CN111243024A - Parking area identification system and method, detection system and method and security system - Google Patents
Parking area identification system and method, detection system and method and security system Download PDFInfo
- Publication number
- CN111243024A CN111243024A CN202010039692.6A CN202010039692A CN111243024A CN 111243024 A CN111243024 A CN 111243024A CN 202010039692 A CN202010039692 A CN 202010039692A CN 111243024 A CN111243024 A CN 111243024A
- Authority
- CN
- China
- Prior art keywords
- parking area
- image
- comparison result
- acquisition unit
- processing unit
- 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
Images
Classifications
-
- 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
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/20—Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles
- G08G1/207—Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles with respect to certain areas, e.g. forbidden or allowed areas with possible alerting when inside or outside boundaries
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30232—Surveillance
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The scheme provides a parking area identification system and method, a detection system and method and a security system, and comprises an image acquisition unit, an intelligent vision processing unit and an intelligent terminal, wherein the image acquisition unit is used for acquiring and transmitting an image of a standard parking area with traffic marked lines drawn thereon to the intelligent vision processing unit and the intelligent terminal; the intelligent vision processing unit is connected with the image acquisition unit and used for identifying and detecting the position coordinates of the traffic marking according to the received image and drawing the corresponding position coordinates on the image through a mark to obtain a processed image; and the intelligent terminal is connected with the image acquisition unit and the intelligent vision processing unit and used for selectively feeding back the processed image to the intelligent vision processing unit or obtaining the reference coordinates of the parking area according to the comparison result of the received processed image and the image of the standard parking area with the traffic marking acquired by the image acquisition unit. The scheme can provide a consistent system and an implementation method thereof, which reduce restriction conditions and improve the intelligence in operation.
Description
Technical Field
The invention relates to the field of vehicle parking area border crossing identification and detection, in particular to a parking area identification system and method, a detection system and method and a security system.
Background
With the increasing number of vehicles, the parking problem of the vehicles is increasingly obvious, for the sake of urban beauty and convenient management, the vehicles need to be parked in a standard area, the standard area is an allowed parking area defined by relevant departments, interference is brought to public transportation when the area exceeds the allowed parking area, and the definition of the standard area is to guide citizens to park reasonably and normally. However, particularly in hot spot areas during peak hours, vehicles are piled up, parked disorderly or not parked in a designated area, and the urban appearance is influenced and the public trip is disturbed.
Based on this, a parking area video security system (namely, a parking area security system) is required to identify vehicle information and pedestrian behaviors through an artificial intelligence algorithm, monitored area object state information is fed back to a supervision and operation and maintenance department in time, so that the influence of the disorderly sequence of the area vehicles on public places is rapidly handled, wherein the out-of-range detection is an inspection item for judging whether the object position identified by the security system falls in a standard area, and if the identified monitored object position exceeds the standard area, a system alarm event is triggered. The parking area security system is an object recognition and detection system based on intelligent vision and depends on signal perception of a camera. The coordinate position of the specification area in the computer system is influenced by the parking area, the position of the camera and the visual angle of the camera. Generally, a certain fixed relation between the camera view angle and the parking area may be required, or parameters related to the camera view angle and the standard area may be measured and input into the system, so as to facilitate the calculation of the corresponding coordinate system. However, in practice, the situation of the parking area is varied, the actual installation position of the camera is adapted according to the situation, the detection accuracy is low, and the traditional vision-based method has high complexity of an image processing algorithm and large calculation amount, so that the cost is high, and the method is not suitable for detection application of large-scale out-of-range parking area.
Disclosure of Invention
In view of the above-mentioned defects in the prior art, the technical problem to be solved by the present invention is the problem caused by the inconsistency of the boundary-crossing areas of each parking area in the existing parking area identification process, and the present invention aims to provide a parking area identification system and method, a detection system and method, and a security system, which can consistently reduce the restriction conditions and improve the intellectualization in operation.
In order to achieve the above object, the present invention provides a parking area recognition system, comprising an image acquisition unit, an intelligent vision processing unit, and an intelligent terminal, wherein,
the intelligent vision processing unit is used for acquiring and transmitting the image of the standard parking area with the traffic marking drawn to the intelligent vision processing unit and the intelligent terminal;
the intelligent vision processing unit is connected with the image acquisition unit and used for identifying and detecting the position coordinates of the traffic marking lines according to the received images and drawing the corresponding position coordinates on the images through marks to obtain processed images;
and the intelligent terminal is connected with the image acquisition unit and the intelligent vision processing unit and used for selectively feeding back the processed image to the intelligent vision processing unit or obtaining the reference coordinates of the parking area according to the comparison result of the received processed image and the image of the standard parking area with the traffic marking acquired by the image acquisition unit.
