Target recognition method based on machine vision, electronic device and storage medium

Abstract

The application discloses a target identification method based on machine vision, an electronic device and a storage medium, and comprises the following steps: receiving target light pulse information and acquiring a first road video; performing target identification on the first road video to obtain a first light-emitting area corresponding to a plurality of first indicator lights, wherein the first indicator lights are generated by corresponding device light sources arranged on corresponding terminals; performing light pulse identification on each first light-emitting area in the first road video to obtain first light pulse information of each terminal; comparing each first light pulse information with the target light pulse information respectively to obtain a comparison result; determining a target terminal in each terminal according to the comparison result; and determining first position information of the target terminal according to the first light-emitting area corresponding to the target terminal. Comparing the target light pulse information with the first light pulse information and determining the target terminal according to the comparison result can effectively improve the accuracy of target identification.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of target identification, and in particular to a target identification method based on machine vision, an electronic device, and a storage medium. BACKGROUND

[0002] In order to save travel time, people often choose to take a taxi. With the development of science and technology, driverless vehicles have gradually entered people's daily life. Driverless vehicles can also be used as taxis to improve the convenience of people's travel.

[0003] In related technologies, during the calling process of a taxi, a satellite positioning system is used to locate the passenger and the vehicle. However, this positioning method has poor accuracy. After the vehicle arrives at the specified location, a person image recognition system provided on the vehicle is used to recognize the person image. The target passenger is identified in the crowd. However, the person image features of different people have certain similarities, which may cause errors in the person image recognition result and make it difficult to accurately identify the target. Therefore, there is an urgent need for an accurate target identification method. SUMMARY

[0004] The embodiments of the present application provide a target identification method based on machine vision, an electronic device, and a storage medium, which can effectively improve the accuracy of target identification.

[0005] In a first aspect, the embodiments of the present application provide a target identification method based on machine vision, applied to a control system of a vehicle, including:

[0006] receiving target light pulse information and obtaining a first road video;

[0007] performing target identification on the first road video to obtain a first light-emitting area corresponding to a plurality of first indicator lights, wherein the first indicator lights are generated by corresponding device light sources, and the device light sources are arranged on corresponding terminals;

[0008] performing light pulse identification on each first light-emitting area in the first road video to obtain first light pulse information of each terminal;

[0009] comparing each first light pulse information with the target light pulse information to obtain a comparison result;

[0010] determining the target terminal among the terminals according to the comparison result;

[0011] determining first position information of the target terminal according to the first light-emitting area corresponding to the target terminal.

[0012] According to some embodiments of the first aspect of the present application, the receiving target light pulse information comprises:

[0013] When the target terminal has a pairing relationship with the vehicle, receiving target light pulse information, wherein the target light pulse information is generated by the pairing relationship;

[0014] Or, when the target terminal does not have a pairing relationship with the vehicle, receiving target light pulse information, wherein the target light pulse information is generated by a preset matching rule.

[0015] According to some embodiments of the first aspect of the application, the target identification on the first road video obtains a plurality of first light-emitting regions, comprising:

[0016] Performing saliency extraction on the first road video to obtain at least one candidate salient region;

[0017] Determining the region brightness of the candidate salient region;

[0018] When the region brightness is greater than a preset brightness threshold, the candidate salient region is taken as a first light-emitting region.

[0019] According to some embodiments of the first aspect of the application, the target light pulse information includes target pulse width information and target light wavelength information, and the first light pulse information includes candidate pulse width information and candidate light wavelength information; the target terminal is determined in each of the terminals according to the comparison result, comprising:

[0020] When the comparison result indicates that the candidate pulse width information is the same as the target pulse width information, and the candidate light wavelength information is the same as the target light wavelength information, the terminal corresponding to the first light pulse information is taken as the target terminal.

[0021] According to some embodiments of the first aspect of the application, the target identification on the first road video comprises:

[0022] Receiving the boarding position information of the target terminal;

[0023] Obtaining vehicle real-time position information;

[0024] When the distance between the vehicle real-time position information and the boarding position information is less than a preset distance threshold, performing target identification on the first road video.

[0025] According to some embodiments of the first aspect of the application, the vehicle is provided with a vehicle light, and the method further comprises:

[0026] Generating a light control instruction according to the target light pulse information;

[0027] sending the light control instruction to the vehicle light to make the vehicle light generate second indicating light carrying the target light pulse information.

[0028] In a second aspect, the embodiments of the present application provide a target identification method based on machine vision, applied to a terminal, comprising:

[0029] receiving first light pulse information;

[0030] generating first indicating light according to the first light pulse information, wherein the first indicating light is used to make first road video acquired by a vehicle control system carry the first light pulse information, and the vehicle control system is used to execute the target identification method based on machine vision as described in the first aspect.

