CN113112813B - Illegal parking detection method and device - Google Patents
Illegal parking detection method and device Download PDFInfo
- Publication number
- CN113112813B CN113112813B CN202110199614.7A CN202110199614A CN113112813B CN 113112813 B CN113112813 B CN 113112813B CN 202110199614 A CN202110199614 A CN 202110199614A CN 113112813 B CN113112813 B CN 113112813B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- parking
- image
- license plate
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a method and a device for detecting illegal parking. The illegal parking detection method comprises the following steps: performing image detection on the image frame to detect a vehicle and a predetermined fixed object in the image frame; tracking the vehicle and the predetermined fixed object based on the continuously acquired image frames, and determining whether the relative position between the vehicle and the predetermined fixed object changes within a preset time; and if the parking position of the vehicle is not changed and is a no-parking area, determining that the vehicle parks illegally. The application can improve the accuracy and the applicability of detecting the illegal parking vehicle.
Description
Technical Field
The application relates to the technical field of images, in particular to a method and a device for detecting illegal parking.
Background
With the rapid development of national economy, the number of motor vehicles is rapidly increased, and effective vehicle management becomes an important subject. The illegal parking is a very common traffic problem, and a great number of vehicles occupy pedestrian lanes and emergency lanes, which brings great harm and potential safety hazards to traffic. In the prior art, illegal parking is discovered and processed mainly by means of manual monitoring and patrol of a traffic police, the method is low in efficiency, and extremely large manpower and material resources are consumed. With the development of science and technology, illegal parking can be judged through videos of fixed monitoring point positions, but the method has high requirements on the density of the deployed point positions, and the condition that license plates cannot be seen occurs when parking is dense.
Disclosure of Invention
The application provides a method and a device for detecting illegal parking, which can improve the accuracy and the adaptability of detection of illegal parking vehicles.
In order to achieve the above purpose, the present application provides a method for detecting illegal parking, which includes:
performing image detection on the image frames to detect a vehicle and a predetermined fixed object in the image frames;
tracking the vehicle and the predetermined fixed object based on the continuously acquired image frames, and determining whether the relative position between the vehicle and the predetermined fixed object changes within a preset time;
and if the parking position of the vehicle is not changed and is a no-parking area, determining that the vehicle parks illegally.
Wherein determining whether a relative position between the vehicle and a predetermined stationary object within a preset time changes comprises:
determining whether the change value of each included angle of a graph formed by the vehicle center point and the corresponding preset fixed object center point within preset time exceeds a first threshold value;
if the parking position of the vehicle is not changed and the parking position of the vehicle is a no-parking area, determining that the vehicle parks in a violation of regulation, comprising the following steps:
and if the parking position of the vehicle is the no-parking area, determining that the vehicle parks in a violation of regulation.
The method includes the steps of tracking a vehicle and a preset fixed object based on continuously acquired image frames, and determining whether a variation value of each included angle of a graph formed by a vehicle center point and a corresponding preset fixed object center point within preset time exceeds a first threshold value, wherein the method includes the following steps:
calculating the degree of each included angle of a graph formed by the vehicle center point and the corresponding preset fixed object center point in each frame of image frame;
determining the maximum value and the minimum value of each included angle of the graph within preset time;
calculating the difference value between the maximum value and the minimum value of each included angle to obtain the change value of each included angle;
it is determined whether the maximum value of the variation values of all the included angles in the graph exceeds a first threshold value.
Wherein tracking the vehicle and the predetermined stationary object previously comprises:
selecting two preset fixed objects as preset fixed objects corresponding to the vehicle;
calculating the degree of each included angle of a graph formed by the vehicle center point and the corresponding preset fixed object center point in each frame of image frame, and the method comprises the following steps:
and calculating the degree of each included angle of a triangle formed by the vehicle center point and the corresponding preset fixed object center point in each frame.
Wherein, if all do not exceed first threshold value, and when the parking position of vehicle was the forbidden parking district, the vehicle parking violating the regulations includes:
responding to the graph, wherein the change value of each included angle does not exceed a first threshold value;
and confirming whether the parking position of the vehicle is a no-parking area or not based on the preset traffic rule and the parking position of the vehicle.
