License plate number identification method and device, equipment and storage medium

Abstract

The invention discloses a license plate number recognition method, device and equipment and a storage medium, and relates to the technical field of image processing, and the license plate number recognition method comprises the steps that a current image outside a vehicle cabin is acquired; when the preset target object exists in the current image, performing continuous image acquisition outside the vehicle cabin to obtain a plurality of reference images; obtaining alternative license plate numbers according to the plurality of reference images; comparing the plurality of alternative license plate numbers to obtain a target license plate number; the method comprises the following steps: acquiring an environment image outside a cabin in real time, continuously acquiring license plate number information in front to obtain alternative license plate numbers when judging that a preset target object exists in front of a vehicle based on the environment image, comparing and screening a plurality of alternative license plate numbers, and forming the license plate number of the vehicle by each license plate number which is most likely to be a real license plate number. The vehicle license plate number information is automatically acquired, the problem that a user needs to manually input a license plate number and then communicate when the vehicle is restricted is avoided, and the user drives the vehicle more smoothly.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a license plate number recognition method, device, equipment and storage medium. Background Art

[0002] The current car system's traffic restriction avoidance function requires users to manually set the license plate number in the car's navigation application, or set it in the brand's mobile app and then sync it to the car through the cloud to achieve the traffic restriction avoidance function. Some car systems cannot even set the license plate number, so traffic restriction avoidance cannot be achieved using the car navigation.

[0003] At present, the license plate recognition barrier technology in residential areas and public facilities has matured. The license plate recognition is completed through the barrier control unit, license plate recognition camera, display screen, vehicle detector, and fill light. After recognition, the license plate information is displayed on the display screen of the barrier, and the license plate number information is broadcast by voice. The current navigation system in the cockpit implements restricted traffic avoidance, which mainly relies on the user to manually set the license plate number. Even the car interface cannot be set and needs to be set through the mobile phone APP and then synchronized to the car. At present, there is no function to fully and actively obtain the license plate number information required for the restricted traffic function, resulting in manual operation and control when the vehicle is restricted, which is not convenient enough.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a license plate number recognition method, device, equipment and storage medium, aiming to solve the technical problem of being unable to actively obtain the license plate number information required for the traffic restriction function.

[0006] To achieve the above purpose, the present application proposes a license plate number recognition method, which includes:

[0007] Get the current image outside the vehicle cabin;

[0008] When a preset target object exists in the current image, continuously capturing images outside the vehicle cabin to obtain a plurality of reference images;

[0009] Obtaining candidate license plate numbers according to multiple reference images;

[0010] Compare multiple candidate license plate numbers to obtain the target license plate number.

[0011] In one embodiment, before acquiring the current image outside the vehicle cabin, the method further includes:

[0012] Acquiring the real-time status of the vehicle, wherein the real-time status includes the driving status and the parking status;

[0013] When the real-time state is switched from the driving state to the parking state, a cockpit license plate recognition function is started and a step of acquiring a current image outside the vehicle cockpit is performed.

[0014] In one embodiment, when there is a preset target object in the current image, continuous image acquisition is performed outside the vehicle cabin to obtain multiple reference images, including:

[0015] Continuously capturing images outside the vehicle cabin at preset time intervals to obtain reference images;

[0016] When there is a preset target object in the current image, before continuously capturing images outside the vehicle cabin to obtain a plurality of reference images, the method further includes:

[0017] Performing target extraction on the current image to obtain a target object;

[0018] Identifying a target object category of the target object;

[0019] When the category of the target object is the same as the category of the preset target object, a step of continuously capturing images outside the vehicle cabin to obtain a reference image is performed.

[0020] In one embodiment, obtaining the candidate license plate number according to the plurality of reference images includes:

[0021] Deduplication is performed on multiple reference images to obtain deduplicated images;

[0022] Using multiple duplicated images as the first candidate license plate number group;

[0023] The voice state outside the vehicle cabin is identified, and an alternative license plate number is obtained based on the voice state and the first group of alternative license plate numbers.

