CN114566063A - Intelligent parking space guiding management method and device and storage medium - Google Patents
Intelligent parking space guiding management method and device and storage medium Download PDFInfo
- Publication number
- CN114566063A CN114566063A CN202210081770.8A CN202210081770A CN114566063A CN 114566063 A CN114566063 A CN 114566063A CN 202210081770 A CN202210081770 A CN 202210081770A CN 114566063 A CN114566063 A CN 114566063A
- Authority
- CN
- China
- Prior art keywords
- area
- analysis model
- scene analysis
- parking space
- image information
- 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
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
- G08G1/142—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces external to the vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
- G08G1/146—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas where the parking area is a limited parking space, e.g. parking garage, restricted space
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
- G08G1/148—Management of a network of parking areas
Abstract
The application discloses a method, a device and a storage medium for intelligent parking space guidance management, which are used for optimizing parking space management. The method comprises the following steps: the method comprises the steps of collecting image information in a parking space area, identifying the image information according to a pre-trained scene analysis model, obtaining an identification result, identifying people and objects in the image information by the scene analysis model, and outputting a guidance prompt according to the identification result.
Description
Technical Field
The application relates to the technical field of intelligent security monitoring, in particular to a method, a device and a storage medium for intelligent parking space guidance management.
Background
With the continuous progress of social economy in recent years, the living conditions of people are improved, the automobile industry is greatly developed in China, and the parking space guiding management has higher requirements.
The existing parking space guidance management mainly manages the judgment of whether a vehicle exists or not and the identification of a license plate in a parking space area.
However, with the increase of vehicles in the future and the continuous development of vehicle management, the current vehicle management method has a single function, is difficult to meet the vehicle management requirements in the future intelligent environment, and has low management efficiency.
Disclosure of Invention
In order to solve the technical problem, the application provides a method, a device and a storage medium for intelligent parking space guidance management, which are used for optimizing parking space management.
The first aspect of the application provides a method for intelligent parking space guidance management, which comprises the following steps:
collecting image information in a parking space area;
identifying the image information according to a pre-trained scene analysis model, and obtaining an identification result, wherein the scene analysis model comprises identification of people and objects in the image information;
and outputting a guidance prompt according to the identification result.
Optionally, recognizing the image information according to a pre-trained scene analysis model, and obtaining a recognition result includes:
when the average gray value of the image information and the passageway gray value in front of the parking space reach preset threshold values and continuously reach preset frame numbers according to the scene analysis model, determining an area of the image information according to the scene analysis model, wherein the area at least comprises one of the following items: the system comprises a license plate identification area, a vehicle head identification area, a fire fighting access area, an illegal parking area and a parallel parking space area;
and identifying the identification area according to the scene analysis model, and obtaining an identification result.
Optionally, the identifying the region according to the scene analysis model, and obtaining an identification result includes:
when the area is determined to be the illegal parking area, identifying the illegal parking condition of the illegal parking area according to the scene analysis model to obtain an illegal parking identification result;
the outputting of the guidance prompt according to the recognition result includes:
and outputting an illegal parking alarm prompt when the illegal parking recognition result indicates that the illegal parking condition occurs.
Optionally, the identifying the region according to the scene analysis model, and obtaining an identification result includes:
when the area is determined to be a parallel parking space area, identifying whether vehicles exist in the parallel parking space area according to the scene analysis model to obtain a parallel parking space identification result;
the outputting of the guidance prompt according to the recognition result includes:
and outputting a guidance prompt of whether the parallel parking spaces exist or not according to the parallel parking space recognition result.
Optionally, the identifying the region according to the scene analysis model, and obtaining an identification result includes:
when the area is determined to be a fire fighting access area, identifying the vehicle condition in the fire fighting access area according to the scene analysis model to obtain a fire fighting access identification result;
the outputting of the guidance prompt according to the recognition result includes:
and when the fire fighting channel identification result is that the vehicle is detected and the detected vehicle is not matched with the preset vehicle, outputting a guidance prompt of illegal occupation.
Optionally, the identifying the region according to the scene analysis model, and obtaining an identification result includes:
when the regions are determined to be a license plate recognition region and a vehicle head recognition region, recognizing the existence of the vehicles in the parking space region and recognizing the license plates according to the scene analysis model to obtain the existence of the vehicles in the parking space region and recognition results of the license plates;
the outputting of the guidance prompt according to the recognition result includes:
and outputting a guidance prompt for guiding a user to park the vehicle according to the recognition result of the existence of the vehicle and the recognition result of the license plate.
