CN114821491A - Vehicle parking violation identification method and device, electronic equipment and storage medium - Google Patents
Vehicle parking violation identification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114821491A CN114821491A CN202210232880.XA CN202210232880A CN114821491A CN 114821491 A CN114821491 A CN 114821491A CN 202210232880 A CN202210232880 A CN 202210232880A CN 114821491 A CN114821491 A CN 114821491A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- parking
- dimensional
- surrounding frame
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000001514 detection method Methods 0.000 claims abstract description 41
- 230000003068 static effect Effects 0.000 claims abstract description 24
- 238000004590 computer program Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 208000004350 Strabismus Diseases 0.000 description 4
- 238000001914 filtration Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of vehicle detection, and provides a vehicle parking violation identification method, a vehicle parking violation identification device, electronic equipment and a storage medium, wherein the method comprises the following steps: determining a vehicle image to be identified; carrying out target detection on the vehicle image to obtain a three-dimensional surrounding frame of the vehicle; carrying out target tracking on the three-dimensional surrounding frame of the vehicle to determine the motion state of the vehicle; and under the condition that the motion state of the vehicle is a static state, determining the vehicle illegal parking recognition result based on the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area. According to the vehicle illegal parking recognition method, the vehicle illegal parking recognition device, the electronic equipment and the storage medium, the vehicle illegal parking recognition result can be accurately determined based on the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area, and the problem that the vehicle illegal parking recognition cannot be accurately carried out by adopting the vehicle image of the overlooking angle or the squinting angle in the traditional method is solved.
Description
Technical Field
The present invention relates to the field of vehicle detection technologies, and in particular, to a method and an apparatus for identifying vehicle parking violation, an electronic device, and a storage medium.
Background
Along with economy constantly develops, people's living standard constantly promotes, and people's car ownership volume is also constantly climbing, and because the parking stall is limited, so can appear some indiscriminate phenomena of stopping randomly putting, and then cause the road to block up easily, influence personnel's trip, can cause the traffic accident even, influence road safety.
At present, a two-dimensional target detection method is used for detecting vehicle parking violation, and specifically comprises the following steps: and acquiring vehicle images of the monitored area by adopting a camera, and judging whether the vehicle parking position is standard or not according to the vehicle images. However, most of the vehicle images collected by the camera are overlook angle images or squint angle images, so that deviation exists when the parking position of the vehicle is judged according to the vehicle images, and further the accuracy of illegal parking recognition is affected.
Disclosure of Invention
The invention provides a vehicle illegal parking identification method and device, electronic equipment and a storage medium, which are used for solving the defect of low vehicle illegal parking identification precision in the prior art.
The invention provides a vehicle illegal parking identification method, which comprises the following steps:
determining a vehicle image to be identified;
carrying out target detection on the vehicle image to obtain a three-dimensional surrounding frame of the vehicle;
carrying out target tracking on the three-dimensional surrounding frame of the vehicle, and determining the motion state of the vehicle;
and under the condition that the motion state of the vehicle is a static state, determining a vehicle illegal parking recognition result based on the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area.
According to the vehicle illegal parking identification method provided by the invention, the target detection is carried out on the vehicle image to obtain the three-dimensional surrounding frame of the vehicle, and the method comprises the following steps:
carrying out target detection on the vehicle image to obtain a two-dimensional frame of the vehicle;
and performing enclosure regression on the two-dimensional frame of the vehicle to obtain a three-dimensional enclosure of the vehicle.
According to the vehicle illegal parking identification method provided by the invention, the vehicle image comprises a plurality of vehicles to be identified;
the target tracking is carried out on the three-dimensional surrounding frame of the vehicle, and the motion state of the vehicle is determined, and the method comprises the following steps:
determining the motion trail of each vehicle to be identified based on the three-dimensional surrounding frame of each vehicle to be identified;
and determining the motion state of each vehicle to be identified based on the motion trail of each vehicle to be identified.
According to the vehicle illegal parking identification method provided by the invention, the motion trail of each vehicle to be identified is determined based on the real-time position of the three-dimensional surrounding frame of each vehicle to be identified and/or the real-time positions of the three-dimensional surrounding frames of other vehicles to be identified.
