阅读说明：本技术 车辆检索方法、装置、电子设备及可读存储介质 (Vehicle retrieval method and device, electronic equipment and readable storage medium ) 是由 刘大侠 于 2019-03-29 设计创作，主要内容包括：本申请提供一种车辆检索方法、装置、电子设备及可读存储介质,该方法包括：接收车辆检索模式选择指令；其中,车辆检索模式的种类大于等于2,所述车辆检索模式选择指令中携带有目标车辆检索模式；确定与所述目标车辆检索模式对应的目标车辆特征信息；根据所述目标车辆特征信息进行车辆检索,以确定与所述目标车辆特征信息匹配的目标车辆图片；将所述目标车辆图片返回给车辆检索发起方。该方法可以提高车辆检索的灵活性。(The application provides a vehicle retrieval method, a vehicle retrieval device, an electronic device and a readable storage medium, wherein the method comprises the following steps: receiving a vehicle retrieval mode selection instruction; the type of the vehicle retrieval mode is more than or equal to 2, and the vehicle retrieval mode selection instruction carries a target vehicle retrieval mode; determining target vehicle characteristic information corresponding to the target vehicle retrieval mode; vehicle retrieval is carried out according to the target vehicle characteristic information so as to determine a target vehicle picture matched with the target vehicle characteristic information; and returning the target vehicle picture to a vehicle retrieval initiator. The method can improve the flexibility of vehicle retrieval.)

1. A vehicle retrieval method, characterized by comprising:

receiving a vehicle retrieval mode selection instruction; the type of the vehicle retrieval mode is more than or equal to 2, and the vehicle retrieval mode selection instruction carries a target vehicle retrieval mode;

determining target vehicle characteristic information corresponding to the target vehicle retrieval mode;

vehicle retrieval is carried out according to the target vehicle characteristic information so as to determine a target vehicle picture matched with the target vehicle characteristic information;

and returning the target vehicle picture to a vehicle retrieval initiator.

2. The method of claim 1, wherein the vehicle retrieval mode comprises an attribute retrieval mode or a model retrieval mode.

3. The method of claim 2, wherein the determining target vehicle characteristic information corresponding to the target vehicle retrieval mode comprises:

when the target vehicle retrieval mode is the attribute retrieval mode, determining target vehicle characteristic information corresponding to the target vehicle retrieval mode as target vehicle attribute information;

the vehicle retrieval is carried out according to the target vehicle characteristic information so as to determine a target vehicle picture matched with the target vehicle characteristic information, and the method comprises the following steps:

comparing the target vehicle attribute information with vehicle attribute information of vehicle pictures stored in a database;

determining a vehicle picture with matched vehicle attribute information and target vehicle attribute information as a target vehicle picture;

and/or the first and/or second light sources,

when the target vehicle retrieval mode is a model retrieval mode, determining target vehicle characteristic information corresponding to the target vehicle retrieval mode as a target vehicle model;

the vehicle retrieval is carried out according to the target vehicle characteristic information so as to determine a target vehicle picture matched with the target vehicle characteristic information, and the method comprises the following steps:

comparing the target vehicle model with vehicle models of vehicle pictures stored in a database;

and determining the vehicle picture of which the vehicle model is matched with the target vehicle model as a target vehicle picture.

4. The method according to claim 3, wherein when the target vehicle retrieval mode is a model retrieval mode,

the determining the vehicle picture matching the vehicle model and the target vehicle model as the target vehicle picture comprises:

determining the vehicle picture with the similarity between the vehicle model and the target vehicle model higher than a target similarity threshold value as a target vehicle picture;

wherein, the target similarity threshold is a similarity threshold carried in the vehicle retrieval request or a default similarity threshold.

5. The method according to any one of claims 1-4, wherein prior to receiving the vehicle retrieval mode selection instruction, further comprising:

receiving a vehicle retrieval request, wherein the vehicle retrieval request carries a picture of a vehicle to be retrieved;

and extracting attribute information and a vehicle model of the vehicle to be retrieved from the picture of the vehicle to be retrieved by utilizing a pre-trained intelligent algorithm model.