Optionally, after the image information is identified according to a pre-trained scene analysis model, and a recognition result is obtained, the method further includes:
and when the recognition result comprises a face recognition result, acquiring pre-bound vehicle information according to the face recognition.
This application second aspect provides a device of intelligence parking stall guide management, includes:
the acquisition unit is used for acquiring image information in the parking space area;
the recognition unit is used for recognizing the image information according to a pre-trained scene analysis model and obtaining a recognition result, wherein the scene analysis model comprises recognition of people and objects in the image information;
and the output unit is used for outputting a guidance prompt according to the identification result.
This application third aspect provides a device of intelligence parking stall guide management, includes:
the system comprises a central processing unit, a memory, an input/output interface, a wired or wireless network interface and a power supply;
the memory is a transient storage memory or a persistent storage memory;
the central processor is configured to communicate with the memory and execute the operations of the instructions in the memory to perform the method of the first aspect.
A fourth aspect of the present application provides a computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the method of the first aspect.
According to the technical scheme, the embodiment of the application has the following advantages:
the method and the device collect image information in the parking space area, recognize the image information according to a pre-trained scene analysis model, and output a guidance prompt according to a recognition result. By identifying the image information, such as illegal parking, parking space occupation and the like, guidance is performed, management of the parking lot is optimized, and identification is performed through the model, so that identification efficiency and accuracy can be effectively improved.
Drawings
In order to more clearly illustrate the technical solutions in the present application, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic diagram of an embodiment of a method for intelligent parking space guidance management in the present application;
FIG. 2 is a schematic diagram of another embodiment of a method for intelligent parking space guidance management in the present application;
FIG. 3 is a schematic view of an apparatus for intelligent parking guidance management in the present application;
FIG. 4 is another schematic diagram of the intelligent parking space guidance management device of the present application;
fig. 5 is a schematic diagram of an entity device for intelligent parking space guidance management in the present application.
Detailed Description
The application provides a method, a system and a scene analysis model for intelligent parking space guidance management, which are used for identifying conditions such as illegal parking and parking space occupation, so that guidance management is performed, and vehicle management efficiency is improved.
The parking stall guiding management system is used for automatically identifying the situations when the vehicle in the vehicle space area occupies the parking stall and violates the parking stall, guiding and managing the vehicle, can be applied to parking stall guiding management of parking lots of shopping malls, hotels, office buildings and residential houses, and is not limited in specific places.
The following method for intelligent parking space guidance management in the application is briefly described:
referring to fig. 1, fig. 1 is a diagram illustrating an embodiment of a method for intelligent parking space guidance management in the present application, where the method may be implemented in a terminal, a server, and other devices, and for convenience of description, the following description is provided by applying the method to a system, and includes:
101. system for collecting image information in parking space area
In this embodiment, a high-definition collection camera can be arranged in the parking space area, and the collection camera can collect image information in the parking space area in real time and upload the image information to the system. When the acquired image information is video information, the video needs to be processed, each frame is extracted or one frame is taken at intervals of a plurality of frames, the extracted frame is extracted as the image information, and the video information is extracted as the image information, so that the image information can be conveniently input into a model for processing. It can be understood that image information of various parking space areas can be acquired, for example, the acquisition camera can be arranged in a parking space area of a parking lot to acquire image information of the parking lot; the system can also be arranged in a parking space area of a fire fighting lane to acquire image information of the fire fighting lane; the image acquisition system can be arranged in a parking space area of a roadside parking lot to acquire image information of the roadside parking lot, and is not limited in detail here.
102. The system identifies the image information according to a pre-trained scene analysis model and obtains an identification result, wherein the scene analysis model comprises identification of people and objects in the image information
In this embodiment, the scene analysis model is set in the system, and an initial scene analysis model needs to be trained first, so that the scene analysis model is more accurate. The method comprises the steps that a large amount of image data under different scenes need to be acquired in the training process of a scene analysis model, the image information can be acquired from a network or an acquisition camera, after a large amount of image data are acquired, due to the fact that the photographed pictures can have the problems of dim light, bright light, backlight, blurring and the like under different environments, the images need to be preprocessed in advance in order to improve image quality, for example, the images are screened out, enhanced, aligned and subjected to feature processing, so that the pictures are suitable for being used as training samples, data enhancement can be performed during training, and the rich samples are generated by color adjustment, size adjustment, horizontal turning, angle rotation and the like. Then, each sample image needs to be labeled, and the labeling information may include a vehicle, a vehicle head, a license plate, a non-motor vehicle, a human face, and the like, which is not limited herein. And then training the model according to the labeling information to obtain a trained scene analysis model. The system mainly trains a series of models such as a vehicle and vehicle head detection model, a license plate detection model, a non-motor vehicle detection model, a face recognition model, a license plate recognition model and the like.