[0024] In one embodiment, the identifying the voice state outside the vehicle cabin and obtaining the candidate license plate number based on the voice state and the first candidate license plate number group includes:

[0025] Identifying a voice status outside the vehicle cabin;

[0026] When the voice state is that there is voice information, a second candidate license plate number group is obtained according to the voice information, and a candidate license plate number is obtained according to the first candidate license plate number group and the second candidate license plate number group;

[0027] When the voice status is that there is no voice information, an alternative license plate number is obtained according to the first alternative license plate number group.

[0028] In one embodiment, comparing the multiple candidate license plate numbers to obtain the target license plate number includes:

[0029] Extracting individual license plate numbers of candidate license plate numbers in sequence;

[0030] Compare the single license plate numbers at the same position among multiple candidate license plate numbers to obtain the target license plate number.

[0031] In one embodiment, comparing a single license plate number at the same position in a plurality of candidate license plate numbers to obtain a target license plate number includes:

[0032] Extract the Nth license plate number from multiple candidate license plate numbers, where N is greater than or equal to 1;

[0033] The license plate number with the highest repetition rate among multiple N-th license plate numbers is used as the N-th target license plate number;

[0034] The target license plate number is obtained according to the Nth target license plate number.

[0035] In addition, to achieve the above purpose, the present application also proposes a license plate number recognition device, the license plate number recognition device comprising:

[0036] An image acquisition module, used to acquire a current image outside the vehicle cabin;

[0037] The image acquisition module is further used to continuously acquire images outside the vehicle cabin to obtain multiple reference images when a preset target object exists in the current image;

[0038] A license plate number recognition module, used to obtain candidate license plate numbers based on multiple reference images;

[0039] The license plate number recognition module is also used to compare the multiple candidate license plate numbers to obtain a target license plate number.

[0040] In addition, to achieve the above-mentioned purpose, the present application also proposes a license plate number recognition device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the license plate number recognition method described above.

[0041] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the license plate number recognition method described above are implemented.

[0042] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the license plate number recognition method described above are implemented.

[0043] One or more technical solutions proposed in this application have at least the following technical effects:

[0044] The image acquisition device outside the vehicle cabin collects the environmental image outside the cabin in real time. When it is judged that there is a preset target object in front of the vehicle based on the environmental image, the license plate number information of the vehicle on the target object in front is continuously collected as an alternative license plate number, and multiple alternative license plate numbers are compared and screened. The license plate number of the vehicle is composed of the license plate numbers that are most likely to be the real license plate numbers, so that the vehicle can automatically obtain the vehicle license plate number information, avoiding the problem of users manually entering the license plate number and then communicating when the vehicle is restricted, making the user's vehicle driving smoother. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0047] Figure 1 A flowchart of the first embodiment of the vehicle license plate number recognition method of the present application is provided;

[0048] Figure 2 A flow chart of the second embodiment of the vehicle license plate number recognition method provided in this application;

[0049] Figure 3 This is a schematic diagram of the module structure of the license plate number recognition device according to an embodiment of the present application;

[0050] Figure 4 This is a schematic diagram of the device structure of the hardware operating environment involved in the license plate number recognition method in the embodiment of the present application. DETAILED DESCRIPTION

[0051] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0052] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0053] The main solution of the embodiment of the present application is: obtaining a current image outside the vehicle cabin; when there is a preset target object in the current image, continuously capturing images outside the vehicle cabin to obtain multiple reference images; obtaining alternative license plate numbers based on the multiple reference images; comparing the multiple alternative license plate numbers to obtain the target license plate number.

[0054] In this embodiment, for ease of description, the following description is made by taking the license plate number recognition device as the execution subject.

[0055] Due to the existing technology, the current car system's traffic restriction avoidance function requires users to manually set the license plate number in the car's navigation application, or set it in the mobile app provided by the brand and then synchronize it to the car through the cloud to achieve the traffic restriction avoidance function. Some car systems cannot even set the license plate number, and traffic restriction avoidance cannot be achieved using the car navigation.

