Parking space identification method, device and system and computer equipment

Abstract

The invention relates to the technical field of parking space identifier identification, and discloses a parking space identifier identification method, device and system and computer equipment, a cloud platform is used as an execution main body of the parking space identifier identification method of a target vehicle, and the parking space identifier of the target vehicle mainly depends on cloud platform identification, so that the identification accuracy of the parking space identifier is improved. The data processing pressure of the vehicle body picture and the chassis picture of the target vehicle depending on the vehicle-mounted host is relieved, other performances of the vehicle-mounted host are further improved, and finally the identification success rate of the parking space identifier is improved. Besides, the parking space identification is identified in a unified mode through the cloud platform, and the problem that the identification results of the same parking space identification cannot be guaranteed to be basically the same due to the fact that the computing power capacity and the identification algorithm of SOC chips of vehicle-mounted hosts of different manufacturers are different is avoided. Moreover, according to the parking space identification method, modeling is not needed, so that the labor cost of manually marking the data can be reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of parking space mark recognition, and in particular to a parking space mark recognition method, device, system and computer equipment. Background Art

[0002] Parking space identification refers to the automatic recognition and extraction of the number, characters or letters on each parking space in the parking lot through computer vision and image processing technology. The recognition of parking space numbers, characters or letters is used for parking lot management, navigation systems or other related applications.

[0003] In the related art, the on-board host on the vehicle side is mainly used to identify the parking space sign image. This method uses a large number of sample parking space signs to perform modeling or calculations through the on-board host to identify the target parking space sign. However, the system on a chip (SOC) computing power of the on-board host is limited, resulting in the process of identifying the parking space sign affecting other performances of the on-board host, and the recognition success rate of the parking space sign is also low. Summary of the invention

[0004] In view of this, the present invention provides a method, device, system and computer equipment for identifying parking space signs to solve the problem that using a vehicle-mounted host on the vehicle side to identify the parking space sign image affects other performances of the vehicle-mounted host and the recognition success rate of the parking space sign is also low.

[0005] In a first aspect, the present invention provides a method for identifying a parking space mark, which is applied to a cloud platform, and the method includes:

[0006] Receive the target vehicle lock signal sent by the vehicle host;

[0007] Sending a photo-taking command to the vehicle host, the photo-taking command is used to instruct the vehicle host to obtain a target body image of the target vehicle to which it belongs and a target chassis image of the target vehicle at the last parking moment;

[0008] Receive a picture data packet uploaded by the vehicle host, the picture data packet is loaded with a target vehicle body picture and a target chassis picture;

[0009] Based on the target vehicle body image and the target chassis image, the parking space identification of the target vehicle is obtained.

[0010] By executing the above implementation, the cloud platform is used as the execution subject of the method for identifying the parking space mark of the target vehicle. Since the parking space mark of the target vehicle in the disclosed embodiment mainly relies on the cloud platform for identification, the pressure of relying on the vehicle host to process the data of the body image and chassis image of the target vehicle is alleviated, thereby improving other performances of the vehicle host, and finally improving the recognition success rate of the parking space mark. In addition, by uniformly identifying the parking space mark through the cloud platform, it also avoids the problem that the vehicle hosts of different manufacturers cannot guarantee that the recognition results of the same parking space mark are basically the same due to differences in SOC chip computing power and recognition algorithms.

[0011] In an optional implementation, the method for identifying a parking space mark in the embodiment of the present disclosure further includes:

[0012] The parking space identification of the target vehicle is sent to the user terminal through the message push unit.

[0013] By executing the above implementation mode, based on the parking space identification information of the target vehicle sent by the cloud platform, when the user urgently needs to park, it is helpful to quickly park the target vehicle in the parking space corresponding to the parking space identification of the target vehicle, thereby improving the user's parking experience.

[0014] In an optional implementation, obtaining a parking space identification of a target vehicle based on a target vehicle body image and a target chassis image includes:

[0015] Extract the target vehicle body image and the target chassis image from the image data packet;

[0016] De-distorting the target vehicle body image and the target chassis image based on the cloud image processing algorithm, and extracting the parking space identification features of the target vehicle from the target vehicle body image and the target chassis image after the image de-distortion processing;

[0017] The parking space identification with the highest confidence level corresponding to the parking space identification feature of the target vehicle is obtained from the cloud identification database and determined as the parking space identification of the target vehicle.

[0018] By executing the above-mentioned implementation mode, the cloud platform is used as the execution subject of the method for identifying the parking space mark of the target vehicle. Since the parking space mark of the target vehicle in the disclosed embodiment mainly relies on the cloud platform for identification, the pressure of relying on the vehicle-mounted host to process the data of the body image and chassis image of the target vehicle is alleviated, thereby improving other performances of the vehicle-mounted host, and finally improving the recognition success rate of the parking space mark. In addition, the unified identification of parking space marks by the cloud platform also avoids the problem that the vehicle-mounted hosts of different manufacturers cannot guarantee that the recognition results of the same parking space mark are basically the same due to differences in SOC chip computing power and recognition algorithms. Moreover, the method for identifying parking space marks in the disclosed embodiment does not require modeling, thereby reducing the labor cost of manually annotating data.