Preferably, the parking area recognition system, wherein the image acquisition unit includes an RGB camera, or a grayscale camera, or an infrared night vision camera.
Preferably, the parking area recognition system, wherein the intelligent terminal includes an image display unit, and the image display unit is configured to display the received processed image and the image of the standard parking area on which the traffic marking is drawn.
Preferably, the parking area recognition system, wherein the intelligent vision processing unit comprises a deep neural network based machine learning artificial intelligence algorithm model.
The scheme also provides a parking area identification method, which comprises the following steps:
s1: acquiring an image of a standard parking area with traffic marked lines;
s2: recognizing and detecting the position coordinates of the traffic marking according to the image acquired in the step S1, drawing the corresponding position coordinates on the image through a mark to obtain a processed image, and continuing to execute the step S3;
s3: selectively executing S4 or returning to S2 according to whether the comparison result between the processed image and the image of the standard parking area with the traffic marking is consistent or not; if the comparison result is inconsistent, returning to the step S2; if the comparison result is consistent, executing S4;
s4: and obtaining the reference coordinates of the parking area.
Preferably, the parking area recognition method, wherein the detecting of the position coordinates of the traffic marking based on the acquired image recognition in S2 specifically includes: and recognizing and detecting the position coordinates of the traffic marking according to the acquired image by adopting a deep neural network-based machine learning artificial intelligence algorithm model.
Preferably, the parking area identification method, wherein if the comparison result in S3 is consistent, executing S4 specifically includes: and when the comparison result of the processed image and the image of the standard parking area with the traffic marking is consistent, the identification is successful, the identification process is ended, and the processed image is used as the reference coordinate of the parking area.
The scheme also provides a parking area detection system, which comprises the parking area identification system and a server connected with the parking area identification system, wherein,
the image acquisition unit is used for acquiring a real-time state image of the parking area and transmitting the real-time state image to the server;
the server is stored with the parking area reference coordinate and used for judging whether the vehicle is parked out of bounds or not according to the comparison result of the acquired real-time state image and the parking area reference coordinate.
Preferably, the parking area detection system further includes an alarm unit, where the alarm unit is connected to the server, and is configured to trigger an alarm event when the server determines that the vehicle is parked out of range.
The scheme also provides a parking area detection method, the detection method adopts the parking area detection system, and the method specifically comprises the following steps:
t1: acquiring a real-time state image of a parking area by using the image acquisition unit and transmitting the real-time state image to the server;
t2: and judging whether the vehicle is parked out of range or not by utilizing the server according to the comparison result of the acquired real-time state image and the parking area reference coordinate.
Preferably, the parking area detection method further includes, after the T2, a step of T3: and when the server judges that the vehicle is parked out of range, triggering an alarm event.
The scheme also provides a parking area security system which is provided with the parking area identification system.
The scheme also provides a parking area security system which is provided with the parking area detection system.
Compared with the prior art, the implementation of the invention achieves the following obvious technical effects:
1. the parking area identification system and the method thereof can provide a consistent standard area identification method without requirements on the position of a parking area, the shape of the standard area, the relative installation position of a camera and the visual angle, have wider application range, can reduce restriction conditions, improve the intelligence of operation, reduce complex coordinate system conversion calculation, can be suitable for the boundary of the parking area with any shape, are not restricted by related factors, and are more suitable for the development direction of the prior art.
2. The parking area identification system and the method thereof based on the invention utilize a deep neural network machine learning artificial intelligence algorithm model to identify and detect the position coordinates of the traffic marking lines, realize optimization through continuous calibration, identify the boundary marks of the parking area to be consistent with the boundary marks in the image, obtain the reference coordinates of the parking area which are the same as the actual parking area, establish the coordinate system conversion of the monitoring area position and the camera video and image positions, implicitly establish the conversion of the coordinate system, reduce the operation flow and have good consistency of the operation flow.
3. The parking area identification system and the method thereof can realize the definition of the standard area by the parking area boundary consistency confirmation strategy, establish each parking area standard area and form the parking area reference coordinate, and the subsequent boundary crossing detection is based on the configuration.
4. The parking area detection system and method provided by the invention provide a scheme for automatically identifying whether the vehicle is parked and out of bounds based on the parking area identification system and method and the parking area reference coordinate formed by the parking area identification system and method.
5. The parking area identification system and method, and the parking area detection system and method are suitable for the border crossing area setting scene in the video security border crossing detection field, and can realize security protection and alarm when automatic vehicles are parked in a border crossing way.
The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, the features and the effects of the present invention.
Drawings
Fig. 1 is a schematic diagram of a parking area recognition system according to a preferred embodiment of the present invention 1.
Fig. 2 is a schematic view of an application scenario of the parking area recognition system in embodiment 1 of the present invention.