[0056] At present, the license plate recognition barrier technology in residential areas and public facilities is mature. The license plate recognition is completed through the barrier control unit, license plate recognition camera, display screen, vehicle detector, and fill light. After recognition, the license plate information is displayed on the display screen of the barrier, and the license plate number information is broadcast by voice. The current navigation system in the cockpit implements restricted traffic avoidance, which mainly relies on the user to manually set the license plate number. Even the car interface cannot be set and needs to be set through the mobile phone APP and then synchronized to the car. At present, there is no function to fully and actively obtain the license plate number information required for the restricted traffic function, resulting in manual operation and control when the vehicle is restricted, which is not convenient enough.

[0057] The present application provides a solution, which collects the environmental image outside the cockpit in real time, and when it is determined based on the environmental image that there is a preset target object in front of the vehicle, continuously collects the license plate number information in front to obtain alternative license plate numbers, and compares and screens multiple alternative license plate numbers, and uses the license plate numbers that are most likely to be the real license plate numbers to form the vehicle license plate number, so that the vehicle automatically obtains the vehicle license plate number information, avoids the problem of users manually entering the license plate number and then communicating when the vehicle is restricted, and makes the user's vehicle driving smoother.

[0058] It can be seen from the above embodiments that the present application discloses a license plate number recognition method, device, equipment and storage medium, which relates to the field of image processing technology, and discloses a license plate number recognition method, including: obtaining a current image outside a vehicle cabin; when a preset target object exists in the current image, continuously capturing images outside the vehicle cabin to obtain multiple reference images; obtaining alternative license plate numbers based on the multiple reference images; comparing the license plate numbers of the multiple alternative license plate numbers to obtain the target license plate number; the method collects the environmental image outside the cabin in real time, and when it is judged based on the environmental image that there is a preset target object in front of the vehicle, continuously collects the license plate number information in front to obtain the alternative license plate number, and compares and screens the multiple alternative license plate numbers, and the license plate numbers that are most likely to be the real license plate numbers constitute the vehicle license plate number, so as to realize the vehicle automatically obtaining the vehicle license plate number information, avoiding the problem that the user needs to manually enter the license plate number and then communicate when the vehicle is restricted, so that the user's vehicle driving is smoother.

[0059] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a license plate number recognition device, etc. The following takes the license plate number recognition device as an example to illustrate this embodiment and the following embodiments.

[0060] Based on this, the present application embodiment provides a license plate number recognition method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the license plate number recognition method of the present application.

[0061] In this embodiment, the license plate number recognition method includes steps S10 to S40:

[0062] Step S10, acquiring a current image outside the vehicle cabin.

[0063] It should be noted that the license plate number recognition method can be applied to a license plate number recognition system, and the license plate number recognition system can include an external camera.

[0064] It is understandable that the outside of the vehicle cabin can be understood as the outside of the vehicle body, and the current image can be an image of the front, left front, or right front of the vehicle cabin.

[0065] In a feasible implementation manner, step S10 may include steps A101 to A102:

[0066] Step A101, obtaining the real-time status of the vehicle, which includes the driving status and the parking status.

[0067] It is understandable that the real-time status of the vehicle can be obtained through the on-board diagnostic system (OBD-II) interface. Many modern cars are equipped with an OBD-II port, through which a special device can be connected or an application that supports the OBD-II protocol can be used to read vehicle data. The data may include information such as engine speed and vehicle speed, thereby determining whether the vehicle is in motion or parked.

[0068] Step A102, when the real-time state is switched from the driving state to the parking state, the cockpit license plate recognition function is started and the step of acquiring the current image outside the vehicle cockpit is executed.

[0069] It is understandable that if the vehicle is always in a parked state, no identification is performed, and if the vehicle is in a driving state, no identification is performed either.

