CN115019547A - Nonstandard in-road parking detection method and system - Google Patents
Nonstandard in-road parking detection method and system Download PDFInfo
- Publication number
- CN115019547A CN115019547A CN202210606713.7A CN202210606713A CN115019547A CN 115019547 A CN115019547 A CN 115019547A CN 202210606713 A CN202210606713 A CN 202210606713A CN 115019547 A CN115019547 A CN 115019547A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- clustering
- berth
- neighborhood
- parking
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 108
- 238000007621 cluster analysis Methods 0.000 claims abstract description 34
- 238000004458 analytical method Methods 0.000 claims description 25
- 230000001788 irregular Effects 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000000034 method Methods 0.000 description 20
- 230000006399 behavior Effects 0.000 description 8
- 230000000694 effects Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
Abstract
The invention discloses a detection method for nonstandard in-road parking, which comprises the following steps that after a vehicle enters a parking space, a vehicle detection frame of the entering vehicle is obtained through a target detection model; performing cluster analysis according to the historical data of the berth and a vehicle detection frame of the driving vehicle; and judging whether the driven vehicle violates the parking according to the clustering result. According to the invention, after a vehicle drives into a certain parking space, a vehicle detection frame of the vehicle is obtained through a target detection model; and then acquiring historical data of the parking space, performing cluster analysis together with the current data, and judging whether the vehicle belongs to illegal parking. Therefore, the detection precision of the illegal parking behavior is improved, the roadside parking management cost is effectively saved, the manual judgment workload is reduced, and roadside parking lot resources are fully utilized.
Description
Technology neighborhood
The invention relates to the field of intelligent parking technology, in particular to a method and a system for detecting nonstandard in-road parking.
Background
Wisdom parking is an important ring in intelligent city construction, and the in-road parking of make full use of urban road is the important component part that realizes wisdom parking. Most car owners can park cars in the parking space line, but few car owners have random parking behaviors, namely, when the cars are parked, the cars partially drive into the parking spaces or park across the parking spaces, and the irregular parking behaviors influence traffic safety and resource use of parking spaces in roads.
At present, high-order videos or video piles are generally used for in-road parking detection, video data are analyzed in real time through AI, and a target detection model and vehicle behavior analysis are used for detecting that a vehicle enters/exits a parking space. For detection of irregular parking, the relative position relationship between the vehicle frame and the parking space frame detected by the target detection model is generally used to judge whether illegal parking is carried out through data calculation. However, in an actual use scene, due to the fact that different scenes such as a near end, a far end, an identical side and an opposite side exist in the installation angle and the position of the camera, the method for judging whether parking is violated by using the matching mode of the vehicle frame and the parking frame is difficult to adapt to various scenes, and meanwhile, the accuracy is low.
Disclosure of Invention
The main purposes of the invention are as follows: aiming at the problems that the existing mode of judging whether the vehicle is parked in violation by using a vehicle frame and parking space frame matching mode is difficult to adapt to various scenes and the accuracy is low, the method and the system for detecting the parking in the non-standard road are provided.
In order to achieve the purpose, the invention provides a nonstandard in-road parking detection method, which comprises the following steps:
after the vehicle drives into the berth, a vehicle detection frame of the driven vehicle is obtained through the target detection model;
performing cluster analysis according to the historical data of the berth and the vehicle detection frame of the driving vehicle; and
and judging whether the driven vehicle is illegally parked according to the clustering result.
In the method for detecting the irregular in-road parking, the step of performing cluster analysis according to the historical data of the berths and the vehicle detection frame of the entering vehicle comprises the following steps:
adjusting clustering parameters for clustering analysis according to the historical data of the berths, wherein the clustering parameters comprise neighborhoods and neighborhood minimum sample numbers;
and carrying out cluster analysis according to the adjusted cluster parameters, the historical data of the berth and the vehicle detection frame of the driving vehicle.
In the method for detecting the irregular in-road parking, the step of adjusting the clustering parameters for clustering analysis according to the historical data of the berth comprises the following steps:
acquiring a neighborhood initial value and a neighborhood minimum sample number initial value of the berth;
increasing the value of the neighborhood minimum number of samples;
increasing the value of the neighborhood;
when the value of the increased neighborhood is larger than a neighborhood preset threshold value, performing cluster analysis on the historical data of the berth by using the adjusted cluster parameters;
and stopping clustering when the proportion of the maximum class sample number to the total sample number obtained by clustering analysis exceeds a proportion threshold, and taking the adjusted values of the neighborhood and the minimum neighborhood sample number as the clustering parameters used by the berth at this time.
