CN117994740A

CN117994740A - Method, device, equipment, medium and product for identifying traffic elements

Info

Publication number: CN117994740A
Application number: CN202311755077.5A
Authority: CN
Inventors: 孔旭旭; 范淼; 肖旭; 韩梦; 车珊珊; 宋向勃
Original assignee: Xi'an Navinfo Information Technology Co ltd
Current assignee: Xi'an Navinfo Information Technology Co ltd
Priority date: 2023-12-19
Filing date: 2023-12-19
Publication date: 2024-05-07

Abstract

The embodiment of the specification discloses a method, a device, equipment, a medium and a product for identifying traffic elements, and the scheme can comprise the following steps: acquiring a traffic road image acquired by acquisition equipment on a traffic road; the traffic road image comprises a plurality of traffic sign bars and a plurality of traffic elements; detecting the traffic road image to obtain a target traffic element positioned on the traffic road; determining a target traffic sign bar where the target traffic element is located; determining traffic elements located on the target traffic sign bar; and determining the traffic element on the target traffic sign bar as the traffic element on the traffic road. According to the embodiment of the specification, other traffic elements on the target traffic sign bar where the target traffic elements are located can be determined to be traffic elements on the traffic path, the traffic elements in the images do not need to be identified one by one, and the identification efficiency of the traffic elements is improved.

Description

Method, device, equipment, medium and product for identifying traffic elements

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, a medium, and a product for identifying traffic elements.

Background

In the electronic map, traffic elements (such as traffic signs, monitoring facilities and the like) are recorded so as to prompt which roads have traffic restrictions, such as which road sections need speed limiting, which road sections have illegal photographing and the like, thereby ensuring that users can timely notice the traffic elements and timely determine corresponding control strategies.

It can be seen that timely updating of the existence of traffic elements in an electronic map is critical for safe driving. The method for updating the existence of the traffic elements in the electronic map at present comprises the steps of collecting images containing the traffic elements in real life on traffic roads by using collecting equipment; then identifying whether the traffic elements in the image are positioned on the traffic road, namely whether the traffic elements are positioned on the traffic road where the acquisition equipment is positioned; and updating the existence of the traffic elements in the electronic map according to the traffic elements on the traffic path. However, in the prior art, when identifying whether the traffic elements are positioned on the traffic path, the traffic elements are identified one by one, and the efficiency of identifying the traffic elements is low.

Disclosure of Invention

The embodiment of the specification provides a method, a device, equipment, a medium and a product for identifying traffic elements so as to improve the identification efficiency of the traffic elements.

In order to solve the above technical problems, the embodiments of the present specification are implemented as follows:

the method for identifying traffic elements provided by the embodiment of the specification comprises the following steps:

Acquiring a traffic road image acquired by acquisition equipment on a traffic road; the traffic road image comprises a plurality of traffic sign bars and a plurality of traffic elements;

Detecting the traffic road image to obtain a target traffic element positioned on the traffic road;

Determining a target traffic sign bar where the target traffic element is located according to the first position information of the target traffic element in the traffic road image and the second position information of each traffic sign bar in the traffic road image;

Determining the traffic elements on the target traffic sign bar according to the third position information of each traffic element in the traffic road image;

and determining the traffic element on the target traffic sign bar as the traffic element on the traffic road.

Optionally, the method further comprises: determining first position information of the target traffic element in the traffic road image and second position information of each traffic sign bar in the traffic road image by using a pre-trained neural network model; the determining the target traffic sign bar where the target traffic element is located specifically includes:

And determining a target traffic sign bar where the target traffic element is located according to the relative position relation between the first position information and each second position information.

Optionally, the determining, according to the relative positional relationship between the first position information and the second position information, the target traffic sign pole where the target traffic element is located specifically includes:

Determining a first area of the target traffic element in the traffic road image according to the first position information;

determining each second area of each traffic sign bar in the traffic road image according to each second position information;

Judging whether any second area has an overlapping area with the first area or not according to any second area in each second area, and obtaining a judging result;

And if the judging result shows that any one of the second areas and the first area have an overlapping area, determining the traffic sign bar corresponding to any one of the second areas as the target traffic sign bar where the target traffic element is located.

Optionally, the determining each second area of each traffic sign pole in the traffic road image according to each second position information specifically includes:

Determining each initial second area of each traffic sign bar in the traffic road image according to each second position information;

And carrying out morphological expansion on each initial second area to obtain each second area of each traffic sign bar in the traffic road image.