[0070] It should be understood that when the real-time state switches from the driving state to the parking state, it can be understood that the vehicle stops driving for some reason. At this time, the cockpit license plate recognition function can be activated to determine whether the reason for the stop is due to traffic restrictions.

[0071] It should be noted that the traffic restriction may be due to toll collection, entering an underground garage, passing through a highway, etc., or it may be due to a variety of reasons such as traffic jams and stopping. It is necessary to further obtain the current image outside the vehicle cabin to make a judgment.

[0072] It should be emphasized that when the cockpit does not obtain or recognize the license plate number information, the cockpit license plate recognition system is automatically activated when the vehicle changes from a driving state to a parking state.

[0073] In this embodiment, by monitoring the real-time status of the vehicle and starting it when the real-time status of the vehicle changes from driving to stopping, it is avoided that the license plate recognition function is continuously started, which leads to a waste of computing resources. At the same time, it is possible to accurately detect the situation where the vehicle needs to be restricted according to the change of the vehicle status, so as to collect the license plate number image.

[0074] The above are merely feasible implementations before step S10 provided in this embodiment, and this embodiment does not specifically limit the specific implementations before step S10.

[0075] Step S20, when there is a preset target object in the current image, continuous image acquisition is performed outside the vehicle cabin to obtain a plurality of reference images.

[0076] It is understandable that the preset target object can be a barrier-type target object. Barrier-type objects generally refer to facilities used to control the entry and exit of vehicles or pedestrians. They are widely used in scenes such as parking lots, community entrances, company gates, and highway toll stations.

[0077] It should be understood that when a barrier-type target object exits the barrier, the vehicle license plate number will be identified and displayed on the barrier display, and some barriers will be accompanied by a voice broadcast of the license plate number.

[0078] It should be noted that when there is a preset target object, images outside the cabin can be collected to identify whether there is relevant information showing the vehicle license plate number in the image.

[0079] It should be emphasized that when the external camera starts to identify the target in front, and the target is a non-barrier object such as a vehicle or pedestrian, the recognition process ends.

[0080] It should be noted that, according to the preset time interval, continuous image capture is performed on the outside of the vehicle cabin to obtain a reference image, which can be understood as when the front target recognized by the external camera is a barrier, the external camera is turned on for continuous shooting; the continuous shooting frequency of the external camera is not higher than 1s, and the preset time interval can be 1s or other time intervals, which can be adjusted according to actual needs, and this embodiment does not limit this.

[0081] In a feasible implementation manner, step S20 may include steps A201 to A203:

[0082] Step A201, extracting a target from the current image to obtain a target object.

[0083] It is understandable that object extraction for the current image may include steps such as preprocessing, feature extraction, object detection and segmentation of the current image.

[0084] It should be understood that target extraction of the current image can be achieved through a variety of methods such as convolutional neural networks and filters, and this implementation does not limit this.

[0085] Step A202: Identify the target object category of the target object.

[0086] It should be noted that the identification of the target object can be performed by extracting and identifying features of the current image, and then classifying the features to obtain the category of the target object. When there is a preset target category in the category of the target object, it can be considered that there is a preset target object.

[0087] Step A203, when the category of the target object is the same as the category of the preset target object, execute the step of continuously capturing images outside the vehicle cabin to obtain a reference image.

[0088] It is understandable that when the target object category is the same as the preset target object category, it is considered that the vehicle's license plate information may be displayed at the barrier at this time. The image outside the cabin can be collected and analyzed to obtain information related to the license plate number, thereby self-identifying the vehicle's accurate license plate number.

[0089] In this implementation, by analyzing the features in the current image being collected, it is determined whether information related to the license plate number appears outside the current cabin based on the analysis results. If it is determined that there is a barrier in the current image, further images can be collected continuously to obtain continuous images related to the license plate number. The license plate number information is extracted based on the continuous images, thereby self-identifying the target license plate number and avoiding the tedious steps of the user entering the target license plate number from the vehicle or terminal.