In the method for detecting the nonstandard in-road parking, the step of judging whether the driven vehicle parks in violation or not according to the clustering result comprises the following steps:
judging whether the vehicle detection frame of the entering vehicle belongs to the maximum classification of the clustering result, if so, judging that the entering vehicle is normally parked, and if not, calculating the confidence coefficient of the vehicle detection frame of the entering vehicle according to the clustering result:
and when the confidence coefficient exceeds a preset threshold value, judging that the driven vehicle is illegally parked.
In addition, to achieve the above object, the present invention further provides an irregular in-road parking detection system, including:
the detection module is used for obtaining a vehicle detection frame of the driven vehicle through the target detection model after the vehicle drives into the berth;
the analysis module is used for carrying out cluster analysis according to the historical data of the berth and the vehicle detection frame of the driving vehicle; and
and the judging module is used for judging whether the driven vehicle violates the parking rule or not according to the clustering result.
In the system for detecting irregular in-road parking provided by the present invention, the analysis module comprises:
the adjusting unit is used for adjusting clustering parameters for clustering analysis according to the historical data of the berth, and the clustering parameters comprise neighborhoods and the minimum sample numbers of the neighborhoods;
and the clustering unit is used for carrying out clustering analysis according to the adjusted clustering parameters, the historical data of the berth and the vehicle detection frame of the driving vehicle.
In the irregular in-road parking detection system provided by the present invention, the adjusting unit includes:
an initial value obtaining subunit, configured to obtain a neighborhood initial value and a neighborhood minimum sample number initial value of the berth;
the clustering parameter adjusting subunit is used for increasing the value of the neighborhood and the value of the minimum sample number of the neighborhood;
the cluster analysis subunit is used for carrying out cluster analysis on the historical data of the berth by utilizing the adjusted cluster parameters when the increased neighborhood value is greater than a preset neighborhood threshold value;
and the comparison subunit is used for stopping clustering when the proportion of the maximum class sample number obtained by clustering analysis to the total sample number exceeds a proportion threshold value, and taking the adjusted values of the neighborhood and the minimum neighborhood sample number as the clustering parameters used by the berth at this time.
In the system for detecting irregular in-road parking provided by the present invention, the determination module comprises:
the first determination unit is used for determining whether the vehicle detection frame of the incoming vehicle belongs to the maximum classification of the clustering result, if not, the incoming vehicle is preliminarily determined to be illegal parking, and if so, the incoming vehicle is determined to be normal parking;
the confidence coefficient calculation unit is used for calculating the confidence coefficient of the vehicle detection frame of the entering vehicle according to the clustering result when the entering vehicle is preliminarily judged to be the illegal parking:
and the second judging unit is used for judging that the vehicle entering the parking space is illegal when the confidence coefficient exceeds a preset threshold value.
The present invention also provides a computer readable storage medium having stored thereon a computer program for implementing the steps of the irregular in-road parking detection method as described above when executed by a processor.
The system and the method for detecting the nonstandard in-road parking, provided by the invention, have the following beneficial effects: the invention provides a nonstandard in-road parking detection method, which comprises the steps of obtaining a vehicle detection frame of a vehicle through a target detection model after the vehicle drives into a certain parking space; then obtaining the historical data of the berth, and carrying out cluster analysis together with the current data; judging whether the vehicle belongs to illegal parking according to the clustering result; therefore, the system can be suitable for various scenes, the detection precision of illegal parking behaviors is improved, the roadside parking management cost is effectively saved, the manual judgment workload is reduced, and roadside parking lot resources are fully utilized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts:
fig. 1 is a flowchart illustrating a method for detecting an irregular on-road parking according to an embodiment of the present invention.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Exemplary embodiments of the invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
The general idea of the invention is as follows: aiming at the problems that the existing mode of judging whether illegal parking is carried out by utilizing a vehicle frame and parking space frame matching mode is difficult to adapt to various scenes and the accuracy is low, a vehicle detection frame of an owner parking each time presents a relatively obvious clustering phenomenon by collecting the same parking space and analyzing, a certain point of the vehicle detection frame is taken for clustering analysis, and the farther the distance from a clustering core is, the higher the confidence coefficient of the illegal parking is. Therefore, after the vehicle enters a certain parking space, the vehicle detection frame of the vehicle is obtained through the target detection model; then obtaining the historical data of the berth, and carrying out cluster analysis together with the current data; and judging whether the vehicle belongs to the illegal parking according to the clustering result. Therefore, the system can be suitable for various scenes, the detection precision of illegal parking behaviors is improved, the roadside parking management cost is effectively saved, the manual judgment workload is reduced, and roadside parking lot resources are fully utilized.