Wherein, confirm whether the parking position of vehicle is the forbidden parking district based on presetting traffic rules and the parking position of vehicle, include:
if the vehicle is parked on a sidewalk or a non-motor vehicle lane, the parking position is not in the parking space wire frame, and no parking indicator indicates that the parking position allows parking, determining that the parking position is a no-parking area;
and if the vehicle is parked in the motor vehicle lane, the signal lamp indicating the vehicle to run is a green lamp, and the number of the vehicles with the speed lower than the fifth threshold value on the motor vehicle lane is less than the third threshold value, the parking position is determined to be a no-parking area.
Wherein, confirm the vehicle parks violating the regulations, later include:
collecting the images of the parking positions of the vehicles and the images of the license plates of the vehicles, identifying the license plates of the vehicles, and determining the license plate numbers of the vehicles which illegally park;
and uploading the image of the vehicle parking position, the image of the vehicle license plate, the license plate number and the video recording of the vehicle to a violation punishment auditing system.
Wherein, confirm the vehicle parks in violation of regulations, later include:
detecting whether a person is in the vehicle;
if the person is present, sending out a prompt signal;
and if the vehicle does not leave the forbidden parking area under the prompt signal or no person exists in the vehicle, collecting the image of the parking position of the vehicle and the image of the license plate of the vehicle, identifying the license plate of the vehicle and determining the license plate number of the vehicle which parks against the regulations.
The method comprises the following steps of collecting images of vehicle parking positions and images of vehicle license plates, identifying the license plates of the vehicles, and determining the license plates of vehicles parked in a violation manner, wherein the method comprises the following steps:
the image frame is obtained by shooting by an unmanned aerial vehicle, if the image shot by the current position of the unmanned aerial vehicle does not contain clear license plate information of the vehicle; adjusting the position of the unmanned aerial vehicle until the image shot by the unmanned aerial vehicle contains clear vehicle license plate information; or the like, or a combination thereof,
the image frame is shot by a rotating ball machine, and if the image shot by the current position of the rotating ball machine does not contain clear license plate information; and adjusting the shooting angle of the rotating ball machine until the image shot by the rotating ball machine contains clear vehicle license plate information.
In order to achieve the above object, the present application provides a illegal parking detection device, which includes a processor; the processor is used for executing instructions to realize the steps of the method.
To achieve the above object, the present application provides a computer-readable storage medium for storing instructions/program data that can be executed to implement the above method.
Whether the vehicle is in a static state or not is judged according to the change condition of the relative position between the vehicle and the predetermined fixed object within the preset time confirmed based on the predetermined fixed object, the accuracy rate of judging whether the vehicle stops or not can be improved in a mode of taking the predetermined fixed object of the image frame as reference, and therefore the accuracy rate of judging whether the vehicle stops violating the regulations can be improved.
Drawings
FIG. 1 is a schematic flow chart diagram of one embodiment of the illegal parking detection method;
FIG. 2 is a schematic flow chart diagram of another embodiment of the illegal parking detection method;
FIG. 3 is a schematic structural diagram of an embodiment of the illegal parking detection device;
FIG. 4 is a schematic structural diagram of an embodiment of a computer-readable storage medium according to the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the illegal parking detection method and apparatus provided by the present application will be described in further detail with reference to the accompanying drawings and the detailed description.
Referring to fig. 1 in detail, fig. 1 is a schematic flow chart of a first embodiment of the illegal parking detection method according to the present application. The illegal parking detection method comprises the following steps. It should be noted that the following numbers are only used for simplifying the description, and are not intended to limit the execution order of the steps, and the execution order of the steps in the present embodiment may be arbitrarily changed without departing from the technical idea of the present application.
S101: image detection is performed on the image frames to detect the vehicle and the predetermined fixed object in the image frames.
And performing image detection on the image frames to detect the vehicle and the predetermined fixed object in the image frames, confirming whether the vehicle is in a static state or not based on the predetermined fixed object, and determining that the vehicle illegally parks if the vehicle is in the static state and the parking area of the vehicle is a no-parking area.