[0090] The above are merely feasible implementations before step S20 provided in this embodiment, and this embodiment does not specifically limit the specific implementations before step S20.

[0091] Step S30, obtaining candidate license plate numbers according to multiple reference images.

[0092] It is understandable that the reference image may be an image continuously captured outside the cockpit, from which digital information about the license plate number is extracted, and the digital information is integrated to obtain a plurality of candidate license plate numbers.

[0093] In the specific implementation, the license plate number related data is extracted from the picture taken by the camera outside the vehicle; due to the limited size of the gate display screen, the same photo may not be able to contain all the license plate number information, and the cockpit needs to compare multiple photos taken and discard duplicate information; based on the license plate number data obtained from this picture, an alternative license plate number is formed.

[0094] It should be understood that the step of acquiring multiple reference images to obtain candidate license plate numbers is repeated to obtain multiple candidate license plate numbers.

[0095] Step S40, comparing the multiple candidate license plate numbers to obtain a target license plate number.

[0096] It is understandable that the license plate number can be a plurality of numbers arranged in a fixed order.

[0097] It should be understood that each of the multiple candidate license plate numbers is a complete license plate number consisting of a group of numbers.

[0098] It should be noted that the license plate number comparison of multiple candidate license plate numbers may be to compare the license plate number characters at the same position in each candidate ticket number, and obtain the target license plate number based on the comparison result.

[0099] In a feasible implementation, step S40 may include steps A41 to A42:

[0100] Step A41, extracting individual license plate numbers of candidate license plate numbers in sequence.

[0101] It is understandable that extracting the individual license plate numbers of the candidate license plate numbers in sequence may be to first extract the first individual license plate number of each candidate license plate number, then extract the second individual license plate number, until the last individual license plate number of the license plate number.

[0102] Step A42, comparing the single license plate numbers at the same position among the multiple candidate license plate numbers to obtain the target license plate number.

[0103] It should be noted that the method of comparing single license plate numbers at the same position in multiple alternative license plate numbers to obtain a target license plate number includes: extracting the Nth license plate number from the multiple alternative license plate numbers, where N is greater than or equal to 1; taking the license plate number with the highest degree of repetition among the multiple Nth license plate numbers as the Nth target license plate number; and obtaining the target license plate number based on the Nth target license plate number.

[0104] It can be understood that taking the license plate number with the highest degree of repetition among multiple Nth license plate numbers as the Nth target license plate number can be by comparing the single license plate numbers at the same position among multiple alternative license plate numbers, and taking the single license plate number with the most repetitions as the license plate number at that position.

[0105] Among them, in the specific implementation, there are 10 alternative license plate numbers, and the 4th of the 10 alternative license plate numbers is a single license plate number, namely 0, 4, 0, 0, 3, 0, 3, 0, 0, 0; among them, 0 appears 7 times in this position, and the repetition rate of 0 is 0.7; 3 appears 2 times in this position, and the repetition rate of 3 is 0.2; 4 appears 1 times in this position, and the repetition rate of 4 is 0.1. Because 0 has the highest repetition rate, 0 is the license plate number at this position, and the comparison of license plate numbers at other positions is similar to this and will not be repeated here.

[0106] In this embodiment, multiple alternative ticket numbers are obtained by repeatedly capturing images outside the cabin, and the license plate number with the highest degree of repetition is selected from the alternative license plate numbers as the final recognized license plate number to avoid inaccurate license plate number recognition caused by errors in a single recognition.

[0107] The above are only feasible implementations of step S40 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S40.

[0108] The present embodiment provides a license plate number recognition method, which collects environmental images outside the cockpit in real time, and when it is determined based on the environmental images that there is a preset target object in front of the vehicle, continuously collects the license plate number information in front to obtain alternative license plate numbers, and compares and screens multiple alternative license plate numbers, and uses the license plate numbers that are most likely to be the real license plate numbers to form the vehicle license plate number, so that the vehicle automatically obtains the vehicle license plate number information, avoids the problem of users manually entering the license plate number and then communicating when the vehicle is restricted, and makes the user's vehicle driving smoother.

[0109] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , step S30, the license plate number recognition method further includes steps S31 to S33:

[0110] Step S31, deduplicate multiple reference images to obtain deduplicated images.

[0111] It should be noted that deduplication of multiple reference images can be performed by using computer vision technology (such as OpenCV) or specialized OCR (optical character recognition) software (such as Tesseract) to detect and read the license plate number in each photo. Through the trained deep learning model, license plates under different lighting conditions and angles can be more accurately identified.

[0112] Furthermore, the image may be preprocessed before recognition, such as denoising, contrast enhancement, etc., to improve recognition accuracy, and an edge detection algorithm may be used to locate the position of the license plate, thereby reducing the possibility of misrecognition.

[0113] Step S32: using the multiple images after deduplication as the first candidate license plate number group.

[0114] It should be noted that the collection of reference images may include many rounds, and multiple reference images will be collected in each round. Deduplication is performed based on the multiple reference images to obtain deduplicated images. Each round of reference image collection can obtain a deduplicated image. After multiple rounds of reference image collection and deduplication, multiple deduplicated images can be obtained, and the multiple deduplicated images are used as the first candidate license plate number group.

[0115] Step S33, identifying the voice status outside the vehicle cabin, and obtaining an alternative license plate number based on the voice status and the first alternative license plate number group.

[0116] It should be noted that the license plate number recognition system can also include an external vehicle voice recognition system, which can perform vehicle wake-up, echo elimination, engine noise reduction, fast interaction, and natural semantic understanding of external vehicle voice.

[0117] It should be further explained that due to the influence of the changing environment outside the car, the recognition rate of outside-car voice recognition is slightly lower than that of inside-car voice recognition.

[0118] It should be understood that the voice status may include the presence of voice information or the absence of voice information.

[0119] In a feasible implementation, step S33 may include steps A331 to A333:

[0120] Step A331, identifying the voice status outside the vehicle cabin.

[0121] It should be noted that the cockpit system extracts license plate number related data from the voice recognition results outside the vehicle. If there is no license plate number related data, the voice recognition result will be discarded and the voice status will be that there is no voice information. If there is license plate number related data, the license plate number information will be extracted and the voice status will be that there is voice information.

[0122] Step A332, when the voice state is that there is voice information, obtain a second alternative license plate number group according to the voice information, and obtain an alternative license plate number according to the first alternative license plate number group and the second alternative license plate number group.

[0123] It should be noted that obtaining the second candidate license plate number group according to the voice information may include voice preprocessing to remove or reduce background noise. If the voice file is long, it can be divided into smaller parts for segmentation processing; then the voice is converted into text using an existing ASR system (such as Google Cloud Speech-to-Text, Microsoft Azure Cognitive Services, or Alibaba Cloud Speech Recognition); then the license plate number in the text is extracted to obtain the license plate number information related to the voice.

[0124] Among them, the method for extracting the license plate number in the text can be to use regular expressions to match the license plate number in a specific format, or to analyze the context of the sentence to confirm whether the extracted character string does refer to the license plate number. The selection can be made according to needs, and this embodiment does not limit this.

[0125] It should be further explained that the voice information may be voice information repeatedly collected in the same time period, or voice information about license plate numbers collected in different time periods, and the license plate numbers extracted from multiple voice information are used as the second candidate license plate number group.

[0126] Step A333, when the voice status is that there is no voice information, obtain an alternative license plate number according to the first alternative license plate number group.

[0127] It is understandable that, in general, the image outside the vehicle cabin can be directly collected for recognition to obtain the first candidate license plate number group, and the license plate number information extracted from the voice may or may not exist.

[0128] It should be understood that if there is only the first alternative license plate number group, the alternative license plate numbers in the first alternative license plate number group are directly compared to obtain the identified license plate number; if there are the first alternative license plate number group and the second alternative license plate number group, the alternative license plate numbers in the two license plate number groups are comprehensively compared to obtain the target license plate number.

[0129] In this implementation, by identifying whether there is voice information in the external voice and whether the voice information includes license plate number information, the group of alternative license plate numbers is enriched, thereby providing more alternative license plate numbers. When performing comparison, more samples can be compared to obtain more accurate comparison results, thereby achieving more accurate license plate number self-recognition.

[0130] The above are only feasible implementations of step S33 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S33.

[0131] The present embodiment provides a license plate number recognition method, which obtains off-vehicle voice information through an off-vehicle voice recognition system, and determines whether the license plate voice information includes the license plate number information. When the license plate number information exists, a second candidate license plate number is obtained according to the license plate number information obtained from the voice information, and a target license plate number is obtained by comparing the second candidate license plate number with the first candidate license plate number. The candidate license plate number is obtained from both image information and voice information, so that the license plate number information can be captured more comprehensively, thereby obtaining a more accurate target license plate number.

[0132] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the license plate number recognition method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0133] This application also provides a license plate number recognition device, please refer to Figure 3 , the license plate number recognition device comprises:

[0134] An image acquisition module 10 is used to acquire a current image outside the vehicle cabin;

[0135] The image acquisition module 10 is further configured to acquire continuous images outside the vehicle cabin to obtain a plurality of reference images when a preset target object exists in the current image;

[0136] A license plate number recognition module 20, used to obtain candidate license plate numbers according to a plurality of reference images;

[0137] The license plate number recognition module 20 is also used to compare the multiple candidate license plate numbers to obtain a target license plate number.

[0138] The license plate number recognition device provided by the present application adopts the license plate number recognition method in the above embodiment, which can solve the technical problem of being unable to actively obtain the license plate number information required for the restricted function. Compared with the prior art, the beneficial effects of the license plate number recognition device provided by the present application are the same as the beneficial effects of the license plate number recognition method provided by the above embodiment, and the other technical features of the license plate number recognition device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0139] The present application provides a license plate number recognition device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the license plate number recognition method in the above-mentioned embodiment one.

[0140] Reference below Figure 4 , which shows a schematic diagram of the structure of a license plate number recognition device suitable for implementing the embodiment of the present application. The license plate number recognition device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The license plate number recognition device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0141] like Figure 4As shown, the license plate number recognition device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the license plate number recognition device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the license plate recognition device to communicate with other devices wirelessly or by wire to exchange data. Although the license plate recognition device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0142] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0143] The license plate number recognition device provided by the present application adopts the license plate number recognition method in the above embodiment, which can solve the technical problem of being unable to actively obtain the license plate number information required for the restricted function. Compared with the prior art, the beneficial effects of the license plate number recognition device provided by the present application are the same as the beneficial effects of the license plate number recognition method provided by the above embodiment, and the other technical features of the license plate number recognition device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0144] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0145] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0146] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the license plate number recognition method in the above-mentioned embodiment.

[0147] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0148] The computer-readable storage medium may be included in the license plate number recognition device; or may exist independently without being assembled into the license plate number recognition device.

[0149] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the license plate number recognition device, the license plate number recognition device: obtains the current image outside the vehicle cabin; when there is a preset target object in the current image, continuously captures images outside the vehicle cabin to obtain multiple reference images; obtains alternative license plate numbers based on the multiple reference images; and compares the multiple alternative license plate numbers to obtain the target license plate number.

[0150] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0151] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0152] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0153] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned license plate number recognition method, and can solve the technical problem of being unable to actively obtain the license plate number information required for the restricted function. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the license plate number recognition method provided by the above-mentioned embodiment, and will not be repeated here.

[0154] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned license plate number recognition method when executed by a processor.

[0155] The computer program product provided by the present application can solve the technical problem of being unable to actively obtain the license plate information required for the restricted function. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the license plate number recognition method provided by the above embodiment, which will not be repeated here.