[0019] In an optional implementation, the method for identifying a parking space mark in the embodiment of the present disclosure further includes:

[0020] If the parking space identification feature of the target vehicle is not found in the cloud identification database, it is determined that the parking space identification recognition of the target vehicle has failed.

[0021] By executing the above implementation method, when the parking space identification of the target vehicle is not found in the cloud identification database, it is determined that the parking space identification recognition of the target vehicle has failed, and further searching in the cloud identification database is stopped, which is conducive to ending the parking space identification of the target vehicle in advance to reduce the working pressure of the cloud platform.

[0022] In a second aspect, the present invention further provides a method for identifying a parking space mark, which is applied to a vehicle-mounted host, and the method comprises:

[0023] Obtain a locking signal of the target vehicle from the vehicle controller, and send the locking signal of the target vehicle to the cloud platform;

[0024] Receive photo-taking instructions from the cloud platform;

[0025] Based on the photo taking instruction, a target body image of the target vehicle and a target chassis image of the target vehicle at the last parking moment are obtained;

[0026] Desensitize the target vehicle body image and target chassis image;

[0027] Packing the desensitized target vehicle body image and target chassis image into an image data packet;

[0028] The image data packet is sent to the cloud platform so that the cloud platform can obtain the parking space identification of the target vehicle based on the target body image and the target chassis image.

[0029] By executing the above implementation, the vehicle host is only responsible for uploading the image data package, and does not identify the parking space logo of the target vehicle body image and the target chassis image. Instead, it is identified through the cloud platform, which alleviates the pressure of relying on the vehicle host to process the data of the target vehicle body image and chassis image, thereby improving other performance of the vehicle host and ultimately improving the success rate of parking space logo recognition. In addition, the unified identification of parking space logos through the cloud platform also avoids the problem that vehicle hosts from different manufacturers cannot guarantee that the recognition results of the same parking space logo are basically the same due to differences in SOC chip computing power and recognition algorithms.

[0030] In a third aspect, the present invention further provides a parking space identification device, which is applied to a cloud platform, and the device includes:

[0031] The first receiving module is used to receive a vehicle locking signal of a target vehicle sent by the vehicle-mounted host;

[0032] The second receiving module is used to send a photo-taking instruction to the vehicle-mounted host, and the photo-taking instruction is used to instruct the vehicle-mounted host to obtain a target body image of the target vehicle to which it belongs and a target chassis image of the target vehicle at the last parking moment;

[0033] A third receiving module is used to receive a picture data packet uploaded by the vehicle-mounted host, where the picture data packet is loaded with a target vehicle body picture and a target chassis picture;

[0034] The identification acquisition module obtains the parking space identification of the target vehicle based on the target body image and the target chassis image.

[0035] In a fourth aspect, the present invention further provides a parking space identification device, which is applied to a vehicle-mounted host, and the device comprises:

[0036] A first sending module is used to obtain a locking signal of a target vehicle from an on-board controller and send the locking signal of the target vehicle to a cloud platform;

[0037] The second sending module is used to receive the photo taking instruction sent by the cloud platform;

[0038] The image acquisition module is used to acquire a target body image of the target vehicle and a target chassis image of the target vehicle at the last parking moment based on a photo taking instruction;

[0039] A desensitization processing module is used to perform desensitization processing on the target vehicle body image and the target chassis image;

[0040] A data packaging module is used to package the desensitized target vehicle body image and target chassis image into an image data packet;

[0041] The third sending module is used to send the image data packet to the cloud platform, so that the cloud platform can obtain the parking space identification of the target vehicle based on the target vehicle body image and the target chassis image.

[0042] In a fifth aspect, the present invention further provides a parking space identification system, comprising: a cloud platform, a vehicle-mounted host and a user terminal;

[0043] The vehicle-mounted host obtains the locking signal of the target vehicle from the vehicle-mounted controller, and sends the locking signal of the target vehicle to the cloud platform. The cloud platform receives the locking signal of the target vehicle sent by the vehicle-mounted host, and sends a photo command to the vehicle-mounted host; the vehicle-mounted host receives the photo command issued by the cloud platform, and based on the photo command, obtains a target body image of the target vehicle and a target chassis image of the target vehicle at the last parking moment; desensitizes the target body image and the target chassis image; packages the desensitized target body image and the target chassis image into a picture data packet and sends it to the cloud platform, so that the cloud platform obtains the parking space identification of the target vehicle based on the target body image and the target chassis image; the user terminal obtains the parking space identification of the target vehicle from the cloud platform through the message push unit.