According to the vehicle illegal parking identification method provided by the invention, the step of determining the vehicle illegal parking identification result based on the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area comprises the following steps:
determining a vehicle chassis area based on the three-dimensional bounding box of the vehicle;
determining a parking line area based on the three-dimensional surrounding frame of the preset parking area;
and determining the vehicle illegal parking recognition result based on the overlapping area between the vehicle chassis area and the stop line area.
According to the vehicle illegal parking identification method provided by the invention, the three-dimensional surrounding frame of the preset parking area is determined based on the following steps:
acquiring a regional image of the preset parking region;
performing linear detection on the area image to obtain a stop line of the preset parking area;
and determining a three-dimensional surrounding frame of the preset parking area based on the parking line.
According to the vehicle illegal parking identification method provided by the invention, the vehicle illegal parking identification result is determined, and then the method further comprises the following steps:
and under the condition that the vehicle illegal parking recognition result shows that the vehicle illegal parking phenomenon exists, carrying out license plate recognition on the vehicle image, taking the moment corresponding to the static state as the illegal parking starting moment, and recording the illegal parking time length until the vehicle leaves.
The present invention also provides a vehicle parking violation recognition apparatus, comprising:
a determination unit for determining a vehicle image to be recognized;
the detection unit is used for carrying out target detection on the vehicle image to obtain a three-dimensional surrounding frame of the vehicle;
the tracking unit is used for carrying out target tracking on the three-dimensional surrounding frame of the vehicle and determining the motion state of the vehicle;
and the identification unit is used for determining the vehicle illegal parking identification result on the basis of the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area under the condition that the motion state of the vehicle is a static state.
The invention further provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of any one of the above-mentioned vehicle parking violation identification methods.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the vehicle parking violation identification method according to any of the above.
The present invention also provides a computer program product comprising a computer program which, when being executed by a processor, carries out the steps of the method for identifying a vehicle parking violation as described in any of the above.
According to the vehicle illegal parking recognition method, the vehicle illegal parking recognition device, the electronic equipment and the storage medium, the motion state of the vehicle can be accurately determined based on the three-dimensional surrounding frame of the vehicle, and under the condition that the motion state is a static state, the vehicle illegal parking recognition result is accurately determined based on the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area, so that the problem that the vehicle illegal parking recognition cannot be accurately carried out by adopting the vehicle image with the overlooking angle or the squinting angle in the traditional method is solved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a vehicle parking violation identification method provided by the present invention;
FIG. 2 is a schematic diagram of a three-dimensional bounding box prediction network structure of a vehicle provided by the present invention;
FIG. 3 is a schematic flow chart diagram of a method for determining a motion state of a vehicle according to the present invention;
FIG. 4 is a second schematic flowchart of a vehicle parking violation identification method according to the present invention;
FIG. 5 is a schematic structural diagram of a vehicle parking violation identification device provided by the present invention;
fig. 6 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, a two-dimensional target detection method is used for detecting vehicle parking violation, and specifically comprises the following steps: and acquiring vehicle images of the monitored area by adopting a camera, and judging whether the vehicle parking position is standard or not according to the vehicle images. However, most of the vehicle images collected by the camera are overlook angle images or squint angle images, so that deviation exists when the parking position of the vehicle is judged according to the vehicle images, and further the accuracy of illegal parking recognition is affected.
For example, when a vehicle image is captured by using a camera in a top view angle, the field of view of the camera is small, the area covered by the captured vehicle image is small, and even a partial image of the vehicle may be captured. When the camera at the squint angle is used for collecting the vehicle image, although the global image of the vehicle can be collected, the squint angle has deviation, so that the parking position of the vehicle cannot be accurately determined by the obtained two-dimensional vehicle image.
In view of the above, the present invention provides a vehicle parking violation identification method. Fig. 1 is a schematic flow chart of a vehicle parking violation identification method provided by the invention, as shown in fig. 1, the method includes the following steps:
Here, the vehicle image to be recognized is an image that needs to be subjected to vehicle parking violation recognition, and the vehicle image may be an image acquired by an image pickup device or an image input by a user.
In addition, when the vehicle image is collected by the camera device, the vehicle image can be collected by the camera device at the top view angle or the vehicle image can be collected by the camera device at the oblique view angle.