After the collected images are input into a pre-trained scene analysis model, the system identifies the images according to the scene analysis model. When the system inputs the image into the scene analysis model, the scene analysis model performs scene judgment through comparison, and the specific implementation manner may be: matching the image information with a trained model in the scene analysis model by the scene analysis model; and when the matching value of the image information and a certain model in the trained models is higher than a preset value, outputting the recognition result of the model. For example, when the information identified in the image information and the license plate identification model are higher than a preset value, the identification result of the license plate can be obtained; when the image information and the vehicle identification model are higher than preset values, the identification result of the vehicle can be obtained; when the matching value of the image and the illegal parking behavior model is higher than a preset value, the recognition result is that the illegal parking behavior occurs; and when the matching value of the image information and the parking space occupation model is higher than a preset value, the recognition result is the parking space occupation.
103. The system outputs a guidance prompt according to the recognition result
In this embodiment, after receiving the recognition result of the scene analysis model, the system sends out a guidance prompt according to the recognition result, where the guidance prompt is preset, and the guidance prompt may have a plurality of different prompts, and outputs different guidance prompts according to different recognition results. For example, if the scene analysis model detects that the vehicle is not a fire-fighting vehicle on the fire-fighting channel and the recognition result is illegal parking, the originally set guidance prompt of the illegal parking of the fire-fighting channel is output, and otherwise, the guidance prompt is not output under the matching condition.
Optionally, a preset number of frames for guidance prompt may be further set, in order to reduce the situation of output guidance prompt in which illegal parking is determined only when the vehicle passes by or is parked temporarily, it may be determined whether the number of illegal parking frames of the illegal parking vehicle identified in the input image reaches the preset number of frames, and guidance prompt may be performed only when the illegal parking or the vehicle occupied in the parking space continuously appears and reaches the set number of frames.
Optionally, there may be a plurality of ways for the system to output the guidance prompt, and the following examples are given to output an alarm horn and output the guidance prompt to the administrator: in one implementation, an alarm horn may be disposed in the parking space area, and the system controls the alarm horn to output a guidance prompt, for example, after the parking violation is identified, the system controls the alarm horn to output a voice guidance prompt such as "please park" or the like. In another implementation manner, after the system acquires the identification result, if a guidance prompt needs to be output, the system sends the guidance prompt and information of the target vehicle to a terminal held by a manager, so that the manager manages the target vehicle according to the guidance prompt. Through can multiple mode guide suggestion, can use in the environment of multiple different demands, improve the managerial efficiency.
In this embodiment, the system collects image information in the parking space area, identifies the image information according to a pre-trained scene analysis model, and outputs a guidance prompt according to an identification result. By identifying the image information, such as illegal parking, parking space occupation and the like, guidance is performed, management of the parking lot is optimized, and identification is performed through the model, so that identification efficiency and accuracy can be effectively improved.
In this embodiment, the scene analysis model first determines a gray scale value of an input image, and determines an area of the image and identifies the area when the gray scale value is normal, which will be described in detail below with reference to the drawings.
Referring to fig. 2, fig. 2 is a schematic view of another embodiment of the method for intelligent parking space guidance management in the present application, and the following detailed description is provided by applying the method to a system:
201. system for collecting image information in parking space area
Step 201 in this embodiment is similar to step 101 in the embodiment shown in fig. 1, and is not described here again.