[0031] According to some embodiments of the second aspect of the present application, the method further comprises:

[0032] acquiring second road video;

[0033] performing target identification on the second road video to obtain second light emitting areas corresponding to second indicating light, wherein the second indicating light is generated by a corresponding vehicle light, and the vehicle light is arranged on a corresponding vehicle;

[0034] performing light pulse identification on each of the second light emitting areas in the second road video to obtain second light pulse information of each of the vehicles;

[0035] comparing each of the second light pulse information with the target light pulse information to obtain a comparison result;

[0036] determining the target vehicle among the vehicles according to the comparison result;

[0037] determining second position information of the target vehicle according to the second light emitting area corresponding to the target vehicle;

[0038] displaying the second position information.

[0039] In a third aspect, the embodiments of the present application provide an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the target identification method based on machine vision as described in the first aspect, or implement the target identification method based on machine vision as described in the second aspect.

[0040] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, which stores computer executable instructions for causing a computer to execute the machine vision based target identification method according to the first aspect, or implement the machine vision based target identification method according to the second aspect.

[0041] The machine vision based target identification method, the electronic device and the storage medium provided in the present application include: receiving target light pulse information and obtaining a first road video; performing target identification on the first road video to obtain a first light emitting area corresponding to a plurality of first indicator lights, wherein the first indicator light is generated by a corresponding device light source, and the device light source is arranged on a corresponding terminal; performing light pulse identification on each first light emitting area in the first road video to obtain first light pulse information of each terminal; comparing each first light pulse information with the target light pulse information respectively to obtain a comparison result; determining a target terminal among the terminals according to the comparison result; and determining first position information of the target terminal according to the first light emitting area corresponding to the target terminal. According to the scheme provided in the embodiments of the present application, the target light pulse information is received and the first road video is obtained, then the target identification is performed on the first road video to obtain the first light emitting area corresponding to the plurality of first indicator lights, and the light pulse identification is performed on each first light emitting area in the first road video to obtain the first light pulse information of each terminal, so as to compare the target light pulse information with the first light pulse information based on the target light pulse information, and realize the screening of the first light pulse information. Moreover, the light pulse identification based on the first road video can ensure the integrity of the first light pulse information, and thus effectively ensure the accuracy of the target identification. The target terminal is determined among the terminals according to the comparison result, so as to accurately identify the target terminal, and then the first position information of the target terminal is determined according to the first light emitting area corresponding to the target terminal, so that the vehicle can accurately reach the position where the target terminal is located according to the first position information. It can be seen that, compared with the technical scheme of using a portrait recognition system to perform target identification in the related art, the machine vision based target identification method provided in the embodiments of the present application can effectively improve the accuracy of target identification by comparing the target light pulse information with the first light pulse information in the first road video and determining the target terminal according to the comparison result. BRIEF DESCRIPTION OF DRAWINGS

[0042] The accompanying drawings are used to provide a further understanding of the technical scheme of the present application, and constitute a part of the specification, and are used to explain the technical scheme of the present application together with the embodiments of the present application, and do not constitute a limitation on the technical scheme of the present application.

[0043] Figure 1 is an optional step flowchart of the machine vision based target identification method provided in the embodiments of the present application;

[0044] Figure 2 is a step flow chart of the first light emitting area determination method provided by the embodiments of the present application;

[0045] Figure 3 is a step flow chart of the target terminal determination method provided by the embodiments of the present application;

[0046] Figure 4 is a step flow chart of the target identification method provided by the embodiments of the present application;

[0047] Figure 5 is an optional step flow chart of the generation of the light control instruction provided by the embodiments of the present application;

[0048] Figure 6 is another optional step flow chart of the target identification method based on machine vision provided by the embodiments of the present application;

[0049] Figure 7 is a step flow chart of the target identification method based on machine vision provided by the embodiments of the present application;

[0050] Figure 8 is a hardware structure schematic diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0051] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0052] In the description of the present application, the meaning of several is one or more, the meaning of multiple is two or more, greater than, less than, more than, etc. are understood as not including the number, above, below, within, etc. are understood as including the number.

[0053] It should be noted that although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flow chart, in some cases, the steps shown or described can be executed in a different order from the module division in the device or the order in the flow chart. The terms "first", "second", etc. in the specification, claims or above are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0054] In the related art, in the process of calling a taxi, the positioning of the passenger and the vehicle is realized by using a satellite positioning system, but the positioning accuracy is poor. After the vehicle arrives at the specified location, a portrait recognition system provided on the vehicle is used to recognize the portrait, and the target passenger is recognized in the crowd. However, the portrait features of different people are similar, which leads to errors in the portrait recognition result and makes it difficult to accurately identify the target. Therefore, there is an urgent need for an accurate target identification method.

