehicle frame detection module uses the YOLO algorithm to detect the multiple vehicle frames in the picture.

[0012] In the on-street parking behavior judgment system provided by the present invention, the reference parking space search module is used to determine that the parking space is a reference parking space when the sum of the ordinate and the height of the target vehicle frame is less than the ordinate of the marking point of the parking space on the outer parking space reference line.

[0013] In the on-street parking behavior judgment system provided by the present invention, the judgment module includes: a first calculation unit, configured to calculate a first ratio of a first length between a bottom edge of a target vehicle frame and a first intersection point to a length of the bottom edge of the vehicle frame, wherein the first intersection point is an intersection point between the bottom edge of the target vehicle frame and the outer berth reference line; a second calculation unit, configured to calculate a second ratio of a second length between a third vertex and a second intersection of the reference berth and a third length between the third vertex and a third intersection of the reference berth, wherein the third vertex is a point of the reference berth located below the inner berth reference line, the second intersection is an intersection of a horizontal line passing through the third vertex on the X axis and the outer berth reference line, the third intersection is an intersection of a horizontal line passing through the third vertex on the X axis and a vertical line passing through a first vertex on the Y axis of the reference berth, and the first vertex is a point of the reference berth located above the outer berth reference line; and A comparing unit is configured to determine that the vehicle is in the reference berth when a difference between the first ratio and the second ratio is less than a preset threshold.

[0014] The present invention also provides an on-street parking behavior judgment device, comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the on-street parking behavior judgment method as described above are implemented.

[0015] The on-street parking behavior judgment system and method provided by the present invention have the following beneficial effects: the on-street parking behavior judgment method provided by the present invention can accurately judge whether the vehicle is parked in the berth by analyzing the ratio relationship between the line segments defined by the vehicle frame and the berth reference line and the ratio relationship between the reference berth and the line segments defined by the berth reference line, and the judgment method is simple; at the same time, even if the inclination angle of the berth recognized in the image is too large, since the proportional relationship of the line segments will not change, it is still possible to accurately identify whether the vehicle is parked in the berth, so the method has strong adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below. Obviously, the drawings in the following description are only embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on the provided drawings without creative work: Figure 1 It is a flow chart of a method for determining on-street parking behavior provided by one embodiment of the present invention; Figure 2 The figure is a schematic diagram of an application scenario of an on-street parking behavior judgment method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to facilitate understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Typical embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0020] Figure 1 Shown is a flow chart of an on-street parking behavior determination method provided by an embodiment of the present invention. Figure 2 FIG. 1 is a schematic diagram of an application scenario of a method for determining on-street parking behavior provided by an embodiment of the present invention. Figure 2 As shown, the on-street parking behavior judgment method provided by the present invention is mainly used to judge the pictures obtained by the video device above the parking space, that is, according to the installation position and angle of the video device, each picture contains multiple parking spaces. Figure 1 As shown, the on-street parking behavior judgment method includes the following steps: Step S1, identifying an outer berth reference line and an inner berth reference line in the picture, and marking a mark point of each berth on the outer berth reference line and the inner berth reference line, wherein the outer berth reference line is a reference line on a side close to the center of the road; Specifically, in one embodiment of the present invention, after obtaining a picture taken by a video device, firstly, the berth reference lines in the picture are identified, wherein the berth reference lines refer to two parallel lines used to define the berth position, the reference line close to the center of the road is defined as the outer berth reference line, and the other is defined as the inner berth reference line. For example, Figure 2As shown, line segment L1 is an outer berth reference line, and line segment L2 is an inner berth reference line, and a plurality of berths are defined between L1 and L2.

[0021] Specifically, in one embodiment of the present invention, after the berth reference lines in the image are identified, the marking points of each berth are marked on the outer berth reference line and the inner berth reference line respectively. The specific position of each berth is defined by the marking points, for example, Figure 2 In the picture shown, the berth points on the L1 and L2 lines from top to bottom are: M1 (xm1, ym1), N1 (xn1, yn1), M2 (xm2, ym2), N2 (xn2, yn2), M3 (xm3, ym3), N3 (xn3, yn3), and so on.

[0022] Step S2, detecting multiple vehicle frames in the image, and calculating the coordinates, width and height of the target vehicle frame; Specifically, in one embodiment of the present invention, the YOLO algorithm is used to detect multiple vehicle frames in the current image. It can be understood by those skilled in the art that when detecting multiple vehicle frames in the current image, if there are multiple vehicles parked in the berth, multiple vehicle frames will be detected in this step, and then one of the vehicle frames is selected for analysis through subsequent steps S3 and S4. After the analysis, the next vehicle frame is selected for analysis, and so on. For the selected target vehicle frame, the characteristic parameters of the target vehicle frame are obtained, and the characteristic parameters include coordinates P(x, y), width w and height h. Figure 2 In the picture shown, the coordinate origin of the image is the upper left corner of the picture, and the coordinates P(x, y) of the target vehicle frame obtained here are the coordinates of the upper left corner of the vehicle frame.