202. When the average gray value of the image information and the passageway gray value in front of the parking space reach the preset threshold value and continuously reach the preset frame number according to the scene analysis model, the system determines the area of the image information according to the scene analysis model, wherein the area at least comprises one of the following areas: license plate recognition area, vehicle head recognition area, fire fighting access area, illegal parking area and parallel parking space area
And after the system inputs the acquired graphic information into the trained model, firstly, judging whether the graphic information is bright or dark. In processing video, image frames in a video stream need to be distinguished, and bright and dark frame images in the video stream need to be separated. The distinguishing between bright and dark images is realized according to the average gray value of the images. After a large number of pictures of the parking space guide scenes with different bright and dark scenes are collected, the average brightness of the whole image is counted, meanwhile, the average brightness of the images of the aisle areas in front of the parking space is selected for counting, and finally, the threshold values of the bright and dark areas of the two areas are counted. After the two areas are obtained, the average brightness of the two areas on the image is counted and compared with a set threshold value, if the average brightness meets the condition, the light is considered to be normal, and subsequent operation is executed.
In practical application, the average gray value of the whole image of the collected image and the average gray value of the aisle region in front of the parking space need to be counted at the same time, if the average gray value of the whole image of the collected image and the average gray value of the aisle region in front of the parking space both reach a set threshold and continuously reach a preset frame number, the brightness is considered to be normal, and a subsequent process, namely a process of determining the region of the image information, can be performed; and when the brightness does not reach the set threshold value or the preset continuous frame number is not reached, the brightness is considered to be abnormal, and the flow of the image information area is not carried out.
In the case where the brightness is normal, it is necessary to determine the area of the image. A plurality of identification areas are arranged in the scene analysis model, and a license plate identification area, a fire fighting access area, an illegal parking area and a parallel parking space area are mainly arranged. The specific settings may be as follows: setting parking space areas, wherein 1-3 parking spaces are generally arranged; the illegal parking area is a road area in front of the parking space area and can be generated by referring to the parking space area; setting a fire fighting access area; the non-motor vehicle area is a parking space area; a parallel parking space area is arranged, and the number of the parking spaces is generally 1-2. The parking space guidance image input in each frame can be used for calculating the intersection ratio of detected targets such as vehicles, vehicle heads, license plates, non-motor vehicles, human faces and the like and various identification areas to judge which area is located. This makes it possible to determine in which area the vehicle is located in the captured image information. The intersection ratio is a ratio of the area of the intersecting regions to the area of the intersecting regions, and it can be determined which region is located when the occupied area is larger. For example, if the detected coordinates of the vehicle and the fire fighting access area are in a cross ratio to reach a set threshold value, the vehicle is considered to be located in the fire fighting access area; and if the intersection ratio of the detected vehicle coordinates and the illegal parking area reaches a set threshold value, the vehicle is considered to be in the illegal parking area. If the detected vehicle coordinates and the parallel parking space area are in a cross ratio reaching a set threshold value, outputting that a vehicle is in the parallel parking space area; and if the detected intersection ratio of the coordinates of the non-motor vehicles and the parking space area reaches a set threshold value, judging that the non-motor vehicle area occupies.
203. The system identifies the identification area according to a scene analysis model and obtains an identification result, wherein the scene analysis model comprises identification of people and objects in the image information
In this embodiment, after the area is determined, the identification area is identified according to the scene analysis model, and an identification result in the area is obtained. It should be understood that the image information may include only one region, or may include a plurality of regions, and in the case of a plurality of regions, a plurality of recognition results can be obtained, which is exemplified below:
when the area is determined to be the illegal parking area, identifying the illegal parking condition of the illegal parking area according to the scene analysis model to obtain an illegal parking identification result, wherein the identification result is as follows: the result of an illegal parking situation and the result of no parking situation;
when the area is determined to be a parallel parking space area, identifying whether vehicles in the parallel parking space area exist or not according to the scene analysis model to obtain a parallel parking space identification result, wherein the parallel vehicle identification result is as follows: with parallel and without parallel wheels;
when the area is determined to be a fire fighting access area, identifying the vehicle condition in the fire fighting access area according to the scene analysis model to obtain a fire fighting access identification result, wherein the fire fighting access identification result is as follows: the situation that the parking spaces of the fire fighting access are occupied and the situation that the parking spaces of the fire fighting access are not occupied are provided.