And 120, carrying out target detection on the vehicle image to obtain a three-dimensional surrounding frame of the vehicle.
Specifically, the three-dimensional bounding box of the vehicle is used for representing the three-dimensional spatial information of the vehicle in the vehicle image. Compared with the two-dimensional position information of the vehicle in the vehicle image, the three-dimensional space information carried by the three-dimensional surrounding frame of the vehicle can represent the position information of the vehicle more accurately.
For example, when a camera device at an oblique angle is used to capture an image of a vehicle, if the vehicle is actually located in a parking area, the two-dimensional position of the vehicle displayed in the image of the vehicle is outside the parking area due to the problem of the image capture angle, and the parking position of the vehicle is erroneously determined.
In contrast, in the embodiment of the invention, the target detection is performed on the vehicle image, the two-dimensional frame of the vehicle can be obtained firstly, and then the enclosure regression is performed on the two-dimensional frame of the vehicle, so that the three-dimensional enclosure used for representing the three-dimensional spatial information of the vehicle can be obtained.
Therefore, the embodiment of the invention adopts the three-dimensional surrounding frame of the vehicle to represent the position information of the vehicle, thereby avoiding the problem that the parking position of the vehicle cannot be accurately determined due to the influence of the shooting angle.
And step 130, carrying out target tracking on the three-dimensional surrounding frame of the vehicle, and determining the motion state of the vehicle.
Specifically, if the vehicle is in motion, it indicates that the vehicle may be looking for a parking space or parking a vehicle. If the vehicle is at rest, it indicates that the vehicle may have finished parking.
The three-dimensional surrounding frame of the vehicle can represent the three-dimensional space information of the vehicle, so that the motion state of the vehicle can be determined when the target tracking is carried out on the three-dimensional surrounding frame of the vehicle. For example, when the target tracking is performed, if the position information of the three-dimensional surrounding frame of the vehicle is continuously unchanged within a preset time period, it indicates that the probability that the vehicle is currently in a stationary state is higher, and if not, it indicates that the probability that the vehicle is currently in a moving state is higher.
And 140, under the condition that the motion state of the vehicle is a static state, determining the vehicle illegal parking recognition result based on the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area.
Specifically, the preset parking area refers to a standard parking area of the vehicle, and the vehicle illegal parking recognition result is used for representing whether the vehicle is parked in the preset parking area. If the vehicle is parked in the preset parking area, the fact that the vehicle does not break is indicated; if the vehicle is parked outside the preset parking area, the fact that the vehicle is parked illegally is indicated.
When the moving state of the vehicle is a static state, the probability that the vehicle is parked is high, and at this time, the parking position of the vehicle can be identified to determine whether the parking position of the vehicle is in the preset parking area.
The three-dimensional surrounding frame of the preset parking area can be determined according to the parking line of the preset parking area, and if the overlapping area of the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area is large, the probability that the vehicle is parked in the preset parking area is high; if the overlapping area of the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area is smaller, the probability that the vehicle is parked outside the preset parking area is higher.
Therefore, the vehicle illegal parking identification method provided by the embodiment of the invention can accurately determine the motion state of the vehicle based on the three-dimensional surrounding frame of the vehicle, accurately determine the vehicle illegal parking identification result based on the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area under the condition that the motion state is in a static state, and avoid the problem that the vehicle illegal parking identification cannot be accurately carried out by adopting the vehicle image of the overlooking angle or the squinting angle in the traditional method.
Based on the above embodiment, the target detection is performed on the vehicle image to obtain the three-dimensional surrounding frame of the vehicle, including:
carrying out target detection on the vehicle image to obtain a two-dimensional frame of the vehicle;
and performing enclosure regression on the two-dimensional frame of the vehicle to obtain the three-dimensional enclosure of the vehicle.
Specifically, the two-dimensional frame of the vehicle is used for representing the two-dimensional position information of the vehicle in the vehicle image, and the three-dimensional surrounding frame of the vehicle is used for representing the three-dimensional space information of the vehicle in the vehicle image. Compared with the two-dimensional position information of the vehicle in the vehicle image, the three-dimensional space information carried by the three-dimensional surrounding frame of the vehicle can represent the position information of the vehicle more accurately.