6. The method according to claim 5, wherein the vehicle retrieval request also carries attribute information of the vehicle to be retrieved;

after the pre-trained intelligent algorithm model is used for extracting the attribute information of the vehicle to be retrieved and the vehicle model from the picture of the vehicle to be retrieved, the method further comprises the following steps:

and determining vehicle attribute information for vehicle retrieval according to the extracted attribute information of the vehicle to be retrieved and the attribute information of the vehicle to be retrieved carried in the vehicle retrieval request.

7. The method according to any one of claims 1-4, wherein prior to determining the target vehicle characteristic information corresponding to the target vehicle retrieval mode, further comprising:

receiving a vehicle retrieval request, wherein the vehicle retrieval request carries a picture of a vehicle to be retrieved;

the determining the target vehicle characteristic information corresponding to the target vehicle retrieval mode comprises:

and extracting target vehicle characteristic information corresponding to the target vehicle retrieval mode from the picture of the vehicle to be retrieved by utilizing a pre-trained intelligent algorithm model.

8. The method according to any one of claims 1-4, wherein the vehicle retrieval according to the target vehicle feature information to determine a target vehicle picture matching the target vehicle feature information comprises:

determining a target channel vehicle picture stored in a database; the target channel vehicle picture is a vehicle picture corresponding to a target channel number carried in the vehicle retrieval request;

comparing the target vehicle characteristic information with the vehicle characteristic information of the target channel vehicle picture;

and determining the target channel vehicle picture with the vehicle characteristic information matched with the target vehicle characteristic information as a target vehicle picture.

9. A vehicle retrieval device characterized by comprising:

a receiving unit for receiving a vehicle retrieval mode selection instruction; the type of the vehicle retrieval mode is more than or equal to 2, and the vehicle retrieval mode selection instruction carries a target vehicle retrieval mode;

a determination unit configured to determine target vehicle feature information corresponding to the target vehicle retrieval mode;

the retrieval unit is used for carrying out vehicle retrieval according to the target vehicle characteristic information so as to determine a target vehicle picture matched with the target vehicle characteristic information;

and the sending unit is used for returning the target vehicle picture to the vehicle retrieval initiator.

10. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;

a memory for storing a computer program;

a processor for implementing the method of any one of claims 1 to 8 when executing a program stored in a memory.

11. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method of any one of claims 1 to 8.

Technical Field

The present disclosure relates to video surveillance technologies, and in particular, to a vehicle retrieval method, a vehicle retrieval device, an electronic device, and a readable storage medium.

Background

The video monitoring system is used as an important technical means for social security management, and is more and more widely applied and deployed in the field of social security maintenance.

Vehicle retrieval is a popular research direction in the application of video surveillance systems in the field of road traffic, and aims to retrieve vehicles from a database that match user-provided vehicle attribute information.

However, practice shows that in the current vehicle retrieval scheme, the retrieval condition is usually fixed as vehicle attribute information, the retrieval mode is single, and the flexibility is poor.

Disclosure of Invention

In view of the above, the present application provides a vehicle retrieval method, a vehicle retrieval device, an electronic device and a readable storage medium.

Specifically, the method is realized through the following technical scheme:

according to a first aspect of embodiments of the present application, there is provided a vehicle retrieval method including:

receiving a vehicle retrieval mode selection instruction; the type of the vehicle retrieval mode is more than or equal to 2, and the vehicle retrieval mode selection instruction carries a target vehicle retrieval mode;

determining target vehicle characteristic information corresponding to the target vehicle retrieval mode;

vehicle retrieval is carried out according to the target vehicle characteristic information so as to determine a target vehicle picture matched with the target vehicle characteristic information;

and returning the target vehicle picture to a vehicle retrieval initiator.

According to a second aspect of embodiments of the present application, there is provided a vehicle retrieval device including:

a receiving unit for receiving a vehicle retrieval mode selection instruction; the type of the vehicle retrieval mode is more than or equal to 2, and the vehicle retrieval mode selection instruction carries a target vehicle retrieval mode;

a determination unit configured to determine target vehicle feature information corresponding to the target vehicle retrieval mode;

the retrieval unit is used for carrying out vehicle retrieval according to the target vehicle characteristic information so as to determine a target vehicle picture matched with the target vehicle characteristic information;

and the sending unit is used for returning the target vehicle picture to the vehicle retrieval initiator.

According to a third aspect of the embodiments of the present application, an electronic device is provided, which includes a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;

a memory for storing a computer program;

and the processor is used for realizing the vehicle retrieval method when executing the program stored in the memory.

According to a fourth aspect of embodiments of the present application, there is provided a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when executed by a processor, the computer program implements the vehicle retrieval method described above.

According to the vehicle retrieval method, the vehicle retrieval mode selection instruction is received, vehicle retrieval is carried out according to the target vehicle characteristic information carried in the vehicle retrieval mode selection instruction, so that the target vehicle picture matched with the target vehicle characteristic information is determined, and then the target vehicle picture is returned to the vehicle retrieval initiator, so that the flexibility of vehicle retrieval is improved.

Drawings

FIG. 1 is a schematic flow chart diagram illustrating a vehicle retrieval method according to an exemplary embodiment of the present application;

FIG. 2A is a schematic illustration of a vehicle search interface according to an exemplary embodiment of the present application;

FIG. 2B is a schematic illustration of a vehicle search interface according to yet another exemplary embodiment of the present application;

fig. 3 is a schematic structural diagram of a vehicle search device according to an exemplary embodiment of the present application;

fig. 4 is a schematic structural diagram of a vehicle retrieval device according to yet another exemplary embodiment of the present application;

fig. 5 is a schematic diagram of a hardware structure of an electronic device according to an exemplary embodiment of the present application.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

In order to make the technical solutions provided in the embodiments of the present application better understood and make the above objects, features and advantages of the embodiments of the present application more comprehensible, the technical solutions in the embodiments of the present application are described in further detail below with reference to the accompanying drawings.

Referring to fig. 1, a schematic flow chart of a vehicle retrieval method according to an embodiment of the present application is shown in fig. 1, where the vehicle retrieval method may include the following steps:

step S100, receiving a vehicle retrieval mode selection instruction; the type of the vehicle retrieval mode is more than or equal to 2, and the target vehicle retrieval mode is carried in the vehicle retrieval mode selection instruction.

In the embodiment of the present application, in order to improve the flexibility of vehicle retrieval, a plurality of vehicle retrieval modes may be provided, for example, vehicle retrieval is performed according to vehicle attribute information (referred to as an attribute retrieval mode herein), or vehicle retrieval is performed according to a vehicle model (referred to as a model retrieval mode herein), and the like.

Accordingly, in the embodiment of the present application, when the vehicle retrieval is required, the vehicle retrieval mode may be specified.

And step S110, determining target vehicle characteristic information corresponding to the target vehicle retrieval mode.

In the embodiment of the application, when a vehicle retrieval mode selection instruction is received, a vehicle retrieval mode (referred to as a target vehicle retrieval mode herein) carried in the vehicle retrieval mode instruction may be acquired, and vehicle feature information (referred to as target vehicle feature information herein) corresponding to the target vehicle retrieval mode may be determined.

Optionally, the vehicle attribute information may include, but is not limited to, one or more of vehicle brand, body color, vehicle type, and license plate number.

In one example, when the target vehicle retrieval mode is the attribute retrieval mode, determining the target vehicle feature information corresponding to the target retrieval mode may include:

and determining the target vehicle characteristic information corresponding to the target vehicle retrieval mode as target vehicle attribute information.

In another example, when the target vehicle retrieval mode is the model retrieval mode, determining the target vehicle feature information corresponding to the target retrieval mode may include:

and determining the target vehicle characteristic information corresponding to the target vehicle retrieval mode as a target vehicle model.

And step S120, vehicle retrieval is carried out according to the target vehicle characteristic information so as to determine a target vehicle picture matched with the target vehicle characteristic information.

In the embodiment of the present application, when the target vehicle feature information corresponding to the target vehicle retrieval mode is determined, a vehicle retrieval may be performed according to the target vehicle feature information to determine a vehicle picture (referred to as a target vehicle picture herein) matching the target vehicle feature information.

For example, vehicle picture information stored in the database may be retrieved according to the target vehicle feature information, and the vehicle picture information may include a vehicle picture and vehicle feature information corresponding to the vehicle picture, so as to determine a target vehicle picture in which the vehicle feature information matches the target vehicle feature information.

In one embodiment of the present application, when the vehicle retrieval mode is the attribute retrieval mode, the performing vehicle retrieval according to the target vehicle feature information to determine a target vehicle picture matching the target vehicle feature information may include:

comparing the target vehicle attribute information with the vehicle attribute information of the vehicle picture stored in the database;

and determining the vehicle picture with the matched vehicle attribute information and target vehicle attribute information as the target vehicle picture.

In this embodiment, when the target vehicle retrieval mode is the attribute retrieval mode, the target vehicle feature information is the target vehicle attribute information.

In this embodiment, after the target vehicle attribute information is determined, the target vehicle attribute information may be compared with the vehicle attribute information of the vehicle pictures stored in the database, and the vehicle picture in which the vehicle attribute information matches the target vehicle attribute information may be determined as the target vehicle picture.

In another embodiment of the present application, when the vehicle search mode is the model search mode, the performing vehicle search according to the target vehicle feature information to determine the target vehicle picture matching the target vehicle feature information may include:

comparing the target vehicle model with vehicle models of vehicle pictures stored in a database;

and determining the vehicle picture of which the vehicle model is matched with the target vehicle model as a target vehicle picture.

In this embodiment, when the target vehicle retrieval mode is the model retrieval mode, the target vehicle feature information is the target vehicle model.

In this embodiment, after the target vehicle model is determined, the target vehicle model may be compared with the vehicle models of the vehicle pictures stored in the database, and the vehicle picture in which the vehicle model matches the target vehicle model may be determined as the target vehicle picture.

In one example, the determining of the vehicle picture matching the vehicle model with the target vehicle model as the target vehicle picture may include:

determining the vehicle picture with the similarity between the vehicle model and the target vehicle model higher than a target similarity threshold value as a target vehicle picture;

the target similarity threshold is a similarity threshold carried in the vehicle retrieval request or a default similarity threshold.

In this example, when the vehicle retrieval mode is the model retrieval mode, the similarity of the target vehicle model and the vehicle model of each vehicle picture existing in the database may be calculated, and the vehicle picture whose similarity with the target vehicle model exceeds the target similarity threshold may be determined as the target vehicle picture.

For example, when a user initiates vehicle retrieval, if the user selects the model retrieval mode, a similarity threshold may be selected or input in the vehicle retrieval initiation interface, and when vehicle retrieval is performed, the similarity threshold may be used as a target similarity threshold for vehicle retrieval.

For another example, when a vehicle search is initiated by a user, if the user selects the model search mode but does not specify a similarity threshold, the vehicle search may be performed with a preset default similarity threshold as the target similarity threshold.

And step S130, returning the target vehicle picture to the vehicle retrieval initiator.

In the embodiment of the application, after the target vehicle picture is determined, the target vehicle picture can be returned to the vehicle retrieval initiator as a vehicle retrieval result.

It can be seen that in the method flow shown in fig. 1, by setting a plurality of vehicle retrieval modes, when vehicle retrieval is performed, the vehicle retrieval mode can be selected, thereby improving flexibility of vehicle retrieval.

Further, in one embodiment of the present application, before receiving the vehicle retrieval mode selection instruction, the method may further include:

receiving a vehicle retrieval request, wherein the vehicle retrieval request carries a picture of a vehicle to be retrieved;

and extracting attribute information of the vehicle to be retrieved and a vehicle model from the picture of the vehicle to be retrieved by utilizing a pre-trained intelligent algorithm model.