Optionally, the method further comprises:

judging whether any traffic element except the target traffic element is positioned on the traffic road or not in the traffic elements positioned on the target traffic sign bar;

the determining the traffic element on the target traffic sign bar as the traffic element on the traffic road specifically comprises:

And if any traffic element except the target traffic element is positioned on the traffic road, determining the traffic element positioned on the target traffic sign bar as the traffic element positioned on the traffic road.

Optionally, the method further comprises:

And if any traffic element except the target traffic element is not positioned on the traffic road in the traffic elements positioned on the target traffic sign bar, determining the traffic element positioned on the target traffic sign bar as the traffic element not positioned on the traffic road.

Optionally, after determining the traffic element located on the target traffic sign bar as the traffic element located on the traffic path in the step, the method further includes:

and updating the existence of the traffic elements on the traffic road in the electronic map.

The embodiment of the present specification provides a computer device, including:

The image acquisition module is used for acquiring traffic road images acquired by the acquisition equipment on traffic roads; the traffic road image comprises a plurality of traffic sign bars and a plurality of traffic elements;

The image detection module is used for detecting the traffic road image to obtain a target traffic element positioned on the traffic road;

The determining module is used for determining a target traffic sign bar where the target traffic element is located according to the first position information of the target traffic element in the traffic road image and the second position information of each traffic sign bar in the traffic road image;

The determining module is further used for determining the traffic elements positioned on the target traffic sign bar according to the third position information of each traffic element in the traffic road image;

The determination module is also used for determining the traffic element positioned on the target traffic sign bar as the traffic element positioned on the traffic road.

The embodiment of the specification provides a computer device, which comprises a memory, a processor and a computer program stored on the memory, wherein the processor executes the computer program to realize the steps of the method for identifying traffic elements.

A computer-readable storage medium provided by embodiments of the present description has computer instructions stored thereon; and/or a computer program product comprising computer instructions which, when executed by a processor, implement the steps of the method of identifying traffic elements described above.

One embodiment of the present specification achieves the following advantageous effects:

According to the embodiment of the specification, the traffic road image can be detected to obtain the target traffic element on the traffic road, the traffic element on the target traffic sign bar where the target traffic element is located is determined, and then each traffic element on the target traffic sign bar can be determined to be the traffic element on the traffic road. That is, in the embodiment of the specification, each traffic element on the target traffic sign bar where the target traffic element is located can be determined as the traffic element located on the traffic path, the traffic elements in the images do not need to be identified one by one, and the identification efficiency of the traffic elements is improved.

Drawings

In order to more clearly illustrate the embodiments of the present description or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic flow chart of a method for identifying traffic elements according to an embodiment of the present disclosure;

Fig. 2 is a schematic diagram of a traffic road image according to an embodiment of the present disclosure;

fig. 3 is a schematic diagram of a sample image during training of a traffic sign bar model according to an embodiment of the present disclosure:

FIG. 4 is a schematic view of a first area according to an embodiment of the present disclosure;

FIG. 5 is a schematic view of an initial second region provided in an embodiment of the present disclosure;

FIG. 6 is a schematic view of a second area provided in an embodiment of the present disclosure;

FIG. 7 is a schematic view of a target traffic element provided in an embodiment of the present disclosure above a traffic sign lever arm body;

Fig. 8 is a schematic diagram of an overlapping area between a first area and an arm area according to an embodiment of the present disclosure;

FIG. 9 is a schematic diagram of a computer device corresponding to FIG. 1 according to an embodiment of the present disclosure;

fig. 10 is a schematic structural diagram of a computer device corresponding to fig. 1 according to an embodiment of the present disclosure.

Detailed Description

For the purposes of making the objects, technical solutions and advantages of one or more embodiments of the present specification more clear, the technical solutions of one or more embodiments of the present specification will be clearly and completely described below in connection with specific embodiments of the present specification and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present specification. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without undue burden, are intended to be within the scope of one or more embodiments herein.

The following describes in detail the technical solutions provided by the embodiments of the present specification with reference to the accompanying drawings.

The crowdsourcing map service is to put in a plurality of vehicles with environment sensing capability, so that the vehicles can run and collect road information data and upload the road information data to the cloud, for example, an image containing the road information data is uploaded to the cloud, and then the cloud builds an electronic map with high reduction degree and instant update according to the fed-back data.

In the electronic map, various traffic elements (such as traffic cameras and traffic signs) are recorded. When the existence of the traffic elements in the electronic map is updated, the image containing the traffic elements in real life can be acquired on the traffic road by utilizing the acquisition equipment; then identifying whether the traffic elements in the image are positioned on the traffic road, namely whether the traffic elements are positioned on the traffic road where the acquisition equipment is positioned; and updating the existence of the traffic elements in the electronic map according to the traffic elements on the traffic path. However, in the prior art, when identifying whether the traffic elements are positioned on the traffic path, the traffic elements are identified one by one, and the efficiency of identifying the traffic elements is low.

In order to solve the drawbacks of the prior art, the present solution provides the following embodiments:

Fig. 1 is a schematic flow chart of a method for identifying traffic elements according to an embodiment of the present disclosure, and from a program perspective, an execution subject of the flow may be a traffic element identification device, or a program of an application server or cloud installed on the traffic element identification device. As shown in fig. 1, the method may include the steps of:

Step 102: acquiring a traffic road image acquired by acquisition equipment on a traffic road; the traffic road image includes a plurality of traffic sign bars and a plurality of traffic elements.

In the present embodiment, the traffic road image may be an image on a traffic road acquired while the acquisition device is traveling on the traffic road or while staying. The collection device may be a crowdsourcing vehicle, that is, a vehicle put in a crowdsourcing map service.

Further, the traffic road image may also be an image about a traffic road acquired by the acquisition device at a certain fixed mounting location. Further, the collection device may be a roadside calculation unit (english name: roadside ComputingUnit, english abbreviation: RCU) installed beside the traffic road, or an image collection device installed on a traffic sign post on the traffic road.

Fig. 2 is a schematic diagram of a traffic road image according to an embodiment of the present disclosure, where, as shown in fig. 2, the traffic road image may include a traffic sign bar and a plurality of traffic elements.

The traffic element may be at least one of a traffic camera, a traffic light, and a traffic sign.

Further, after the collection device collects the traffic road image, the traffic road image can be sent to an execution main body of the flow, and then the execution main body of the flow obtains the traffic road image; of course, the execution subject of the flow may actively acquire the traffic road image from the acquisition device periodically or aperiodically, which is not limited herein.

Step 104: and detecting the traffic road image to obtain the target traffic element on the traffic road.

The traffic road image can be detected manually, and the target traffic elements on the traffic road can be obtained.

The traffic road image can also be detected or identified by adopting a pre-trained neural network model for identifying traffic elements on the traffic road, so as to obtain the traffic elements on the traffic road where the acquisition equipment is located. For example, a pre-trained traffic element classification model is adopted to detect the position information of the traffic element in the traffic road image, and then the target traffic element on the traffic road can be obtained based on the position information of the traffic element in the traffic road image and the position information of the traffic road in the traffic road image.

Step 106: and determining the target traffic sign bar where the target traffic element is located according to the first position information of the target traffic element in the traffic road image and the second position information of each traffic sign bar in the traffic road image.

In the embodiment of the present specification, the target traffic sign bar where the target traffic element is located may be determined according to the first position information of the target traffic element in the traffic road image and the second position information of each traffic sign bar in the traffic road image. For example, according to the relative position relation between the first position information and each second position information, determining the target traffic sign pole where the target traffic element is located.

Step 108: and determining the traffic elements on the target traffic sign bar according to the third position information of each traffic element in the traffic road image.

In the embodiment of the present specification, the traffic element located on the target traffic sign bar may be determined according to the relative positional relationship between the third positional information of each traffic element in the traffic road image and the positional information of the target traffic sign bar.

Or the traffic elements within a certain threshold range from the target traffic element can be determined according to the third position information of each traffic element in the traffic road image, and the traffic elements within the certain threshold range from the target traffic element are determined to be the traffic elements positioned on the target traffic sign bar.

Step 110: and determining the target traffic element on the target traffic sign bar as the traffic element on the traffic road.

Since the target traffic element is located on the traffic path, the target traffic sign bar on which the target traffic element is located is also located on the traffic path, and each traffic element on the target traffic sign bar can be determined as the traffic element located on the traffic path. Thus, the traffic elements in the images do not need to be identified one by one, and the traffic element identification efficiency can be improved.

It should be understood that the method according to one or more embodiments of the present disclosure may include the steps in which some of the steps are interchanged as needed, or some of the steps may be omitted or deleted.

The examples of the present specification also provide some specific embodiments of the method based on the method of fig. 1, which is described below.

In the embodiment of the present specification, the traffic road image may be detected manually to determine the target traffic element located on the traffic road. But the manual detection of the traffic road image is adopted, so that the manual detection method has higher labor cost and lower efficiency. Thus, embodiments of the present disclosure may also utilize a relatively low cost, relatively efficient pre-trained traffic element classification model to determine target traffic elements located on a traffic path. However, in practical application, the position information of the traffic elements detected by the pre-trained traffic element classification model in the traffic road image and the position information of the used traffic road in the traffic road image are two-dimensional information, and whether the traffic elements are positioned on the traffic road or not needs to be determined, so that the spatial three-dimensional relationship is related, and in practical application, the spatial three-dimensional relationship is determined by utilizing the two-dimensional information, so that errors exist.

Based on this, the embodiment of the present disclosure may further detect the traffic road image by using a pre-trained traffic element detection model, so as to obtain the target traffic element located on the traffic road. Specifically, the method comprises the following steps:

Detecting the traffic road image by using a pre-trained traffic element detection model to obtain a target traffic element positioned on the traffic road; the pre-trained traffic element detection model is used for detecting traffic elements on the traffic road where the acquisition equipment is located in the traffic road image.

Wherein the pre-trained traffic element detection model may be a classification model. The traffic road image is detected by using a pre-trained traffic element detection model, so that a classification detection result can be obtained, for example, 1 or 0 can be obtained. When the detection result is 1, it can be understood that the traffic element is located on the traffic path, and when the detection result is 0, it can be understood that the traffic element is not located on the traffic path.

In the embodiment of the present specification, the position information and the attribute information of the traffic element may be marked in the sample picture of the traffic element detection model. The marked position information can be the abscissa of the traffic element in the rectangular coordinate system where the sample picture is located, the marked attribute information can be information of whether the traffic element is located on the traffic path, for example, the traffic element is located on the traffic path, the attribute information of the traffic element can be marked as 1, the traffic element is not located on the traffic path, and the attribute information of the traffic element can be marked as 0. And training the traffic element detection model based on the marked sample picture to obtain a pre-trained traffic element detection model.

In a specific embodiment, the traffic road image is detected by using a pre-trained traffic element detection model, so that the confidence that the traffic element belongs to the traffic element on the traffic road can be obtained, and the target traffic element can be determined based on the confidence. Namely, the detecting the traffic road image to obtain the target traffic element on the traffic road may specifically include:

Detecting the traffic road image by using a pre-trained traffic element detection model to obtain the confidence that each traffic element belongs to the traffic element positioned on the traffic road;

And determining the traffic element corresponding to the confidence coefficient meeting the preset condition as the target traffic element positioned on the traffic road.

The confidence coefficient meeting the preset condition can be a confidence coefficient which is larger than or equal to a certain confidence coefficient threshold value; or may be the confidence of the previous part in the respective confidence of the small-to-large arrangement, wherein the respective confidence of the small-to-large arrangement includes the confidence of the previous part and the confidence of the subsequent part, and the confidence of the previous part is larger than the confidence of the subsequent part, and in addition, the confidence of the previous part may be a certain set number of confidence degrees or a certain set proportion of the respective confidence degrees.

The embodiment of the specification detects the traffic road image, and can obtain a plurality of target traffic elements on the traffic road. Assuming that the target traffic element includes a plurality of target traffic elements, a target traffic sign bar where any target traffic element is located may be determined for any target traffic element of the plurality of target traffic elements.

In the present embodiment, the traffic marking bars in the traffic road image may include several traffic marking bars, that is, may include one or more traffic marking bars. According to the embodiment of the specification, the target traffic sign bar where the target traffic element is located can be determined according to the first position information of the target traffic element in the traffic road image and the second position information of each traffic sign bar in the traffic road image. The determining the target traffic sign bar where the target traffic element is located may specifically include:

Determining first position information of the target traffic element in the traffic road image;

determining second position information of each traffic sign bar in the traffic road image;

In the embodiment of the present specification, the first location information of the target traffic element in the traffic road image may be determined using a neural network model trained in advance. The first location information is determined, for example, using a pre-trained traffic element classification model or a pre-trained traffic element detection model.

The first position information of the target traffic element in the traffic road image may be an abscissa and an ordinate of the target traffic element in an orthogonal coordinate system where the traffic road image is located.

Further, the embodiment of the present disclosure may also determine each second location information of each traffic sign bar in the traffic road image using a pre-trained neural network model. Such as determining the second location information using a pre-trained traffic sign post detection model.

The pre-trained traffic sign bar detection model can be obtained by training a sample image marked with the position information of the traffic sign bar. Fig. 3 is a schematic diagram of a sample image during training of a traffic sign bar model according to an embodiment of the present disclosure, as shown in fig. 3, the sample image is marked with position information of a traffic sign bar, where the position information of the traffic sign bar may be coordinates in a rectangular coordinate system where the sample image is located, such as (x 1, y 1), (x 2, y 2), (x 3, y 3), (x 4, y 4), (x 5, y 5), (x 6, y 6), (x 7, y 7), and (x 8, y 8), where an upper left corner of the sample image may be an origin of coordinates in the rectangular coordinate system where the sample image is located.

That is, the second position information detected by the pre-trained traffic sign bar detection model may be an abscissa and an ordinate of the traffic sign bar in the rectangular coordinate system in which the traffic road image is located.

Further, the determining, according to the relative positional relationship between the first position information and the second position information, the target traffic sign pole where the target traffic element is located may specifically include:

The first area may be an area surrounded by position points represented by the first position information, and specifically may be an area surrounded by coordinate points corresponding to the abscissa and the ordinate of the target traffic element in the traffic road image. In practical applications, the first location information may be location information of an outline of the traffic element, and the first area may also represent an area formed by outline points of the traffic element.

Fig. 4 is a schematic diagram of a first area provided in the embodiment of the present disclosure, as shown in fig. 4, the top left corner of the traffic road image may be the origin of coordinates of a rectangular coordinate system where the traffic road image is located, and the first area may be a rectangular area with a length w and a width h in the rectangular coordinate system, where the vertex coordinates of the top left corner of the rectangular area are (x, y).

In a specific embodiment, the first area may be a detection frame that is output by detecting the traffic road image by a pre-trained traffic element detection model or a pre-trained traffic element classification model.

In the embodiment of the present specification, the second area may be determined using the second position information of the traffic sign bar in the traffic road image. The determining each second area of each traffic sign bar in the traffic road image according to each second position information may specifically include:

The initial second area may be an area surrounded by position points represented by the second position information, and specifically may be an area surrounded by coordinate points corresponding to the abscissa and ordinate of the traffic sign bar in the traffic road image. In practical applications, the second position information may be position information of a contour of the traffic sign bar, and the initial second area may also represent an area formed by contour points of the traffic sign bar.

Fig. 5 is a schematic view of an initial second area provided in the embodiment of the present disclosure, as shown in fig. 5, where the initial second area may be a discontinuous area, such as the leftmost initial second area in fig. 5. This may be due to the fact that the pre-trained traffic rod detection model has poor detection accuracy, or that a discontinuous area is blocked by a shade such as a branch and not detected by the traffic rod detection model.

In order to solve the problem that the initial second region has discontinuous regions, so as to improve the accuracy of the determined second region, in this embodiment of the present disclosure, the initial second region may be further expanded morphologically, where the expansion kernel may be a matrix of 7×13, and the characteristic value of the matrix may be 1, and the number of expansion times may be determined according to the needs, for example, 1, 3,5, etc., which is not limited herein.

And carrying out morphological expansion on the initial second area to obtain the second area of the traffic sign bar in the traffic road image. Fig. 6 is a schematic view of a second area provided in the embodiment of the present disclosure, where, as shown in fig. 6, the second area does not have a discontinuous area.

The embodiment of the specification can be that the target traffic sign bar is determined according to whether the first area and the second area have the overlapping area or not, that is, the target traffic sign bar is determined according to whether the area where the target traffic element is located and the area where the traffic sign bar is located have the overlapping area or not. And when the target traffic element is above or below the traffic sign lever arm body, there may be no overlapping area between the area where the target traffic element is located and the area where the traffic sign lever is located. After the initial second area is subjected to morphological expansion, a larger second area can be obtained, and the larger second area can be overlapped with the area where the target traffic element is located, so that the target traffic sign post where the target traffic element is located can be more accurately determined.

In the present embodiments, the traffic sign bar may include a column and an arm. The upright post may be a portion of the traffic sign bar perpendicular or approximately perpendicular to the traffic road, which may be understood that an included angle with the traffic road is between 90±a first angle threshold, and the arm body may be a portion of the traffic sign bar parallel or approximately parallel to the traffic road, which may be understood that an included angle with the traffic road is between 180±a second angle threshold. The first angle threshold may be 3 °,5 ° and 10 °, and the second angle threshold may also be 3 °,5 ° and 10 °, and the first angle threshold and the second angle threshold may be determined according to actual requirements, which is not limited herein.

Fig. 7 is a schematic diagram of the embodiment of the present disclosure when the target traffic element is above the traffic sign lever arm, as shown in fig. 7, where the area where the target traffic element is located and the area where the traffic sign lever is located do not have an overlapping area.

In a specific embodiment, the position information of the traffic marker lever noted in the sample image of the traffic marker lever detection model contains position information of traffic elements on the traffic marker lever. That is, the initial second region detected by the pre-trained traffic sign bar detection model may include a region where each traffic element on the traffic sign bar corresponding to the initial second region is located. Therefore, whether the second area and the first area have an overlapping area or not can be conveniently judged, and the target traffic sign bar where the target traffic element is located can be more accurately determined.

In practical applications, the traffic element is generally located above or below the arm of the traffic sign post. Therefore, in the embodiment of the present disclosure, the arm region in the second region may be acquired, and the target traffic sign bar may be determined according to whether there is an overlapping region between the arm regions in the first region and the second region.

Wherein acquiring the arm region in the second region may specifically include acquiring a portion of the second region parallel or approximately parallel to the traffic road, and determining the portion of the second region parallel or approximately parallel to the traffic road as the arm region in the second region.

Or each traffic element contained in the second area may be determined, and the arm body area in the second area may be determined according to the area in which each traffic element is contained. Specifically, the position information of each traffic element in the road image is detected by using a pre-trained traffic element classification model, the area where each traffic element is located is determined based on the position information, and if an overlapping area exists between the second area and the area where the traffic element is located, the second area is determined to contain the traffic element; the maximum ordinate and the minimum ordinate in the position information of each traffic element included in the second area are respectively used as the maximum ordinate and the minimum ordinate of the arm area, and the maximum abscissa and the minimum abscissa of the second area are respectively used as the maximum abscissa and the minimum abscissa of the arm area, so that the arm area can be determined based on the maximum ordinate, the minimum ordinate, the maximum abscissa and the minimum abscissa of the arm area.

Fig. 8 is a schematic diagram of an overlapping area between a first area and an arm area provided in the embodiment of the present disclosure, and as shown in fig. 8, if the first area and the arm area have an overlapping area, a traffic sign bar corresponding to the arm area may be determined as a target traffic sign bar.

Similarly, in the embodiment of the present disclosure, morphological expansion may be performed on the first area to improve accuracy of determining the first area and accuracy of determining the target traffic sign pole where the target traffic element is located, which will not be described herein.

In the embodiment of the present disclosure, the detection of the traffic road image may result in an error in the target traffic element located on the traffic path, that is, the target traffic element located on the traffic path may not be located on the traffic path in practice. Therefore, in order to more accurately determine the traffic element located on the traffic path, the embodiment of the present specification may also determine the traffic element located on the traffic path by using other traffic elements on the target traffic sign post where the target traffic element is located. If other traffic elements are located on the traffic road, it can be stated that the traffic elements located on the traffic sign bars on which the other traffic elements are located are also located on the traffic road. The method for identifying traffic elements provided in the embodiments of the present disclosure may further include:

The determining the traffic element on the target traffic sign bar as the traffic element on the traffic road specifically may include:

Otherwise, if the other traffic elements are not located on the traffic path, the traffic sign bars where the other traffic elements are located are not located on the traffic path, and then the traffic elements on the traffic sign bars where the other traffic elements are located are not located on the traffic path. The method for identifying traffic elements provided in the embodiments of the present disclosure may further include:

Further, when determining whether any traffic element is located on the traffic road, the traffic road image can be determined by manually detecting the traffic road image; the traffic road image can also be detected and determined by adopting a pre-trained traffic element classification model; of course, the traffic road image may be determined by detecting a traffic road image using a pre-trained traffic element detection model, for example, a traffic element corresponding to a detection result of 1 may be determined as a traffic element located on a traffic path, or a traffic element corresponding to a confidence degree meeting a preset condition in the detection result may be determined as a traffic element located on the traffic path.

It may be further understood that, by detecting the traffic road image in the embodiment of the present disclosure, a plurality of target traffic elements located on the traffic road may be obtained, and for any one of the plurality of target traffic elements, a target traffic sign bar where any one of the target traffic elements is located may be determined, so that other traffic elements on the target traffic sign bar and the target traffic elements may be determined as traffic elements located on the traffic road. In this case, when determining whether any one of the other traffic elements is located on the traffic road, it may be determined whether any one of the traffic elements belongs to the traffic element among the plurality of target traffic elements; if the traffic element belongs to the traffic element, the traffic element can be determined to be positioned on the traffic path, and if the traffic element does not belong to the traffic element, the traffic element can be determined to not be positioned on the traffic path. Therefore, the traffic road image is not required to be detected, and the traffic element identification efficiency can be improved.

In the embodiment of the present specification, if there is no traffic element other than the target traffic element on the target traffic sign bar, the target traffic element may be determined as a traffic element located on the traffic path.

Further, after determining the traffic element located on the target traffic sign bar as the traffic element located on the traffic path, the method for identifying the traffic element provided in the embodiment of the present disclosure may further include:

For example, the traffic element in the position information in the electronic map can be determined according to the position information of the traffic element on the traffic road in the traffic road image. If no traffic element exists in the electronic map at the position information, updating the existence of the traffic element on the traffic path in the electronic map, wherein the traffic element can be added in the electronic map at the position information; if the traffic element exists in the electronic map at the position information, the existence of the traffic element on the traffic road in the electronic map is updated, and the position information of the traffic element in the electronic map can be updated according to the position information of the traffic element on the traffic road in the traffic road image.

It is understood that the updated existence of traffic elements on the traffic road in the electronic map may also include the update time. Thus, the user can know the update time of the electronic map conveniently when using the electronic map.

Based on the same thought, the embodiment of the specification also provides a device corresponding to the method. Fig. 9 is a schematic structural diagram of a computer device corresponding to fig. 1 according to an embodiment of the present disclosure. As shown in fig. 9, the apparatus may include:

an image acquisition module 902, configured to acquire a traffic road image acquired by an acquisition device on a traffic road; the traffic road image comprises a plurality of traffic sign bars and a plurality of traffic elements;

The image detection module 904 is configured to detect the traffic road image to obtain a target traffic element located on the traffic road;

A determining module 906, configured to determine a target traffic sign bar where the target traffic element is located according to the first location information of the target traffic element in the traffic road image and each second location information of each traffic sign bar in the traffic road image;

The determining module 906 is further configured to determine a traffic element located on the target traffic sign pole according to third location information of each traffic element in the traffic road image;

The determining module 906 is further configured to determine a traffic element located on the target traffic sign bar as a traffic element located on the traffic road.

Optionally, the image detection module 904 may specifically be configured to:

Optionally, the device further determines first position information of the target traffic element in the traffic road image and second position information of each traffic sign bar in the traffic road image by using a pre-trained neural network model; the determining module 906 may specifically include:

And the first determining submodule is used for determining the target traffic sign bar where the target traffic element is located according to the relative position relation between the first position information and the second position information.

Optionally, the first determining sub-module may specifically include:

a first determining unit configured to determine a first area of the target traffic element in the traffic road image according to the first location information;

A second determining unit configured to determine, according to each of the second position information, each second area of each traffic sign bar in the traffic road image;

the judging unit is used for judging whether any second area has an overlapping area with the first area or not according to any second area in the second areas, and obtaining a judging result;

And the third determining unit is used for determining the traffic sign bar corresponding to any second area as the target traffic sign bar where the target traffic element is located when the judging result shows that any second area and the first area have an overlapping area.

Optionally, the second determining unit may specifically include:

A first determining subunit, configured to determine, according to each of the second position information, each initial second area of each traffic sign bar in the traffic road image;

And the expansion subunit is used for carrying out morphological expansion on each initial second area to obtain each second area of each traffic sign rod in the traffic road image.

Optionally, the apparatus may further include:

The judging module is used for judging whether any traffic element except the target traffic element is positioned on the traffic road or not in the traffic elements positioned on the target traffic sign bar; the determining module 906 may also be configured to:

And when any traffic element except the target traffic element is positioned on the traffic road, determining the traffic element positioned on the target traffic sign bar as the traffic element positioned on the traffic road.

Optionally, the determining module 906 may also be configured to:

And when any traffic element except the target traffic element is not positioned on the traffic road in the traffic elements positioned on the target traffic sign bar, determining the traffic element positioned on the target traffic sign bar as the traffic element not positioned on the traffic road.

Optionally, the traffic element includes at least one of a traffic camera, a traffic light, and a traffic sign.

Optionally, the apparatus may further include:

And the updating module is used for updating the existence of the traffic elements on the traffic road in the electronic map.

Based on the same thought, the embodiment of the specification also provides equipment corresponding to the method.

Fig. 10 is a schematic structural diagram of a computer device corresponding to fig. 1 according to an embodiment of the present disclosure. As shown in fig. 10, the apparatus 100 may include: comprising a memory 110, a processor 120 and a computer program 130 stored on the memory 110, the processor 120 executing the computer program 130 to carry out the steps of the above-described method of identifying traffic elements.

Based on the same thought, the embodiments of the present disclosure further provide a computer readable storage medium corresponding to the above method, where computer instructions are stored; and/or a computer program product comprising computer instructions which, when executed by a processor, implement the steps of the above-described method of identifying traffic elements.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for the computer device shown in fig. 10, the description is relatively simple, as it is substantially similar to the method embodiment, with reference to the partial description of the method embodiment being relevant.

In the 90 s of the 20 th century, improvements to one technology could clearly be distinguished as improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software (improvements to the process flow). However, with the development of technology, many improvements of the current method flows can be regarded as direct improvements of hardware circuit structures. Designers almost always obtain corresponding hardware circuit structures by programming improved method flows into hardware circuits. Therefore, an improvement of a method flow cannot be said to be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD) (e.g., field programmable gate array (Field Programmable GATEARRAY, FPGA)) is an integrated circuit whose logic functions are determined by user programming of the device. A designer programs to "integrate" a digital system onto a PLD without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, such programming is mostly implemented with "logic compiler (logic compiler)" software, which is similar to the software compiler used in program development and writing, and the original code before being compiled is also written in a specific programming language, which is called hardware description language (Hardware Description Language, HDL), but HDL is not just one, but a plurality of kinds, such as ABEL(AdvancedBoolean Expression Language)、AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language), and VHDL (Very-High-SPEED INTEGRATED Circuit Hardware Description Language) and Verilog are currently most commonly used. It will also be apparent to those skilled in the art that a hardware circuit implementing the logic method flow can be readily obtained by merely slightly programming the method flow into an integrated circuit using several of the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application SPECIFIC INTEGRATED Circuits (ASICs), programmable logic controllers, and embedded microcontrollers, examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, atmel AT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic of the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller may thus be regarded as a kind of hardware component, and means for performing various functions included therein may also be regarded as structures within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.

The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in the same piece or pieces of software and/or hardware when implementing the present application.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.

Claims

1. A method of identifying traffic elements, comprising:

2. The method as recited in claim 1, further comprising: determining first position information of the target traffic element in the traffic road image and second position information of each traffic sign bar in the traffic road image by using a pre-trained neural network model; the determining the target traffic sign bar where the target traffic element is located specifically includes:

3. The method according to claim 2, wherein the determining the target traffic sign bar where the target traffic element is located according to the relative positional relationship between the first positional information and the second positional information specifically includes:

4. A method according to claim 3, wherein said determining each second area of each traffic sign bar in said traffic road image based on each said second location information, in particular comprises:

5. The method as recited in claim 1, further comprising:

6. The method according to claim 1 or 5, further comprising:

7. The method of claim 1, further comprising, after the step of determining the traffic element located on the target traffic sign bar as the traffic element located on the traffic path:

8. A computer apparatus, comprising:

9. A computer device comprising a memory, a processor and a computer program stored on the memory, characterized in that the processor executes the computer program to carry out the steps of the method of any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon computer instructions; and/or a computer program product comprising computer instructions which, when executed by a processor, implement the steps of the method of any one of claims 1 to 7.