Fig. 3 is a schematic diagram of a parking area identification method according to a preferred embodiment of the present invention in embodiment 2.
Fig. 4 is a schematic diagram of a parking area detection method according to a preferred embodiment of the present invention in embodiment 4.
Wherein: 100-a parking area identification system, 10-an image acquisition unit, 20-an intelligent vision processing unit and 30-an intelligent terminal.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the drawings only show the components related to the present invention rather than the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
Example 1:
as shown in fig. 1 and 2, embodiment 1 provides a parking area recognition system 100, which includes an image acquisition unit 10, an intelligent vision processing unit 20, and an intelligent terminal 30, wherein,
the image acquisition unit 10 is used for transmitting the image of the standard parking area with the traffic marking drawn thereon to the intelligent vision processing unit 20 and the intelligent terminal 30;
the intelligent vision processing unit 20 is connected with the image acquisition unit 10 and used for identifying and detecting the position coordinates of the traffic marking according to the received image and drawing the corresponding position coordinates on the image through a mark to obtain a processed image;
and the intelligent terminal 30 is connected with the image acquisition unit 10 and the intelligent vision processing unit 20, and is used for selectively feeding back the processed image to the intelligent vision processing unit 20 or obtaining the reference coordinates of the parking area according to the comparison result between the received processed image and the image of the standard parking area with the traffic marking acquired by the image acquisition unit 10. Specifically, the comparison between the processed image and the image of the standard parking area with traffic markings acquired by the image acquisition unit 10 is to observe whether the two images coincide with each other, if so, it is indicated that the comparison result between the processed image and the image of the standard parking area with traffic markings acquired by the image acquisition unit 10 is consistent, and if not, it is indicated that the comparison result between the processed image and the image of the standard parking area with traffic markings acquired by the image acquisition unit 10 is inconsistent; when the received processed image is inconsistent with the comparison result of the image of the standard parking area with the traffic marking, which is acquired by the image acquisition unit 10, it indicates that there is still an error in the establishment of the reference coordinate of the parking area, and the comparison result needs to be continuously fed back to the intelligent vision processing unit 20 for processing, and the contents of the comparison result and the like are selectively fed back to the intelligent vision processing unit 20 for circular processing, and the comparison result can be used as the reference data for circular processing by the intelligent vision processing unit 20, and the intelligent vision processing unit 20 repeatedly learns and works, that is, the position coordinate of the traffic marking is detected according to the received image identification, and the corresponding position coordinate is marked on the image to obtain the processed image. Until the processed image coincides with the image of the standard parking area with the traffic marking acquired by the image acquisition unit 10, that is, when the comparison result between the received processed image and the image of the standard parking area with the traffic marking acquired by the image acquisition unit 10 is consistent, the processed image can be used as an accurate parking area reference coordinate, and at this time, the identification process can be ended, and the parking area reference coordinate can be obtained.
The parking regulation area is a regulation parking area set by a relevant department and is drawn with corresponding traffic marking lines. The image acquisition unit 10 includes an RGB camera, a grayscale camera, or an infrared night vision camera, specifically, the image acquisition unit 10 may select a camera with a caucasian model of DS-2CD3T45P1-I, the image acquisition unit 10 may acquire an image or a video, the video may be decoded by the image acquisition unit 10 to obtain a picture, the general video is 25 frames per second, that is, the video is synthesized from 25 pictures in one second. The intelligent terminal 30 may be a smart phone, a tablet, or the like, and may have a video display function, an image display function, and a wired or wireless connection function to implement data transmission and storage.
The intelligent terminal 30 includes an image display unit for displaying the received processed image and the image of the standard parking area on which the traffic marking is drawn. The image display unit may also be a video playing client, and may receive and play video and image data sensed by the camera and video and image data processed by the intelligent visual processing unit 20.
In some embodiments, the intelligent vision processing unit 20 includes a deep neural network based machine learning artificial intelligence algorithm model. A Yolov3 model is selected based on a deep neural network machine learning artificial intelligence algorithm model, and the Yolov3 model has the advantages of full coverage of mainstream business, high speed and high precision.
The parking area recognition system 100 of the invention can provide a consistent standard area recognition method without requirements on the position of a parking area, the shape of the standard area, the relative installation position of a camera and the visual angle, has wider application range, can reduce restriction conditions, simultaneously improves the intelligence of operation, reduces the complicated coordinate system conversion calculation, can be suitable for the boundary of the parking area with any shape, is not restricted by related factors, and is more suitable for the development direction of the prior art; the method comprises the steps of recognizing and detecting position coordinates of traffic marking lines by using a deep neural network machine learning artificial intelligence algorithm model, realizing optimization through continuous calibration, obtaining parking area reference coordinates which are the same as actual parking areas, recognizing that boundary marks of the parking areas are consistent with boundary marks in images, establishing coordinate system conversion of monitoring area positions and camera video image positions, and implicitly establishing coordinate system conversion, so that the problem caused by possible inconsistency of boundary-crossing areas of each parking area in the recognition process is solved, operation processes are reduced, and the operation processes have good consistency; by the parking area identification system 100 and the method thereof, the specification areas can be defined by the parking area boundary consistency confirmation strategy, each parking area specification area is established, the parking area reference coordinate is formed, and the subsequent boundary crossing detection is based on the configuration.