[0044] In a sixth aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for identifying parking space signs of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0045] In a seventh aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for identifying a parking space sign according to the first aspect or any corresponding embodiment thereof.

[0046] In an eighth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the method for identifying a parking space sign according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 is a schematic diagram of the structure of a parking space identification system according to an embodiment of the present invention;

[0049] Figure 2 is a schematic flow chart of a method for identifying a parking space mark according to an embodiment of the present invention;

[0050] Figure 3 is a flow chart of another method for identifying a parking space mark according to an embodiment of the present invention;

[0051] Figure 4is a flow chart of another method for identifying a parking space mark according to an embodiment of the present invention;

[0052] Figure 5 is a flow chart of another method for identifying a parking space mark according to an embodiment of the present invention;

[0053] Figure 6 is a schematic diagram of a specific process of a method for identifying a parking space mark according to an embodiment of the present invention;

[0054] Figure 7 is a schematic diagram of multi-terminal interaction of a method for identifying a parking space mark according to an embodiment of the present invention;

[0055] Figure 8 is a structural block diagram of a device for identifying a parking space mark according to an embodiment of the present invention;

[0056] Fig. 9 is a structural block diagram of another parking space identification device according to an embodiment of the present invention;

[0057] Fig.10 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0059] According to an embodiment of the present invention, an embodiment of a method for identifying a parking space sign is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0060] In this embodiment, a method for identifying a parking space mark is provided. The parking space mark is also called the parking space number, which includes some characters, letters or digital numbers marked on the parking space of the target vehicle. The method for identifying the parking space mark can be used in a cloud platform of a parking space mark identification system, and the cloud platform can be represented by TSP. Figure 1 FIG. 1 is a schematic diagram of the structure of the parking space identification system in the embodiment of the present disclosure. Figure 1In the system, the cloud platform 110, the vehicle host 120 and the user terminal 130 are connected via a wireless transmission network, and the cloud platform 110 and the user terminal 130 are also connected via a wireless transmission network. The cloud platform 110 is used to identify the parking space mark of the target vehicle. For the specific implementation process, please refer to the parking space mark identification method on the cloud platform side in the following embodiment; Figure 1 In the embodiment, the vehicle host 120 can be a multimedia networkable host, which can be represented by THU or HU. The vehicle host 120 is used to obtain the target body image and the target chassis image of the target vehicle, and send the obtained target body image and the target chassis image of the target vehicle to the cloud platform 110, so that the cloud platform 110 can recognize the parking space mark of the target vehicle, thereby alleviating the data processing pressure of the vehicle host 120. For the specific implementation process, please refer to the method for identifying the parking space mark on the vehicle host side in the following embodiment. Figure 1 In the embodiment, the user terminal 130 may be a mobile phone terminal of the user, and the number of the user terminals may be one or more. The user terminal 130 is used to receive the recognition result of the parking space identification of the target vehicle sent by the cloud platform 110, specifically, the APP on the mobile phone terminal receives the parking space identification of the target vehicle sent by the cloud platform. It can be understood that the parking space identification recognition system in the embodiment of the present disclosure can be used in a variety of specific parking application scenarios such as parking lots and stations, and the cloud platform and the vehicle-mounted host can be computer devices, such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc.

[0061] In a specific example, the parking space marking recognition system in the embodiment of the present disclosure also includes: an on-board controller, which is used to determine whether the target vehicle is parked and locked. If the target vehicle is locked, the locking signal is sent to the cloud platform through the on-board host. If the target vehicle is not parked and locked, the recognition action of the parking space marking of the target vehicle will be stopped.

[0062] Specifically, the vehicle controller can be represented by BDC, and the main function of the vehicle control in the embodiment of the present disclosure is to determine whether the target vehicle is parked and locked. The vehicle controller can be connected to the vehicle host through a connecting harness, and the vehicle host can be connected to the cloud platform through a wireless network.

[0063] In the parking space identification recognition system of the disclosed embodiment, the vehicle-mounted host obtains the locking signal of the target vehicle from the vehicle-mounted controller, and sends the locking signal of the target vehicle to the cloud platform, the cloud platform receives the locking signal of the target vehicle sent by the vehicle-mounted host, and sends a photo command to the vehicle-mounted host; the vehicle-mounted host receives the photo command issued by the cloud platform, and based on the photo command, obtains a target body image of the target vehicle and a target chassis image of the target vehicle at the last parking moment; desensitizes the target body image and the target chassis image; packages the desensitized target body image and the target chassis image into a picture data packet and sends it to the cloud platform, so that the cloud platform obtains the parking space identification of the target vehicle based on the target body image and the target chassis image; the user terminal obtains the parking space identification of the target vehicle from the cloud platform through the message push unit.