[0023] Step S3, searching for a reference berth corresponding to the target vehicle frame according to the coordinates and height of the target vehicle frame and the marking points of each berth; Specifically, in one embodiment of the present invention, after obtaining the characteristic parameters of the target vehicle frame, it is necessary to determine the reference berth of the target vehicle frame, that is, determine the berth where the target vehicle frame may park. Specifically, after using the ordinate and height of the target vehicle frame, traverse each berth point on the outer berth reference line in turn, that is, Figure 2 M1 (xm1, ym1), M2 (xm2, ym2), Mi (xmi, ymi) ... etc. on the line segment L1 shown in the figure, when it satisfies That is, in step S2, if the sum of the ordinate and the height of the target vehicle frame is less than the ordinate of the marking point of the berth on the outer berth reference line, the berth is determined to be a reference berth.

[0024] Specifically, in one embodiment of the present invention, after locating the reference berth, the coordinate information of the reference berth is obtained, wherein the point of the reference berth located above the outer berth reference line is defined as the first vertex of the reference berth (i.e. Figure 2 The point P1 (x1, y1) shown in FIG. 1 is a point where the reference berth is located above the inner berth reference line and is defined as the second vertex of the reference berth (i.e. Figure 2 The point P2 (x2, y2) shown in FIG. 1 is a point where the reference berth is located below the inner berth reference line and is defined as the third vertex of the reference berth (i.e. Figure 2 The point P3 (x3, y3) shown in FIG. 1 is a point where the reference berth is located below the outer berth reference line and is defined as the fourth vertex of the reference berth (i.e. Figure 2 The point P4 (x4, y4) shown).

[0025] Step S4, judging whether the vehicle is parked at the reference berth according to the coordinates, width, height of the target vehicle frame and the coordinates of the reference berth; Specifically, in one embodiment of the present invention, first, the intersection of the outer berth reference line L1 and the bottom edge of the target vehicle frame is calculated, which is defined as R1 (x5, y5), where the Y-axis coordinate and the X-axis coordinate are calculated as follows: y5=y+h; The two-point formula of the straight line passing through P1(x1,y1) and P4(x4,y4) is: ; Substituting the coordinate value of y5: y+h, we get the following formula: ; After conversion, the x5 coordinate is: .

[0026] Then, the intersection of the outer berth reference line L1 and the horizontal line passing through the third vertex P3 (x3, y3) of the reference berth is calculated and defined as R2 (x6, y6), where the Y-axis coordinate and the X-axis coordinate are: y6=y3; The two-point formula of the straight line passing through P1(x1,y1) and P4(x4,y4) is: ; Substituting the coordinate value of y6: y3, we get the following formula: ; After conversion, the x6 coordinate is: ; Then, calculate the intersection of the horizontal line of the X axis passing through the third vertex P3 (x3, y3) of the reference berth and the vertical line of the Y axis passing through the first vertex P1 (x1, y1) of the reference berth, and define it as R3 (x7, y7), where the Y axis coordinates and the X axis coordinates are: y7=y3; x7=x1; Finally, the ratio of the length of the bottom edge of the target vehicle frame and the line segment between the third vertex of the reference berth and the intersection R3 after being divided by the outer berth reference line is calculated. Figure 2 As shown, the bottom edge of the target vehicle frame is divided into a1 and b1 by the outer berth reference line L1, and the line segment between the third vertex of the reference berth and the intersection R3 is divided into a2 and b2 by the outer berth reference line L1. The calculation formula of the ratio of the length b2 of the line segment between the third vertex of the reference berth and the intersection R3 distributed inside the berth to the line segment between the third vertex of the reference berth and the intersection R3 is: ; The calculation formula for the ratio of the length b1 of the bottom edge of the target vehicle frame distributed inside the berth to the bottom edge of the target vehicle frame is: .

[0027] According to the analysis of multiple parking data, usually when a vehicle is parked in a parking space, Therefore, when the difference between the two is less than a preset threshold (for example, 0.1), the vehicle is considered to be in the berth.