In order to better understand the technical solutions, the technical solutions will be described in detail below with reference to the drawings and the specific embodiments of the specification, and it should be understood that the embodiments and specific features of the embodiments of the present invention are detailed descriptions of the technical solutions of the present application, and are not limited to the technical solutions of the present application, and the technical features of the embodiments and examples of the present invention may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic diagram illustrating an irregular on-road parking detection method according to an embodiment of the present invention, where the irregular on-road parking detection method includes the following steps:
step S1, after the vehicle enters the parking space, obtaining a vehicle detection frame of the entering vehicle through a target detection model;
specifically, in an embodiment of the present invention, after the vehicle enters the parking lot, a camera acquires a picture of the vehicle parked on the parking lot, and then a vehicle detection frame of the current vehicle is detected by using the target detection model. And selecting the upper left point and the lower right point of the rectangular frame as target points for cluster analysis. The method for detecting the vehicle by using the target detection model to obtain the vehicle detection frame is the prior art, and the method is not repeated herein.
Step S2, performing cluster analysis according to the historical data of the berth and the vehicle detection frame of the driving vehicle;
specifically, in an embodiment of the present invention, after obtaining sample data of a vehicle detection box of a current vehicle entering a parking lot, a density-based clustering algorithm is used to perform cluster analysis on the sample data of the current vehicle and historical data of the parking lot. The density-based clustering algorithm does not need to specify the category number of the clusters, can cluster any shape, and only needs two clustering parameters. Therefore, the detection precision of the illegal parking behavior can be improved by adopting cluster analysis, the workload of manual judgment is reduced, and the roadside parking management cost is effectively saved.
Specifically, in an embodiment of the present invention, the historical data of the berth refers to collecting and storing sample data of the berth in units of berths, and persisting the sample data. A certain number of samples need to be collected for each berth to perform cluster analysis. When a vehicle enters the berth, the camera acquires a picture of the vehicle parked on the berth, and then the target detection model is used for detecting a vehicle detection frame of the current vehicle. And selecting the upper left point and the lower right point of the rectangular frame as target points for cluster analysis, and storing the data of the target points as historical data of the berth. The illegal parking conditions under various scenes can be included by collecting the historical data of the parking space, so that the method disclosed by the invention can be suitable for various scenes.
Specifically, in an embodiment of the present invention, the clustering parameters adopted by the density-based clustering algorithm include:
neighborhood ε: distance threshold, for x j E.g. D, its neighborhood epsilon is the sum x in the sample set D j The number of samples with the distance not more than epsilon; the farther the berth is away from the camera, the smaller the image is in the picture, so that the neighborhood epsilon needs to be dynamically fine-tuned in each use;
neighborhood minimum number of samples minPoints: the smallest number of samples in the neighborhood, if greater than the threshold, is referred to as the core sample.
Further, in an embodiment of the present invention, since the clustering parameters for achieving the optimal clustering effect for the berths in different scenes are different, each berth needs to be adjusted individually. Therefore, in order to obtain the best clustering effect and further improve the detection accuracy, the clustering parameters for the berth need to be finely adjusted after the vehicle is driven into the berth every time. Therefore, step S2 includes:
step S21, adjusting clustering parameters for clustering analysis according to the historical data of the berth;
and step S22, performing cluster analysis according to the adjusted cluster parameters, the historical data of the berths and the vehicle detection frame of the driving vehicle.
Specifically, in an embodiment of the present invention, when the clustering parameter is fine-tuned according to the historical data of the berths, the method includes:
step S211, acquiring a neighborhood initial value and a neighborhood minimum sample number initial value of the berth;
step S212, increasing the minimum number of samples in the neighborhood, for example, increasing 1 each time;
step S213, increasing the neighborhood value, for example, by 1 each time;
step S214, comparing the increased neighborhood value with a neighborhood preset threshold, if the neighborhood value is less than or equal to the neighborhood preset threshold, returning to step S212, and if the neighborhood value is greater than the neighborhood preset threshold, proceeding to step S215;
step S215, performing cluster analysis on the historical data of the berth by using the adjusted neighborhood value and the value of the minimum neighborhood sample number to obtain the cluster number and the sample number of each cluster;
step S216, comparing the proportion of the maximum class of samples to the total number of samples with a proportion threshold, returning to step S213 if the proportion of the maximum class of samples to the total number of samples is less than or equal to the proportion threshold, and proceeding to step S217 if the proportion of the maximum class of samples to the total number of samples is greater than the proportion threshold (for example, 80%);
step S217, stopping clustering, and taking the adjusted neighborhood and the value of the minimum sample number of the neighborhood as the clustering parameter used by the berth this time.
Further, in an embodiment of the present invention, the initial value of the neighborhood minimum sample number may be selected according to a typical scenario, for example, 5; the initial value of the neighborhood is obtained by the following formula:
the ratio of the berth relative picture E1 ═ W1/W2
The initial value eps ═ Es (E1/Rs) of the neighborhood epsilon of the Poise
W1 is the width of a berth frame in a picture, W2 is the width of the picture, Es is a standard value of a neighborhood epsilon, Rs is a standard proportion of the berth relative to the picture, and Rs and Es are obtained by collecting historical data of typical scene berths and averaging. Further, in an embodiment of the present invention, after the adjustment of the clustering parameter of the berth is completed, the historical data and the current data of the berth are taken, and the adjusted clustering parameter is used together for clustering analysis, so that the optimal clustering effect can be obtained.
And step S3, judging whether the vehicle entering the vehicle is illegally parked according to the clustering result.
Specifically, in an embodiment of the present invention, after the adjusted clustering parameter is used to obtain the clustering result of the vehicle entering the parking lot this time, whether the target point of the vehicle detection frame of the vehicle input this time belongs to the maximum classification in the clustering result is analyzed, and if so, it is determined that the vehicle input this time is normally parked; if the target point of the vehicle detection frame of the input vehicle does not belong to the maximum classification in the clustering result, the driving vehicle is preliminarily judged to be illegal parking; and after the vehicle entering the vehicle is preliminarily determined to be the illegal parking, calculating the confidence coefficient of the vehicle detection frame of the vehicle entering the vehicle according to the clustering result, and determining that the vehicle entering the vehicle is the illegal parking when the confidence coefficient exceeds a preset threshold value. Since most of the car owners can park the cars in the parking space line according to the specifications, and only a small number of car owners have illegal parking behaviors, the maximum classification in the clustering result corresponds to the condition of normal parking, and if the clustering result obtained by clustering analysis of the historical data of the current driving-in car and the parking space is that the sample data of the car is not in the maximum classification, the condition that the current driving-in car possibly has illegal parking is indicated; since the farther the distance from the clustering core is, the higher the confidence coefficient of the illegal parking is, whether the vehicle is illegal to park can be finally judged by continuously analyzing the confidence coefficient of the vehicle which is driven in this time, the accuracy of detection is greatly improved by further judging the confidence coefficient, and the condition of misjudgment is avoided.
Further, in an embodiment of the present invention, assuming that the length from the current position to the maximum clustering core is Da, and the distance from the current position to the maximum clustering nearest edge point is Db, the confidence of the current position is (1-Db/Da), and the value range is [0,1 ].
The detection process of the present invention is illustrated in one detailed example below:
1) collecting 100 samples in total for the berth A, calculating the average coordinate of the upper left point of each sample according to the collected sample set, taking the average coordinate as a core point, recording the average coordinate as Pc, and taking the average coordinate as (1621,808) as historical data of the berth A;
2) when a new vehicle is detected to drive into the berth A, the upper left point record of the vehicle detection frame is obtained through the target detection model as follows: p1, value (1624,898);
3) according to the historical data of the berth A, the clustering parameters of the berth A are adjusted, and the adjusted berth parameters are that neighborhood epsilon is 55 and minPoints is 5;
4) forming a new sample set by the newly detected data of the vehicle and the historical data of the berth A, and clustering by using the adjusted clustering parameters to obtain 101 samples in total;
5) the clustering result is: (-1:18, main: 83); a total of two groups, with group ids of-1 and main, respectively
6) Because the clustering result of the vehicle driven into the vehicle belongs to the-1 group, the vehicle is preliminarily judged to possibly stop illegally;
7) finding the point in the main group closest to the coordinates of the detection box, and recording the point as P2 with a value of (1622,809);
8) the calculation of d1 ═ Euclidean distance (P1, Pn), d2 ═ Euclidean distance (P2, Pn), confidence ═ d2/d1
9) If the confidence is greater than 0.8 (configurable), the parking violation is considered.
Correspondingly, the invention also provides an irregular in-road parking detection system, which comprises: the detection module is used for obtaining a vehicle detection frame of the driven vehicle through the target detection model after the vehicle drives into the berth; the analysis module is used for carrying out cluster analysis according to the historical data of the berth and the vehicle detection frame of the driving vehicle; and the judging module is used for judging whether the driven vehicle violates the parking according to the clustering result.
Specifically, in an embodiment of the present invention, after the vehicle enters the parking space, the camera acquires a picture of the vehicle parked on the parking space, and then the detection module detects the vehicle detection frame of the current vehicle by using the target detection model. And selecting the upper left point and the lower right point of the rectangular frame as target points for cluster analysis.
Specifically, in an embodiment of the present invention, since the clustering parameters for achieving the optimal clustering effect for the berths in different scenes are different, each berth needs to be adjusted individually. Therefore, in order to obtain the best clustering effect and further improve the detection accuracy, the clustering parameters for the berth need to be finely adjusted after the vehicle is driven into the berth every time. Thus, the analysis module comprises: the adjusting unit is used for adjusting clustering parameters for clustering analysis according to the historical data of the berth, and the clustering parameters comprise neighborhoods and the minimum sample number of the neighborhoods; and the clustering unit is used for carrying out clustering analysis according to the adjusted clustering parameters, the historical data of the berth and the vehicle detection frame of the driving vehicle.
Further, in an embodiment of the present invention, the adjusting unit includes:
the initial value acquisition subunit is used for acquiring a neighborhood initial value and a neighborhood minimum sample number initial value of the berth;
the clustering parameter adjusting subunit is used for increasing the value of the neighborhood and the value of the minimum sample number of the neighborhood;
the cluster analysis subunit is used for carrying out cluster analysis on the historical data of the berth by utilizing the adjusted cluster parameters when the increased neighborhood value is greater than a preset neighborhood threshold value;
and the comparison subunit is used for stopping clustering when the proportion of the maximum class sample number obtained by clustering analysis to the total sample number exceeds a proportion threshold value, and taking the adjusted values of the neighborhood and the minimum neighborhood sample number as the clustering parameters used by the berth at this time.
Specifically, in an embodiment of the present invention, since most vehicle owners park vehicles in the parking space line according to the specification, and only a few vehicle owners have illegal parking behaviors, the maximum classification in the clustering result corresponds to the normal parking condition, and if the clustering result obtained by performing cluster analysis on the historical data of the vehicle entering this time and the parking space is that the sample data of the vehicle is not in the maximum classification, it indicates that the vehicle entering this time may have illegal parking; because the farther the distance from the clustering core is, the higher the confidence coefficient of illegal parking is, whether the vehicle violates the parking can be finally judged by continuously analyzing the confidence coefficient of the vehicle driven in this time, the accuracy of detection is greatly improved by further judging the confidence coefficient, and the condition of misjudgment is avoided. Therefore, the determination module comprises:
the first judgment unit is used for judging whether the vehicle detection frame of the entering vehicle belongs to the maximum classification of the clustering result, if not, the entering vehicle is preliminarily judged to be illegal parking, and if so, the entering vehicle is judged to be normal parking;
and the confidence coefficient calculation unit is used for calculating the confidence coefficient of the vehicle detection frame of the entering vehicle according to the clustering result when the entering vehicle is preliminarily judged to be the illegal parking:
and the second judging unit is used for judging that the vehicle entering the parking system is illegally parked when the confidence coefficient exceeds a preset threshold value.
The embodiment of the invention also provides an irregular in-road parking detection device, which comprises:
a memory for storing a computer program;
the processor, when used for executing the computer program stored in the memory, can realize the following steps:
after the vehicle drives into the berth, a vehicle detection frame of the driven vehicle is obtained through the target detection model; performing cluster analysis according to the historical data of the berth and the vehicle detection frame of the driving vehicle; and judging whether the driven vehicle is illegally parked according to the clustering result.
The embodiment of the invention also provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program can realize the following steps when being executed by a processor;
after the vehicle drives into the berth, a vehicle detection frame of the driven vehicle is obtained through the target detection model; performing cluster analysis according to the historical data of the berth and the vehicle detection frame of the driving vehicle; and judging whether the driven vehicle is illegally parked according to the clustering result.
The computer-readable storage medium may include: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM) > Random Access Memory (RAM), a magnetic disk, or an optical disk.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and placed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that although some embodiments herein include some features included in other embodiments rather than others, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in accordance with embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media 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 in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Claims (10)
1. An irregular in-road parking detection method is characterized by comprising the following steps:
after the vehicle drives into the berth, a vehicle detection frame of the driven vehicle is obtained through the target detection model;
performing cluster analysis according to the historical data of the berth and the vehicle detection frame of the driving vehicle; and
and judging whether the driven vehicle is illegally parked according to the clustering result.
2. The irregular in-road parking detection method according to claim 1, wherein the step of performing cluster analysis based on the historical data of the berth and the vehicle detection frame of the incoming vehicle comprises:
adjusting clustering parameters for clustering analysis according to the historical data of the berth, wherein the clustering parameters comprise neighborhoods and the minimum sample numbers of the neighborhoods;
and carrying out cluster analysis according to the adjusted cluster parameters, the historical data of the berth and the vehicle detection frame of the driving vehicle.
3. The irregular in-road parking detection method of claim 2 wherein the step of adjusting the clustering parameters for cluster analysis based on the historical data of the berths comprises:
acquiring a neighborhood initial value and a neighborhood minimum sample number initial value of the berth;
increasing the value of the neighborhood minimum number of samples;
increasing the value of the neighborhood;
when the value of the increased neighborhood is larger than a neighborhood preset threshold value, performing cluster analysis on the historical data of the berth by using the adjusted cluster parameters;
and stopping clustering when the proportion of the maximum class sample number to the total sample number obtained by clustering analysis exceeds a proportion threshold, and taking the adjusted values of the neighborhood and the minimum neighborhood sample number as the clustering parameters used by the berth at this time.
4. The irregular in-road parking detection method according to claim 1, wherein the step of determining whether the incoming vehicle is parking in violation based on the clustering result comprises:
judging whether the vehicle detection frame of the entering vehicle belongs to the maximum classification of the clustering result, if so, judging that the entering vehicle is normally parked, and if not, calculating the confidence coefficient of the vehicle detection frame of the entering vehicle according to the clustering result:
and when the confidence coefficient exceeds a preset threshold value, judging that the driven vehicle is illegally parked.
5. An irregular in-road parking detection system, comprising:
the detection module is used for obtaining a vehicle detection frame of the driven vehicle through the target detection model after the vehicle drives into the berth;
the analysis module is used for carrying out cluster analysis according to the historical data of the berth and the vehicle detection frame of the driving vehicle; and
and the judging module is used for judging whether the driven vehicle violates the parking rule or not according to the clustering result.
6. The irregular in-road parking detection system of claim 5 wherein the analysis module comprises:
the adjusting unit is used for adjusting clustering parameters for clustering analysis according to the historical data of the berth, and the clustering parameters comprise neighborhoods and the minimum sample numbers of the neighborhoods;
and the clustering unit is used for carrying out clustering analysis according to the adjusted clustering parameters, the historical data of the berth and the vehicle detection frame of the driving vehicle.
7. The irregular on-road parking detection system of claim 6 wherein the adjustment unit comprises:
an initial value obtaining subunit, configured to obtain a neighborhood initial value and a neighborhood minimum sample number initial value of the berth;
the clustering parameter adjusting subunit is used for increasing the value of the neighborhood and the value of the minimum sample number of the neighborhood;
the cluster analysis subunit is used for carrying out cluster analysis on the historical data of the berth by utilizing the adjusted cluster parameters when the increased neighborhood value is greater than a preset neighborhood threshold value;
and the comparison subunit is used for stopping clustering when the proportion of the maximum class sample number obtained by clustering analysis to the total sample number exceeds a proportion threshold value, and taking the adjusted values of the neighborhood and the minimum neighborhood sample number as the clustering parameters used by the berth at this time.
8. The irregular in-road parking detection system of claim 5 wherein the decision module comprises:
the first determination unit is used for determining whether the vehicle detection frame of the incoming vehicle belongs to the maximum classification of the clustering result, if not, the incoming vehicle is preliminarily determined to be illegal parking, and if so, the incoming vehicle is determined to be normal parking;
the confidence coefficient calculation unit is used for calculating the confidence coefficient of the vehicle detection frame of the entering vehicle according to the clustering result when the entering vehicle is preliminarily judged to be the illegal parking:
and the second judging unit is used for judging that the vehicle entering the parking space is illegal when the confidence coefficient exceeds a preset threshold value.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, carries out the steps of the irregular in-road parking detection method according to any one of claims 1 to 4.
10. An irregular in-road parking detection device, characterized by comprising a processor and a memory, said memory storing a computer program which, when executed by the processor, implements the steps of the irregular in-road parking detection method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210606713.7A CN115019547A (en) | 2022-05-31 | 2022-05-31 | Nonstandard in-road parking detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210606713.7A CN115019547A (en) | 2022-05-31 | 2022-05-31 | Nonstandard in-road parking detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115019547A true CN115019547A (en) | 2022-09-06 |
Family
ID=83071110
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210606713.7A Pending CN115019547A (en) | 2022-05-31 | 2022-05-31 | Nonstandard in-road parking detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115019547A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105427606A (en) * | 2015-12-24 | 2016-03-23 | 重庆云途交通科技有限公司 | Pavement condition information acquisition and release method |
| CN106023595A (en) * | 2016-06-13 | 2016-10-12 | 北京精英智通科技股份有限公司 | Abnormal parking determination method, abnormal parking determination device and dome camera |
| US20170098376A1 (en) * | 2014-12-02 | 2017-04-06 | Kevin Sunlin Wang | Method and system for avoidance of parking violations |
| CN107289974A (en) * | 2017-07-14 | 2017-10-24 | 芜湖泰领信息科技有限公司 | The positioning calibration method and system of public bicycles |
| KR20190005343A (en) * | 2017-07-06 | 2019-01-16 | (주) 알티솔루션 | Movable regulation system for stoping and parking car and that of method for identifying drive on or not |
| KR102011624B1 (en) * | 2019-03-29 | 2019-08-16 | 주식회사 넥스파시스템 | Improved vehicle detection method abnormal illegal parking vehicle system |
| CN111565360A (en) * | 2020-04-26 | 2020-08-21 | 上海钧正网络科技有限公司 | Vehicle parking position detection method and device, computer equipment and storage medium |
| CN111862625A (en) * | 2020-07-13 | 2020-10-30 | 深圳前海华夏智信数据科技有限公司 | In-road parking video pile and parking management method |
| US20200394425A1 (en) * | 2019-06-11 | 2020-12-17 | Tata Consultancy Services Limited | System and method for detecting on-street parking violations |
| CN112289037A (en) * | 2020-10-29 | 2021-01-29 | 南通中铁华宇电气有限公司 | Motor vehicle illegal parking detection method and system based on high visual angle under complex environment |
| CN112598146A (en) * | 2020-12-22 | 2021-04-02 | 南京领行科技股份有限公司 | Method and device for determining parking position, electronic equipment and readable storage medium |
| CN113221677A (en) * | 2021-04-26 | 2021-08-06 | 阿波罗智联(北京)科技有限公司 | Track abnormity detection method and device, road side equipment and cloud control platform |
-
2022
- 2022-05-31 CN CN202210606713.7A patent/CN115019547A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170098376A1 (en) * | 2014-12-02 | 2017-04-06 | Kevin Sunlin Wang | Method and system for avoidance of parking violations |
| CN105427606A (en) * | 2015-12-24 | 2016-03-23 | 重庆云途交通科技有限公司 | Pavement condition information acquisition and release method |
| CN106023595A (en) * | 2016-06-13 | 2016-10-12 | 北京精英智通科技股份有限公司 | Abnormal parking determination method, abnormal parking determination device and dome camera |
| KR20190005343A (en) * | 2017-07-06 | 2019-01-16 | (주) 알티솔루션 | Movable regulation system for stoping and parking car and that of method for identifying drive on or not |
| CN107289974A (en) * | 2017-07-14 | 2017-10-24 | 芜湖泰领信息科技有限公司 | The positioning calibration method and system of public bicycles |
| KR102011624B1 (en) * | 2019-03-29 | 2019-08-16 | 주식회사 넥스파시스템 | Improved vehicle detection method abnormal illegal parking vehicle system |
| US20200394425A1 (en) * | 2019-06-11 | 2020-12-17 | Tata Consultancy Services Limited | System and method for detecting on-street parking violations |
| CN111565360A (en) * | 2020-04-26 | 2020-08-21 | 上海钧正网络科技有限公司 | Vehicle parking position detection method and device, computer equipment and storage medium |
| CN111862625A (en) * | 2020-07-13 | 2020-10-30 | 深圳前海华夏智信数据科技有限公司 | In-road parking video pile and parking management method |
| CN112289037A (en) * | 2020-10-29 | 2021-01-29 | 南通中铁华宇电气有限公司 | Motor vehicle illegal parking detection method and system based on high visual angle under complex environment |
| CN112598146A (en) * | 2020-12-22 | 2021-04-02 | 南京领行科技股份有限公司 | Method and device for determining parking position, electronic equipment and readable storage medium |
| CN113221677A (en) * | 2021-04-26 | 2021-08-06 | 阿波罗智联(北京)科技有限公司 | Track abnormity detection method and device, road side equipment and cloud control platform |
Non-Patent Citations (2)
| Title |
|---|
| 包磊;: "基于聚类距离计算的船舶轨迹异常检测方法", 舰船电子工程, no. 09, 20 September 2020 (2020-09-20) * |
| 李;孙静怡;张旭东;: "城市停车状况的模糊聚类分析", 昆明理工大学学报(理工版), no. 02, 15 April 2008 (2008-04-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11380104B2 (en) | Method and device for detecting illegal parking, and electronic device | |
| CN111339994B (en) | Method and device for judging temporary illegal parking | |
| CN103824452B (en) | A kind of peccancy parking detector based on panoramic vision of lightweight | |
| CN102231236B (en) | Method and device for counting vehicles | |
| WO2017125063A1 (en) | Processing method and device for vehicle traffic violation | |
| CN108597219B (en) | Road section pedestrian crossing control method based on machine vision | |
| CN111815959B (en) | Vehicle violation detection method and device and computer readable storage medium | |
| CN106373426A (en) | Computer vision-based parking space and illegal lane occupying parking monitoring method | |
| CN108961825B (en) | Parking lot parking guiding method based on vehicle secondary identification | |
| CN102867415B (en) | Video detection technology-based road jam judgement method | |
| CN112509325B (en) | Video deep learning-based off-site illegal automatic discrimination method | |
| CN204856897U (en) | It is detection device violating regulations in abscission zone territory that motor vehicle stops promptly | |
| CN112289037A (en) | Motor vehicle illegal parking detection method and system based on high visual angle under complex environment | |
| CN113450578B (en) | Traffic violation event evidence obtaining method, device, equipment and system | |
| CN103150910A (en) | Cross automatic capturing and analysis method for yellow light running traffic violation vehicle | |
| CN115019547A (en) | Nonstandard in-road parking detection method and system | |
| CN113011331A (en) | Method and device for detecting whether motor vehicle gives way to pedestrians, electronic equipment and medium | |
| CN114463416A (en) | Vehicle lane change detection method and device, electronic equipment and storage medium | |
| CN111160183A (en) | Method and device for detecting red light running of vehicle | |
| CN114898309A (en) | City intelligent inspection vehicle system and inspection method based on visual AI technology | |
| CN115294774A (en) | Non-motor vehicle road illegal parking detection method and device based on deep learning | |
| CN113177443A (en) | Method for intelligently identifying road traffic violation based on image vision | |
| CN114141022B (en) | Emergency lane occupation behavior detection method and device, electronic equipment and storage medium | |
| CN115187886A (en) | Vehicle violation detection method and device and electronic equipment | |
| CN114038209A (en) | Bus lane occupation processing method, device and equipment |
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 |