The predetermined fixed object may be a reference object with a preset fixed position, for example, an object such as a tree, a traffic light, a telegraph pole, a flower bed, or a building. Specifically, the predetermined fixed object may be recognized by a deep learning model, for example, the predetermined fixed object in the image frame may be detected based on an AI deep learning target detection recognition algorithm.
Alternatively, a deep learning model may be used to detect vehicles in the image frames. The vehicle and the predetermined fixed object in the image frame may be detected by using the same deep learning model, or the vehicle and the predetermined fixed objects in the image frame may be detected by using a plurality of deep learning models.
Before step S101, the deep learning model may be trained by using a sample training set, so that the trained deep learning model can detect a vehicle and/or a plurality of predetermined fixed objects in an image. Wherein the sample training set may comprise a number of images comprising vehicles and/or predetermined stationary objects.
S102: and tracking the vehicle and the predetermined fixed object based on the continuously acquired image frames, and determining whether the relative position between the vehicle and the predetermined fixed object changes within a preset time.
After the vehicle and the predetermined fixed object in the image frame are detected based on step S101, the vehicle and the predetermined fixed object may be tracked based on the continuously acquired image frame, and it is determined whether the relative position between the vehicle and the predetermined fixed object changes within the preset time, if it is determined that the relative position between the vehicle and the predetermined fixed object does not change, it is determined that the vehicle is in a stationary state, and then it may be determined whether the position where the vehicle is parked is a no-parking zone, so as to determine whether the vehicle parks in violation of the vehicle.
It is to be understood that, after the vehicle and the predetermined fixed objects in the image frame are detected, a plurality of predetermined fixed objects may be selected for each vehicle in the image frame from all the predetermined fixed objects in the image frame, the plurality of predetermined fixed objects selected for each vehicle may be used as the predetermined fixed objects corresponding to each vehicle, and then it may be confirmed whether each vehicle is in a stationary state using the selected plurality of predetermined fixed objects as a reference in step S102. It is understood that the predetermined fixed object corresponding to the vehicle is not always constant, and when it is determined that the vehicle is moving based on the tracking result of the vehicle or when an image including the vehicle and the predetermined fixed object corresponding thereto is not captured, the predetermined fixed object corresponding to the vehicle may be newly selected for the vehicle so as to determine whether the vehicle is in a stationary state in real time.
Different predetermined fixed objects can be selected for different vehicles, and of course, in other embodiments, the same predetermined fixed object can be selected for different vehicles. Preferably, a plurality of predetermined fixed objects which are closer to each vehicle can be selected for each vehicle, so as to avoid that images containing the vehicles and the corresponding predetermined fixed objects are not easy to capture due to the fact that the distance between the predetermined fixed objects and the vehicles is longer, and avoid that missed detection is caused by the fact that the included angle between the predetermined fixed objects and the images formed by the vehicles is not changed greatly due to the fact that the distance between the predetermined fixed objects and the vehicles is longer. Furthermore, two predetermined fixed objects which are close to each vehicle and located on different sides of a road where the vehicle is located can be selected for each vehicle, so that the running track of the vehicle and the straight line where the two fixed objects are located are prevented from being approximately parallel due to the fact that the two predetermined fixed objects are located on the same side, and the accuracy of vehicle state detection is improved.
After the predetermined fixed object is selected for each vehicle, it is possible to confirm whether or not the relative position between the vehicle and the predetermined fixed object is changed within a predetermined time by any of the following methods.
Firstly, the central points of the vehicle and the preset fixed objects can be used as tracking points to judge whether the change value of the linear distance between the vehicle and the preset fixed objects exceeds a sixth threshold value; if the relative position between the vehicle and the preset fixed object does not change within the preset time, determining that the relative position between the vehicle and the preset fixed object does not change; and if the distance exceeds the sixth threshold, confirming that the relative position between the vehicle and the preset fixed object is changed within the preset time, so as to reduce the detection error caused by the change of the visual angle of the shooting equipment.
The sixth threshold may be set according to an actual situation, and is not limited herein. In addition, the sixth threshold value may have a certain relationship with the vehicle body length, for example, the sixth threshold value is 3 times the vehicle body length.
Secondly, after the vehicle and the corresponding preset fixed object are detected from the image frame, the center point of the vehicle and the center point of each preset fixed object corresponding to the vehicle can be determined; then determining the degree of each included angle of a graph formed by the vehicle center point and the corresponding at least two preset fixed object center points; then, according to the multi-frame image frames in the preset time, determining the change value of each included angle in the graph formed by the vehicle and the corresponding preset fixed object center point in the preset time, and then judging whether the change value of each included angle in the graph formed by the vehicle center point and the corresponding preset fixed object center point exceeds a first threshold value; if the first threshold value is not exceeded, confirming that the relative position between the vehicle and the preset fixed object is not changed within the preset time; and if the first threshold value is exceeded, confirming that the relative position between the vehicle and the preset fixed object is changed within the preset time.
More specifically, the maximum value and the minimum value of each included angle of a graph formed by a vehicle and the center point of a corresponding predetermined fixed object within preset time can be determined based on multi-frame image frames within preset time; and then calculating the difference value between the maximum value and the minimum value of each included angle to obtain the change value of each included angle. Of course, the variation value of each included angle of the graph formed by the vehicle and the corresponding predetermined fixed object center point within the preset time can be calculated in other implementation manners.
Preferably, after determining the change value of each included angle in a graph formed by the vehicle and the corresponding center point of the predetermined fixed object within the preset time, determining whether the maximum value of the change values of all included angles in the graph exceeds a first threshold value; if the maximum value does not exceed the first threshold value, the change values of all included angles in the image do not exceed the first threshold value; if the maximum value exceeds a first threshold value, the change value of at least part of included angles in the image exceeds the first threshold value.
The preset time and the first threshold may be set according to an actual situation, and are not limited herein. The preset time may be set to be slightly longer so as to avoid that the vehicle state cannot be accurately judged due to too short time, for example, the preset time may be 1min or 5 min. Of course, in order to improve the detection rate, a more appropriate first threshold may be determined based on the height of the device for capturing the image frame and the preset time, so that the vehicle can be indicated as being in a stopped state by "the change value of all the included angles in the image does not exceed the first threshold".
In addition, if the device for capturing the image frame is a mobile device, for example, an unmanned aerial vehicle, the first threshold may be preset, and the relationship between the height H, the moving speed V, and the preset time T of the device for capturing the image frame may be based on the first threshold, so as to improve the detection accuracy.
For example, assuming that the first threshold is 20, in order to reduce the influence of the change of the angle of view of the object caused by the movement of the drone, the relationship between the height H of the image capturing device, the moving speed V, and the preset time T is constrained to V × T <0.5H, that is, the farthest straight distance that the image capturing device moves in the preset time cannot be greater than half of the height.
S103: and if the parking position of the vehicle is not changed and is a no-parking area, determining that the vehicle parks illegally.
After the relative position between the vehicle and the corresponding predetermined fixed object is determined not to be changed through the step S102, the vehicle can be judged to be in a static state, at this time, whether the parking position of the vehicle is a no-parking area or not can be judged, and if the parking position of the vehicle is the no-parking area, the vehicle is confirmed to be parked illegally.
Whether the parking position of the vehicle is a no-parking zone may be confirmed based on preset traffic rules and the parking position of the vehicle.
More specifically, the method for determining the no-parking area may include: if the vehicle is parked on a sidewalk or a non-motor vehicle lane, the parking position is not in the parking space wire frame, and no parking indicator indicates that the parking position allows parking, determining that the parking position is a no-parking area; if the vehicle is parked in the motor vehicle lane, the signal lamp for indicating the vehicle to run is a green lamp, and the number of the vehicles on the motor vehicle lane is less than a third threshold value, determining that the parking position is a no-parking area; the no-parking area other than the no-parking area may be determined by other implementation manners.