[0156] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A vehicle license plate recognition method, characterized in that: The license plate number recognition method comprises: Get the current image outside the vehicle cabin; When a preset target object exists in the current image, continuously capturing images outside the vehicle cabin to obtain a plurality of reference images; Obtaining candidate license plate numbers according to multiple reference images; Compare multiple candidate license plate numbers to obtain the target license plate number.

2. The vehicle license plate number recognition method according to claim 1, characterized in that: Before acquiring the current image outside the vehicle cabin, the method further includes: Acquiring the real-time status of the vehicle, wherein the real-time status includes the driving status and the parking status; When the real-time state is switched from the driving state to the parking state, a cockpit license plate recognition function is started and a step of acquiring a current image outside the vehicle cockpit is performed.

3. The vehicle license plate number recognition method according to claim 1, characterized in that: When there is a preset target object in the current image, continuous image acquisition is performed outside the vehicle cabin to obtain multiple reference images, including: Continuously capturing images outside the vehicle cabin at preset time intervals to obtain reference images; When there is a preset target object in the current image, before continuously capturing images outside the vehicle cabin to obtain a plurality of reference images, the method further includes: Performing target extraction on the current image to obtain a target object; Identifying a target object category of the target object; When the category of the target object is the same as the category of the preset target object, a step of continuously capturing images outside the vehicle cabin to obtain a reference image is performed.

4. The vehicle license plate recognition method according to claim 1, characterized in that: The method of obtaining candidate license plate numbers according to a plurality of reference images comprises: Deduplication is performed on multiple reference images to obtain deduplicated images; Using multiple duplicated images as the first candidate license plate number group; The voice state outside the vehicle cabin is identified, and an alternative license plate number is obtained based on the voice state and the first group of alternative license plate numbers.

5. The vehicle license plate number recognition method according to claim 4, characterized in that: The identifying the voice state outside the vehicle cabin and obtaining the candidate license plate number based on the voice state and the first candidate license plate number group includes: Identifying a voice status outside the vehicle cabin; When the voice state is that there is voice information, a second candidate license plate number group is obtained according to the voice information, and a candidate license plate number is obtained according to the first candidate license plate number group and the second candidate license plate number group; When the voice status is that there is no voice information, an alternative license plate number is obtained according to the first alternative license plate number group.

6. The vehicle license plate recognition method according to claim 1, characterized in that: The step of comparing the multiple candidate license plate numbers to obtain the target license plate number includes: Extracting individual license plate numbers of candidate license plate numbers in sequence; Compare the single license plate numbers in the same position among multiple candidate license plate numbers to obtain the target license plate number.

7. The vehicle license plate number recognition method according to claim 6, characterized in that: The step of comparing the single license plate numbers at the same position in the plurality of candidate license plate numbers to obtain the target license plate number includes: Extract the Nth license plate number from multiple candidate license plate numbers, where N is greater than or equal to 1; The license plate number with the highest repetition rate among multiple N-th license plate numbers is used as the N-th target license plate number; The target license plate number is obtained according to the Nth target license plate number.

8. A vehicle license plate recognition device, characterized in that: The vehicle license plate number recognition device comprises: An image acquisition module, used to acquire a current image outside the vehicle cabin; The image acquisition module is further configured to acquire continuous images outside the vehicle cabin to obtain a plurality of reference images when a preset target object exists in the current image; A license plate number recognition module, used to obtain candidate license plate numbers based on multiple reference images; The license plate number recognition module is also used to compare the multiple candidate license plate numbers to obtain a target license plate number.

9. A vehicle license plate recognition device, characterized in that: The device comprises: a memory, a processor, and a license plate number recognition program stored in the memory and executable on the processor, wherein the license plate number recognition program is configured to implement the license plate number recognition method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a license plate number recognition program, which, when executed by a processor, implements the license plate number recognition method according to any one of claims 1 to 7.

Images