[0055] To solve the problem of inaccurate target identification, the present application provides a target identification method based on machine vision, an electronic device and a storage medium. The method comprises: receiving target light pulse information and obtaining a first road video; performing target identification on the first road video to obtain a first light-emitting area corresponding to a plurality of first indicator lights, wherein the first indicator light is generated by a corresponding device light source provided on a corresponding terminal; performing light pulse identification on each first light-emitting area in the first road video to obtain first light pulse information of each terminal; comparing each first light pulse information with the target light pulse information to obtain a comparison result; determining a target terminal among the terminals according to the comparison result; and determining first position information of the target terminal according to the first light-emitting area corresponding to the target terminal. According to the scheme provided in the embodiments of the present application, the target light pulse information is received and the first road video is obtained, then the target identification is performed on the first road video to obtain a first light-emitting area corresponding to a plurality of first indicator lights, and the light pulse identification is performed on each first light-emitting area in the first road video to obtain first light pulse information of each terminal, so as to compare the target light pulse information with the first light pulse information based on the target light pulse information, and realize the screening of the first light pulse information. Moreover, the light pulse identification based on the first road video can ensure the integrity of the first light pulse information, thereby effectively ensuring the accuracy of target identification. According to the comparison result, the target terminal is determined among the terminals to accurately identify the target terminal, and then the first position information of the target terminal is determined according to the first light-emitting area corresponding to the target terminal, so that the vehicle can accurately arrive at the position of the target terminal according to the first position information. It can be seen that the target identification method based on machine vision provided in the embodiments of the present application compares the target light pulse information with the first light pulse information in the first road video, determines the target terminal according to the comparison result, and compared with the technical solution of using a portrait recognition system to identify the target in the related art, the accuracy of target identification can be effectively improved.

[0056] The target identification method based on machine vision, the electronic device and the storage medium provided in the embodiments of the present application are specifically described as follows. First, the target identification method based on machine vision in the embodiments of the present application is described.

[0057] The target recognition method based on machine vision provided in the embodiments of the present application relates to the technical field of target recognition. The target recognition method based on machine vision provided in the embodiments of the present application can be applied to a terminal, can also be applied to a server end, and can further be software running in the terminal or the server end. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, or the like; the server end can be configured as a stand-alone physical server, can also be configured as a server cluster or a distributed system formed by multiple physical servers, and can further be configured as a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, and big data and artificial intelligence platform; and the software can be an application program for implementing the target recognition method based on machine vision, but is not limited to the above forms.

[0058] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as a program module. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment, in which tasks are performed by remote processing devices connected by a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0059] It should be noted that in each specific embodiment of the present application, when relevant processing needs to be performed according to user information, user behavior data, user historical data, and user location information, and the like related to the identity or characteristics of the user, the user's permission or consent will be obtained first, and the collection, use, and processing of the data will comply with relevant laws, regulations, and standards. In addition, when the embodiments of the present application need to obtain sensitive personal information of the user, the separate permission or separate consent of the user will be obtained through a pop-up window or a jump to a confirmation page, and after obtaining the separate permission or separate consent of the user, the necessary user-related data for enabling the embodiments of the present application to normally operate will be obtained.

[0060] The embodiments of the present application will be further described below with reference to the accompanying drawings.

[0061] Reference Figure 1 , Figure 1is an optional step flowchart of a target recognition method based on machine vision provided by the embodiment of the present application. The target recognition method based on machine vision can be applied to a vehicle control system. The target recognition method based on machine vision includes but is not limited to the following steps:

[0062] In step S110, target light pulse information is received, and a first road video is acquired.

[0063] In step S120, target recognition is performed on the first road video to obtain a first light-emitting area corresponding to a plurality of first indicator lights. The first indicator lights are generated by corresponding device light sources arranged on corresponding terminals.

[0064] In step S130, light pulse recognition is performed on each first light-emitting area in the first road video to obtain first light pulse information of each terminal.

[0065] In step S140, each first light pulse information is compared with the target light pulse information to obtain a comparison result.

[0066] In step S150, the target terminal is determined among the terminals according to the comparison result.

[0067] In step S160, first position information of the target terminal is determined according to the first light-emitting area corresponding to the target terminal.

[0068] It should be noted that the vehicle is provided with a vehicle-mounted camera. The vehicle control system is in communication connection with the vehicle-mounted camera. The vehicle control system acquires the first road video through the vehicle-mounted camera. The administrator or passenger can communicate with the vehicle control system through a terminal such as a mobile phone or a laptop computer.