[0028] Therefore, step S4 includes: Step S41, calculating a first ratio of a first length between a bottom edge of a target vehicle frame and a first intersection point to a length of the bottom edge of the vehicle frame, wherein the first intersection point is an intersection point of the bottom edge of the target vehicle frame and the outer berth reference line; Step S42, calculating a second ratio of a second length between a third vertex of the reference berth and a second intersection point to a third length between the third vertex of the reference berth and a third intersection point, wherein the second intersection point is an intersection point of a horizontal line passing through the X-axis of the third vertex and the outer berth reference line, and the third intersection point is an intersection point of a horizontal line passing through the X-axis of the third vertex and a vertical line passing through the Y-axis of the first vertex of the reference berth; and Step S43: When the difference between the first ratio and the second ratio is smaller than a preset threshold, it is determined that the vehicle is in the reference berth.

[0029] The on-street parking behavior judgment method provided by the present invention can accurately judge whether the vehicle is parked in the parking space by analyzing the ratio relationship between the line segments defined by the vehicle frame and the parking space reference line and the ratio relationship between the reference parking space and the line segments defined by the parking space reference line. The judgment method is simple. At the same time, even if the inclination angle of the parking space recognized in the image is too large, since the ratio relationship of the line segments will not change, it is still possible to accurately identify whether the vehicle is parked in the parking space. Therefore, the method has strong adaptability.

[0030] Correspondingly, the present invention also provides an on-street parking behavior judgment system, comprising: a parking space reference line identification and marking module, used to identify an outer parking space reference line and an inner parking space reference line in a picture, and mark a mark point of each parking space on the outer parking space reference line and the inner parking space reference line, wherein the outer parking space reference line is a reference line on the side close to the center of the road; a vehicle frame detection module, used to detect multiple vehicle frames in the picture, and calculate the coordinates, width and height of the target vehicle frame; a reference parking space search module, used to search for a reference parking space corresponding to the target vehicle frame according to the coordinates, height and mark points of each parking space of the target vehicle frame; and a judgment module, used to judge whether the vehicle is parked at the reference parking space according to the coordinates, width, height of the target vehicle frame and the coordinates of the reference parking space.

[0031] Specifically, in one embodiment of the present invention, the vehicle frame detection module uses the YOLO algorithm to detect the multiple vehicle frames in the picture.

[0032] Specifically, in one embodiment of the present invention, the reference berth search module is used to determine that the berth is a reference berth when the sum of the ordinate and the height of the target vehicle frame is less than the ordinate of a marking point of the berth on the outer berth reference line.

[0033] Specifically, in an embodiment of the present invention, the determination module includes: a first calculation unit, configured to calculate a first ratio of a first length between a bottom side of a target vehicle frame and a first intersection point to a length of the bottom side of the vehicle frame, wherein the first intersection point is an intersection point between the bottom side of the target vehicle frame and the outer berth reference line; a second calculation unit, configured to calculate a second ratio of a second length between a third vertex of the reference berth and a second intersection point to a third length between a third vertex of the reference berth and a third intersection point, wherein the third vertex is a point of the reference berth located below the inner berth reference line, the second intersection point is an intersection point of a horizontal line of an X-axis passing through the third vertex and the outer berth reference line, the third intersection point is an intersection point of a horizontal line of an X-axis passing through the third vertex and a vertical line of an Y-axis passing through a first vertex of the reference berth, the first vertex being a point of the reference berth located above the outer berth reference line; and a comparison unit, configured to determine that the vehicle is in the reference berth when a difference between the first ratio and the second ratio is less than a preset threshold.

[0034] The embodiment of the present invention further provides an on-street parking behavior judgment device, which may include: Memory for storing computer programs; The processor can implement the following steps when executing the computer program stored in the above memory: Identify an outer berth reference line and an inner berth reference line in the image, and mark a mark point of each berth on the outer berth reference line and the inner berth reference line, wherein the outer berth reference line is a reference line on the side close to the center of the road; detect multiple vehicle frames in the image, and calculate the coordinates, width and height of the target vehicle frame; find the reference berth corresponding to the target vehicle frame according to the coordinates, height and mark points of each berth of the target vehicle frame; and determine whether the vehicle is parked at the reference berth according to the coordinates, width, height of the target vehicle frame and the coordinates of the reference berth.

[0035] The embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps can be implemented; Identify an outer berth reference line and an inner berth reference line in the image, and mark a mark point of each berth on the outer berth reference line and the inner berth reference line, wherein the outer berth reference line is a reference line on the side close to the center of the road; detect multiple vehicle frames in the image, and calculate the coordinates, width and height of the target vehicle frame; find the reference berth corresponding to the target vehicle frame according to the coordinates, height and mark points of each berth of the target vehicle frame; and determine whether the vehicle is parked at the reference berth according to the coordinates, width, height of the target vehicle frame and the coordinates of the reference berth.

[0036] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM) > a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0037] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0038] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0039] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and further may be divided into a plurality of submodules or subunits or subcomponents. All features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device so disclosed may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0040] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0041] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the embodiments of the present invention. The present invention may also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0042] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

Claims

1. A method for determining on-street parking behavior, characterized in that: The following steps are involved: Identify an outer berth reference line and an inner berth reference line in the picture, and mark a mark point of each berth on the outer berth reference line and the inner berth reference line, wherein the outer berth reference line is a reference line on a side close to the center of the road; Detect multiple vehicle frames in the image, and calculate the coordinates, width, and height of the target vehicle frame; According to the coordinates and height of the target vehicle frame and the marking points of each berth, searching for a reference berth corresponding to the target vehicle frame; as well as According to the coordinates, width, height of the target vehicle frame and the coordinates of the reference parking space, it is determined whether the vehicle is parked at the reference parking space.

2. The method for determining on-street parking behavior according to claim 1, characterized in that: The multiple vehicle frames in the picture are detected using the YOLO algorithm.

3. The method for determining on-street parking behavior according to claim 1, wherein: In the step of searching for a reference berth corresponding to the target vehicle frame according to the coordinates, height and marking points of each berth of the target vehicle frame, if the sum of the ordinate and height of the target vehicle frame is less than the ordinate of the marking point of the berth on the outer berth reference line, the berth is determined to be a reference berth.

4. The method for determining on-street parking behavior according to claim 1, wherein: The step of determining whether the vehicle is parked at the reference berth according to the coordinates, width, height of the target vehicle frame and the coordinates of the reference berth comprises: Calculating a first ratio of a first length between a bottom edge of a target vehicle frame and a first intersection point to a length of the bottom edge of the vehicle frame, wherein the first intersection point is an intersection point between the bottom edge of the target vehicle frame and the outer berth reference line; calculating a second ratio of a second length between a third vertex and a second intersection of the reference berth and a third length between the third vertex and a third intersection of the reference berth, wherein the third vertex is a point of the reference berth located below the inner berth reference line, the second intersection is an intersection of a horizontal line passing through the third vertex on the X axis and the outer berth reference line, the third intersection is an intersection of a horizontal line passing through the third vertex on the X axis and a vertical line passing through a first vertex on the Y axis of the reference berth, and the first vertex is a point of the reference berth located above the outer berth reference line; and When the difference between the first ratio and the second ratio is smaller than a preset threshold, it is determined that the vehicle is in the reference parking space.

5. A system for determining on-street parking behavior, characterized in that: include: A berth reference line identification and marking module is used to identify an outer berth reference line and an inner berth reference line in the picture, and mark a mark point of each berth on the outer berth reference line and the inner berth reference line, wherein the outer berth reference line is a reference line on the side close to the center of the road; A vehicle frame detection module, used to detect multiple vehicle frames in the picture and calculate the coordinates, width and height of the target vehicle frame; A reference berth search module, used to search for a reference berth corresponding to the target vehicle frame according to the coordinates and height of the target vehicle frame and the marking points of each berth; and The determination module is used to determine whether the vehicle is parked at the reference parking space according to the coordinates, width, height of the target vehicle frame and the coordinates of the reference parking space.

6. The on-street parking behavior judgment system according to claim 5, characterized in that: The vehicle frame detection module uses the YOLO algorithm to detect the multiple vehicle frames in the picture.

7. The on-street parking behavior judgment system according to claim 5, characterized in that: The reference berth search module is used to determine that the berth is a reference berth when the sum of the ordinate and the height of the target vehicle frame is less than the ordinate of a marking point of the berth on the outer berth reference line.

8. The on-street parking behavior judgment system according to claim 5, characterized in that: The determination module comprises: a first calculation unit, configured to calculate a first ratio of a first length between a bottom edge of a target vehicle frame and a first intersection point to a length of the bottom edge of the vehicle frame, wherein the first intersection point is an intersection point between the bottom edge of the target vehicle frame and the outer berth reference line; a second calculation unit, configured to calculate a second ratio of a second length between a third vertex and a second intersection of the reference berth and a third length between the third vertex and a third intersection of the reference berth, wherein the third vertex is a point of the reference berth located below the inner berth reference line, the second intersection is an intersection of a horizontal line passing through the third vertex on the X axis and the outer berth reference line, the third intersection is an intersection of a horizontal line passing through the third vertex on the X axis and a vertical line passing through a first vertex on the Y axis of the reference berth, and the first vertex is a point of the reference berth located above the outer berth reference line; and A comparing unit is used to determine that the vehicle is in the reference berth when a difference between the first ratio and the second ratio is less than a preset threshold.

9. A device for determining on-street parking behavior, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the on-street parking behavior judgment method according to any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images