[0064] In another specific example, the parking space marking recognition system in the embodiment of the present disclosure further includes: a vehicle-mounted camera, which is connected to the vehicle-mounted host via a connecting harness and is used to collect multiple target vehicle body images of the target vehicle.

[0065] Specifically, the vehicle-mounted camera is composed of four vehicle-mounted fisheye cameras, which can rotate 360 ​​degrees and can simultaneously capture four pictures around the target vehicle body.

[0066] In another specific example, the parking space identification system may further include a management device for managing the system (such as managing the connection status between the terminal and the cloud platform, etc.), and the management device and the cloud platform are connected via a communication network. Optionally, the communication network is a wired network or a wireless network.

[0067] Optionally, the above-mentioned wireless network or wired network uses standard communication technology and / or protocol. The network is usually the Internet, but it can also be any other network, including but not limited to any combination of local area network, metropolitan area network, wide area network, mobile, limited or wireless network, private network or virtual private network. In some embodiments, the technology and / or format including hypertext markup language, extensible markup language, etc. are used to represent the data exchanged through the network. In addition, conventional encryption technologies such as secure socket layer, transport layer security, virtual private network, Internet protocol security, etc. can also be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technology can also be used to replace or supplement the above-mentioned data communication technology.

[0068] In the traditional parking space sign recognition method, the image captured by the on-board fisheye camera during the parking process is mainly used for recognition. The recognition process mainly includes image de-distortion, parking space coordinate alignment, model operation, and output recognition results. Among them, the image distortion processing is mainly affected by the camera, and the model operation is greatly affected by the parking space annotation of the training model of each manufacturer and the main chip of the multimedia host itself. At present, the solutions of multimedia hosts of various manufacturers on the market are mostly different, mainly because the main chips SOC / RAM / EMMC are quite different, which leads to the impact on other functions of the on-board host itself during the recognition of parking space signs, and the recognition success rate of parking space signs is not high; at the same time, the model operation is limited by the number of parking space signs collected and annotated by the project, and this process is very labor-intensive and resource-intensive.

[0069] In view of this, based on Figure 1 The application scenario of the parking space sign recognition system shown in the figure, the embodiment of the present disclosure provides a parking space sign recognition method, which is applied to a cloud platform, and the cloud platform can be a computer device, such as a mobile phone, a tablet computer, a desktop computer, a portable notebook, a server, etc. Figure 2 is a flow chart of a method for identifying a parking space mark according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0070] Step S201, receiving a vehicle lock signal sent by a vehicle-mounted host.

[0071] Specifically, the vehicle host is located near the front steering wheel of the target vehicle. The vehicle host can be a multimedia networkable host. The vehicle host can be represented by THU or HU. The vehicle host is the core part of the vehicle audio and video system. Its main function is to play the audio source, which is equivalent to the DVD player of a home theater. The target vehicle is the currently identified vehicle. The target vehicle can be a private car, a bus or an electric car. The locking signal of the target vehicle comes from the vehicle controller (BDC). If the vehicle controller (BDC) determines that the target vehicle is parked and locked, the locking signal corresponding to the parking lock is transmitted to the vehicle host through the connecting harness. If the vehicle controller (BDC) determines that the target vehicle is not parked, the recognition action of the parking space mark of the target vehicle is stopped. The parking space mark recognition method in the disclosed embodiment is mainly aimed at when the vehicle controller (BDC) determines that the target vehicle is parked and locked, the vehicle host obtains the corresponding locking signal of the target vehicle from the vehicle controller (BDC).

[0072] Step S202, sending a photographing instruction to the vehicle-mounted host, the photographing instruction is used to instruct the vehicle-mounted host to obtain a target body image of the target vehicle to which it belongs and a target chassis image of the target vehicle at the last parking moment.

[0073] Specifically, the photo-taking instruction can be remotely transmitted to the vehicle-mounted host through a wireless network. The photo-taking instruction can be a code instruction for prompting the vehicle-mounted host to execute control. For example, the photo-taking instruction is used to prompt the vehicle-mounted host to simultaneously collect four pictures of the body surroundings of the target vehicle through the vehicle-mounted camera (four vehicle-mounted fisheye cameras), and to search for the transparent chassis picture when the vehicle was parked for the last time through the storage unit of the vehicle-mounted host. Therefore, the target body pictures mentioned above are the four body pictures of the target vehicle, and the target chassis picture is the transparent chassis picture when the target vehicle was parked for the last time. The target body pictures and target chassis pictures mentioned above at least contain part or all of the parking space identification information.

[0074] Step S203, receiving a picture data packet uploaded by the vehicle-mounted host, wherein the picture data packet is loaded with a target vehicle body picture and a target chassis picture.