For example, when a camera device at an oblique angle is used to capture an image of a vehicle, if the vehicle is actually located in a parking area, the two-dimensional position of the vehicle displayed in the image of the vehicle is outside the parking area due to the problem of the image capture angle, and the parking position of the vehicle is erroneously determined.
In contrast, in the embodiment of the invention, the target detection is performed on the vehicle image, the two-dimensional frame of the vehicle can be obtained firstly, and then the enclosure regression is performed on the two-dimensional frame of the vehicle, so that the three-dimensional enclosure used for representing the three-dimensional spatial information of the vehicle can be obtained.
Therefore, the embodiment of the invention adopts the three-dimensional surrounding frame of the vehicle to represent the position information of the vehicle, thereby avoiding the problem that the parking position of the vehicle cannot be accurately determined due to the influence of the shooting angle.
Optionally, in the embodiment of the present invention, the three-dimensional bounding box of the vehicle may be obtained based on a deep learning three-dimensional bounding box prediction Network structure, and as shown in fig. 2, the vehicle image may be first input to a 2D proxy Network to obtain a two-dimensional bounding box of the vehicle, and then the two-dimensional bounding box of the vehicle may be input to a 3D Regression/Classification Network to obtain the three-dimensional bounding box of the vehicle.
According to any embodiment of the above, the vehicle image includes a plurality of vehicles to be identified;
the method comprises the following steps of carrying out target tracking on a three-dimensional surrounding frame of a vehicle and determining the motion state of the vehicle, wherein the steps comprise:
determining the motion trail of each vehicle to be identified based on the three-dimensional surrounding frame of each vehicle to be identified;
and determining the motion state of each vehicle to be identified based on the motion trail of each vehicle to be identified.
Specifically, the vehicle image includes a plurality of vehicles to be identified, and if the motion state of any vehicle to be identified is a static state, the vehicle to be identified can be subjected to illegal parking identification, that is, the method provided by the embodiment of the invention can be used for illegal parking identification of the plurality of vehicles to be identified at the same time.
Optionally, the target detection may be performed on the vehicle image to determine the three-dimensional enclosure frame of each vehicle to be recognized, and since the three-dimensional enclosure frame of the vehicle may be used to represent three-dimensional spatial information of the vehicle, that is, the three-dimensional enclosure frame of the vehicle may be used to represent three-dimensional position information of the vehicle, the motion trajectory of the vehicle to be recognized may be determined according to the three-dimensional enclosure frame of the vehicle to be recognized at each moment.
After the motion trail of the vehicle to be identified is determined, if the position information of the vehicle is unchanged or is in a static state within a preset time period, the probability that the vehicle is in the static state at present is high, and if the position information of the vehicle is not changed or is in the static state, the probability that the vehicle is in the motion state at present is high.
Based on any embodiment, the motion track of each vehicle to be identified is determined based on the real-time position of the three-dimensional surrounding frame of each vehicle to be identified and/or the real-time positions of the three-dimensional surrounding frames of other vehicles to be identified.
Specifically, if each vehicle to be recognized can be displayed in the vehicle image in real time and is not blocked by other vehicles, the motion track of each vehicle to be recognized can be determined based on the real-time position of the three-dimensional surrounding frame corresponding to the vehicle to be recognized; if each vehicle to be identified is blocked by other vehicles in the vehicle image or does not appear in the current vehicle image temporarily, the motion trail of the corresponding vehicle can be predicted based on the real-time positions of the three-dimensional surrounding frames of other vehicles.
As shown in fig. 3, target detection is performed on a vehicle image to obtain N three-dimensional bounding boxes, then the motion positions of the three-dimensional bounding boxes of the current M tracks are predicted, and the M predicted bounding boxes and the N detected bounding boxes are associated by using the hungarian algorithm. And then, correcting the position of the updated track by adopting a Kalman filtering method based on the detection frame associated with each track, predicting the position of the track by utilizing Kalman filtering for the detection frames which do not correspond to the detection surrounding frames, newly establishing the track for the detection frames which are not associated with any track, deleting the track which exceeds q frames and is continuously not associated with the detection frames, and further obtaining the motion track of each vehicle to be identified.