And when the regions are determined to be a license plate recognition region and a vehicle head recognition region, recognizing the existence of the vehicles in the parking space region and recognizing the license plates according to the scene analysis model to obtain the existence of the vehicles in the parking space region and the recognition results of the license plates. The identification result mainly comprises the following steps: the results of "there is a car with a license plate", "there is no car with a license plate", and "there is no car with an empty space". The method mainly comprises the steps of detecting the vehicle head to identify whether the vehicle is in the parking space area, and outputting 'the vehicle is in the parking space area' if the vehicle head is detected successfully. If the locomotive is not detected successfully, judging that the locomotive does not meet the condition of 'having the locomotive', and ending the current frame operation. If the license plate recognition result meets the preset confidence coefficient requirement and meets the 'vehicle condition', the recognition result is 'the vehicle with the license plate'; when the license plate recognition result meets the preset confidence requirement but does not meet the condition of 'vehicle presence', the license plate is judged as 'vehicle absence'; if the vehicle is 'present' but the license plate recognition result does not exist, whether the condition of voting as 'no-license vehicle' is met or not is judged, and if the condition is met, the 'no-license vehicle' is output; and if the license plate identification has no result and the vehicle head and vehicle detection result, judging whether the condition of voting as the 'empty space' is met, and if so, outputting the 'empty space'. The voting method can be as follows: and a video stream voting method is adopted, a queue is reserved, when the license plate recognition result reserved by the queue reaches a threshold value, voting is triggered, and the license plate recognition result is output, wherein the voting can be performed manually.
204. When the recognition result comprises a face recognition result, the system acquires pre-bound vehicle information according to the face recognition
Optionally, the scene analysis model can also be used for face recognition, and the system can acquire information of the vehicle bound with the face after receiving the face recognition result, so that reverse vehicle searching can be performed. Firstly, carrying out face detection on an input image, comparing a face coordinate with a parking space area, judging that a face exists in the parking space area after a set threshold value is reached and a frame number meets a set condition, realizing face correction through face key point positioning, and then carrying out feature extraction on a corrected face image by using a face recognition model. And binding the obtained face features with the license plate number. When the acquisition camera acquires the acquired face, the acquired face characteristics are compared with the face characteristics acquired in the previous parking space area, the same face is judged after the set threshold value is reached, and the system outputs the corresponding license plate number. The reverse vehicle searching is realized through the face recognition, the vehicle corresponding to the vehicle owner can be quickly known, and the vehicle management efficiency is improved.
205. The system outputs a guidance prompt according to the recognition result
In this embodiment, after the recognition result is obtained in step 203, different guidance prompts are output according to different recognition results, and it can be understood that when there are a plurality of different recognition results, a plurality of different guidance prompts may be output. For example: when the illegal parking recognition result is that the illegal parking condition occurs, outputting an illegal parking alarm prompt to prompt a user to normally park the vehicle, so that the management is convenient; the guidance prompt of whether the parallel parking space exists or not is output according to the parallel parking space recognition result, so that a user can conveniently park the vehicle according to the prompt under the condition that the user wants to park the vehicle; when the fire fighting channel recognition result indicates that a vehicle is detected and the detected vehicle is not matched with a preset vehicle, outputting a guidance prompt of illegal occupation, prompting a user not to occupy a fire fighting lane, and improving management efficiency; after the recognition result of whether the vehicle exists or not and the recognition result of the license plate are obtained, the vehicle can be guided to park according to the result, for example, when a certain vehicle region is detected to be an empty parking space, the parking space region is displayed for a large screen, a user with parking requirements can quickly find the region of the empty parking space, the parking space region can also be sent to a guiding terminal, and the user can know the region of the empty parking space by checking the terminal. By identifying the vehicle and the license plate and guiding the user according to the identification result, the management can be more convenient and the user experience is improved.
In this embodiment, the system collects image information in a parking space area, identifies the image information according to a pre-trained scene analysis model, determines an area, identifies the area to obtain an identification result, and if face information exists in the identification result, can acquire information of a vehicle bound with the face information, and can output a guidance prompt according to the identification result. Different areas can be determined by the scene analysis model, so that various different scenes can be identified, different guide prompts are output according to different scenes, the management of a parking lot is optimized, the information of the vehicle is acquired by face recognition, reverse vehicle searching is realized, the user experience is improved, the recognition is carried out through the model, and the recognition efficiency and accuracy can be effectively improved.
The method for intelligent parking space guidance management is explained above, and the following describes the device for intelligent parking space guidance management:
referring to fig. 3, an intelligent parking space guidance management apparatus in the present application includes:
the acquisition unit 301 is used for acquiring image information in a parking space area;
the recognition unit 302 is configured to recognize the image information according to a pre-trained scene analysis model, and obtain a recognition result, where the scene analysis model includes recognition of people and objects in the image information;
and an output unit 303, configured to output a guidance prompt according to the recognition result.