In addition, if the distance between the parking position of the vehicle and the lane is larger than a second threshold value, determining that the parking position of the vehicle is not a no-parking area; or if the vehicle is parked on the sidewalk or the non-motor vehicle lane and the parking position of the vehicle is in the parking space wire frame, determining that the parking position of the vehicle is not the no-parking area; or if the vehicle is parked on a sidewalk or a non-motor vehicle lane, the vehicle is not parked in the wire frame of the parking space, but the parking indicator indicates that the parking position of the vehicle allows parking, the parking position is determined not to be a no-parking area; or if the vehicle is parked in the motor vehicle lane, the signal lamp indicating the vehicle to run is a red lamp, and the distance between the vehicle and the previous vehicle or the zebra crossing is smaller than a fourth threshold value, determining that the parking position is not the no-parking area; or if the vehicles are parked in the motor vehicle lane, the signal lamps indicating the vehicles to run are green lamps, and the number of the vehicles with the speed lower than the fifth threshold value on the motor vehicle lane where the vehicles are located is more than the third threshold value, namely the motor vehicle lane where the vehicles are located is in a congestion state, the parking position is not the no parking area 8230, 8230is confirmed, wherein the vehicles with the speed lower than the fifth threshold value refer to the vehicles in a stop state and/or a slow running state.
The third threshold, the fourth threshold, and the fifth threshold may be set according to actual conditions, and are not limited herein. For example, the fifth threshold may be 5m/min.
In the embodiment, whether the vehicle is in a static state or not is judged by the change condition of the relative position between the vehicle and the predetermined fixed object in the preset time confirmed by the predetermined fixed object, so that the accuracy of judging whether the vehicle stops or not can be improved by taking the predetermined fixed object in the image frame as a reference, and the accuracy of illegal parking detection can be improved.
Referring to fig. 2 in detail, fig. 2 is a schematic flow chart of a second embodiment of the illegal parking detection method according to the present application. The illegal parking detection method comprises the following steps.
S201: image detection is performed on the image frames to detect the vehicle and the predetermined fixed object in the image frames.
See step S101, which is not described herein.
Optionally, after detecting the predetermined fixed objects in the image frame, the predetermined fixed objects which may move may be screened out; then, in step S202, two predetermined fixed objects are selected for each vehicle of the image frame from the screened predetermined fixed objects. Here, a predetermined fixed object whose size does not match its type may be a predetermined fixed object that is likely to move, or a predetermined fixed object placed on a vehicle may be a predetermined fixed object that is likely to move, although not limited thereto.
In addition, before step S201, a detection area may be defined, so that only whether the vehicle in the detection area is in a stop state is determined in the following, and then only whether the vehicle in the detection area parks in violation of regulations is determined, so as to reduce the detection range and improve the detection efficiency of parking in violation of regulations. Lanes (which may include motorways, pedestrian lanes, and non-motorways) may be used as detection zones. Or the distance between the vehicle and the lane is smaller than a second threshold value and the lane is used as a detection area.
S202: two predetermined stationary objects are selected for each vehicle of the image frame.
See step S102, which is not described herein.
S203: the method comprises the steps of tracking a vehicle and a corresponding preset fixed object based on continuously acquired image frames, and determining whether a change value of each included angle of a graph formed by a vehicle center point and a corresponding preset fixed object center point within preset time exceeds a first threshold value.
See step S102, which is not described herein.
If the change value of each included angle does not exceed the first threshold value, the step S204 is executed; and if the change value of at least part of included angles of the graph is confirmed to exceed the first threshold value, returning to the step S203 again to continuously judge whether the vehicle parks illegally.
S204: and confirming whether the vehicle parking position is a no-parking area.
See step S103, which is not described herein.
If the vehicle parking position is determined to be the no-parking area, the step S205 is executed; and if the parking position of the vehicle is not the no-parking area, returning to the step S203 again to continuously judge whether the vehicle parks in violation of regulations.
S205: and confirming that the vehicle parks illegally.
S206: and collecting illegal parking vehicle information.
After the illegal parking of the vehicle is confirmed, the information of the illegal parking vehicle can be collected so as to be conveniently uploaded to an illegal penalty auditing system for traffic police to audit, and the illegal parking vehicle information can be used as a penalty basis. The information of the illegal parking vehicle can comprise a vehicle parking position image, a vehicle license plate image and/or a license plate number of the illegal parking vehicle.
The license plate number of the illegal parking vehicle can be obtained by detecting the image frame containing the vehicle. If the image frame containing the vehicle does not contain clear license plate information of the vehicle, the image shooting equipment can be adjusted, so that the image shooting equipment can shoot the image containing the clear license plate information of the vehicle. And may even zoom to magnify the license plate in the image frame. Specifically, if the device for shooting the image is an unmanned aerial vehicle, the position and shooting angle of the unmanned aerial vehicle can be adjusted until the image shot by the unmanned aerial vehicle contains clear vehicle license plate information; if the equipment for shooting the images is a ball machine, the shooting angle of the rotating ball machine can be adjusted until the images shot by the rotating ball machine contain clear vehicle license plate information.
Before step S206, it may be detected whether there is a person in the vehicle; if there is a person, a prompt signal is sent, and if the vehicle does not leave the no-parking area under the prompt signal, or no person is in the vehicle, step S206 is executed. Preferably, the apparatus for photographing an image may be adjusted so that the apparatus for photographing an image can photograph an image including vehicle interior information to determine whether a person is present in the vehicle based on the image including vehicle interior information. Specifically, the system can be used for zooming and amplifying through the linkage flight control system and the camera control system, and whether people exist in the vehicle or not can be identified through the front windshield.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an embodiment of the illegal parking detection device 10 according to the present application. The present parking violation detection apparatus 10 includes a processor 12, the processor 12 being configured to execute instructions to implement the methods provided by any of the embodiments of the present parking violation detection methods and any non-conflicting combinations described above.
The illegal parking detection device 10 can be a mobile phone, a notebook computer and other terminals, or can also be a server.
The parking violation detection device 10 may be coupled to at least one camera to obtain image frames containing the vehicle via the at least one camera.
The illegal parking detection device 10 may further include a memory 11 for storing instructions and data necessary for operation of the processor 12.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present disclosure. The computer readable storage medium 20 of the embodiments of the present application stores instructions/program data 21 that when executed 21 implement the methods provided by any of the above-described embodiments of the methods of the present application, as well as any non-conflicting combinations. The instructions/program data 21 may form a program file stored in the storage medium 20 in the form of a software product, so as to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute all or part of the steps of the methods according to the embodiments of the present application. And the aforementioned storage medium 20 includes: various media capable of storing program codes, such as a usb disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, or terminal devices, such as a computer, a server, a mobile phone, and a tablet.
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 manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is only a logical division, and other divisions may be realized in practice, 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 interfaces, devices or units, and may be in an electrical, mechanical or other form.
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 integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The above are only embodiments of the present application, and not intended to limit the scope of the present application, and all equivalent structures or equivalent processes performed by the present application and the contents of the attached drawings, which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (10)
1. A method of illegal parking detection, the method comprising:
performing image detection on an image frame to detect a vehicle and at least two predetermined fixed objects in the image frame;
tracking the vehicle and the at least two preset fixed objects based on continuously acquired image frames, and determining whether a change value of each included angle of a graph formed by the vehicle center point and the corresponding at least two preset fixed object center points exceeds a first threshold value within preset time;
if the parking position of the vehicle is a no-parking area, determining that the vehicle parks in a violation of regulation;
the image frames are shot by a mobile device, the moving distance of the mobile device in a preset time is smaller than the farthest straight-line distance, and the farthest straight-line distance is determined based on a preset first threshold and the height of the mobile device.
2. The method according to claim 1, wherein the tracking the vehicle and the at least two predetermined fixed objects based on the continuously acquired image frames, and the determining whether the change value of each angle of the graph formed by the vehicle center point and the corresponding at least two predetermined fixed object center points within a preset time exceeds a first threshold value comprises:
calculating the degree of each included angle of a graph formed by the vehicle central point and at least two corresponding preset fixed object central points in each frame of image frame;
determining the maximum value and the minimum value of each included angle of the graph within preset time;
calculating the difference value between the maximum value and the minimum value of each included angle to obtain the change value of each included angle;
determining whether the maximum value of the variation values of all included angles in the graph exceeds a first threshold value.
3. The method of claim 2, wherein the tracking the vehicle and the at least two predetermined stationary objects previously comprises:
selecting two preset fixed objects as preset fixed objects corresponding to the vehicle;
the calculating of the degree of each included angle of the graph formed by the vehicle center point and the corresponding preset fixed object center point in each frame of image frame comprises the following steps:
and calculating the degree of each included angle of a triangle formed by the vehicle central point and the corresponding preset fixed object central point in each frame.
4. The method of claim 1 wherein said violating parking of said vehicle if none of said first threshold values is exceeded and when said parking location of said vehicle is a no-parking zone comprises:
responding to the fact that the change value of each included angle of the graph does not exceed a first threshold value;
and determining whether the parking position of the vehicle is a no-parking area or not based on a preset traffic rule and the parking position of the vehicle.
5. The method of claim 4, wherein the confirming whether the parking location of the vehicle is a no-parking zone based on preset traffic rules and the parking location of the vehicle comprises:
if the vehicle is parked on a sidewalk or a non-motor vehicle lane, the parking position is not in a parking space wire frame, and no parking indicator indicates that the parking position allows parking, determining that the parking position is a no-parking area;
and if the vehicle is parked in a motor lane, a signal lamp indicating the vehicle to run is a green lamp, and vehicles with the speed lower than a fifth threshold value on the motor lane are less than a third threshold value, the parking position is determined to be a no-parking area.
6. The method of claim 1 wherein said determining that said vehicle is parking violations thereafter comprises:
collecting the vehicle parking position image and the vehicle license plate image, identifying the license plate of the vehicle, and determining the license plate number of the vehicle which parks against the regulations;
and uploading the vehicle parking position image, the vehicle license plate image, the license plate number and the video recording of the vehicle to a violation punishment auditing system.
7. The method of claim 6 wherein said determining that the vehicle is parking violations thereafter comprises:
detecting whether a person is in the vehicle;
if the vehicle is not driven away from the no-parking area under the prompt signal, or no person exists in the vehicle, the steps of collecting the vehicle parking position image and the vehicle license plate image, identifying the vehicle license plate and determining the license plate number of the vehicle which parks against the regulations are executed.
8. The method of claim 6, wherein collecting the image of the parking location of the vehicle and the image of the license plate of the vehicle, identifying the license plate of the vehicle, and determining the license plate number of the parking violation vehicle comprises:
the image frame is obtained by shooting by an unmanned aerial vehicle, and if the image shot by the current position of the unmanned aerial vehicle does not contain clear license plate information of the vehicle; adjusting the position of the unmanned aerial vehicle until the image shot by the unmanned aerial vehicle contains clear vehicle license plate information.
9. A parking violation detection device, wherein the parking violation detection device comprises a processor; the processor is configured to execute instructions to carry out the steps of the method according to any one of claims 1 to 8.
10. A computer-readable storage medium having stored thereon instruction data, the instruction data, when executed by a processor, implementing the steps of the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110199614.7A CN113112813B (en) | 2021-02-22 | 2021-02-22 | Illegal parking detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110199614.7A CN113112813B (en) | 2021-02-22 | 2021-02-22 | Illegal parking detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113112813A CN113112813A (en) | 2021-07-13 |
| CN113112813B true CN113112813B (en) | 2022-12-20 |
Family
ID=76709389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110199614.7A Active CN113112813B (en) | 2021-02-22 | 2021-02-22 | Illegal parking detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113112813B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113593256B (en) * | 2021-09-29 | 2021-12-28 | 深圳联和智慧科技有限公司 | Unmanned aerial vehicle intelligent driving-away control method and system based on city management and cloud platform |
| CN115019546B (en) * | 2022-05-26 | 2024-09-17 | 北京精英路通科技有限公司 | Parking prompt method and device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102288957A (en) * | 2010-05-26 | 2011-12-21 | 三菱电机株式会社 | Angular velocity estimation apparatus and angular velocity estimation method |
| CN112232441A (en) * | 2020-11-18 | 2021-01-15 | 中国联合网络通信集团有限公司 | Illegal parking judgment method, system, computer equipment and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100430971C (en) * | 2005-04-08 | 2008-11-05 | 中国科学院自动化研究所 | Motor vehicle peccancy behavior automatic shooting device and method mounted on bus |
| CN103021183A (en) * | 2012-12-07 | 2013-04-03 | 北京中邮致鼎科技有限公司 | Method for detecting regulation-violating motor vehicles in monitoring scene |
| CN103116984B (en) * | 2013-01-21 | 2016-03-23 | 信帧电子技术（北京）有限公司 | Detect the method for parking offense |
| CN105047001B (en) * | 2015-08-06 | 2018-03-20 | 平安科技（深圳）有限公司 | Realize method, vehicle and mobile terminal that vehicle parking management and control is reminded |
| CN106935035B (en) * | 2017-04-07 | 2019-07-23 | 西安电子科技大学 | Parking offense vehicle real-time detection method based on SSD neural network |
| CN111105637A (en) * | 2019-12-27 | 2020-05-05 | 智慧互通科技有限公司 | Illegal vehicle early warning method and system based on electronic tag |
-
2021
- 2021-02-22 CN CN202110199614.7A patent/CN113112813B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102288957A (en) * | 2010-05-26 | 2011-12-21 | 三菱电机株式会社 | Angular velocity estimation apparatus and angular velocity estimation method |
| CN112232441A (en) * | 2020-11-18 | 2021-01-15 | 中国联合网络通信集团有限公司 | Illegal parking judgment method, system, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113112813A (en) | 2021-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018223955A1 (en) | Target monitoring method, target monitoring device, camera and computer readable medium | |
| CN110738857B (en) | Vehicle violation evidence obtaining method, device and equipment | |
| CN106571039A (en) | Automatic snapshot system for highway traffic offence | |
| KR101671428B1 (en) | Intelligent Monitoring System For Violation Vehicles in crossroads | |
| CN108806272B (en) | Method and device for reminding multiple motor vehicle owners of illegal parking behaviors | |
| CN112163543A (en) | Method and system for detecting illegal lane occupation of vehicle | |
| CN111444798B (en) | Identification method and device for driving behavior of electric bicycle and computer equipment | |
| CN113112813B (en) | Illegal parking detection method and device | |
| WO2021227586A1 (en) | Traffic accident analysis method, apparatus, and device | |
| CN108932851B (en) | Method and device for recording illegal parking behaviors of motor vehicle | |
| CN108932849B (en) | Method and device for recording low-speed running illegal behaviors of multiple motor vehicles | |
| CN105046966A (en) | System and method for automatically detecting illegal parking behaviors in drop-off areas | |
| CN111753634B (en) | Traffic event detection method and equipment | |
| CN112991130B (en) | Urban treatment event processing method and device based on artificial intelligence | |
| CN111739305B (en) | Multi-type camera-based illegal parking management method and system | |
| CN111292530A (en) | Method, device, server and storage medium for processing violation pictures | |
| CN116311166A (en) | Traffic obstacle recognition method and device and electronic equipment | |
| CN112750301A (en) | Target object tracking method, device, equipment and computer readable storage medium | |
| CN114141022B (en) | Emergency lane occupation behavior detection method and device, electronic equipment and storage medium | |
| CN111526475A (en) | Target vehicle tracking method and device, electronic equipment and storage medium | |
| CN114913470B (en) | Event detection method and device | |
| CN114078319A (en) | Method and device for detecting potential hazard site of traffic accident | |
| CN115762153A (en) | Method and device for detecting backing up | |
| CN115909314A (en) | License plate shielding detection method, illegal parking detection method and equipment thereof | |
| CN113449624B (en) | Method and device for determining vehicle behavior based on pedestrian re-identification |
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 |