Example 2:
as shown in fig. 3, embodiment 2 provides a parking area identification method, including the steps of:
s1: and acquiring an image of the standard parking area with the traffic marking lines. The image obtaining unit 10 may be used to obtain an image of a standard parking area on which traffic markings are drawn, which is previously drawn by a relevant department.
S2: recognizing and detecting the position coordinates of the traffic markings according to the image acquired in the step S1, drawing the corresponding position coordinates on the image through a mark to obtain a processed image, and continuing to execute the step S3; the step S2 of recognizing and detecting the position coordinates of the traffic marking based on the acquired image includes: and recognizing and detecting the position coordinates of the traffic marking according to the acquired image by adopting a deep neural network-based machine learning artificial intelligence algorithm model. After the image of the standard parking area is obtained, the image of the standard parking area can be obtained by the streaming media server in a wireless or wired mode, then the streaming media server identifies and detects the position coordinates of the traffic marking according to the obtained image, the above process can be realized in a certain process after the streaming media server is started, namely, the position coordinates of the traffic marking can be predicted through an intelligent visual algorithm when the streaming media server is started. The streaming server may be specifically implemented by an app.
S3: selectively executing S4 or returning to S2 according to whether the comparison result between the processed image and the image of the standard parking area with the traffic marking is consistent or not; if the comparison result is inconsistent, returning to the step S2; if the comparison result is consistent, executing S4;
the main body executed in S3 is the intelligent terminal 30, and may be specifically implemented by an app on the intelligent terminal 30, and the comparison result of the image of the standard parking area on which the traffic marking is drawn may be compared by a user to obtain a comparison result, and it is determined by human vision whether the processed image coincides with the image of the standard parking area on which the traffic marking is drawn. If the comparison result is matched, the following S4 is executed. Whether the comparison result is consistent or not can be judged by the user, and as corresponding to the embodiment 1, the comparison between the processed image and the image of the standard parking area with the traffic marking acquired by the image acquisition unit 10 is to observe whether the comparison result is coincident or not, if so, the comparison result between the processed image and the image of the standard parking area with the traffic marking acquired by the image acquisition unit 10 is consistent, and if not, the comparison result between the processed image and the image of the standard parking area with the traffic marking acquired by the image acquisition unit 10 is inconsistent; when the received processed image is inconsistent with the comparison result of the image of the standard parking area with the traffic marking, which is acquired by the image acquisition unit 10, it indicates that there is still an error in the establishment of the reference coordinate of the parking area, and the comparison result needs to be continuously fed back to the intelligent vision processing unit 20 for processing, and the contents of the comparison result and the like are selectively fed back to the intelligent vision processing unit 20 for circular processing, and the comparison result can be used as the reference data for circular processing by the intelligent vision processing unit 20, and the intelligent vision processing unit 20 repeatedly learns and works, that is, the position coordinate of the traffic marking is detected according to the received image identification, and the corresponding position coordinate is marked on the image to obtain the processed image. Until the processed image coincides with the image of the standard parking area with the traffic marking acquired by the image acquisition unit 10, that is, when the comparison result between the received processed image and the image of the standard parking area with the traffic marking acquired by the image acquisition unit 10 is consistent, the processed image can be used as an accurate parking area reference coordinate, and at this time, the identification process can be ended, and the parking area reference coordinate can be obtained. The position coordinates for drawing the traffic marking lines are drawn by the streaming media server, the coordinates consistent with the actual marking lines are obtained through feedback learning, the coordinates can be recorded by a system to be used as parking area reference coordinates, and the reference coordinates of the parking area can be used as standard coordinates in the later (corrected) image or video for parking area detection.
S4: and obtaining the reference coordinates of the parking area. Specifically, the method comprises the following steps: and when the comparison result of the processed image and the image of the standard parking area with the traffic marking is consistent, the identification is successful, the identification process is ended, and the processed image is used as the reference coordinate of the parking area.
It can be seen that in S4, if the comparison result is determined to be inconsistent, the process returns to S2 to S3, and S2 to S3 are executed in a loop until the comparison result is finally determined to be consistent, the recognition is successful and the recognition process is ended, and the processed image is used as the parking area reference coordinate.
The above-mentioned S1 to S4 may be implemented by using the above-mentioned parking area recognition system, and the principle and process of implementation thereof are consistent, or other systems and units may be used, and the finally obtained parking area reference coordinates may be used by the following parking area detection system and method, parking area security system and method, and the applied scene is not limited to the following parking area detection system and parking area detection method, parking area security system and parking area security method, and may have other uses, for example, optimization of a parking area, and the like, and the use is very wide.
In some embodiments, through one cycle, the processed image may not be consistent with the image of the standard parking area with the traffic marking, and multiple times of feedback and learning are required, so that the processed image is gradually consistent with the image of the standard parking area with the traffic marking, and finally, the processed image is overlapped with the image of the standard parking area with the traffic marking, and the parking area is successfully identified, and the conversion of a coordinate system is completed. The processed image is obtained through calculation of an artificial intelligence algorithm, and the image of the standard parking area with the traffic marking lines can be obtained through a camera.
The parking area identification method provided by the invention can provide a consistent standard area identification method without requirements on the position of the parking area, the shape of the standard area, the relative installation position of the camera and the visual angle, has a wider application range, can reduce restriction conditions, simultaneously improves the intelligence in operation, reduces the complicated coordinate system conversion calculation, can be suitable for the parking area boundary with any shape, is not restricted by related factors, and is more suitable for the development direction of the prior art; the method comprises the steps of recognizing and detecting position coordinates of traffic marking lines by using a deep neural network machine learning artificial intelligence algorithm model, realizing optimization through continuous calibration, obtaining parking area reference coordinates which are the same as actual parking areas, recognizing that boundary marks of the parking areas are consistent with boundary marks in images, establishing coordinate system conversion of monitoring area positions and camera video image positions, and implicitly establishing coordinate system conversion, so that the problem caused by possible inconsistency of boundary-crossing areas of each parking area in the recognition process is solved, operation processes are reduced, and the operation processes have good consistency; by the parking area identification system 100 and the method thereof, the specification areas can be defined by the parking area boundary consistency confirmation strategy, each parking area specification area is established, the parking area reference coordinate is formed, and the subsequent boundary crossing detection is based on the configuration.
Example 3:
embodiment 3 provides a parking area detection system including the parking area recognition system 100, and further including a server connected to the parking area recognition system 100, wherein,
the image acquisition unit 10 is configured to acquire a real-time status image of a parking area and transmit the real-time status image to the server;
the server comprises a storage medium, wherein the parking area reference coordinate is stored in the storage medium and is used for judging whether the vehicle is parked out of bounds or not according to the comparison result of the acquired real-time state image and the parking area reference coordinate.
The method of using the parking area detection system of embodiment 3 includes the steps of:
t1: the image acquisition unit 10 is used for acquiring a real-time state image of the parking area and transmitting the real-time state image to the server. The real-time status image is a real-time status image including that the vehicle is parked in the parking area, and the acquired image is an image within a certain range of the parking area.
T2: the server is used for judging whether the vehicle is parked out of bounds or not according to the comparison result of the acquired real-time state image and the parking area reference coordinate, the vehicle is observed through human eyes, the camera can shoot an actual drawn line (an actual traffic marking line), a virtual area frame can be drawn after artificial intelligence identification, and whether the actual drawn line is overlapped or not is observed and compared through the human eyes.
T3: and when the server judges that the vehicle is parked out of range, triggering an alarm event. The warning event can be pushed to a responsible person or related personnel in the parking area through the server, so that the vehicles in the border-crossing area can be tidied in time, and the parking standard of the vehicles is ensured. The parking area detection system of the invention provides a scheme for automatically identifying whether the vehicle is parked out of bounds, namely whether the vehicle exceeds the boundary of a standard area or not based on the parking area identification method and the formed parking area reference coordinate. The parking area detection method is simple to implement, has a very accurate detection result, is not limited to a certain vehicle parking area or parking scene, is wide in application range, and reduces cost.
The image acquisition unit 10 can also acquire information of vehicles and pedestrians in a parking area in real time; the intelligent vision processing unit 20 can also recognize the detected vehicle information, the traffic density, and the type and specific position of the object. The image acquisition unit 10 in the parking area detection system and the image acquisition unit 10 in the parking area recognition system 100 may be the same camera, and there is no requirement for the position, the placement angle, etc. of the camera.
The server only needs to be capable of storing data and receiving and sending related instructions, has a video and image playing function, can manually judge whether the vehicle is parked out of bounds according to a comparison result of the acquired real-time state image and the parking area reference coordinate, can also judge whether the vehicle is parked out of bounds according to a comparison result of the acquired real-time state image and the parking area reference coordinate, and can also adopt the intelligent terminal 30. As a preferred embodiment, the server may be selected from, but not limited to, an arilocos GPU server GN5(Nvidia P100).