[0075] Specifically, in order to improve the transmission efficiency of images, the vehicle-mounted host packages and compresses the target body image and the target chassis image together, and then uploads them to the cloud platform. Therefore, here, the cloud platform receives the packaged image data packet from the vehicle-mounted host, which is conducive to saving network transmission traffic and improving network transmission speed.

[0076] Step S204, based on the target vehicle body image and the target chassis image, obtain the parking space identification of the target vehicle.

[0077] Specifically, the cloud platform first de-distorts the target body image and the target chassis image based on the target body image and the target chassis image uploaded by the vehicle-mounted host through some models, algorithms or databases set by the cloud platform itself, and then extracts the parking space identification features of the de-distorted target body image and the target chassis image. Finally, the extracted parking space identification features are compared and identified with the information in the parking space number recognition library to obtain the parking space identification of the target vehicle.

[0078] Since the parking space identification of the target vehicle in the disclosed embodiment mainly relies on the cloud platform for identification, the pressure of relying on the vehicle host to process the data of the body image and chassis image of the target vehicle is alleviated, thereby improving other performances of the vehicle host and ultimately improving the recognition success rate of the parking space identification. In addition, by uniformly identifying the parking space identification through the cloud platform, it also avoids the problem that the vehicle hosts of different manufacturers cannot guarantee that the recognition results of the same parking space identification are basically the same due to differences in SOC chip computing power and recognition algorithms.

[0079] In this embodiment, a method for identifying a parking space mark is provided, which can be used for the above-mentioned cloud platform, and the cloud platform can be a computer device, such as a mobile phone, a tablet computer, a desktop computer, a portable notebook, a server, etc. Figure 3 is a flow chart of a method for identifying a parking space mark according to an embodiment of the present invention. Figure 3 As shown, the process also includes the following steps:

[0080] Step S205: Send the parking space identification of the target vehicle to the user terminal through the message push unit.

[0081] Specifically, the message push unit is part of the cloud platform, and is mainly used to push various types of messages to the user terminal. For example, the message may be a recognition result message of the parking space identification of the target vehicle by the cloud platform, or may be some news messages, navigation messages, or entertainment messages. The message push unit may add the parking space identification message of the target vehicle to the message template according to the pre-established message push rules, and then push the entire message to the APP of the user terminal to inform the user of the parking space identification information of the target vehicle. The number of user terminals mentioned above may be one or more. When the number of user terminals is multiple, the cloud platform simultaneously sends the parking space identification of the target vehicle to the APPs of multiple user terminals through the message push unit.

[0082] Therefore, the parking space identification method in the disclosed embodiment is based on the parking space identification information of the target vehicle issued by the cloud platform. When the user is in urgent need of parking, it is helpful to quickly park the target vehicle in the parking space corresponding to the parking space identification of the target vehicle, thereby improving the user's parking experience.

[0083] exist Figure 3 For the specific example process of step S201 to step S204, please refer to the above embodiment and will not be repeated here.

[0084] In this embodiment, a method for identifying a parking space sign is provided. The embodiment of the present disclosure provides a method for identifying a parking space sign, which is applied to a cloud platform. The cloud platform can be a computer device, such as a mobile phone, a tablet computer, a desktop computer, a portable notebook, a server, etc. Figure 4 is a flow chart of a method for identifying a parking space mark according to an embodiment of the present invention. Figure 4 As shown, the above step S204, based on the target vehicle body image and the target chassis image, obtains the parking space identification of the target vehicle, including:

[0085] Step S2041, decompressing the target vehicle body image and the target chassis image from the image data packet.

[0086] Specifically, in order to improve the transmission speed of images, the vehicle host compresses the target body image and the target chassis image into a picture data packet together. Therefore, after the cloud platform receives the picture data packet, it needs to decompress it in advance to obtain the target body image and the target chassis image.

[0087] Step S2042: De-distort the target vehicle body image and the target chassis image based on a cloud-based image processing algorithm, and extract the parking space identification features of the target vehicle from the target vehicle body image and the target chassis image after the image de-distortion processing.

[0088] Specifically, the cloud-based image processing algorithm here is deployed in the cloud platform, not in the vehicle-mounted host. Therefore, by using the cloud platform as the executor of the method for identifying the parking space sign of the target vehicle, the data processing pressure of the vehicle-mounted host for the body and chassis images of the target vehicle is alleviated, thereby improving other performance of the vehicle-mounted host and ultimately improving the recognition success rate of the parking space sign.

[0089] Furthermore, the cloud-based image processing algorithm can be an existing commonly used image dedistortion algorithm. Since the target body image and the target chassis image mentioned above contain at least part or all of the parking space identification information, the parking space identification features can be extracted from the target body image and the target chassis image after image dedistortion processing. The parking space identification features are used to represent the character features, letter features or digital features of the parking space identification information.