[0069] It can be understood that the first indicator light generated by the device light source of the terminal has adjustability. The first indicator light has different light-emitting rules, light-emitting colors, and light-emitting energies, and the corresponding light pulse information is also different. In addition, the transmission stability of light is high and is not easily affected by the environment. Therefore, according to the received target light pulse information, the first light pulse information of each terminal is compared with the target light pulse information, and then the target terminal is determined according to the comparison result, which can ensure the recognition accuracy of the target terminal.

[0070] It can be understood that the target light pulse information is received, and the first road video is acquired, and then target identification is performed on the first road video to obtain a first light-emitting area corresponding to a plurality of first indicator lights, so as to narrow the identification area and further improve the target identification efficiency and accuracy, wherein the first indicator light is generated by a corresponding device light source arranged on a corresponding terminal. Then, light pulse identification is performed on each first light-emitting area in the first road video to obtain first light pulse information of each terminal, so as to compare the target light pulse information with the first light pulse information based on the target light pulse information, and realize screening of the first light pulse information. Moreover, the light pulse identification based on the first road video can ensure the integrity of the first light pulse information, and further effectively ensure the accuracy of target identification. According to the comparison result, when the comparison result indicates that the target light pulse information is the same as the first light pulse information, the terminal corresponding to the first light pulse information is determined as the target terminal from the terminals, so as to accurately identify the target terminal, and then the first position information of the target terminal is determined according to the first light-emitting area corresponding to the target terminal, so that the vehicle can accurately arrive at the position of the target terminal according to the first position information. It can be seen that the target identification method based on machine vision provided in the embodiment of the application compares the target light pulse information with the first light pulse information in the first road video, and determines the target terminal according to the comparison result. Compared with the technical solution of using a portrait recognition system for target identification in the related art, the accuracy of target identification can be effectively improved.

[0071] In addition, in an embodiment, Figure 1 The receiving target light pulse information of step S110 in the illustrated embodiment further includes but is not limited to the following steps:

[0072] When the target terminal and the vehicle have a pairing relationship, the target light pulse information is received, wherein the target light pulse information is generated by the pairing relationship;

[0073] Or, when the target terminal and the vehicle do not have a pairing relationship, the target light pulse information is received, wherein the target light pulse information is generated by a preset matching rule.

[0074] It can be understood that the vehicle control system and the terminal can be respectively connected with the cloud server, and the application program can be deployed in the cloud server. In the process of calling a vehicle, the passenger sends a vehicle calling instruction to the cloud server through the terminal, the cloud server determines a target vehicle from a plurality of candidate vehicles, and establishes a pairing relationship between the target vehicle and the terminal.

[0075] It can be understood that when the target terminal and the vehicle exist a pairing relationship, it means that in the process of calling a vehicle, the passenger sends a vehicle calling instruction to the cloud server through the target terminal, the cloud server determines a vehicle from a plurality of candidate vehicles, and establishes a pairing relationship between the target terminal and the vehicle. Subsequently, the cloud server generates target light pulse information according to the pairing relationship, and the target light pulse information is received by the vehicle control system corresponding to the vehicle.

[0076] It can be understood that when the target terminal and the vehicle do not exist a pairing relationship, it means that in the process of calling a vehicle, the passenger sends a vehicle calling instruction to the cloud server through the terminal, but the cloud server fails to determine a target vehicle from a plurality of candidate vehicles. Moreover, the current vehicle is also in a state of not establishing a pairing relationship. The cloud server generates target light pulse information according to a preset matching rule, and the target light pulse information indicates that the target terminal is in a vehicle calling state and has not established a pairing relationship. After the vehicle receives the target light pulse information, in the process of driving, the vehicle can determine the target terminal which has not established a pairing relationship according to the target light pulse information, and timely arrive at the position of the target terminal, thereby expanding the calling way, realizing roadside instant calling through the terminal to generate indicating light, and improving the calling experience of the passenger.

[0077] It can be understood that in an embodiment, after the cloud server generates the target light pulse information according to the preset matching rule, the cloud server can send the target light pulse information to at least one candidate vehicle which has not established a pairing relationship near the target terminal according to a preset target light pulse information sending rule.

[0078] It can be understood that when the unmanned vehicle is used as a taxi, the unmanned vehicle can reach a preset passenger pickup point according to an existing positioning system in a paired state, obtain a first road video, and compare the received target light pulse information with first light pulse information of each terminal in the first road video. According to the comparison result, the target terminal is determined from each terminal. Alternatively, the unmanned vehicle can obtain a first road video in real time or at a certain time interval in an unpaired state, and compare the received target light pulse information with first light pulse information of each terminal in the first road video. According to the comparison result, the target terminal is determined from each terminal. Based on the target light pulse information and the first light pulse information, the near distance interaction between the vehicle and the target terminal is realized, so that the unmanned vehicle accurately identifies and reaches the position of the target terminal.

[0079] In addition, with reference to Figure 2 In an embodiment, Figure 1 The step S120 in the embodiment shown further includes but is not limited to the following steps:

[0080] In step S210, saliency extraction is performed on the first road video to obtain at least one candidate salient region.

[0081] Step S220, determining the region brightness of the candidate salient region.

[0082] Step S230, when the region brightness is greater than the preset brightness threshold, taking the candidate salient region as the first light-emitting region.

[0083] It can be understood that the saliency extraction is performed on the first road video to identify the region in the first road video that presents obvious spatial color difference from the surrounding environment, and filter the redundant information to obtain at least one candidate salient region, which can ensure the accuracy of the light pulse information in the candidate salient region. The region brightness of the candidate salient region is determined, and when the region brightness is greater than the preset brightness threshold, it indicates that the candidate salient region exists the first indicating light generated by the device light source. The candidate salient region is taken as the first light-emitting region to reduce the subsequent light pulse identification region, which can effectively improve the light pulse identification efficiency.

[0084] In addition, with reference to Figure 3 In an embodiment, the target light pulse information includes target pulse width information and target light wavelength information, the first light pulse information includes candidate pulse width information and candidate light wavelength information, Figure 1 The step S150 in the illustrated embodiment further includes but is not limited to the following steps:

[0085] Step S310, when the comparison result indicates that the candidate pulse width information is the same as the target pulse width information, and the candidate light wavelength information is the same as the target light wavelength information, taking the terminal corresponding to the first light pulse information as the target terminal.

[0086] It can be understood that the first indicating light generated by the device light source of the terminal can be color-changing light or light with time-varying light intensity. Different colors of light correspond to different light wavelengths, different interval times of light intensity variation correspond to different pulse widths. Therefore, the target pulse width information and the candidate pulse width information are compared, and the target light wavelength information and the candidate light wavelength information are compared. In the case that the candidate pulse width information is the same as the target pulse width information, and the candidate light wavelength information is the same as the target light wavelength information, the terminal corresponding to the first light pulse information is taken as the target terminal, which can ensure the accuracy of the target identification.

[0087] It can be understood that the target pulse width information and the candidate pulse width information can be compared based on the preset time length to determine whether the pulse width change in the target pulse width information and the pulse width change in the candidate pulse width information are the same. The target light wavelength information and the candidate light wavelength information are compared to determine whether the light wavelength change in the target light wavelength information and the light wavelength change in the candidate light wavelength information are the same, so as to ensure the accuracy of the comparison between the target light pulse information and the candidate light pulse information.

[0088] In addition, with reference to Figure 4 In an embodiment, Figure 1 The target identification on the first road video in step S120 in the illustrated embodiment further includes but is not limited to the following steps:

[0089] Step S410, receiving the pickup location information of the target terminal;

[0090] Step S420, acquiring the real-time location information of the vehicle;

[0091] Step S430, when the distance between the real-time location information of the vehicle and the pickup location information is less than a preset distance threshold, performing target identification on the first road video.

[0092] It can be understood that in the case where the vehicle and the target terminal establish a pairing relationship, the pickup location information of the target terminal is received, so that the vehicle reaches the area corresponding to the pickup location information according to the pickup location information, and the real-time location information of the vehicle is acquired. When the distance between the real-time location information of the vehicle and the pickup location information is less than a preset distance threshold, it indicates that the vehicle has reached the nearby area corresponding to the pickup location information, and target identification is performed on the first road video, so as to realize automatic identification of the target terminal by the vehicle.

[0093] In addition, in an embodiment, the target identification method based on machine vision includes but is not limited to the following steps: when the time length of target identification on the first road video reaches a preset identification time length threshold, generating identification failure information, and reacquiring the pickup location information of the target terminal.

[0094] It can be understood that when the time length of target identification on the first road video reaches a preset identification time length threshold, identification failure information is generated, which can avoid the vehicle consuming too long identification time. The pickup location information of the target terminal is reacquired, so that the vehicle can plan a route according to the reacquired pickup location information. When the distance between the real-time location information of the vehicle and the reacquired pickup location information is less than a preset distance threshold, target identification is performed on the first road video, so as to ensure the efficiency and accuracy of target identification.

[0095] In addition, with reference toFigure 5 In an embodiment, the vehicle is provided with a vehicle light, and the target recognition method based on machine vision further includes but is not limited to the following steps:

[0096] In step S510, a light control instruction is generated according to the target light pulse information.

[0097] In step S520, the light control instruction is sent to the vehicle light to make the vehicle light generate a second indicating light carrying the target light pulse information.

[0098] It can be understood that the vehicle light control instruction is generated according to the target light pulse information, and the light control instruction is sent to the vehicle light to make the vehicle light generate a second indicating light carrying the target light pulse information, so that the target terminal can recognize the second indicating light, realize mutual recognition between the vehicle and the target terminal, and then the passenger can determine the position of the vehicle according to the recognition result displayed by the terminal.

[0099] In addition, in an embodiment, the target recognition method based on machine vision applied to the vehicle control system can further include but is not limited to the following steps:

[0100] The first road video is subjected to road recognition to determine road information.

[0101] The first position information of the target terminal is determined according to the first light-emitting area corresponding to the target terminal and the road information.

[0102] It can be understood that the first road video is subjected to road recognition to determine road information, and after the target terminal is determined, the first position information of the target terminal is determined according to the first light-emitting area corresponding to the target terminal and the road information, so as to avoid the influence of complex road conditions such as curved roads and inclined roads on the position judgment of the target terminal, and ensure the accuracy of the first position information.

[0103] It can be understood that in an embodiment, when the vehicle is in the process of slow driving, the first position information of the target terminal can also be determined in real time according to the road information and the vehicle speed, so that the vehicle can accurately reach the position of the target terminal.

[0104] In addition, in an embodiment, the target recognition method based on machine vision applied to the vehicle control system can further include but is not limited to the following steps:

[0105] The first position information is sent to the vehicle display screen to make the vehicle display screen display the first position information.

[0106] It can be understood that when the vehicle is driven by a person or shared by multiple passengers, the first position information is sent to the vehicle display screen to make the vehicle display screen display the first position information, so that the driver or passenger in the vehicle can intuitively understand the first position information.

[0107] Referring to Figure 6 , Figure 6 is another optional step flowchart of the target identification method based on machine vision provided by the embodiment of the application, which can be applied to a terminal. The target identification method based on machine vision includes but is not limited to the following steps:

[0108] Step S610, receiving first light pulse information;

[0109] Step S610, generating first indicating light according to the first light pulse information, wherein the first indicating light is used to make the first road video acquired by the vehicle control system carry the first light pulse information, and the vehicle control system is used to execute the target identification method based on machine vision as described above.

[0110] It can be understood that the terminal can be an independent light source sending device, a mobile phone, a tablet computer, a notebook computer, a smart watch, smart jewelry, smart clothing and other smart wearable devices. The specific type of the terminal is not limited here, but the terminal needs to be provided with a device light source, and the terminal can control the device light source to generate the first indicating light, so that passengers can call a vehicle through the terminal.

[0111] It can be understood that the specific implementation of the target identification method based on machine vision applied to the terminal is basically the same as the specific implementation of the target identification method based on machine vision applied to the vehicle control system as described above, and will not be repeated here.

[0112] In addition, referring to Figure 7 , in an embodiment, the target identification method based on machine vision applied to the terminal includes but is not limited to the following steps:

[0113] Step S710, acquiring second road video;

[0114] Step S720, performing target identification on the second road video to obtain a second light-emitting area corresponding to a plurality of second indicating lights, wherein the second indicating light is generated by a corresponding vehicle light, and the vehicle light is arranged on a corresponding vehicle;

[0115] Step S730, performing light pulse identification on each second light-emitting area in the second road video to obtain second light pulse information of each vehicle;

[0116] Step S740, comparing each second light pulse information with target light pulse information respectively to obtain a comparison result;

[0117] Step S750, determining a target vehicle among the vehicles according to the comparison result;

[0118] In step S760, the second position information of the target vehicle is determined according to the second light-emitting area corresponding to the target vehicle.

[0119] In step S770, the second position information is displayed.

[0120] It can be understood that the second road video is acquired, and then target recognition is performed on the second road video to obtain a second light-emitting area corresponding to a second indicator light, so as to narrow the recognition area and further improve the target vehicle recognition efficiency and accuracy, wherein the second indicator light is generated by a corresponding vehicle lamp arranged on a corresponding vehicle. Then, light pulse recognition is performed on each second light-emitting area in the second road video to obtain second light pulse information of each vehicle, so as to compare the target light pulse information with the second light pulse information based on the target light pulse information, and realize the screening of the second light pulse information. Moreover, the light pulse recognition based on the second road video can ensure the integrity of the second light pulse information, and further effectively ensure the accuracy of the target vehicle recognition. Each second light pulse information is compared with the target light pulse information respectively to obtain a comparison result. According to the comparison result, when the comparison result indicates that the target light pulse information is the same as the second light pulse information, a vehicle corresponding to the second light pulse information is determined as the target vehicle from each vehicle, so as to accurately identify the target vehicle. Then, the second position information of the target vehicle is determined according to the second light-emitting area corresponding to the target vehicle, and the second position information is displayed, so as to prompt the passenger to reach the position of the target vehicle according to the second position information displayed by the terminal.

[0121] In addition, referring to Figure 8 , Figure 8 The hardware structure of the electronic device of another embodiment is illustrated, and the electronic device includes:

[0122] The processor 801 can be implemented in a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, and is used to execute related programs to implement the technical solutions provided by the embodiments of the present application.

[0123] The memory 802 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 802 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 802 and called by the processor 801 to execute the machine vision-based target recognition method applied to the vehicle control system of this application embodiment, for example, executing the above-described... Figure 1 Method steps S110 to S160 in the above method steps Figure 2 Method steps S210 to S230 in the middle Figure 3 Method steps S310, Figure 4 Method steps S410 to S430 and Figure 5 Method steps S510 to S520, or the target recognition method based on machine vision applied to a terminal according to the embodiments of this application, for example, performing the above-described method. Figure 6 Method steps S610 to S620 and Figure 7 Method steps S710 to S770;

[0124] The 803 input / output interface is used to implement information input and output.

[0125] The communication interface 804 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0126] Bus 805 transmits information between various components of the device (e.g., processor 801, memory 802, input / output interface 803, and communication interface 804);

[0127] The processor 801, memory 802, input / output interface 803, and communication interface 804 are connected to each other within the device via bus 805.

[0128] This application embodiment also provides a storage medium, which is a computer-readable storage medium for computer-readable storage. The storage medium stores one or more programs, which can be executed by one or more processors to implement the above-described machine vision-based target recognition method applied to a vehicle control system. For example, it executes the above-described... Figure 1 Method steps S110 to S160 in the above method steps Figure 2the method steps S210 to S230 in the method of Figure 3 the method steps S310 in the method of Figure 4 the method steps S410 to S430 in the method of Figure 5 the method steps S510 to S520 in the method of Figure 6 the method steps S610 to S620 in the method of Figure 7 the method steps S710 to S770 in the method of

[0129] The memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include a high-speed random access memory and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory that is remotely disposed relative to the processor, and these remote memories can be connected to the processor through 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.

[0130] The machine vision-based target identification method, the electronic device, and the storage medium provided by the embodiments of the present application can receive target light pulse information, and obtain a first road video. Then, target identification is performed on the first road video to obtain a first light-emitting area corresponding to a plurality of first indicator lights, so as to narrow the identification area and further improve the target identification efficiency and accuracy. The first indicator light is generated by a corresponding device light source, and the device light source is arranged on a corresponding terminal. Then, light pulse identification is performed on each first light-emitting area in the first road video to obtain first light pulse information of each terminal. The target light pulse information is compared with the first light pulse information based on the target light pulse information, so as to realize screening of the first light pulse information. In addition, the light pulse identification based on the first road video can ensure the integrity of the first light pulse information, and further effectively ensure the accuracy of target identification. According to the comparison result, when the comparison result indicates that the target light pulse information is the same as the first light pulse information, a terminal corresponding to the first light pulse information is determined as a target terminal from each terminal, so as to accurately identify the target terminal. Then, first position information of the target terminal is determined according to the first light-emitting area corresponding to the target terminal, so that the vehicle can accurately arrive at the position of the target terminal according to the first position information. It can be seen that, compared with the technical solution of using a portrait recognition system to identify a target in the related art, the machine vision-based target identification method provided by the embodiments of the present application can effectively improve the accuracy of target identification by comparing the target light pulse information with the first light pulse information in the first road video and determining the target terminal according to the comparison result.

[0131] The embodiments described in the specification of the present application are intended to more clearly illustrate the technical solutions of the present application, and do not constitute a limitation on the technical solutions provided by the present application. Those skilled in the art can know that, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the present application are also applicable to similar technical problems.

[0132] Those skilled in the art can understand that, Figures 1 to 7 The technical solutions shown in the above description do not constitute a limitation on the embodiments of the present application, and can include more or fewer steps than those shown, or combine certain steps, or different steps.

[0133] The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separate, that is, they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0134] Those skilled in the art can understand that all or some of the steps in the above disclosed method, the function modules / units in the system and the device can be implemented as software, firmware, hardware and their appropriate combinations.

[0135] The terms "first", "second", "third", "fourth" and the like (if any) in the specification of the present application and the above description are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0136] It should be understood that, in the application, "at least one" refers to one or more, and "multiple" refers to two or more. "And / or" is used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, "A and / or B" can represent three cases of only A, only B, and A and B existing at the same time, wherein A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can represent a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, and c can be single or multiple.

[0137] In several embodiments provided in the application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the above units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0138] The units described above as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. According to actual needs, some or all of the units can be selected to achieve the purpose of the embodiment scheme.

[0139] In addition, the functional units in each embodiment of the application can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0140] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program storage media.

[0141] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, and are not limited to the scope of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.

Claims

1. A machine vision-based target recognition method applied to a vehicle control system, characterized by, The method comprises the following steps: When the target terminal has a pairing relationship with the vehicle, receiving target light pulse information generated by the pairing relationship, when the target terminal does not have a pairing relationship with the vehicle, receiving target light pulse information generated by a preset matching rule, and obtaining a first road video and a second road video, wherein the target pulse information comprises target pulse width information and target light wavelength information; Performing target identification on the first road video to obtain a first light-emitting area corresponding to a plurality of first indicator lights, and performing target identification on the second road video to obtain a second light-emitting area corresponding to a plurality of second indicator lights, wherein the first indicator light is generated by a corresponding device light source arranged on a corresponding terminal, and the second indicator light is generated by a corresponding vehicle light arranged on a corresponding vehicle; In the first road video, performing light pulse identification on each first light-emitting area to obtain first light pulse information of each terminal, the first light pulse information comprising candidate pulse width information and candidate light wavelength information; comparing each first light pulse information with the target light pulse information respectively to obtain a first comparison result; when the first comparison result indicates that the candidate pulse width information is the same as the target pulse width information, and the candidate light wavelength information is the same as the target light wavelength information, the terminal corresponding to the first light pulse information is taken as a target terminal; In the second road video, performing light pulse identification on each second light-emitting area to obtain second light pulse information of each vehicle; comparing each second light pulse information with the target light pulse information respectively to obtain a second comparison result; determining a target vehicle from each vehicle according to the second comparison result; According to the first light-emitting area corresponding to the target terminal, determining first position information of the target terminal, so that the target vehicle moves to the position where the target terminal is located based on the first position information, according to the second light-emitting area corresponding to the target vehicle, determining second position information of the target vehicle, displaying the second position in the target terminal, so that the use object of the target terminal moves to the position where the target vehicle is located based on the second position information; When the length of time for performing target identification on the first road video reaches a preset identification time length threshold, generating an identification failure information, and reacquiring the boarding position information of the target terminal. 2.The machine vision-based target identification method of claim 1, wherein, The method comprises the following steps: Performing saliency extraction on the first road video to obtain at least one candidate salient region; Determining the region brightness of the candidate salient region; When the region brightness is greater than a preset brightness threshold, taking the candidate salient region as a first light-emitting area. 3.The machine vision-based target identification method of claim 1, wherein, The method comprises the following steps: Receiving the boarding position information of the target terminal; Obtaining vehicle real-time position information; When a distance between the real-time vehicle position information and the boarding position information is less than a preset distance threshold, performing target recognition on the first road video. 4.The machine vision-based target identification method of claim 1, wherein, The vehicle is provided with a vehicle light, and the method further comprises: generating a light control instruction according to the target light pulse information; sending the light control instruction to the vehicle light to make the vehicle light generate a second indicating light carrying the target light pulse information. 5.A method for target recognition based on machine vision, applied to a terminal, and having the characteristics that, Comprise: receiving first light pulse information; generating a first indicating light according to the first light pulse information, wherein the first indicating light is used to make a first road video acquired by a vehicle control system carry the first light pulse information, and the vehicle control system is used to perform the machine vision-based target recognition method according to any one of claims 1 to 4; acquiring a second road video, performing target recognition on the second road video to obtain a second light-emitting area corresponding to a second indicating light, wherein the second indicating light is generated by a corresponding vehicle light, and the vehicle light is arranged on a corresponding vehicle; performing light pulse recognition on each second light-emitting area in the second road video to obtain second light pulse information of each vehicle; comparing each second light pulse information with the target light pulse information respectively to obtain a second comparison result; and determining the target vehicle from the vehicles according to the second comparison result; determining second position information of the target vehicle according to the second light-emitting area corresponding to the target vehicle, and displaying the second position in the target terminal to make a user of the target terminal move to a position where the target vehicle is located based on the second position information.

6. An electronic device comprising: A memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the machine vision-based target recognition method according to any one of claims 1 to 4 or the machine vision-based target recognition method according to any one of claim 5 when executing the computer program.

7. A computer-readable storage medium, characterized in that: The computer readable storage medium stores computer executable instructions for making a computer execute the machine vision-based target recognition method according to any one of claims 1 to 4 or the machine vision-based target recognition method according to any one of claim 5.

Images