In some embodiments, the system further comprises an alarm unit, wherein the alarm unit is connected to the server and is used for triggering an alarm event when the server determines that the vehicle is parked out of bounds. The out-of-range detection is an inspection item for judging whether the position of an object identified by the security system falls in a standard area, and if the identified position of the monitored object exceeds the standard area, a system alarm event is triggered. The warning event can be pushed to a responsible person or related personnel in the parking area through the server, so that the vehicles in the border-crossing area can be tidied in time, and the parking standard of the vehicles is ensured.
Example 4:
as shown in fig. 4, embodiment 4 provides a parking area detection method, where the detection method employs the parking area detection system, and specifically includes the following steps:
t1: the image acquisition unit 10 is used for acquiring a real-time state image of the parking area and transmitting the real-time state image to the server. The real-time status image is a real-time status image including that the vehicle is parked in the parking area, and the acquired image is an image within a certain range of the parking area.
T2: the server is used for judging whether the vehicle is parked out of bounds or not according to the comparison result of the acquired real-time state image and the parking area reference coordinate, the camera can shoot an actual drawn line (an actual traffic marking line) and draw a virtual area frame after artificial intelligent identification, and at the moment, whether the actual drawn line is overlapped or not can be easily observed and compared.
T3: and when the server judges that the vehicle is parked out of range, triggering an alarm event. The warning event can be pushed to a responsible person or related personnel in the parking area through the server, so that the vehicles in the border-crossing area can be tidied in time, and the parking standard of the vehicles is ensured.
The parking area detection system and method provided by the invention provide a scheme for automatically identifying whether the vehicle is parked out of bounds, namely whether the vehicle exceeds the boundary of a standard area or not based on the parking area identification method and the formed parking area reference coordinate. The parking area detection method is simple to implement, has a very accurate detection result, is not limited to a certain vehicle parking area or parking scene, is wide in application range, and reduces cost.
Example 5:
the scheme also provides a parking area security system which is provided with the parking area identification system 100. The parking area security system in embodiment 5 is mainly applied to video security when the vehicle is in a parking area, and the vehicle can be a shared bicycle, a shared electric bicycle, a shared automobile, or the like. When the vehicle is a shared bicycle or a shared electric bicycle, the parking area identification system 100 is partially installed on the vehicle or in a parking area, and forms a parking area security system together with other security devices.
The server included in the parking area security system may be only required to be capable of storing data and receiving and sending related instructions, and have a video and image playing function, and may manually determine whether the vehicle is parked out of bounds according to a comparison result between the acquired real-time state image and the parking area reference coordinate, or may automatically determine whether the vehicle is parked out of bounds according to a comparison result between the acquired real-time state image and the parking area reference coordinate, and the server may also adopt the intelligent terminal 30.
Example 6:
the scheme also provides a parking area security system which is provided with the parking area detection system. The parking area security system in embodiment 6 is mainly applied to video security when the vehicle is in a parking area, and the vehicle can be a shared bicycle, a shared electric bicycle, a shared automobile, or the like. When the vehicle is a shared bicycle or a shared electric bicycle, the parking area detection system is partially arranged on the vehicle or in a parking area and forms a parking area security system together with other security devices.
The server included in the parking area security system may be only required to be capable of storing data and receiving and sending related instructions, and have a video and image playing function, and may manually determine whether the vehicle is parked out of bounds according to a comparison result between the acquired real-time state image and the parking area reference coordinate, or may automatically determine whether the vehicle is parked out of bounds according to a comparison result between the acquired real-time state image and the parking area reference coordinate, and the server may also adopt the intelligent terminal 30.
The parking area identification system 100 and method thereof, and the parking area detection system and method are suitable for setting a boundary crossing area scene in the video security boundary crossing detection field, and can realize security protection and alarm when automatic vehicles are parked in a boundary crossing way.
Storage medium in the above embodiments-any of various types of memory devices or storage devices. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk, or tape devices; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, Lanbas (Rambus) RAM, etc.; non-volatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the computer system in which the program is executed, or may be located in a different second computer system connected to the computer system through a network (such as the internet). The second computer system may provide the program instructions to the computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations, such as in different computer systems that are connected by a network. The storage medium may store program instructions (e.g., embodied as a computer program) that are executable by one or more processors.
Of course, the storage medium provided in the embodiments of the present application and containing computer-executable instructions is not limited to the operations of the parking area identification method and the parking area detection method described above, and may also perform related operations in the parking area identification method and the parking area detection method provided in any embodiments of the present application.
It should be noted that the computer readable medium mentioned above in the present application may be a computer readable signal medium or a computer readable medium or any combination of the two. A computer readable medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to perform: responding to a key operation of a user, and determining an operation instruction type based on the key operation; encrypting the operation instruction type, the timestamp and the instruction serial number by adopting a preset key to obtain and send an encryption instruction; and receiving a reply instruction of the vehicle, wherein the reply instruction comprises an execution result of the encryption instruction.
Or performing:
receiving an encryption command which is sent by a remote control key and contains an operation command type; the encryption instruction further comprises a timestamp and an instruction serial number, and the encryption instruction is obtained by encrypting with a preset key; decrypting the encrypted instruction, verifying a timestamp and an instruction sequence number in the encrypted instruction, and if the encrypted instruction passes the verification, executing an operation instruction of the operation instruction type; and sending a reply instruction to the remote control key, wherein the reply instruction comprises an execution result of the encryption instruction.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or electronic device. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software or hardware. The names of the modules and units do not limit the modules and units in some cases.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the disclosure. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (12)
1. A parking area recognition system is characterized by comprising an image acquisition unit, an intelligent vision processing unit and an intelligent terminal, wherein,
the intelligent vision processing unit is used for acquiring and transmitting the image of the standard parking area with the traffic marking drawn to the intelligent vision processing unit and the intelligent terminal;
the intelligent vision processing unit is connected with the image acquisition unit and used for identifying and detecting the position coordinates of the traffic marking lines according to the received images and drawing the corresponding position coordinates on the images through marks to obtain processed images;
and the intelligent terminal is connected with the image acquisition unit and the intelligent vision processing unit and used for selectively feeding back the processed image to the intelligent vision processing unit or obtaining the reference coordinates of the parking area according to the comparison result of the received processed image and the image of the standard parking area with the traffic marking acquired by the image acquisition unit.
2. The parking area recognition system of claim 1, wherein the intelligent terminal comprises an image display unit, and the image display unit is configured to display the received processed image and the image of the standardized parking area on which the traffic markings are drawn.
3. The parking area recognition system of claim 1, wherein the intelligent vision processing unit comprises a deep neural network based machine learning artificial intelligence algorithm model.
4. A parking area identification method, comprising the steps of:
s1: acquiring an image of a standard parking area with traffic marked lines;
s2: recognizing and detecting the position coordinates of the traffic marking according to the image acquired in the step S1, drawing the corresponding position coordinates on the image through a mark to obtain a processed image, and continuing to execute the step S3;
s3: selectively executing S4 or returning to S2 according to whether the comparison result between the processed image and the image of the standard parking area with the traffic marking is consistent or not; if the comparison result is inconsistent, returning to the step S2; if the comparison result is consistent, executing S4;
s4: and obtaining the reference coordinates of the parking area.
5. The parking area recognition method according to claim 4, wherein the detecting of the position coordinates of the traffic markings based on the acquired image recognition in S2 specifically includes: and recognizing and detecting the position coordinates of the traffic marking according to the acquired image by adopting a deep neural network-based machine learning artificial intelligence algorithm model.
6. The parking area recognition method of claim 4, wherein if the comparison result in the step S3 is consistent, the step S4 further comprises: and when the comparison result of the processed image and the image of the standard parking area with the traffic marking is consistent, the identification is successful, the identification process is ended, and the processed image is used as the reference coordinate of the parking area.
7. A parking area detection system comprising the parking area identification system of claim 1, further comprising a server connected to the parking area identification system, wherein,
the image acquisition unit is used for acquiring a real-time state image of the parking area and transmitting the real-time state image to the server;
the server is stored with the parking area reference coordinate and used for judging whether the vehicle is parked out of bounds or not according to the comparison result of the acquired real-time state image and the parking area reference coordinate.
8. The parking area detection system of claim 7, further comprising an alarm unit, connected to the server, for triggering an alarm event when the server determines that the vehicle is parked out of bounds.
9. A parking area detection method, characterized in that the detection method employs the parking area detection system of claim 8, and specifically comprises the steps of:
t1: acquiring a real-time state image of a parking area by using the image acquisition unit and transmitting the real-time state image to the server;
t2: and judging whether the vehicle is parked out of range or not by utilizing the server according to the comparison result of the acquired real-time state image and the parking area reference coordinate.
10. The parking area detection method of claim 9, further comprising a T3 after the T2: and when the server judges that the vehicle is parked out of range, triggering an alarm event.
11. A parking area security system characterized in that a parking area identification system according to any one of claims 1 to 3 is provided.
12. A parking area security system characterized in that a parking area detection system according to any one of claims 7 to 8 is provided.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010039692.6A CN111243024A (en) | 2020-01-14 | 2020-01-14 | Parking area identification system and method, detection system and method and security system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010039692.6A CN111243024A (en) | 2020-01-14 | 2020-01-14 | Parking area identification system and method, detection system and method and security system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111243024A true CN111243024A (en) | 2020-06-05 |
Family
ID=70871126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010039692.6A Pending CN111243024A (en) | 2020-01-14 | 2020-01-14 | Parking area identification system and method, detection system and method and security system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111243024A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111915898A (en) * | 2020-07-24 | 2020-11-10 | 杭州金通科技集团股份有限公司 | Parking monitoring AI electronic post house |
| CN112507970A (en) * | 2020-12-24 | 2021-03-16 | 杭州电子科技大学 | Unmanned car washing image recognition anti-collision system and recognition method based on PointRend algorithm |
| CN113780183A (en) * | 2021-09-13 | 2021-12-10 | 宁波小遛共享信息科技有限公司 | Standard parking determination method and device for shared vehicles and computer equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086708A (en) * | 2018-07-25 | 2018-12-25 | 深圳大学 | A kind of parking space detection method and system based on deep learning |
| CN109389829A (en) * | 2018-11-05 | 2019-02-26 | 湖北民族学院 | A kind of illegal parking recognition methods and system |
| CN109741625A (en) * | 2019-02-15 | 2019-05-10 | 江苏镭博智能科技有限公司 | A kind of prison bat identification equipment and its prison bat recognition methods for parking lot |
| CN110176151A (en) * | 2019-06-17 | 2019-08-27 | 北京精英路通科技有限公司 | A kind of method, apparatus, medium and the equipment of determining parking behavior |
-
2020
- 2020-01-14 CN CN202010039692.6A patent/CN111243024A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086708A (en) * | 2018-07-25 | 2018-12-25 | 深圳大学 | A kind of parking space detection method and system based on deep learning |
| CN109389829A (en) * | 2018-11-05 | 2019-02-26 | 湖北民族学院 | A kind of illegal parking recognition methods and system |
| CN109741625A (en) * | 2019-02-15 | 2019-05-10 | 江苏镭博智能科技有限公司 | A kind of prison bat identification equipment and its prison bat recognition methods for parking lot |
| CN110176151A (en) * | 2019-06-17 | 2019-08-27 | 北京精英路通科技有限公司 | A kind of method, apparatus, medium and the equipment of determining parking behavior |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111915898A (en) * | 2020-07-24 | 2020-11-10 | 杭州金通科技集团股份有限公司 | Parking monitoring AI electronic post house |
| CN112507970A (en) * | 2020-12-24 | 2021-03-16 | 杭州电子科技大学 | Unmanned car washing image recognition anti-collision system and recognition method based on PointRend algorithm |
| CN113780183A (en) * | 2021-09-13 | 2021-12-10 | 宁波小遛共享信息科技有限公司 | Standard parking determination method and device for shared vehicles and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111243024A (en) | Parking area identification system and method, detection system and method and security system | |
| US10740964B2 (en) | Three-dimensional environment modeling based on a multi-camera convolver system | |
| CN110738150B (en) | Camera linkage snapshot method and device and computer storage medium | |
| CN105632182B (en) | A kind of method and its system that rule-breaking vehicle behavior is put to the proof | |
| CN110533923A (en) | Parking management method, device, computer equipment and storage medium | |
| CN108128245A (en) | Vehicle environmental imaging system and method | |
| US11842516B2 (en) | Homography through satellite image matching | |
| CN110705359B (en) | Parking space detection method | |
| CN106791710A (en) | Object detection method, device and electronic equipment | |
| CN103359020A (en) | Motorcycle driving training or examination monitoring method and system | |
| CN111340877B (en) | Vehicle positioning method and device | |
| CN106503622A (en) | A kind of vehicle antitracking method and device | |
| CN112597807B (en) | Violation detection system, method and device, image acquisition equipment and medium | |
| CN111784923A (en) | Shared bicycle parking management method, system and server | |
| AU2018410435A1 (en) | Port area monitoring method and system, and central control system | |
| CN108805184B (en) | Image recognition method and system for fixed space and vehicle | |
| CN103177582A (en) | All-in-one machine with video velocity measurement and vehicle license plate recognition | |
| CN107464446A (en) | A kind of method for inspecting and device of vertical parking stall parking information | |
| US20140320645A1 (en) | Method for Detecting and Documenting the Speeds of a Plurality of Vehicles in an Image Document | |
| CN109785654A (en) | Vehicle guidance based on locational space model | |
| CN113990101B (en) | Method, system and processing device for detecting vehicles in no-parking area | |
| WO2022088766A1 (en) | Image processing method, medium, device, and image processing system | |
| CN109903308B (en) | Method and device for acquiring information | |
| CN108256502A (en) | Security system based on image procossing | |
| CN112422895A (en) | Image analysis tracking and positioning system and method based on unmanned aerial vehicle |
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 |