The acquisition unit 301 acquires image information in a parking space area, the recognition unit 302 recognizes the image information according to a pre-trained scene analysis model, and the output unit 303 outputs a guidance prompt according to a recognition result. By identifying the image information, such as illegal parking, parking space occupation and the like, guidance is performed, management of the parking lot is optimized, and identification is performed through the model, so that identification efficiency and accuracy can be effectively improved.
Referring to fig. 4, another intelligent parking space guidance management device in the present application includes:
the acquisition unit 401 is used for acquiring image information in a parking space area;
the recognition unit 402 includes:
the determining module 4021 is configured to determine, according to the scene analysis model, an area of the image information when the average gray value of the image information and the grayscale value of the aisle in front of the parking space both reach a preset threshold and continuously reach a preset number of frames, where the area at least includes one of the following: the system comprises a license plate identification area, a vehicle head identification area, a fire fighting access area, an illegal parking area and a parallel parking space area;
the identification module 4022 is used for identifying the identification area according to the scene analysis model and obtaining an identification result, wherein the scene analysis model comprises identification of people and objects in the image information;
an obtaining unit 403, configured to obtain pre-bound vehicle information according to the face recognition when the recognition result includes a face recognition result.
And an output unit 404, configured to output a guidance prompt according to the recognition result.
In this embodiment, the acquisition unit 401 acquires image information in a parking space area, the recognition unit 402 recognizes the image information according to a pre-trained scene analysis model, the determination module 4021 determines an area, the first recognition module 4022 recognizes the area to obtain a recognition result, if face information exists in the recognition result, the acquisition unit 403 may acquire information of a vehicle bound with the face information, and the output unit 404 may output a guidance prompt according to the recognition result. Different areas can be determined by the scene analysis model, so that various different scenes can be identified, different guide prompts are output according to different scenes, the management of a parking lot is optimized, the information of the vehicle is acquired by face recognition, reverse vehicle searching is realized, the user experience is improved, the recognition is carried out through the model, and the recognition efficiency and accuracy can be effectively improved.
Referring to fig. 5, a schematic diagram of an entity device for intelligent parking space guidance management in the present application includes:
a central processing unit 502, a memory 501, an input/output interface 503, a wired or wireless network interface 504 and a power supply 1005;
the memory 501 is a transient storage memory or a persistent storage memory;
the central processor 502 is configured to communicate with the memory 501 and execute the instruction operations in the memory 501 to perform the steps in any of the embodiments shown in fig. 1-2.
The application provides a computer-readable storage medium, which includes instructions that, when executed on a computer, cause the computer to perform a method corresponding to any one of the embodiments of fig. 1-2.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
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 units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes 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 application. 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 the like.
Claims (10)
1. The utility model provides a method of intelligence parking stall guide management which characterized in that includes:
collecting image information in a parking space area;
identifying the image information according to a pre-trained scene analysis model, and obtaining an identification result, wherein the scene analysis model comprises identification of people and objects in the image information;
and outputting a guidance prompt according to the identification result.
2. The method of claim 1, wherein recognizing the image information according to a pre-trained scene analysis model and obtaining a recognition result comprises:
when the average gray value of the image information and the passageway gray value in front of the parking space reach preset threshold values and continuously reach preset frame numbers according to the scene analysis model, determining an area of the image information according to the scene analysis model, wherein the area at least comprises one of the following items: the system comprises a license plate identification area, a vehicle head identification area, a fire fighting access area, an illegal parking area and a parallel parking space area;
and identifying the identification area according to the scene analysis model, and obtaining an identification result.
3. The method of claim 2, wherein identifying the region according to the scene analysis model and obtaining the identification result comprises:
when the area is determined to be the illegal parking area, identifying the illegal parking condition of the illegal parking area according to the scene analysis model to obtain an illegal parking identification result;
the outputting of the guidance prompt according to the recognition result includes:
and outputting an illegal parking alarm prompt when the illegal parking recognition result indicates that the illegal parking condition occurs.
4. The method of claim 2, wherein identifying the region according to the scene analysis model and obtaining the identification result comprises:
when the area is determined to be a parallel parking space area, identifying whether vehicles exist in the parallel parking space area according to the scene analysis model to obtain a parallel parking space identification result;
the outputting of the guidance prompt according to the recognition result includes:
and outputting a guidance prompt of whether the parallel parking spaces exist or not according to the parallel parking space identification result.