[0090] Step S2043, obtaining the parking space identification with the highest confidence corresponding to the parking space identification feature of the target vehicle from the cloud identification database, and determining it as the parking space identification of the target vehicle.

[0091] Specifically, the cloud-based identification database is generated through a large amount of parking space identification information. The cloud-based identification database does not need to be modeled by manually annotating a large number of parking space identifications, but can be uploaded by users. Therefore, the parking space identification method in the embodiment of the present disclosure does not require modeling, thereby reducing the labor cost of manually annotating data.

[0092] Furthermore, after feature comparison of the parking space identification of the target vehicle is performed through the cloud database, some feature-similar comparison results are output, and these comparison results are sorted in descending order according to confidence, and finally the parking space identification of the target vehicle with the highest confidence is output.

[0093] In summary, since the parking space identification of the target vehicle in the disclosed embodiment mainly relies on the cloud platform for identification, the pressure of relying on the vehicle-mounted host to process the data of the body image and chassis image of the target vehicle is alleviated, thereby improving other performances of the vehicle-mounted host, and ultimately improving the recognition success rate of the parking space identification. In addition, the unified identification of parking space identification by the cloud platform also avoids the problem that the vehicle-mounted hosts of different manufacturers cannot guarantee that the recognition results of the same parking space identification are basically the same due to differences in SOC chip computing power and recognition algorithms. Moreover, the identification method of the parking space identification in the disclosed embodiment does not require modeling, thereby reducing the labor cost of manually annotating data.

[0094] exist Figure 4 For the specific example process of step S201 to step S205, please refer to the above embodiment and will not be repeated here.

[0095] In some optional implementations, the method for identifying a parking space mark in the embodiment of the present disclosure further includes: if the parking space mark feature of the target vehicle is not found in the cloud mark database, determining that the parking space mark identification of the target vehicle has failed.

[0096] Specifically, if the parking space identification feature of the target vehicle is not searched from the cloud identification database, it means that the cloud identification database does not store the corresponding parking space identification, which means that the parking space identification recognition of the target vehicle has failed. At this time, the parking space identification action is terminated.

[0097] In this embodiment, a method for identifying a parking space sign is provided. The embodiment of the present disclosure provides a method for identifying a parking space sign, which is applied to a vehicle-mounted host, which can be a computer device, such as a mobile phone, a tablet computer, a desktop computer, a portable notebook, a server, etc. Figure 5 is a flow chart of a method for identifying a parking space mark according to an embodiment of the present invention. Figure 5 As shown, the process includes the following steps:

[0098] Step S501, obtaining a locking signal of a target vehicle from an onboard controller, and sending the locking signal of the target vehicle to a cloud platform.

[0099] Specifically, the vehicle host can be a multimedia networkable host, which can be represented by THU or HU. The vehicle host is located near the steering wheel at the front of the target vehicle. The vehicle host is the core part of the vehicle audio and video system, and its main function is to play the audio source, which is equivalent to the DVD player of a home theater. The target vehicle is the currently identified vehicle, which can be a private car, a bus or an electric car. The locking signal of the target vehicle comes from the vehicle controller (BDC). If the vehicle controller (BDC) determines that the target vehicle is parked and locked, the locking signal corresponding to the parking lock is transmitted to the vehicle host through the connecting harness. If the vehicle controller (BDC) determines that the target vehicle is not parked, the recognition action of the parking space mark of the target vehicle is stopped. The parking space mark recognition method in the disclosed embodiment is mainly aimed at when the vehicle controller (BDC) determines that the target vehicle is parked and locked, the vehicle host obtains the corresponding locking signal of the target vehicle from the vehicle controller.

[0100] Step S502, receiving a photo taking instruction issued by the cloud platform.

[0101] Step S503, based on the photographing instruction, obtaining a target body image of the target vehicle and a target chassis image of the target vehicle at the last parking moment.

[0102] Specifically, the photo-taking instruction can be remotely transmitted to the vehicle-mounted host through a wireless network. The photo-taking instruction can be a code instruction for prompting the vehicle-mounted host to execute control. For example, the photo-taking instruction is used to prompt the vehicle-mounted host to simultaneously collect four pictures of the body surroundings of the target vehicle through the vehicle-mounted camera (four vehicle-mounted fisheye cameras), and to search for the transparent chassis picture when the vehicle was parked for the last time through the storage unit of the vehicle-mounted host. Therefore, the target body pictures mentioned above are the four body pictures of the target vehicle, and the target chassis picture is the transparent chassis picture when the target vehicle was parked for the last time. The target body pictures and target chassis pictures mentioned above at least contain part or all of the parking space identification information.

[0103] Step S504, desensitizing the target vehicle body image and the target chassis image.

[0104] Specifically, the desensitization process can be based on automobile-related regulations to delete some private image content related to the driver user, for example, deleting some license plate logos in the target body image and the target chassis image. Desensitization processing is conducive to protecting the private information security of the driver user.

[0105] Step S505, packing the desensitized target vehicle body image and target chassis image into an image data packet.

[0106] Specifically, packaging the desensitized target vehicle body image and target chassis image together into an image data packet is beneficial to saving network transmission traffic and improving network transmission speed.

[0107] Step S506, sending the image data packet to the cloud platform, so that the cloud platform obtains the parking space identification of the target vehicle based on the target vehicle body image and the target chassis image.

[0108] Specifically, the vehicle-mounted host is only responsible for uploading image data packets, and does not identify the parking space signs of the target vehicle body images and target chassis images. Instead, it identifies them through the cloud platform, which alleviates the data processing pressure of the vehicle-mounted host for the target vehicle body images and chassis images, thereby improving other performance of the vehicle-mounted host and ultimately improving the success rate of parking space sign recognition.

[0109] like Figure 6 FIG. 1 is a flow chart of a method for identifying a parking space mark in an embodiment of the present disclosure. Figure 6In the process, the vehicle controller (BDC) first determines whether the target vehicle is parked and locked. If the target vehicle is already locked, the locking signal is sent to the cloud platform through the vehicle host. If the target vehicle is not parked and locked, the recognition action of the parking space mark of the target vehicle is stopped. Then, the vehicle host (THU or HU) executes the above steps S501-S506, and the cloud platform (TSP) executes the above steps S201-S204. Finally, the user terminal (mobile phone APP) receives the parking space mark of the target vehicle sent by the cloud platform (TSP). Figure 7 The figure shows the interaction between the cloud platform and the vehicle host and user terminal.

[0110] In this embodiment, a parking space identification device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0111] This embodiment provides a parking space identification device, which is applied to a cloud platform, such as Figure 8 As shown, including:

[0112] The first receiving module 81 is used to receive a vehicle locking signal of a target vehicle sent by the vehicle-mounted host;

[0113] The second receiving module 82 is used to send a photo-taking instruction to the vehicle-mounted host, where the photo-taking instruction is used to instruct the vehicle-mounted host to obtain a target body image of the target vehicle to which it belongs and a target chassis image of the target vehicle at the last parking moment;

[0114] The third receiving module 83 is used to receive a picture data packet uploaded by the vehicle-mounted host, where the picture data packet is loaded with a target vehicle body picture and a target chassis picture;

[0115] The identification acquisition module 84 acquires the parking space identification of the target vehicle based on the target vehicle body image and the target chassis image.

[0116] In some optional implementations, the device for identifying a parking space mark in the embodiment of the present disclosure further includes:

[0117] The identification sending module is used to send the parking space identification of the target vehicle to the user terminal through the message pushing unit.

[0118] In some optional implementations, the identification acquisition module 84 includes:

[0119] A data decompression submodule is used to decompress the target vehicle body image and the target chassis image from the image data packet;

[0120] A data processing submodule is used to perform image dedistortion processing on the target vehicle body image and the target chassis image based on a cloud image processing algorithm, and to extract parking space identification features of the target vehicle from the target vehicle body image and the target chassis image after the image dedistortion processing;

[0121] The data feature extraction submodule is used to obtain the parking space identification with the highest confidence corresponding to the parking space identification feature of the target vehicle from the cloud identification database, and determine it as the parking space identification of the target vehicle.

[0122] In some optional implementations, the device for identifying a parking space mark in the embodiment of the present disclosure further includes:

[0123] The action determination module is used to determine that the parking space identification feature of the target vehicle has failed if the parking space identification feature of the target vehicle is not found in the cloud identification database.

[0124] This embodiment provides a parking space identification device, which is applied to a vehicle-mounted host, such as Fig. 9 As shown, including:

[0125] A first sending module 91 is used to obtain a locking signal of a target vehicle from an onboard controller and send the locking signal of the target vehicle to a cloud platform;

[0126] The second sending module 92 is used to receive a photo taking instruction sent by the cloud platform;

[0127] The picture acquisition module 93 is used to acquire a target body picture of the target vehicle and a target chassis picture of the target vehicle at the last parking moment based on the photo taking instruction;

[0128] A desensitization processing module 94 is used to perform desensitization processing on the target vehicle body image and the target chassis image;

[0129] The data packaging module 95 is used to package the desensitized target vehicle body image and the target chassis image into an image data packet;

[0130] The third sending module 96 is used to send the image data packet to the cloud platform, so that the cloud platform can obtain the parking space identification of the target vehicle based on the target vehicle body image and the target chassis image.

[0131] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0132] The parking space identification device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0133] An embodiment of the present invention further provides a computer device having the above-mentioned parking space identification device.

[0134] See also Fig.10 , Fig.10 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Fig.10 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.10 A processor 10 is taken as an example.

[0135] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0136] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0137] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0138] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0139] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Fig.10 The example of connecting through bus is taken in the following.

[0140] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0141] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0142] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0143] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for identifying a parking space mark, characterized in that: Applied to a cloud platform, the method includes: Receive the target vehicle lock signal sent by the vehicle host; Sending a photographing instruction to the vehicle-mounted host, wherein the photographing instruction is used to instruct the vehicle-mounted host to obtain a target body image of the target vehicle to which it belongs and a target chassis image of the target vehicle at the last parking moment; Receiving a picture data packet uploaded by the vehicle-mounted host, wherein the picture data packet is loaded with the target vehicle body picture and the target chassis picture; Based on the target vehicle body image and the target chassis image, a parking space identification of the target vehicle is obtained.

2. The method according to claim 1, characterized in that Also includes: The parking space identification of the target vehicle is sent to the user terminal through the message push unit.

3. The method according to claim 1, characterized in that The step of obtaining the parking space identification of the target vehicle based on the target vehicle body image and the target chassis image includes: Decompressing the target vehicle body image and the target chassis image from the image data packet; Performing image dedistortion processing on the target vehicle body image and the target chassis image based on a cloud image processing algorithm, and extracting parking space identification features of the target vehicle from the target vehicle body image and the target chassis image after the image dedistortion processing; The parking space identification with the highest confidence level corresponding to the parking space identification feature of the target vehicle is obtained from the cloud identification database, and is determined as the parking space identification of the target vehicle.

4. A method for identifying a parking space mark, characterized in that: Applied to a vehicle-mounted host, the method comprises: Acquire a locking signal of a target vehicle from an onboard controller, and send the locking signal of the target vehicle to a cloud platform; Receiving a photo-taking instruction issued by the cloud platform; Based on the photographing instruction, a target body image of the target vehicle and a target chassis image of the target vehicle at the last parking moment are acquired; Performing desensitization processing on the target vehicle body image and the target chassis image; Packing the desensitized target vehicle body image and the target chassis image into an image data packet; The image data packet is sent to the cloud platform, so that the cloud platform obtains the parking space identification of the target vehicle based on the target vehicle body image and the target chassis image.

5. A parking space identification device, characterized in that: Applied to a cloud platform, the device comprises: The first receiving module is used to receive a vehicle locking signal of a target vehicle sent by the vehicle-mounted host; A second receiving module is used to send a photo-taking instruction to the vehicle-mounted host, wherein the photo-taking instruction is used to instruct the vehicle-mounted host to obtain a target body image of the target vehicle to which it belongs and a target chassis image of the target vehicle at the last parking moment; A third receiving module is used to receive a picture data packet uploaded by the vehicle-mounted host, wherein the picture data packet is loaded with the target vehicle body picture and the target chassis picture; The identification acquisition module acquires the parking space identification of the target vehicle based on the target vehicle body image and the target chassis image.

6. A parking space identification device, characterized in that: Applied to a vehicle-mounted host, the device comprises: A first sending module, used to obtain a locking signal of a target vehicle from an on-board controller, and send the locking signal of the target vehicle to a cloud platform; A second sending module, used to receive a photo taking instruction sent by the cloud platform; A picture acquisition module, for acquiring a target body picture of the target vehicle and a target chassis picture of the target vehicle at the last parking moment based on the photo taking instruction; A desensitization processing module, used for performing desensitization processing on the target vehicle body image and the target chassis image; A data packaging module, used for packaging the desensitized target vehicle body image and the target chassis image into an image data packet; The third sending module is used to send the image data packet to the cloud platform, so that the cloud platform obtains the parking space identification of the target vehicle based on the target vehicle body image and the target chassis image.

7. A parking space identification system, characterized in that: include: Cloud platform, vehicle host and user terminal; The vehicle-mounted host obtains a locking signal of the target vehicle from the vehicle-mounted controller, and sends the locking signal of the target vehicle to the cloud platform; the cloud platform receives the locking signal of the target vehicle sent by the vehicle-mounted host, and sends a photo-taking instruction to the vehicle-mounted host; the vehicle-mounted host receives the photo-taking instruction sent by the cloud platform, and obtains a target body image of the target vehicle and a target chassis image of the target vehicle at the last parking moment based on the photo-taking instruction; Performing desensitization processing on the target vehicle body image and the target chassis image; The desensitized target vehicle body image and the target chassis image are packaged into an image data packet and sent to the cloud platform, so that the cloud platform obtains the parking space identification of the target vehicle based on the target vehicle body image and the target chassis image; the user terminal obtains the parking space identification of the target vehicle from the cloud platform through the message push unit.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for identifying a parking space mark according to any one of claims 1 to 4 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for identifying a parking space mark according to any one of claims 1 to 4.

10. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to enable a computer to execute the method for identifying a parking space mark according to any one of claims 1 to 4.

Images