Based on any one of the above embodiments, determining the vehicle illegal parking recognition result based on the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area includes:
determining a vehicle chassis area based on a three-dimensional enclosure frame of the vehicle;
determining a parking line area based on a three-dimensional surrounding frame of a preset parking area;
and determining the vehicle illegal parking recognition result based on the overlapping area between the vehicle chassis area and the parking line area.
In particular, the vehicle chassis region is used to characterize vehicle chassis plane area information, position information, and the like. The parking line area is used for representing plane area information, position information and the like of a preset parking area. The three-dimensional surrounding frame of the vehicle contains the three-dimensional space information of the vehicle, so that the vehicle chassis area can be determined according to the three-dimensional surrounding frame of the vehicle. The three-dimensional surrounding frame of the preset parking area comprises the three-dimensional space information of the preset parking area, so that the parking line area can be determined according to the three-dimensional surrounding frame of the preset parking area.
In addition, the overlapping area between the vehicle chassis area and the parking line area is used for representing the overlapping degree between the chassis and the preset parking area, and the larger the overlapping area is, the higher the probability that the vehicle chassis area is located in the preset parking area is, that is, the higher the probability of the vehicle parking standard is; the smaller the overlap area, the smaller the probability that the vehicle chassis region is located within the preset parking region, i.e., the greater the probability of a vehicle parking violation.
It will be appreciated that after the overlap area is determined, a ratio of the overlap area to the stop line region may be determined, and that when the ratio is greater than a threshold (e.g., 90%), a vehicle parking specification is indicated; when the ratio is less than or equal to the threshold, a vehicle parking violation is indicated.
Based on any of the above embodiments, the three-dimensional enclosure frame of the preset parking area is determined based on the following steps:
acquiring a regional image of a preset parking region;
performing linear detection on the area image to obtain a stop line of a preset parking area;
and determining a three-dimensional surrounding frame of the preset parking area based on the parking line.
Specifically, the preset parking area is usually represented by a rectangular frame, that is, when the vehicle is parked in the rectangular frame, it indicates that the vehicle does not have an illegal parking phenomenon; when the vehicle is parked outside the rectangular frame, the phenomenon that the vehicle is parked illegally is indicated.
When the three-dimensional surrounding frame of the preset parking area is obtained, linear detection (such as Hough transformation) can be firstly carried out on the area image, so that a parking line of the preset parking area can be obtained, and then the internal and external parameters of the camera are calibrated by utilizing two groups of parallel lines in the transverse direction and the longitudinal direction of the parking line, so that the three-dimensional surrounding frame of the preset parking area can be obtained, and the illegal parking recognition result of the vehicle can be accurately determined based on the three-dimensional surrounding frame of the preset parking area and the three-dimensional surrounding frame of the vehicle.
Based on any embodiment, the method for determining the vehicle parking violation identification result further comprises the following steps:
and under the condition that the vehicle illegal parking recognition result shows that the vehicle illegal parking phenomenon exists, carrying out license plate recognition on the vehicle image, taking the moment corresponding to the static state as the illegal parking starting moment, and recording the illegal parking duration until the vehicle leaves.
Specifically, under the condition that the vehicle illegal parking recognition result shows that the vehicle illegal parking phenomenon exists, the embodiment of the invention carries out license plate recognition on the vehicle image to obtain the license plate number of the vehicle, records the illegal parking time length, and establishes the mapping relation between the license plate number and the illegal parking time length, so that the illegal parking time length of the vehicle can be quickly inquired. The starting moment of the illegal parking is the moment corresponding to the static state, and the ending moment of the illegal parking is the moment corresponding to the state that the vehicle is switched from the static state to the moving state.
It can be understood that the early warning prompt can be carried out under the condition that the vehicle parking violation phenomenon exists; the warning prompt may also be performed when the duration of the illegal stop exceeds a preset duration, which is not specifically limited in the embodiment of the present invention.
Based on any of the above embodiments, the present invention further provides a vehicle parking violation identification method, as shown in fig. 4, the method includes:
firstly, a video stream is read through a camera, a vehicle image to be recognized is obtained, target detection is carried out on the vehicle image, and a three-dimensional surrounding frame of the vehicle is determined.
And then, carrying out multi-target tracking on the three-dimensional surrounding frame of the vehicle, determining the motion track of the vehicle, and determining the motion state of the vehicle according to the motion track of the vehicle.
When the motion state of the vehicle is a static state, determining whether the vehicle is illegal to park based on the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area, and if so, acquiring the license plate number of the vehicle and performing illegal parking alarm and illegal parking timing.
The following describes the vehicle illegal parking recognition device provided by the present invention, and the vehicle illegal parking recognition device described below and the vehicle illegal parking recognition method described above can be referred to correspondingly.
Based on any of the above embodiments, the present invention further provides a vehicle parking violation identification apparatus, as shown in fig. 5, the apparatus includes:
a determination unit 510 for determining a vehicle image to be recognized;
the detection unit 520 is used for performing target detection on the vehicle image to obtain a three-dimensional surrounding frame of the vehicle;
a tracking unit 530, configured to perform target tracking on the three-dimensional bounding box of the vehicle, and determine a motion state of the vehicle;
and the identifying unit 540 is configured to determine a vehicle illegal parking identifying result based on the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area when the moving state of the vehicle is a static state.
Based on any of the above embodiments, the detecting unit 520 includes:
the target detection unit is used for carrying out target detection on the vehicle image to obtain a two-dimensional frame of the vehicle;
and the regression unit is used for performing enclosure regression on the two-dimensional frame of the vehicle to obtain a three-dimensional enclosure of the vehicle.
According to any one of the above embodiments, the vehicle image includes a plurality of vehicles to be identified;
the tracking unit 530 includes:
the track determining unit is used for determining the motion track of each vehicle to be identified based on the three-dimensional surrounding frame of each vehicle to be identified;
and the state determining unit is used for determining the motion state of each vehicle to be identified based on the motion trail of each vehicle to be identified.
Based on any embodiment, the motion track of each vehicle to be identified is determined based on the real-time position of the three-dimensional surrounding frame of each vehicle to be identified and/or the real-time positions of the three-dimensional surrounding frames of other vehicles to be identified.
Based on any of the above embodiments, the identifying unit 540 includes:
a chassis region determination unit for determining a vehicle chassis region based on a three-dimensional enclosure frame of the vehicle;
the parking line area determining unit is used for determining a parking line area based on the three-dimensional surrounding frame of the preset parking area;
and the illegal parking result determining unit is used for determining the illegal parking recognition result of the vehicle based on the overlapping area between the vehicle chassis area and the stop line area.
Based on any embodiment above, the apparatus further comprises:
the acquisition unit is used for acquiring an area image of the preset parking area;
the straight line detection unit is used for carrying out straight line detection on the area image to obtain a stop line of the preset parking area;
and the parking area determining unit is used for determining a three-dimensional surrounding frame of the preset parking area based on the parking line.
Based on any embodiment above, the apparatus further comprises:
and the timing unit is used for carrying out license plate recognition on the vehicle image under the condition that the vehicle illegal parking recognition result is that the vehicle illegal parking phenomenon exists after the vehicle illegal parking recognition result is determined, and recording illegal parking duration by taking the moment corresponding to the static state as illegal parking starting moment until the vehicle is driven away.
Fig. 6 is a schematic structural diagram of an electronic device provided in the present invention, and as shown in fig. 6, the electronic device may include: a processor (processor)610, a communication Interface (Communications Interface)620, a memory (memory)630 and a communication bus 640, wherein the processor 610, the communication Interface 620 and the memory 630 communicate with each other via the communication bus 640. The processor 610 may invoke logic instructions in the memory 630 to perform a vehicle violation identification method comprising: determining a vehicle image to be identified; carrying out target detection on the vehicle image to obtain a three-dimensional surrounding frame of the vehicle; carrying out target tracking on the three-dimensional surrounding frame of the vehicle, and determining the motion state of the vehicle; and under the condition that the motion state of the vehicle is a static state, determining a vehicle illegal parking recognition result based on the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area.
In addition, the logic instructions in the memory 630 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention or a part thereof which substantially contributes to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, which when executed by a computer, enable the computer to perform the vehicle violation identification method provided by the above methods, the method comprising: determining a vehicle image to be identified; carrying out target detection on the vehicle image to obtain a three-dimensional surrounding frame of the vehicle; carrying out target tracking on the three-dimensional surrounding frame of the vehicle, and determining the motion state of the vehicle; and under the condition that the motion state of the vehicle is a static state, determining a vehicle illegal parking recognition result based on the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor is implemented to perform the vehicle parking violation identification methods provided above, the method comprising: determining a vehicle image to be identified; carrying out target detection on the vehicle image to obtain a three-dimensional surrounding frame of the vehicle; carrying out target tracking on the three-dimensional surrounding frame of the vehicle, and determining the motion state of the vehicle; and under the condition that the motion state of the vehicle is a static state, determining a vehicle illegal parking recognition result based on the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A vehicle parking violation identification method is characterized by comprising the following steps:
determining a vehicle image to be identified;
carrying out target detection on the vehicle image to obtain a three-dimensional surrounding frame of the vehicle;
carrying out target tracking on the three-dimensional surrounding frame of the vehicle, and determining the motion state of the vehicle;
and under the condition that the motion state of the vehicle is a static state, determining a vehicle illegal parking recognition result based on the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area.
2. The vehicle parking violation identification method according to claim 1, wherein the performing object detection on the vehicle image to obtain a three-dimensional enclosure frame of the vehicle comprises:
carrying out target detection on the vehicle image to obtain a two-dimensional frame of the vehicle;
and performing enclosure regression on the two-dimensional frame of the vehicle to obtain a three-dimensional enclosure of the vehicle.
3. The vehicle parking violation identification method according to claim 1, wherein a plurality of vehicles to be identified are included in the vehicle image;
the target tracking is carried out on the three-dimensional surrounding frame of the vehicle, and the motion state of the vehicle is determined, and the method comprises the following steps:
determining the motion trail of each vehicle to be identified based on the three-dimensional surrounding frame of each vehicle to be identified;
and determining the motion state of each vehicle to be identified based on the motion trail of each vehicle to be identified.
4. The vehicle parking violation identification method according to claim 3, wherein the motion trajectory of each vehicle to be identified is determined based on the real-time position of the three-dimensional bounding box of each vehicle to be identified and/or the real-time positions of the three-dimensional bounding boxes of other vehicles to be identified.
5. The vehicle parking violation identification method according to any one of claims 1-4, wherein the determining a vehicle parking violation identification result based on the three-dimensional enclosure frame of the vehicle and the three-dimensional enclosure frame of the preset parking area comprises:
determining a vehicle chassis area based on the three-dimensional bounding box of the vehicle;
determining a parking line area based on the three-dimensional surrounding frame of the preset parking area;
and determining the vehicle illegal parking recognition result based on the overlapping area between the vehicle chassis area and the stop line area.
6. The vehicle parking violation identification method according to any of claims 1-4, wherein the three-dimensional enclosure of the preset parking area is determined based on the following steps:
acquiring a regional image of the preset parking region;
performing linear detection on the region image to obtain a parking line of the preset parking region;
and determining a three-dimensional surrounding frame of the preset parking area based on the parking line.
7. The vehicle parking violation identification method according to any of claims 1-4, wherein said determining a vehicle parking violation identification result further comprises:
and under the condition that the vehicle illegal parking recognition result shows that the vehicle illegal parking phenomenon exists, carrying out license plate recognition on the vehicle image, taking the moment corresponding to the static state as the illegal parking starting moment, and recording the illegal parking time length until the vehicle leaves.
8. A vehicle parking violation identification device, comprising:
a determination unit for determining a vehicle image to be recognized;
the detection unit is used for carrying out target detection on the vehicle image to obtain a three-dimensional surrounding frame of the vehicle;
the tracking unit is used for carrying out target tracking on the three-dimensional surrounding frame of the vehicle and determining the motion state of the vehicle;
and the identification unit is used for determining the vehicle illegal parking identification result on the basis of the three-dimensional surrounding frame of the vehicle and the three-dimensional surrounding frame of the preset parking area under the condition that the motion state of the vehicle is a static state.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the vehicle violation identification method according to any of claims 1 to 7 are implemented by the processor when executing the program.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the vehicle violation identification method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210232880.XA CN114821491A (en) | 2022-03-09 | 2022-03-09 | Vehicle parking violation identification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210232880.XA CN114821491A (en) | 2022-03-09 | 2022-03-09 | Vehicle parking violation identification method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114821491A true CN114821491A (en) | 2022-07-29 |
Family
ID=82528239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210232880.XA Pending CN114821491A (en) | 2022-03-09 | 2022-03-09 | Vehicle parking violation identification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114821491A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079619A (en) * | 2019-12-10 | 2020-04-28 | 北京百度网讯科技有限公司 | Method and apparatus for detecting target object in image |
| CN112487884A (en) * | 2020-11-16 | 2021-03-12 | 香港中文大学（深圳） | Traffic violation behavior detection method and device and computer readable storage medium |
| CN113850872A (en) * | 2021-09-18 | 2021-12-28 | 华设设计集团股份有限公司 | Service area parking line pressing detection method based on high-level video |
| CN113947892A (en) * | 2021-08-26 | 2022-01-18 | 北京万集科技股份有限公司 | Abnormal parking monitoring method and device, server and readable storage medium |
| CN113989715A (en) * | 2021-10-28 | 2022-01-28 | 深圳市商汤科技有限公司 | Vehicle parking violation detection method and device, electronic equipment and storage medium |
-
2022
- 2022-03-09 CN CN202210232880.XA patent/CN114821491A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079619A (en) * | 2019-12-10 | 2020-04-28 | 北京百度网讯科技有限公司 | Method and apparatus for detecting target object in image |
| CN112487884A (en) * | 2020-11-16 | 2021-03-12 | 香港中文大学（深圳） | Traffic violation behavior detection method and device and computer readable storage medium |
| CN113947892A (en) * | 2021-08-26 | 2022-01-18 | 北京万集科技股份有限公司 | Abnormal parking monitoring method and device, server and readable storage medium |
| CN113850872A (en) * | 2021-09-18 | 2021-12-28 | 华设设计集团股份有限公司 | Service area parking line pressing detection method based on high-level video |
| CN113989715A (en) * | 2021-10-28 | 2022-01-28 | 深圳市商汤科技有限公司 | Vehicle parking violation detection method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298300B (en) | Method for detecting vehicle illegal line pressing | |
| CN108513674B (en) | Detection and alarm method for accumulated snow and icing in front of vehicle, storage medium and server | |
| CN106611512B (en) | Method, device and system for processing starting of front vehicle | |
| CN110321814B (en) | Vehicle violation evidence obtaining method and device, electronic equipment and storage medium | |
| US10212397B2 (en) | Abandoned object detection apparatus and method and system | |
| CN110223511A (en) | A kind of automobile roadside is separated to stop intelligent monitoring method and system | |
| US11361556B2 (en) | Deterioration diagnosis device, deterioration diagnosis system, deterioration diagnosis method, and storage medium for storing program | |
| CN109377694B (en) | Monitoring method and system for community vehicles | |
| Bedruz et al. | Real-time vehicle detection and tracking using a mean-shift based blob analysis and tracking approach | |
| CN112562406B (en) | Method and device for identifying off-line driving | |
| CN111428644A (en) | Zebra crossing region monitoring method, system and medium based on deep neural network | |
| KR20180127245A (en) | Method for Predicting Vehicle Collision Using Data Collected from Video Games | |
| CN112487884A (en) | Traffic violation behavior detection method and device and computer readable storage medium | |
| CN113469115A (en) | Method and apparatus for outputting information | |
| CN111383248B (en) | Pedestrian red light running judging method and device and electronic equipment | |
| CN109003457B (en) | Method and device for recording behaviors of multiple motor vehicles illegally occupying emergency lane | |
| CN113112813B (en) | Illegal parking detection method and device | |
| CN116434161B (en) | Method and system for judging whether parking behavior based on high-order video is credible | |
| CN114821491A (en) | Vehicle parking violation identification method and device, electronic equipment and storage medium | |
| CN116152753A (en) | Vehicle information identification method and system, storage medium and electronic device | |
| KR101407394B1 (en) | System for abandoned and stolen object detection | |
| WO2017077261A1 (en) | A monocular camera cognitive imaging system for a vehicle | |
| CN113112814B (en) | Snapshot method and device without stopping right turn and computer storage medium | |
| CN112597924B (en) | Electric bicycle track tracking method, camera device and server | |
| CN115115978A (en) | Object identification method and device, storage medium and processor |
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 |