5. The method of claim 2, wherein identifying the region according to the scene analysis model and obtaining the identification result comprises:
when the area is determined to be a fire fighting access area, identifying the vehicle condition in the fire fighting access area according to the scene analysis model to obtain a fire fighting access identification result;
the outputting of the guidance prompt according to the recognition result includes:
and when the fire fighting channel identification result is that the vehicle is detected and the detected vehicle is not matched with the preset vehicle, outputting a guidance prompt of illegal occupation.
6. The method of claim 2, wherein identifying the region according to the scene analysis model and obtaining the identification result comprises:
when the regions are determined to be a license plate recognition region and a vehicle head recognition region, recognizing the existence of the vehicles in the parking space region and recognizing the license plates according to the scene analysis model to obtain the existence of the vehicles in the parking space region and recognition results of the license plates;
the outputting of the guidance prompt according to the recognition result includes:
and outputting a guidance prompt for guiding a user to park the vehicle according to the recognition result of the existence of the vehicle and the recognition result of the license plate.
7. The method according to any one of claims 1 to 6, wherein after the image information is recognized according to a pre-trained scene analysis model and a recognition result is obtained, the method further comprises:
and when the recognition result comprises a face recognition result, acquiring pre-bound vehicle information according to the face recognition.
8. The utility model provides an intelligence parking stall guide management's device which characterized in that includes:
the acquisition unit is used for acquiring image information in the parking space area;
the recognition unit is used for recognizing the image information according to a pre-trained scene analysis model and obtaining a recognition result, wherein the scene analysis model comprises recognition of people and objects in the image information;
and the output unit is used for outputting a guidance prompt according to the identification result.
9. The utility model provides an intelligence parking stall guide management's device which characterized in that includes:
the system comprises a central processing unit, a memory, an input/output interface, a wired or wireless network interface and a power supply;
the memory is a transient memory or a persistent memory;
the central processor is configured to communicate with the memory and execute the instruction operations in the memory to perform the method of any one of 1 to 7.
10. A computer-readable storage medium comprising instructions that, when executed on a computer, cause the computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210081770.8A CN114566063A (en) | 2022-01-24 | 2022-01-24 | Intelligent parking space guiding management method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210081770.8A CN114566063A (en) | 2022-01-24 | 2022-01-24 | Intelligent parking space guiding management method and device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114566063A true CN114566063A (en) | 2022-05-31 |
Family
ID=81713368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210081770.8A Pending CN114566063A (en) | 2022-01-24 | 2022-01-24 | Intelligent parking space guiding management method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114566063A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001194167A (en) * | 2000-10-24 | 2001-07-19 | Matsushita Electric Ind Co Ltd | Vehicle navigation device |
| CN106652551A (en) * | 2016-12-16 | 2017-05-10 | 浙江宇视科技有限公司 | Parking stall detection method and device |
| CN108154708A (en) * | 2018-01-19 | 2018-06-12 | 北京悦畅科技有限公司 | Parking lot management method, server, video camera and terminal device |
| CN108428360A (en) * | 2018-02-01 | 2018-08-21 | 武汉无线飞翔科技有限公司 | A kind of Parking inducible system |
| CN108766028A (en) * | 2018-08-01 | 2018-11-06 | 星络科技有限公司 | Community's parking lot management method |
| CN208655048U (en) * | 2018-08-01 | 2019-03-26 | 恒大智慧科技有限公司 | Community's managing system of car parking |
| CN109902676A (en) * | 2019-01-12 | 2019-06-18 | 浙江工业大学 | A kind of separated based on dynamic background stops detection algorithm |
| CN110766975A (en) * | 2018-07-27 | 2020-02-07 | 比亚迪股份有限公司 | Intelligent vehicle searching management method and system for parking lot |
| CN111368687A (en) * | 2020-02-28 | 2020-07-03 | 成都市微泊科技有限公司 | Sidewalk vehicle illegal parking detection method based on target detection and semantic segmentation |