In this embodiment, before the user selects the vehicle retrieval mode, the user may submit a vehicle retrieval request carrying a picture of a vehicle to be retrieved.

Correspondingly, when a vehicle retrieval request is received, the picture of the vehicle to be retrieved carried in the vehicle retrieval request can be obtained, the picture of the vehicle to be retrieved is input into the pre-trained intelligent algorithm model, and the attribute information of the vehicle to be retrieved and the vehicle model are extracted from the picture of the vehicle to be retrieved by utilizing the pre-trained intelligent algorithm model.

The pre-trained intelligent algorithm model can be a convolutional neural network model, and intelligent analysis can be performed through a deep learning algorithm.

In this embodiment, after obtaining the attribute information of the vehicle to be retrieved and the vehicle model, the vehicle retrieval may be performed according to the target vehicle retrieval mode carried in the vehicle retrieval mode selection instruction in the manner described in the above embodiment.

For example, when the target vehicle retrieval mode is the attribute retrieval mode, the attribute information of the vehicle to be retrieved may be determined as the target vehicle feature information, and the vehicle retrieval may be performed in the manner described in the above embodiment.

For another example, when the target vehicle search mode is the model search mode, the vehicle model of the vehicle to be searched may be determined as the target vehicle feature information, and the vehicle search may be performed in the manner described in the above embodiment.

Further, in this embodiment, the vehicle retrieval request may also carry attribute information of the vehicle to be retrieved, that is, when the vehicle retrieval request is submitted, the attribute information of the vehicle to be retrieved may be uploaded in addition to the picture of the vehicle to be retrieved.

Accordingly, in an example, after extracting the attribute information of the vehicle to be retrieved and the vehicle model from the picture of the vehicle to be retrieved by using the pre-trained intelligent algorithm model, the method may further include:

and determining vehicle attribute information for vehicle retrieval according to the extracted attribute information of the vehicle to be retrieved and the attribute information of the vehicle to be retrieved carried in the vehicle retrieval request.

In this example, when the vehicle retrieval request carries attribute information (referred to as first attribute information herein) of a vehicle to be retrieved, after the attribute information (referred to as second attribute information herein) of the vehicle to be retrieved is extracted in the manner described in the above embodiment, vehicle attribute information (referred to as third attribute information herein) for vehicle retrieval may be determined according to the first attribute information and the second attribute information.

For any vehicle to be retrieved, comparing the first attribute information with the second attribute information, and adding the attribute information which exists in the first attribute information but does not exist in the second attribute information or the attribute information which does not exist in the first attribute information but exists in the second attribute information into third attribute information; and adding the attribute information in the second attribute information (or the first attribute information) to the third attribute information for the attribute information existing in both the first attribute information and the second attribute information, and further obtaining third vehicle attribute information for vehicle retrieval.

In this example, the first attribute information or the second attribute information may be directly used as the third attribute information for vehicle search.

In another embodiment of the present application, before determining the target vehicle characteristic information corresponding to the target vehicle retrieval mode, the method may further include:

receiving a vehicle retrieval request, wherein the vehicle retrieval request carries a picture of a vehicle to be retrieved;

determining target vehicle characteristic information corresponding to the target vehicle retrieval mode may include:

and extracting target vehicle characteristic information corresponding to the target vehicle retrieval mode from the picture of the vehicle to be retrieved by utilizing a pre-trained intelligent algorithm model.

In this embodiment, after receiving the vehicle retrieval request and acquiring the picture of the vehicle to be retrieved carried in the vehicle retrieval request, the picture of the vehicle to be retrieved may not be analyzed first, but after receiving the selection instruction of the vehicle retrieval mode, the target vehicle feature information corresponding to the target vehicle retrieval mode is extracted from the picture of the vehicle to be retrieved by using a pre-trained intelligent algorithm model according to the target vehicle retrieval mode carried in the vehicle retrieval mode selection instruction.

For example, assuming that the target vehicle retrieval mode is the attribute retrieval mode, the pre-trained intelligent algorithm model may be used to extract the vehicle attribute information of the picture of the vehicle to be retrieved from the picture of the vehicle to be retrieved.

For another example, assuming that the target vehicle retrieval mode is the model retrieval mode, the vehicle model of the picture of the vehicle to be retrieved can be extracted from the picture of the vehicle to be retrieved by using the pre-trained intelligent algorithm model.

It should be noted that, in the embodiment of the present application, the vehicle retrieval mode selection instruction may also be directly carried in the vehicle retrieval request, that is, the vehicle retrieval request may carry the vehicle retrieval mode selection instruction and the picture of the vehicle to be retrieved, and further, when the vehicle retrieval request is received, the pre-trained intelligent algorithm model may be directly used to extract the target vehicle feature information corresponding to the target vehicle retrieval mode from the picture of the vehicle to be retrieved, and specific implementation thereof is not described herein again.

Further, in the embodiment of the present application, it is considered that in an actual video monitoring scene, a plurality of front-end video capture devices (e.g., IPCs (Internet Protocol cameras)) generally exist, different front-end video capture devices correspond to different channels, and when vehicle retrieval is performed, a channel number of a channel that needs to be retrieved may also be specified.

Accordingly, in one embodiment of the present application, the vehicle retrieving according to the target vehicle feature information to determine the target vehicle picture matching the target vehicle feature information may include:

determining a target channel vehicle picture stored in a database; the target channel vehicle picture is a vehicle picture corresponding to a target channel number carried in the vehicle retrieval request;

comparing the target vehicle characteristic information with the vehicle characteristic information of the target channel vehicle picture;

and determining the target passage vehicle picture matched with the vehicle characteristic information and the target vehicle characteristic information as a target vehicle picture.

In this embodiment, the vehicle picture information stored in the database also records the lane number of the vehicle picture.

For example, assuming that the channel number corresponding to IPC1 is C1, the channel number of the vehicle picture captured by IPC1 stored in the database is C1.

In this embodiment, when a vehicle retrieval request is received, the vehicle picture information stored in the database may be queried according to a lane number (referred to as a target lane number herein) carried in the vehicle retrieval request to determine a vehicle picture (referred to as a target lane vehicle picture herein) corresponding to the target lane number.

After the target lane vehicle picture is determined, the target vehicle feature information (which may be vehicle attribute information or a vehicle model) may be compared with the vehicle feature information of the target lane vehicle picture, and the target lane vehicle picture in which the vehicle feature information matches the target vehicle feature information may be determined as the target vehicle picture.

It should be noted that, in the embodiment of the present application, the vehicle retrieval request may carry information described in the above embodiment, and may also carry other information, such as a retrieval time period, and accordingly, when performing vehicle retrieval, the finally returned target vehicle picture may also be determined according to the other information, for example, a vehicle picture matching the target vehicle feature information in the vehicle pictures of which the time information stored in the database is within the retrieval time period is determined as the target vehicle picture, and specific implementation thereof is not described herein again.

In addition, in the embodiment of the present application, in order to improve accuracy of vehicle retrieval, vehicle retrieval may also be performed according to the vehicle attribute information and the vehicle model at the same time (a corresponding mode may be referred to as a comprehensive retrieval mode), and in this retrieval mode, the vehicle image in which both the vehicle attribute information and the vehicle model stored in the database are matched with the vehicle attribute information and the vehicle model of the vehicle to be retrieved may be determined as the target vehicle image, and specific implementation thereof is not described herein again.

In order to enable those skilled in the art to better understand the technical solutions provided by the embodiments of the present application, the technical solutions provided by the embodiments of the present application are described below with reference to specific examples.

In this embodiment, an NVR (Network Video Recorder) is taken as an example of a retrieval device for vehicle retrieval, wherein an intelligent chip with an intelligent analysis function is loaded in the NVR.

However, it should be appreciated that in the embodiment of the present application, the retrieval device for vehicle retrieval is not limited to NVR, and may be other retrieval devices having a vehicle retrieval function and performing vehicle retrieval in the manner described in the above embodiment.

In this embodiment, the vehicle retrieval scheme implementation flow is as follows: