A method and device for returning a road image, an electronic device and a storage medium

Abstract

The application relates to the technical field of electronic maps, and provides a road image return method and device, electronic equipment and a storage medium, wherein a plurality of track point data are acquired, a to-be-processed track line feature sequence set corresponding to the plurality of track point data is determined, a to-be-matched track line feature sequence is determined from a preset candidate track line feature sequence set, a target track line feature sequence is determined from the to-be-processed track line feature sequence set, a track line feature sequence group set is obtained, a target track point is determined from the track point data according to track line features corresponding to the same type of label in the to-be-matched track line feature sequence and the target track line feature sequence, a return instruction is sent to a collection device to instruct the collection device to return a road image corresponding to the target track point. The application can reduce the flow of acquired data, effectively screen out abnormal track points, send collection instructions in a targeted manner, improve collection efficiency and reduce collection cost.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electronic maps, and in particular to a road image return method and device, electronic equipment and a storage medium. BACKGROUND

[0002] In the existing road image return scheme, the server only simply groups, aggregates and removes duplicates of the point element information reported by the device, and then issues a collection command to the device, so that the device receiving the command returns the image containing the recognition result to the server, and then the map data production part completes the audit and production. This scheme relies heavily on the recognition accuracy of the device, and the returned image may contain a large amount of invalid data that can easily cause misidentification. Moreover, the coverage rate of the road change elements that are truly valuable in the large amount of point element information reported by the device is extremely low, and a large amount of invalid cost is easily generated. SUMMARY

[0003] In order to solve the problem that the existing technology relies heavily on the recognition accuracy of the device and cannot accurately recognize road change elements, the present application provides a road image return method, device, electronic equipment and storage medium:

[0004] According to a first aspect of the present application, a road image return method is provided, comprising:

[0005] Obtaining a plurality of track point data uploaded by a collection device for a target road; the track point data includes a type label and coordinate data of each track point, the type label representing the road element type to which the track point belongs, and the coordinate data representing the position of the track point;

[0006] Determining a set of to-be-processed track line feature sequences corresponding to the plurality of track point data;

[0007] From a set of candidate track line feature sequences, a to-be-matched track line feature sequence is determined, and a target track line feature sequence is determined from the set of to-be-processed track line feature sequences, to obtain a set of track line feature sequence groups; the to-be-matched track line feature sequence and the target track line feature sequence in each track line feature sequence group represent the same road, and the candidate track line feature sequence in the set of candidate track line feature sequences indicates a road in the map data;

[0008] For each track line feature sequence group, a target track point is determined from the track point data according to the track line features corresponding to the same type label in the to-be-matched track line feature sequence and the target track line feature sequence; the target track point is a road element collected by the collection device from the target road and different from the road element recorded in the map data;

[0009] Sending a return instruction to the collection device; the return instruction is used to instruct the collection device to return a road image corresponding to the target track point.

[0010] According to a second aspect of the present application, a road image feedback device is provided, comprising:

[0011] An acquisition module is configured to acquire a plurality of track point data uploaded by a collection device for a target road; the track point data comprises a type label and coordinate data of each track point, the type label representing a road element type to which the track point belongs, and the coordinate data representing a position of the track point;

[0012] A first determination module is configured to determine a set of to-be-processed track line feature sequences corresponding to the plurality of track point data;

[0013] A second determination module is configured to determine a to-be-matched track line feature sequence from a preset set of candidate track line feature sequences and determine a target track line feature sequence from the set of to-be-processed track line feature sequences, to obtain a set of track line feature sequence groups; the to-be-matched track line feature sequence and the target track line feature sequence in each track line feature sequence group represent the same road, and the candidate track line feature sequence in the set of candidate track line feature sequences indicates a road in map data;

[0014] A third determination module is configured to, for each track line feature sequence group, determine a target track point from the track point data according to track line features corresponding to the same type labels in the to-be-matched track line feature sequence and the target track line feature sequence; the target track point is a road element collected by the collection device from the target road and different from a road element recorded in the map data;

[0015] A sending module is configured to send a feedback instruction to the collection device; the feedback instruction is used to instruct the collection device to feed back a road image corresponding to the target track point.

[0016] On the other hand, a to-be-processed track line feature in each to-be-processed track line feature sequence represents a difference value of coordinate data of two adjacent track points in the track point data,

[0017] The second determination module is configured to determine a target track line feature sequence from the set of to-be-processed track line feature sequences; the target track line feature sequence is any one of the to-be-processed track line feature sequences in the set of to-be-processed track line feature sequences;

[0018] For any one of the candidate track line feature sequences in the set of candidate track line feature sequences, coordinate data corresponding to each candidate track line feature in the any one candidate track line feature sequence is determined according to a sum value of two adjacent candidate track line features in the any one candidate track line feature sequence; the coordinate data corresponding to the candidate track line feature represents a position of a point on a road in the map data indicated by the any one candidate track line feature sequence;

[0019] If the coordinate data of the trajectory point data corresponding to the target trajectory line feature sequence coincides with the coordinate data corresponding to the candidate trajectory line feature in any one of the candidate trajectory line feature sequences more than a preset coincidence frequency threshold, any one of the candidate trajectory line feature sequences is taken as a to-be-matched trajectory line feature sequence corresponding to the target trajectory line feature sequence, and a trajectory line feature sequence group set is obtained.

[0020] On the other hand, the second determination module is configured to determine a target trajectory line feature sequence from the set of to-be-processed trajectory line feature sequences; the target trajectory line feature sequence is any one of the to-be-processed trajectory line feature sequences in the set of to-be-processed trajectory line feature sequences.

[0021] For any one of the candidate trajectory line features in any one of the candidate trajectory line feature sequences, a to-be-processed trajectory line feature corresponding to the candidate trajectory line feature is determined from the target trajectory line feature sequence; the candidate trajectory line feature and the corresponding to-be-processed trajectory line feature have the same type label.

[0022] If the difference between the candidate trajectory line feature and the corresponding to-be-processed trajectory line feature is less than a preset difference threshold, the to-be-processed trajectory line feature is taken as a non-target trajectory line feature.

[0023] According to a ratio of the number of to-be-processed trajectory line features other than the non-target trajectory line feature in the target trajectory line feature sequence to a total number, a to-be-matched trajectory line feature sequence corresponding to the target trajectory line feature sequence is matched from the set of candidate trajectory line feature sequences, and the trajectory line feature sequence group set is obtained; the total number is the number of candidate trajectory line features in any one of the candidate trajectory line feature sequences.

[0024] On the other hand, the to-be-processed trajectory line feature in each to-be-processed trajectory line feature sequence represents a difference between coordinate data of two adjacent trajectory points in the trajectory point data,

[0025] The second determination module is configured to determine a to-be-matched trajectory line feature sequence from the set of candidate trajectory line feature sequences; the to-be-matched trajectory line feature sequence is any one of the candidate trajectory line feature sequences in the set of candidate trajectory line feature sequences.

[0026] For any one of the to-be-processed trajectory line features in any one of the to-be-processed trajectory line feature sequences, a candidate trajectory line feature corresponding to the to-be-processed trajectory line feature is determined from the to-be-matched trajectory line feature sequence; the to-be-processed trajectory line feature and the corresponding candidate trajectory line feature have the same type label.

[0027] If the difference between the to-be-processed trajectory line feature and the corresponding candidate trajectory line feature is less than a preset difference threshold, the to-be-processed trajectory line feature is taken as a non-target trajectory line feature.

[0028] According to a ratio of a number of the to-be-processed trajectory line features other than the target trajectory line feature in the to-be-processed trajectory line feature sequence to a total number, a target trajectory line feature sequence corresponding to the to-be-matched trajectory line feature sequence is matched from the to-be-processed trajectory line feature sequence set, and a trajectory line feature sequence group set is obtained; the total number is a number of the candidate trajectory line features in the to-be-matched trajectory line feature sequence.

[0029] On the other hand, the to-be-processed trajectory line feature in each to-be-processed trajectory line feature sequence represents a difference value of coordinate data of two adjacent trajectory points in the trajectory point data,

[0030] The first determining module is configured to, for any one trajectory point in the trajectory point data, determine a neighboring trajectory point corresponding to the any one trajectory point from the trajectory point data according to a difference value of coordinate data of the any one trajectory point and the trajectory points other than the any one trajectory point in the trajectory point data;

[0031] The to-be-processed trajectory line feature corresponding to the any one trajectory point is determined according to the difference value of the coordinate data of the any one trajectory point and the corresponding neighboring trajectory point;

[0032] The to-be-processed trajectory line features corresponding to the preset number of neighboring trajectory points are sorted to obtain a to-be-processed trajectory line feature sequence set corresponding to the plurality of trajectory point data.

[0033] On the other hand, the to-be-processed trajectory line feature in each to-be-processed trajectory line feature sequence represents a difference value of coordinate data of two adjacent trajectory points in the trajectory point data,

[0034] The third determining module is configured to, for any one to-be-processed trajectory line feature in any one to-be-processed trajectory line feature sequence, determine a candidate trajectory line feature corresponding to the any one to-be-processed trajectory line feature from the to-be-matched trajectory line feature sequence; the to-be-processed trajectory line feature and the corresponding candidate trajectory line feature have the same type label;

[0035] If the difference value of the any one to-be-processed trajectory line feature and the corresponding candidate trajectory line feature is less than a preset difference threshold, the any one to-be-processed trajectory line feature is taken as a non-target trajectory line feature;

[0036] The trajectory points corresponding to the to-be-processed trajectory line features other than the non-target trajectory line feature in the to-be-processed trajectory line feature sequence are taken as target trajectory points.

[0037] On the other hand, the obtaining module is configured to obtain trajectory point data uploaded by each acquisition device in the plurality of acquisition devices on a target road;

[0038] The sending module is configured to send a back transmission instruction to at least one of the plurality of collection devices for a target trajectory point determined from the trajectory point data uploaded by the plurality of collection devices, if a repetition frequency of the target trajectory point is greater than a preset repetition frequency threshold.

[0039] According to a third aspect of the present application, an electronic device is provided, which comprises a processor and a memory, and the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the road image back transmission method of the first aspect of the present application.

[0040] According to a fourth aspect of the present application, a computer storage medium is provided, which stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the road image back transmission method of the first aspect of the present application.

[0041] According to a fifth aspect of the present application, a computer program product is provided, which comprises at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the road image back transmission method of the first aspect of the present application.

[0042] The road image back transmission method, device, electronic device and storage medium provided by the embodiments of the present application have the following technical effects:

[0043] The method comprises the following steps: acquiring a plurality of track point data uploaded by a collection device for a target road; the track point data comprises a type label and coordinate data of each track point, the type label representing a road element type to which the track point belongs, and the coordinate data representing a position of the track point; determining a set of to-be-processed track line feature sequences corresponding to the plurality of track point data; determining a to-be-matched track line feature sequence from a preset set of candidate track line feature sequences and a target track line feature sequence from the set of to-be-processed track line feature sequences, to obtain a set of track line feature sequence groups; the to-be-matched track line feature sequence and the target track line feature sequence in each track line feature sequence group represent the same road, and a candidate track line feature sequence in the set of candidate track line feature sequences indicates a road in map data; for each track line feature sequence group, determining a target track point from the track point data according to track line features corresponding to the same type label in the to-be-matched track line feature sequence and the target track line feature sequence; the target track point is a road image collected by the collection device from the target road and different from a road element recorded in the map data; and sending a return instruction to the collection device; the return instruction is used to instruct the collection device to return a road image corresponding to the target track point. In the method, the road element is identified from the track point data instead of the image uploaded by the collection device, so that the data flow can be reduced. The to-be-processed track line feature sequence is determined according to the coordinate data of the track point, and the to-be-matched track line feature sequence is compared with the candidate track line feature sequence, so that the abnormal track points can be effectively screened out, and the road change element can be effectively mined. The collection instruction is sent according to the target track point, so that the collection efficiency is improved and the collection cost is reduced. The collection instruction is sent according to the target track point in the track point data uploaded by the plurality of collection devices, so that the problem of low recognition confidence of a single collection device can be solved, the accuracy of subsequent return can be improved, and the quality of the road image obtained by processing the road image returned for each collection device can be improved. The return of invalid images can be reduced, and the computing resources of the system can be saved. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, a brief introduction will be given to the drawings needed in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor based on these drawings.

[0045] Figure 1 is a schematic diagram of an application environment provided by an embodiment of the present application;

[0046] Figure 2 is a flowchart of a road image return method provided by an embodiment of the present application;

[0047] Figure 3 is a flow diagram of another method for returning a road image provided by an embodiment of the present application;

[0048] Figure 4 is a schematic diagram of trajectory point data provided by an embodiment of the present application;

[0049] Figure 5 is a schematic diagram of determining a sequence of features of a trajectory line to be matched provided by an embodiment of the present application;

[0050] Figure 6 is a structural schematic diagram of a device for returning a road image provided by an embodiment of the present application;

[0051] Figure 7 is a hardware structural schematic diagram of an electronic device for implementing the method for returning a road image provided by an embodiment of the present application. DETAILED DESCRIPTION

[0052] To make the objectives, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings. Obviously, the described embodiments are only one of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0053] The term "embodiment" referred to herein means a specific feature, structure or characteristic that can be included in at least one implementation of the present application. In the description of the embodiments of the present application, it should be understood that the terms "first", "second" and "third" are used only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" and "third" can be explicitly or implicitly included one or more of the features. Moreover, the terms "first", "second" and "third" are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way 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", "have" and "be" and any variations thereof are intended to cover non-exclusive inclusion.

[0054] It can be understood that in the detailed description of the present application, the data related to trajectory point data and the like is required to obtain user permission or consent when the above embodiments of the present application are applied to specific products or technologies, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0055] Before the embodiments of the present application are further described in detail, the terms and phrases involved in the embodiments of the present application are explained, and the terms and phrases involved in the embodiments of the present application are applicable to the following explanations.

[0056] Road collection device: refers to a hardware device installed in a vehicle that can record road information, including a smart rearview mirror, a drive recorder, a vehicle-mounted camera and other hardware devices that can record road information. Hereinafter, it is referred to as a collection device.

[0057] Road element: refers to common information in a road, including road driving turning marks, traffic speed limit signs, point speed limit marks, electronic eyes, traffic lights, danger signs, road name signs, etc.

[0058] Master library: also known as a pre-set candidate trajectory line feature sequence set, which can reflect the map data information of the real world more reliably, and is the final product of map data processing, which needs to be continuously corrected by real world data.

[0059] Trajectory point: a single road element, with a category label and coordinate data.

[0060] Line element feature: also known as trajectory line feature sequence, element Link, refers to a line obtained by combining trajectory points on the same road.

[0061] Please refer to Figure 1 , Figure 1 is a schematic diagram of an application environment provided by the embodiments of the present application, which can include a collection device 10 and a server 20. The collection device 10 and the server 20 can be directly or indirectly connected through wired or wireless communication.

[0062] In some possible embodiments, the collection device 10 can send the server 20 to-be-processed trajectory point data. The server can provide an image return service, collect the to-be-processed trajectory point data uploaded by the collection device, mine road change elements different from the road elements recorded in the map data from the to-be-processed trajectory point data, and then issue a collection instruction to the collection device to make the collection device return the road image corresponding to the road change element.

[0063] The collection device 10 can include at least one of a smart rearview mirror, a drive recorder, a vehicle-mounted camera and other hardware devices that can record road information.

[0064] The server 20 can be a standalone physical server, a service cluster or a distributed system composed of multiple physical servers, a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and basic cloud computing services such as big data and artificial intelligence platforms. Among them, the server can include a network communication unit, a processor, a memory, and the like. The server can provide an image backhaul service.

[0065] In some possible embodiments, the client 10 and the server 20 can be node devices in a blockchain system, capable of sharing the acquired and generated information to other node devices in the blockchain system, realizing information sharing between multiple node devices. The multiple node devices in the blockchain system can be configured with the same blockchain, which is composed of multiple blocks, and the adjacent blocks have a correlation relationship, so that when the data in any block is tampered with, it can be detected through the next block, thereby avoiding the data in the blockchain being tampered with, and ensuring the security and reliability of the data in the blockchain.

[0066] The following describes a specific embodiment of a road image backhaul method of the present application, Figure 2 is a flowchart of a road image backhaul method provided by an embodiment of the present application, Figure 3 is a flowchart of another road image backhaul method provided by an embodiment of the present application. The present specification provides method operation steps as shown in the embodiments or flowcharts, but more or fewer operation steps can be included based on conventional or non-creative labor. The order of steps listed in the embodiments is only one of many execution orders, and does not represent the only execution order. In actual execution, the method order shown in the embodiments or the drawings can be executed in sequence or in parallel (for example, in a parallel processor or multi-threaded processing environment).

[0067] As shown in Figure 2 and 3 , the road image backhaul method can include:

[0068] S201: Obtain a plurality of trajectory point data uploaded by a collection device for a target road; the trajectory point data includes a type label and coordinate data of each trajectory point, the type label represents the road element type to which the trajectory point belongs, and the coordinate data represents the position of the trajectory point.

[0069] In the embodiments of the present application, the plurality of collection devices installed on the vehicle can collect and process the driving turning marks, traffic speed limit signs, point speed limit marks, electronic eyes, traffic lights, road name plates and other road elements on the target road when the vehicle drives on the target road to obtain trajectory point data. Then the obtained trajectory point data can be uploaded to the server. The trajectory point data can include one or more road elements. For example, trajectory point data containing multiple road elements can be obtained for urban roads, and trajectory point data containing one road element can be obtained for remote and open roads. The server can obtain the trajectory point data uploaded by the collection device for the target road, and analyze and process the trajectory point data to obtain the type label and coordinate data of each trajectory point. By obtaining the trajectory point data instead of identifying the road elements from the images uploaded by the collection device, the data traffic can be reduced.

[0070] In some possible implementations, the server can obtain trajectory point data of driving turning marks, traffic speed limit signs, point speed limit marks, electronic eyes, traffic lights, road name plates and the like uploaded by any one of the plurality of collection devices for the target road. Then the trajectory point data can be analyzed and processed to obtain the road element type and latitude and longitude to which each trajectory point belongs. By obtaining the trajectory point data uploaded by a single collection device, the number of trajectory point data can be reduced, and the computing resources of the system can be saved.

[0071] In some possible implementations, the server can obtain trajectory point data of driving turning marks, traffic speed limit signs, point speed limit marks, electronic eyes, traffic lights, road name plates and the like uploaded by each of the plurality of collection devices for the target road. Then the trajectory point data can be analyzed and processed to obtain the road element type and latitude and longitude to which each trajectory point belongs. By obtaining the trajectory point data uploaded by a plurality of collection devices, the problem of low recognition confidence of a single collection device can be compensated, and the accuracy of subsequent feedback and the quality of the road image of the feedback can be improved.

[0072] In order to facilitate understanding, the following examples illustrate the trajectory point data. Figure 4 is a schematic diagram of trajectory point data provided by the embodiments of the present application. In actual application process, the server analyzes and processes the trajectory point data to obtain the road element type label A and latitude and longitude (x1, y1) of trajectory point A, the road element type label B and latitude and longitude (x2, y2) of trajectory point B, and the road element type C and latitude and longitude (x3, y3) of trajectory point label C.

[0073] S203: Determine a plurality of trajectory point data corresponding to a to-be-processed trajectory line feature sequence set.

[0074] In the embodiments of the present application, the to-be-processed trajectory line feature in each to-be-processed trajectory line feature sequence in the to-be-processed trajectory line feature sequence set can represent the difference between the coordinate data of two adjacent trajectory points in the trajectory point data.

[0075] In the embodiments of the present application, for any one trajectory point in the trajectory point data, the adjacent trajectory point corresponding to the any one trajectory point can be determined from the trajectory point data according to the difference between the coordinate data of the any one trajectory point and the trajectory points other than the any one trajectory point. Then, the to-be-processed trajectory line feature corresponding to the any one trajectory point can be determined according to the difference between the coordinate data of the any one trajectory point and the corresponding adjacent trajectory point, and the to-be-processed trajectory line features corresponding to a preset number of adjacent trajectory points can be sorted to obtain the to-be-processed trajectory line feature sequence set corresponding to the trajectory point data.

[0076] In some possible implementations, the difference between the longitude and latitude of each trajectory point and other trajectory points other than itself can be determined, and then the other trajectory point corresponding to the minimum difference can be taken as the adjacent trajectory point, and the minimum difference can be taken as the to-be-processed trajectory line feature corresponding to the self. For example, based on the example of the trajectory point data listed above, the difference between the longitude and latitude (x2, y2) of the trajectory point B and the longitude and latitude (x1, y1) of the trajectory point A is calculated, and the difference between the longitude and latitude (x3, y3) of the trajectory point C and the longitude and latitude of the trajectory point A is calculated. When the difference between the longitude and latitude (x2, y2) of the trajectory point B and the longitude and latitude (x1, y1) of the trajectory point A is less than the difference between the longitude and latitude (x3, y3) of the trajectory point C and the longitude and latitude of the trajectory point A, the trajectory point B can be determined as the adjacent trajectory point of the trajectory point A. The expression of the difference between the longitude and latitude (x2, y2) of the trajectory point B and the longitude and latitude (x1, y1) of the trajectory point A can be {(x2-x1), (y2-y1)}, and the numerical value of the difference between the longitude and latitude (x2, y2) of the trajectory point B and the longitude and latitude (x1, y1) of the trajectory point A can be (x2-x1) 2 +(y2-y1) 2 . Then, the numerical value of the difference between the coordinate data of the trajectory point A and the corresponding adjacent trajectory point B can be determined as the to-be-processed trajectory line feature corresponding to the trajectory point A. In this way, the to-be-processed trajectory line feature sequence corresponding to the trajectory point data can be obtained:

[0077] [{A, x1, y1}, {B, (x2-x1), (y2-y1)}, {C, (x3-x2), (y3-y2)}]

[0078] In some possible implementation manners, when the plurality of collection devices installed on the vehicle are driving on the target road, the server can obtain road elements collected by the collection devices at different collection moments to obtain the trajectory point sequence data. Then, the server can determine a to-be-processed trajectory line feature corresponding to each trajectory point according to a difference between coordinate data of two adjacent trajectory points in the trajectory point sequence data. In actual application, the server can determine the to-be-processed trajectory line feature corresponding to each trajectory point according to a difference between coordinate data of a trajectory point located in front of itself in the trajectory point sequence and coordinate data of itself to obtain a to-be-processed trajectory line feature sequence corresponding to the trajectory point sequence data.

[0079] S205: determining a to-be-matched trajectory line feature sequence from the preset candidate trajectory line feature sequence set and determining a target trajectory line feature sequence from the to-be-processed trajectory line feature sequence set to obtain a trajectory line feature sequence group set.

[0080] In the embodiments of the present application, the to-be-matched trajectory line feature sequence and the target trajectory line feature sequence in each trajectory line feature sequence group represent the same road, and the candidate trajectory line feature sequence in the candidate trajectory line feature sequence set indicates a road in the map data. The to-be-processed trajectory line feature in each to-be-processed trajectory line feature sequence can represent a difference between coordinate data of two adjacent trajectory points in the trajectory point data.

[0081] In some possible implementation, any one of the to-be-processed trajectory feature sequences can be determined from the set of to-be-processed trajectory feature sequences as a target trajectory feature sequence. For any one of the candidate trajectory feature sequences in the candidate trajectory feature sequence set, the coordinate data corresponding to each candidate trajectory feature in the any one of the candidate trajectory feature sequences can be determined according to the sum of any two adjacent candidate trajectory features in the any one of the candidate trajectory feature sequences. The coordinate data corresponding to the candidate trajectory feature can represent the position of a point on a road in the map data indicated by the any one of the candidate trajectory feature sequences. That is, the above-mentioned determination of the to-be-processed trajectory feature is reversed to determine the coordinate data corresponding to each candidate trajectory feature according to any two adjacent candidate trajectory features in the candidate trajectory feature sequence. Then, the frequency of coincidence of the coordinate data of the trajectory point data corresponding to the target trajectory feature sequence and the coordinate data of the candidate trajectory features in any one of the candidate trajectory feature sequences can be determined with the preset frequency. If the frequency of coincidence of the coordinate data of the trajectory point data corresponding to the target trajectory feature sequence and the coordinate data of the candidate trajectory features in any one of the candidate trajectory feature sequences is greater than the preset frequency threshold, the any one of the candidate trajectory feature sequences can be determined as the to-be-matched trajectory feature sequence corresponding to the target trajectory feature sequence, and a trajectory feature sequence group is obtained. If the frequency of coincidence of the coordinate data of the trajectory point data corresponding to the target trajectory feature sequence and the coordinate data of the candidate trajectory features in any one of the candidate trajectory feature sequences is less than or equal to the preset frequency threshold, it can be considered that the candidate trajectory feature sequence is not the to-be-matched trajectory feature sequence corresponding to the target trajectory feature sequence. Then, a candidate trajectory feature sequence can be selected from the set of candidate trajectory feature sequences, and the above steps can be repeated until the to-be-matched trajectory feature sequence corresponding to the target trajectory feature sequence is determined, and a set of trajectory feature sequence groups is obtained. The preset frequency threshold can be 80%, 90%, or other numerical values, which are not limited in the embodiments of the present application. In actual application, each line element in each candidate line element feature sequence in the candidate line element feature sequence set can have coordinate data representing the position of a point on a road in the map data. When matching, the to-be-matched trajectory feature sequence corresponding to the target trajectory feature sequence can be directly determined according to the frequency of coincidence of the coordinate data corresponding to each candidate line element feature sequence and the coordinate data in the trajectory point data.

[0082] In some possible implementation, any one of the to-be-processed trajectory feature sequence from the set of to-be-processed trajectory feature sequences can be determined as the target trajectory feature sequence. For any one of the candidate trajectory feature sequences in the candidate trajectory feature sequence set, the coordinate data and the type label corresponding to each candidate trajectory feature in the any one of the candidate trajectory feature sequences can be determined according to the sum of the two adjacent candidate trajectory features in the any one of the candidate trajectory feature sequences. The coordinate data corresponding to the candidate trajectory feature represents the position of the point on the road in the map data indicated by the any one of the candidate trajectory feature sequences. The type label corresponding to the candidate trajectory feature represents the road element type of the point on the road in the map data indicated by the any one of the candidate trajectory feature sequences. That is, the above-mentioned determination of the to-be-processed trajectory feature is reversed, and each candidate trajectory feature corresponding coordinate data is determined according to the two adjacent candidate trajectory features in the candidate trajectory feature sequence. When the type label of the trajectory point data corresponding to the target trajectory feature sequence is the same as the type label corresponding to the candidate trajectory feature in the any one of the candidate trajectory feature sequences, and the difference between the coordinate data of the trajectory point data corresponding to the target trajectory feature sequence and the coordinate data corresponding to the candidate trajectory feature in the any one of the candidate trajectory feature sequences is less than the preset difference threshold, it can be determined that the coordinate data of the trajectory point data corresponding to the target trajectory feature sequence coincides with the coordinate data corresponding to the candidate trajectory feature in the any one of the candidate trajectory feature sequences. Then, the coincidence frequency of the coordinate data of the trajectory point data corresponding to the target trajectory feature sequence and the coordinate data corresponding to the candidate trajectory feature in the any one of the candidate trajectory feature sequences is determined. If the coincidence frequency of the coordinate data of the trajectory point data corresponding to the target trajectory feature sequence and the coordinate data corresponding to the candidate trajectory feature in the any one of the candidate trajectory feature sequences is greater than the preset coincidence frequency threshold, the any one of the candidate trajectory feature sequences is taken as the to-be-matched trajectory feature sequence corresponding to the target trajectory feature sequence, and a trajectory feature sequence group is obtained. If the coincidence frequency of the coordinate data of the trajectory point data and the coordinate data corresponding to the candidate trajectory feature in the any one of the candidate trajectory feature sequences is less than or equal to the preset coincidence frequency threshold, it is considered that the candidate trajectory feature sequence is not the to-be-matched trajectory feature sequence corresponding to the target trajectory feature sequence. Then, a candidate trajectory feature sequence can be selected from the set of candidate trajectory feature sequences, and the above steps can be repeated until the to-be-matched trajectory feature sequence corresponding to the trajectory point data is determined, and a set of trajectory feature sequence groups is obtained.

[0083] In some possible implementation, for each candidate trajectory feature {label, Δx, Δy} in the candidate trajectory feature sequence, Δx, Δy in the candidate trajectory feature sequence and Δx, Δy in the to-be-processed trajectory feature sequence can be fuzzily matched under the premise that the type label label is the same. Within a certain error allowance, the trajectory features in the two elements Link can be considered equal. According to the above determination rule, the edit distance of the two elements Link can be calculated, which can represent the difference between the two elements Link.

[0084] In some possible implementation, any one to-be-processed trajectory feature sequence can be determined from the set of to-be-processed trajectory feature sequences as a target trajectory feature sequence. For any candidate trajectory feature in any candidate trajectory feature sequence, a to-be-processed trajectory feature corresponding to the candidate trajectory feature can be determined from the target trajectory feature sequence. The type label of the candidate trajectory feature is the same as that of the corresponding to-be-processed trajectory feature. Then, the difference between the candidate trajectory feature and the corresponding to-be-processed trajectory feature and the preset difference threshold can be determined. If the difference between the candidate trajectory feature and the corresponding to-be-processed trajectory feature is less than the preset difference threshold, the to-be-processed trajectory feature can be determined as a non-target trajectory feature. Then, according to the ratio of the number of to-be-processed trajectory features in the target trajectory feature sequence except the non-target trajectory feature to the total number, the to-be-matched trajectory feature sequence corresponding to the target trajectory feature sequence can be matched from the set of candidate trajectory feature sequences, to obtain a trajectory feature sequence group. The total number is the number of candidate trajectory features in any candidate trajectory feature sequence.

[0085] In some possible implementation manners, any one candidate trajectory feature sequence can be determined from the set of candidate trajectory feature sequences as a trajectory feature sequence to be matched. For any one trajectory feature to be processed in any one trajectory feature sequence to be processed, a candidate trajectory feature corresponding to the trajectory feature to be processed can be determined from the trajectory feature sequence to be matched. The type label of the trajectory feature to be processed is the same as that of the corresponding candidate trajectory feature. Then, a difference between the trajectory feature to be processed and the corresponding candidate trajectory feature and a preset difference threshold can be determined. If it is determined that the difference between the trajectory feature to be processed and the corresponding candidate trajectory feature is less than the preset difference threshold, the trajectory feature to be processed can be regarded as a non-target trajectory feature. Then, a target trajectory feature sequence corresponding to the trajectory feature sequence to be matched can be matched from the set of trajectory feature sequences to be processed according to a ratio of a quantity of the trajectory features to be processed, except the non-target trajectory feature, to a total quantity in the trajectory feature sequence to be processed, to obtain a trajectory feature sequence group. The total quantity is the quantity of the candidate trajectory features in the trajectory feature sequence to be matched. Figure 5 is a schematic diagram for determining a target trajectory feature sequence provided by an embodiment of the present application, in which, element Link1 is any one candidate line element sequence determined from a mother library, i.e., a set of candidate line element sequences, element Link2 is a trajectory feature sequence to be processed 1, and element Link3 is a trajectory feature sequence to be processed 2. The edit distance between element Link2 and element Link1 is 1, i.e., there is one different trajectory feature in the trajectory feature to be processed. The edit distance between element Link3 and element Link1 is 4, i.e., there are four different trajectory features in the trajectory feature to be processed. Then, according to a ratio of the edit distance to a total quantity of the trajectory features in element Link1, it can be determined that the edit distance difference ratio between element Link2 and element Link1 is 20%, and the edit distance difference ratio between element Link3 and element Link1 is 80%. Therefore, it can be considered that element Link2 is similar to element Link1, and element Link3 is not similar to element Link1, i.e., element Link1 is a matched element Link corresponding to element Link2. By determining the trajectory feature sequence according to the coordinate data of the trajectory points, and performing difference comparison with the candidate trajectory feature sequence, non-normal trajectory points can be effectively screened out, and road change elements can be effectively mined.

[0086] S207: For each trajectory feature sequence group, a target trajectory point is determined from the trajectory point data according to the trajectory features with the same type label in the trajectory feature sequence to be matched and the target trajectory feature sequence. The target trajectory point refers to a road element collected by the collection device from a target road and different from the road element recorded in the map data.

[0087] In the embodiments of the present application, the difference between the coordinate data of the adjacent two trajectory points in the trajectory point data represented by each to-be-processed trajectory feature in the to-be-processed trajectory feature sequence is represented.

[0088] In some possible implementation manners, for any one to-be-processed trajectory feature in the to-be-processed trajectory feature sequence, any one to-be-processed trajectory feature corresponding to-be-matched trajectory feature can be determined from the to-be-matched trajectory feature sequence. The type label of any one to-be-processed trajectory feature is the same as that of the corresponding candidate trajectory feature. Then, the difference between any one to-be-processed trajectory feature and the corresponding candidate trajectory feature can be determined. If the difference between any one to-be-processed trajectory feature and the corresponding candidate trajectory feature is less than the preset difference threshold, any one to-be-processed trajectory feature can be regarded as a non-target trajectory feature. Then, the trajectory point corresponding to the to-be-processed trajectory feature other than the non-target trajectory feature in the to-be-processed trajectory feature sequence can be regarded as a target trajectory point. If no to-be-matched trajectory feature with the same type label as that of any one to-be-processed trajectory feature is determined from the to-be-matched feature sequence, any one to-be-processed trajectory feature can be regarded as a target trajectory feature. If the to-be-matched trajectory feature with the same type label as that of any one to-be-processed trajectory feature can be determined from the to-be-matched feature sequence, but the difference between any one to-be-processed trajectory feature and the corresponding candidate trajectory feature is greater than or equal to the preset difference threshold, any one to-be-processed trajectory feature can be regarded as a target trajectory feature. Then, the trajectory point corresponding to the target trajectory feature can be regarded as a target trajectory point.

[0089] For example, based on the example that the element Link2 is similar to the element Link1 listed above, the edit distance between the element Link2 and the element Link1 is 1, that is, there is one different trajectory feature in the to-be-processed trajectory feature. The trajectory point corresponding to the different trajectory feature can be a target trajectory point, also referred to as an edit point E, that is, a road element collected by the collection device from the target road and different from the road element recorded in the map data, that is, a road change element.

[0090] S209: sending a feedback instruction to the collection device; the feedback instruction is used to instruct the collection device to feed back a road image corresponding to the target trajectory point.

[0091] In the embodiments of the present application, if the server obtains the driving turning marks, traffic speed limit signs, point speed limit signs, electronic eyes, traffic lights, road signs and other trajectory point data uploaded by each of the plurality of collection devices for the target road. After determining the target trajectory point, if the target road indeed has road change elements, there must be a large number of trajectory point data with the target trajectory point in the plurality of collection devices. When a certain number is accumulated, it can be considered that the target trajectory point is reliable and can be used to generate a candidate collection instruction. Therefore, for the target trajectory point in the trajectory point data uploaded by the plurality of collection devices, the ratio of the repetition frequency of the target trajectory point to the preset repetition frequency threshold can be determined. If it is determined that the repetition frequency of the target trajectory point is greater than the preset repetition frequency threshold, a return instruction can be sent to each of the plurality of collection devices to instruct each of the plurality of collection devices to return the road image corresponding to the target trajectory point. In this way, not only can the collection instruction be sent in a targeted manner to improve the collection efficiency and reduce the collection cost, but also the problem of low recognition confidence of a single collection device can be compensated for, the accuracy of subsequent return can be improved, and the quality of the road image obtained by processing the road image returned by each of the plurality of collection devices can be improved. If it is determined that the repetition frequency of the target trajectory point is greater than the preset repetition frequency threshold, the road image corresponding to the target trajectory point can also be returned to part of the plurality of collection devices, wherein the part of the plurality of collection devices can be the collection devices whose uploaded trajectory point data contains the target trajectory point. In this way, not only can the collection instruction be sent in a targeted manner to improve the collection efficiency and reduce the collection cost, but also the problem of low recognition confidence of a single collection device can be compensated for, the accuracy of subsequent return can be improved, and the quality of the road image obtained by processing the road image returned by each of the plurality of collection devices can be improved. In addition, the return of invalid images can also be reduced, and the computing resources of the system can be saved. If it is determined that the repetition frequency of the target trajectory point is less than or equal to the preset repetition frequency threshold, the target trajectory point can be considered unreliable and may be a single device misidentification.

[0092] The road image transmission method provided in this application reduces data acquisition overhead by acquiring trajectory point data instead of identifying road features from images uploaded by acquisition devices. By determining the feature sequence of the trajectory line to be processed based on the coordinate data of the trajectory points and comparing it with the feature sequence of candidate trajectory lines through differential analysis, abnormal trajectory points can be effectively screened out, and road change elements can be effectively discovered. Acquisition commands can be sent purposefully based on the target trajectory point, improving acquisition efficiency and reducing acquisition costs. Sending acquisition commands based on the target trajectory point from trajectory point data uploaded from multiple acquisition devices can compensate for the low confidence level of a single acquisition device, improve the accuracy of subsequent transmissions, and enhance the quality of road images obtained by processing the road images transmitted from each acquisition device. It also reduces the transmission of invalid images, saving system computing resources.

[0093] This application also provides a road image transmission device in its embodiments. Figure 6 This is a schematic diagram of the structure of a road image transmission device provided in an embodiment of this application, as shown below. Figure 6 As shown, the device for transmitting the road image may include:

[0094] The acquisition module 601 is used to acquire multiple trajectory point data uploaded by the acquisition device for the target road; the trajectory point data includes the type label and coordinate data of each trajectory point, the type label represents the type of road element to which the trajectory point belongs, and the coordinate data represents the location of the trajectory point;

[0095] The first determining module 603 is used to determine the set of feature sequences of trajectory lines to be processed corresponding to multiple trajectory point data;

[0096] The second determining module 605 is used to determine the trajectory line feature sequence to be matched from the preset set of candidate trajectory line feature sequences and to determine the target trajectory line feature sequence from the set of trajectory line feature sequences to be processed, so as to obtain a set of trajectory line feature sequence groups; the trajectory line feature sequence to be matched and the target trajectory line feature sequence in each trajectory line feature sequence group represent the same road, and the candidate trajectory line feature sequences in the set of candidate trajectory line feature sequences indicate the roads in the map data;

[0097] The third determining module 607 is used to determine the target trajectory point from the trajectory point data for each trajectory line feature sequence group based on the trajectory line features corresponding to the same type of labels in the trajectory line feature sequence to be matched and the target trajectory line feature sequence; the target trajectory point refers to the road element collected by the acquisition device from the target road that is different from the road element recorded in the map data;

[0098] The sending module 609 is used to send a return command to the acquisition device; the return command is used to instruct the acquisition device to return the road image corresponding to the target trajectory point.

[0099] In some possible implementation, each to-be-processed trajectory feature in the to-be-processed trajectory feature sequence represents a difference value of coordinate data of two adjacent trajectory points in the trajectory point data,

[0100] The second determination module 605 is configured to determine a target trajectory feature sequence from the set of to-be-processed trajectory feature sequences; the target trajectory feature sequence is any one of the to-be-processed trajectory feature sequences in the set of to-be-processed trajectory feature sequences.

[0101] For any one of the candidate trajectory feature sequences in the set of candidate trajectory feature sequences, the coordinate data corresponding to each candidate trajectory feature in the any one of the candidate trajectory feature sequences is determined according to the sum of two adjacent candidate trajectory features in the any one of the candidate trajectory feature sequences; the coordinate data corresponding to the candidate trajectory feature represents the position of a point on a road in the map data indicated by the any one of the candidate trajectory feature sequences.

[0102] If the coordinate data of the trajectory point data corresponding to the target trajectory feature sequence coincides with the coordinate data corresponding to the candidate trajectory features in any one of the candidate trajectory feature sequences more frequently than a preset coincidence frequency threshold, the any one of the candidate trajectory feature sequences is taken as a to-be-matched trajectory feature sequence corresponding to the target trajectory feature sequence, and the set of trajectory feature sequence groups is obtained.

[0103] In some possible implementation, the second determination module 605 is configured to determine a target trajectory feature sequence from the set of to-be-processed trajectory feature sequences; the target trajectory feature sequence is any one of the to-be-processed trajectory feature sequences in the set of to-be-processed trajectory feature sequences.

[0104] For any one of the candidate trajectory features in any one of the candidate trajectory feature sequences, a to-be-processed trajectory feature corresponding to the any one of the candidate trajectory features is determined from the target trajectory feature sequence; the candidate trajectory feature and the corresponding to-be-processed trajectory feature have the same type label.

[0105] If the difference between the candidate trajectory feature and the corresponding to-be-processed trajectory feature is less than a preset difference threshold, the to-be-processed trajectory feature is taken as a non-target trajectory feature.

[0106] According to a ratio of a quantity of to-be-processed trajectory features other than the non-target trajectory features in the target trajectory feature sequence to a total quantity, a to-be-matched trajectory feature sequence corresponding to the target trajectory feature sequence is matched from the set of candidate trajectory feature sequences, and the set of trajectory feature sequence groups is obtained; the total quantity is the sum of the quantities of the candidate trajectory features in any one of the candidate trajectory feature sequences.

[0107] In some possible implementation manners, the difference between the coordinate data of the two adjacent trajectory points in the trajectory point data represented by each to-be-processed trajectory feature in the to-be-processed trajectory feature sequence is a distance between the two adjacent trajectory points.

[0108] The second determination module 605 is configured to determine a to-be-matched trajectory feature sequence from the candidate trajectory feature sequence set; the to-be-matched trajectory feature sequence is any one of the candidate trajectory feature sequences in the candidate trajectory feature sequence set.

[0109] For any to-be-processed trajectory feature in any to-be-processed trajectory feature sequence, a corresponding candidate trajectory feature is determined from the to-be-matched trajectory feature sequence; the to-be-processed trajectory feature and the corresponding candidate trajectory feature have the same type label.

[0110] If the difference between the to-be-processed trajectory feature and the corresponding candidate trajectory feature is less than the preset difference threshold, the to-be-processed trajectory feature is regarded as a non-target trajectory feature.

[0111] According to a ratio of a quantity of to-be-processed trajectory features other than the non-target trajectory features in the to-be-processed trajectory feature sequence to a total quantity, a target trajectory feature sequence corresponding to the to-be-matched trajectory feature sequence is matched from the to-be-processed trajectory feature sequence set, to obtain a trajectory feature sequence group set; the total quantity is a quantity of candidate trajectory features in the to-be-matched trajectory feature sequence.

[0112] In some possible implementation manners, the difference between the coordinate data of the two adjacent trajectory points in the trajectory point data represented by each to-be-processed trajectory feature in the to-be-processed trajectory feature sequence is a distance between the two adjacent trajectory points.

[0113] The first determination module 603 is configured to, for any one trajectory point in the trajectory point data, determine a corresponding adjacent trajectory point of the any one trajectory point from the trajectory point data according to a difference between the coordinate data of the any one trajectory point and the trajectory points other than the any one trajectory point in the trajectory point data.

[0114] According to the difference between the coordinate data of the any one trajectory point and the corresponding adjacent trajectory point, a to-be-processed trajectory feature corresponding to the any one trajectory point is determined.

[0115] The to-be-processed trajectory features corresponding to the preset quantity of adjacent trajectory points are sorted to obtain a to-be-processed trajectory feature sequence set corresponding to the plurality of trajectory point data.

[0116] In some possible implementation manners, the difference between the coordinate data of the two adjacent trajectory points in the trajectory point data represented by each to-be-processed trajectory feature in the to-be-processed trajectory feature sequence is a distance between the two adjacent trajectory points.

[0117] The third determination module 607 is configured to determine, for any one to-be-processed trajectory feature in the to-be-processed trajectory feature sequence, a candidate trajectory feature corresponding to the any one to-be-processed trajectory feature from the to-be-matched trajectory feature sequence; the to-be-processed trajectory feature and the corresponding candidate trajectory feature have the same type label;

[0118] If the difference between the any one to-be-processed trajectory feature and the corresponding candidate trajectory feature is less than the preset difference threshold, the any one to-be-processed trajectory feature is regarded as a non-target trajectory feature.

[0119] The trajectory points corresponding to the to-be-processed trajectory features other than the non-target trajectory feature in the to-be-processed trajectory feature sequence are regarded as target trajectory points.

[0120] In some possible implementation manners, the acquisition module 601 is configured to acquire trajectory point data uploaded by each of the plurality of collection devices for the target road;

[0121] The sending module 609 is configured to, for the target trajectory point determined from the trajectory point data uploaded by the plurality of collection devices, if a repetition frequency of the target trajectory point is greater than a preset repetition frequency threshold, send a back transmission instruction to at least one of the plurality of collection devices.

[0122] The device and method embodiments in the embodiments of the present application are based on the same application concept.

[0123] The embodiments of the present application provide an electronic device, which includes a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement the road image back transmission method provided in the above method embodiments.

[0124] Figure 7 is a hardware structure schematic diagram of an electronic device for implementing the road image back transmission method provided in the embodiments of the present application. The electronic device can participate in constituting or containing the road image back transmission device provided in the embodiments of the present application. As shown in Figure 7 The electronic device can include one or more (in the figure, processors 701a and 701b are used to show) processors 701 (the processor 701 can include but is not limited to a microprocessor 701 MCU or a programmable logic device FPGA and other processing devices), a memory 703 for storing data, and a transmission device 705 for communication function. In addition, it can also include a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which can be included as one of the ports of the I / O interface), a network interface and / or a power supply. Those skilled in the art can understand that, Figure 7The illustrated structure is merely schematic and does not limit the structure of the electronic device described above. For example, the electronic device can further include more or fewer components than those shown in FIG. 6, or have a different configuration from that shown in FIG. 6. Figure 7 Figure 7 The illustrated structure is merely schematic and does not limit the structure of the electronic device described above. For example, the electronic device can further include more or fewer components than those shown in FIG. 6, or have a different configuration from that shown in FIG. 6.

[0125] It should be noted that the one or more processors 701 and / or other data processing circuitry described above can be referred to as "data processing circuitry" in the present application. The data processing circuitry can be embodied in whole or in part as software, hardware, firmware, or any combination thereof. In addition, the data processing circuitry can be a single independent processing module, or be incorporated into any one of other elements in the electronic device (or mobile device) in whole or in part. As referred to in the embodiments of the present application, the data processing circuitry serves as a processor 701 to control (e.g., selection of a variable resistance terminal path connected to an interface).

[0126] The memory 703 can be used to store software programs and modules of application software, such as program instructions / data storage means corresponding to the method for returning a road image according to an embodiment of the present application. The processor 701 can implement each function application and data processing by running the software programs and modules stored in the memory 703, i.e., implement the method for returning a road image described above. The memory 703 can include a high-speed random access memory, and can further include a non-volatile random access memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some possible embodiments, the memory 703 can further include a memory 703 disposed remotely with respect to the processor, and these remote memories 703 can be connected to the electronic device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0127] The transmission device 705 is configured to receive or send data via a network. Specific examples of the network can include a wireless network provided by a communication provider of the electronic device. In one example, the transmission device 705 includes a network interface controller (NIC) that can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 705 can be a radio frequency (RF) module configured to communicate with the Internet in a wireless manner.

[0128] The display can be, for example, a liquid crystal display (LCD) in a touch screen type, which can enable a user to interact with a user interface of the electronic device (or mobile device).

[0129] ​The embodiment of the present application provides a computer readable storage medium, which can be arranged in an electronic device to save at least one instruction or at least one program related to a road image returning method in the method embodiment, and the at least one instruction or the at least one program is loaded and executed by the processor to realize the road image returning method provided by the above method embodiment.

[0130] Optionally, in the embodiment, the storage medium can be located in at least one of a plurality of network servers of a computer network. Optionally, in the embodiment, the storage medium can include but is not limited to a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various storage program code media.

[0131] It should be noted that the above-mentioned order of the embodiments of the present application is only for description, not representing the advantages and disadvantages of the embodiments, and the above-mentioned description is for specific embodiments, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be executed in different orders in different embodiments and can achieve the expected results. In addition, the processes depicted in the drawings do not necessarily require a specific order or connection order to achieve the desired results, and in some embodiments, multi-task parallel processing is possible or can be advantageous.

[0132] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment mainly describes the differences from other embodiments. Especially, the embodiments of the device and the electronic device are described simply because they are based on the similar method embodiments, and the related parts can be referred to the part of the method embodiment.

[0133] The above is the preferred embodiment of the present application, and it should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements are also considered within the protection scope of the present application.

Claims

1. A method of backhaul of road images, characterized in that, The method comprises the following steps: acquiring a plurality of track point data uploaded by a collection device for a target road; the track point data comprises a type label and coordinate data of each track point, the type label representing a road element type to which the track point belongs, and the coordinate data representing a position of the track point; determining a set of to-be-processed track line feature sequences corresponding to the plurality of track point data; determining a to-be-matched track line feature sequence from a preset candidate track line feature sequence set and a target track line feature sequence from the set of to-be-processed track line feature sequences, to obtain a set of track line feature sequence groups; the to-be-matched track line feature sequence and the target track line feature sequence in each track line feature sequence group represent the same road, and a candidate track line feature sequence in the candidate track line feature sequence set indicates a road in map data; for each track line feature sequence group, determining a target track point from the track point data according to track line features corresponding to the same type labels in the to-be-matched track line feature sequence and the target track line feature sequence; the target track point is a road element collected by the collection device from the target road and different from a road element recorded in the map data; sending a feedback instruction to the collection device; the feedback instruction is used to instruct the collection device to feed back a road image corresponding to the target track point.

2. The method of claim 1, wherein, each to-be-processed track line feature in each to-be-processed track line feature sequence represents a difference value of coordinate data of two adjacent track points in the track point data, the determining of the to-be-matched track line feature sequence from the preset candidate track line feature sequence set and the target track line feature sequence from the set of to-be-processed track line feature sequences to obtain the set of track line feature sequence groups comprises: determining the target track line feature sequence from the set of to-be-processed track line feature sequences; the target track line feature sequence is any one of the to-be-processed track line feature sequences in the set of to-be-processed track line feature sequences; for any one of the candidate track line feature sequences in the candidate track line feature sequence set, determining coordinate data corresponding to each candidate track line feature in the any one of the candidate track line feature sequences according to a sum of two adjacent candidate track line features in the any one of the candidate track line feature sequences; the coordinate data corresponding to the candidate track line feature represents a position of a point on a road in map data indicated by the any one of the candidate track line feature sequences; if a coincidence frequency of coordinate data of the track point data corresponding to the target track line feature sequence and coordinate data corresponding to a candidate track line feature in the any one of the candidate track line feature sequences is greater than a preset coincidence frequency threshold, the any one of the candidate track line feature sequences is taken as the to-be-matched track line feature sequence corresponding to the target track line feature sequence, to obtain the set of track line feature sequence groups.

3. The method of claim 2, wherein, the determining of the to-be-matched track line feature sequence from the preset candidate track line feature sequence set and the target track line feature sequence from the set of to-be-processed track line feature sequences to obtain the set of track line feature sequence groups comprises: determining the target trajectory feature sequence from the set of to-be-processed trajectory feature sequences; the target trajectory feature sequence is any one of the set of to-be-processed trajectory feature sequences; for any one candidate trajectory feature in the any one candidate trajectory feature sequence, determining a to-be-processed trajectory feature corresponding to the any one candidate trajectory feature from the target trajectory feature sequence; the to-be-processed trajectory feature and the corresponding candidate trajectory feature have the same type label; if the difference between the to-be-processed trajectory feature and the corresponding candidate trajectory feature is less than a preset difference threshold, regarding the to-be-processed trajectory feature as a non-target trajectory feature; according to a ratio of a number of to-be-processed trajectory features in the target trajectory feature sequence excluding the non-target trajectory feature to a total number, matching the target trajectory feature sequence corresponding to the to-be-matched trajectory feature sequence from the set of candidate trajectory feature sequences, to obtain the set of trajectory feature sequence groups; the total number is a sum of the number of candidate trajectory features in the any one candidate trajectory feature sequence.

4. The method of claim 1, wherein, each to-be-processed trajectory feature in each to-be-processed trajectory feature sequence represents a difference between coordinate data of two adjacent trajectory points in the trajectory point data, the determining the set of to-be-processed trajectory feature sequences corresponding to the plurality of trajectory point data, comprises: determining the to-be-matched trajectory feature sequence from the set of candidate trajectory feature sequences; the to-be-matched trajectory feature sequence is any one of the set of candidate trajectory feature sequences; for any one to-be-processed trajectory feature in the any one to-be-processed trajectory feature sequence, determining a candidate trajectory feature corresponding to the any one to-be-processed trajectory feature from the to-be-matched trajectory feature sequence; the to-be-processed trajectory feature and the corresponding candidate trajectory feature have the same type label; if the difference between the to-be-processed trajectory feature and the corresponding candidate trajectory feature is less than a preset difference threshold, regarding the to-be-processed trajectory feature as a non-target trajectory feature; according to a ratio of a number of to-be-processed trajectory features in the target trajectory feature sequence excluding the non-target trajectory feature to a total number, matching the target trajectory feature sequence corresponding to the to-be-matched trajectory feature sequence from the set of candidate trajectory feature sequences, to obtain the set of trajectory feature sequence groups; the total number is a sum of the number of candidate trajectory features in the any one candidate trajectory feature sequence.

5. The method of claim 1, wherein, each to-be-processed trajectory feature in each to-be-processed trajectory feature sequence represents a difference between coordinate data of two adjacent trajectory points in the trajectory point data, the determining the set of to-be-processed trajectory feature sequences corresponding to the plurality of trajectory point data, comprises: For any one of the trajectory point data, according to the difference between the coordinate data of the trajectory point and the coordinate data of the trajectory point other than the any one of the trajectory point data, the adjacent trajectory point corresponding to the any one of the trajectory point data is determined from the trajectory point data; According to the difference between the coordinate data of the any one of the trajectory point and the corresponding adjacent trajectory point, the to-be-processed trajectory line feature corresponding to the any one of the trajectory point is determined; The to-be-processed trajectory line features corresponding to a preset number of adjacent trajectory points are sorted to obtain a plurality of to-be-processed trajectory line feature sequence sets corresponding to the trajectory point data.

6. The method of claim 1, wherein, The to-be-processed trajectory line features in each to-be-processed trajectory line feature sequence represent the difference between the coordinate data of two adjacent trajectory points in the trajectory point data, The to-be-processed trajectory line feature sequence set corresponding to each trajectory line feature sequence group is obtained by determining the target trajectory point from the trajectory point data according to the trajectory line features corresponding to the same type label in the to-be-matched trajectory line feature sequence and the target trajectory line feature sequence. For any one to-be-processed trajectory line feature in any one to-be-processed trajectory line feature sequence, the candidate trajectory line feature corresponding to the any one to-be-processed trajectory line feature is determined from the to-be-matched trajectory line feature sequence; the type label of the to-be-processed trajectory line feature and the corresponding candidate trajectory line feature is the same; If the difference between the any one to-be-processed trajectory line feature and the corresponding candidate trajectory line feature is less than a preset difference threshold, the any one to-be-processed trajectory line feature is taken as a non-target trajectory line feature; The trajectory points corresponding to the to-be-processed trajectory line features other than the non-target trajectory line feature in the to-be-processed trajectory line feature sequence are taken as the target trajectory points.

7. The method of claim 1, wherein, The trajectory point data uploaded by the collection device for the target road is obtained, including: Obtaining the trajectory point data uploaded by each collection device for the target road; The back transmission instruction is sent to the collection device, including: For the target trajectory point determined from the trajectory point data uploaded by the plurality of collection devices, if the repetition frequency of the target trajectory point is greater than a preset repetition frequency threshold, the back transmission instruction is sent to at least one of the plurality of collection devices.

8. A device for returning a road image, characterized by Including: An acquisition module is configured to obtain a plurality of trajectory point data uploaded by a collection device for a target road; The trajectory point data includes a type label and coordinate data of each trajectory point, the type label represents a road element type to which the trajectory point belongs, and the coordinate data represents a position of the trajectory point; A first determination module is configured to determine a to-be-processed trajectory line feature sequence set corresponding to a plurality of trajectory point data; A second determination module is configured to determine a to-be-matched trajectory line feature sequence from a preset candidate trajectory line feature sequence set and a target trajectory line feature sequence from the to-be-processed trajectory line feature sequence set to obtain a trajectory line feature sequence group set; the to-be-matched trajectory line feature sequence and the target trajectory line feature sequence in each trajectory line feature sequence group represent the same road, and the candidate trajectory line feature sequence in the candidate trajectory line feature sequence set indicates a road in map data; The third determining module is configured to determine, for each track feature sequence group, a target track point from the track point data according to track features corresponding to the same type of label in the track feature sequence to be matched and the target track feature sequence; the target track point refers to a road element collected by the collection device from the target road and different from the road element recorded in the map data; The occurrence module is configured to send a feedback instruction to the collection device; the feedback instruction is used to instruct the collection device to feed back a road image corresponding to the target track point.

9. An electronic device, comprising: The electronic device includes a processor and a memory, and the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the road image feedback method according to any one of claims 1-7.

10. A computer storage medium, characterized in that The storage medium stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the road image feedback method according to any one of claims 1-7.

11. A computer program product, characterised in that, The computer program product includes at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the road image feedback method according to any one of claims 1-6.

Images