| CN111508269A (en) * | 2020-04-23 | 2020-08-07 | 深圳智优停科技有限公司 | Open type parking space vehicle distinguishing method and device based on image recognition |
| CN111935281A (en) * | 2020-08-10 | 2020-11-13 | 北京海益同展信息科技有限公司 | Method and device for monitoring illegal parking |
| CN113688717A (en) * | 2021-08-20 | 2021-11-23 | 云往(上海)智能科技有限公司 | Image recognition method and device and electronic equipment |
| CN113822285A (en) * | 2021-09-29 | 2021-12-21 | 重庆市云迈科技有限公司 | Vehicle illegal parking identification method for complex application scene |
-
2022
- 2022-01-24 CN CN202210081770.8A patent/CN114566063A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001194167A (en) * | 2000-10-24 | 2001-07-19 | Matsushita Electric Ind Co Ltd | Vehicle navigation device |
| CN106652551A (en) * | 2016-12-16 | 2017-05-10 | 浙江宇视科技有限公司 | Parking stall detection method and device |
| CN108154708A (en) * | 2018-01-19 | 2018-06-12 | 北京悦畅科技有限公司 | Parking lot management method, server, video camera and terminal device |
| CN108428360A (en) * | 2018-02-01 | 2018-08-21 | 武汉无线飞翔科技有限公司 | A kind of Parking inducible system |
| CN110766975A (en) * | 2018-07-27 | 2020-02-07 | 比亚迪股份有限公司 | Intelligent vehicle searching management method and system for parking lot |
| CN108766028A (en) * | 2018-08-01 | 2018-11-06 | 星络科技有限公司 | Community's parking lot management method |
| CN208655048U (en) * | 2018-08-01 | 2019-03-26 | 恒大智慧科技有限公司 | Community's managing system of car parking |
| CN109902676A (en) * | 2019-01-12 | 2019-06-18 | 浙江工业大学 | A kind of separated based on dynamic background stops detection algorithm |
| CN111368687A (en) * | 2020-02-28 | 2020-07-03 | 成都市微泊科技有限公司 | Sidewalk vehicle illegal parking detection method based on target detection and semantic segmentation |
| CN111508269A (en) * | 2020-04-23 | 2020-08-07 | 深圳智优停科技有限公司 | Open type parking space vehicle distinguishing method and device based on image recognition |
| CN111935281A (en) * | 2020-08-10 | 2020-11-13 | 北京海益同展信息科技有限公司 | Method and device for monitoring illegal parking |
| CN113688717A (en) * | 2021-08-20 | 2021-11-23 | 云往(上海)智能科技有限公司 | Image recognition method and device and electronic equipment |
| CN113822285A (en) * | 2021-09-29 | 2021-12-21 | 重庆市云迈科技有限公司 | Vehicle illegal parking identification method for complex application scene |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3806064B1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| US6442474B1 (en) | Vision-based method and apparatus for monitoring vehicular traffic events | |
| KR101908611B1 (en) | Parking control method for vehicle | |
| CN106815574B (en) | Method and device for establishing detection model and detecting behavior of connecting and calling mobile phone | |
| CN108197526A (en) | Detection method, system and computer readable storage medium | |
| CN114037924A (en) | Vehicle brake-passing judgment method based on image recognition technology and related device | |
| CN105551261A (en) | False-license-plate vehicle detection method and system | |
| CN112419733A (en) | Method, device, equipment and storage medium for detecting irregular parking of user | |
| Hakim et al. | Implementation of an image processing based smart parking system using Haar-Cascade method | |
| CN108805184B (en) | Image recognition method and system for fixed space and vehicle | |
| CN112381014A (en) | Illegal parking vehicle detection and management method and system based on urban road | |
| CN114898297A (en) | Non-motor vehicle illegal behavior determination method based on target detection and target tracking | |
| CN113781827A (en) | Video data management method of cloud platform and cloud platform | |
| CN113408364B (en) | Temporary license plate recognition method, system, device and storage medium | |
| CN108198433B (en) | Parking identification method and device and electronic equipment | |
| CN112580531B (en) | Identification detection method and system for true and false license plates | |
| CN113076852A (en) | Vehicle-mounted snapshot processing system occupying bus lane based on 5G communication | |
| CN109325755A (en) | Electronics charge system based on automotive hub | |
| CN111950499A (en) | Method for detecting vehicle-mounted personnel statistical information | |
| CN109920255B (en) | Management method and management system for vehicle passage | |
| CN114566063A (en) | Intelligent parking space guiding management method and device and storage medium | |
| CN115880632A (en) | Timeout stay detection method, monitoring device, computer-readable storage medium, and chip | |
| Bachtiar et al. | Parking management by means of computer vision | |
| CN113283303A (en) | License plate recognition method and device | |
| CN113449624B (en) | Method and device for determining vehicle behavior based on pedestrian re-identification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |