Method, device, storage medium and computer program product for determining a road condition

Abstract

Embodiments of the present application provide a method, device, storage medium and computer program product for determining road state, wherein the method for determining road state comprises: obtaining at least one acquisition image obtained by at least one acquisition device during image acquisition in a road in a target area, and a positioning position corresponding to the acquisition image, the positioning position corresponding to the acquisition image being used to indicate the position of the acquisition device when the acquisition image is acquired; determining the acquisition image of the positioning position in the target road in the target area and / or the acquisition image of the positioning position in the associated road connected with the target road as a target image; performing image recognition on the target image, determining the road state displayed by the target image according to the image recognition result; and determining whether the target road is closed according to the road state displayed by at least one target image. The accuracy of determining whether the road is closed is improved, the real-time performance is better, and the road range that can be recognized is more extensive.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of dynamic traffic, and in particular, to a method, device, storage medium and computer program product for determining road state. BACKGROUND

[0002] For map software, in order to ensure the accuracy of the map, it is necessary to update the road data according to the actual situation. In some application scenarios, it is necessary to determine whether the road is closed. In the prior art, it can be determined whether the road is closed by accumulating a large number of driving trajectories, but the data update is not timely, and congestion and other conditions can be misidentified as closed. It can also be monitored online by manual operation, but this will consume a lot of manpower, and the manual operation has no unified standard, which can lead to poor accuracy of identifying the closed condition. It can also be identified by high-definition images, but the coverage of high-definition images is small and cannot be identified comprehensively. SUMMARY

[0003] Therefore, embodiments of the present application provide a method, device, storage medium and computer program product for determining road state to at least partially solve the above problems.

[0004] According to a first aspect of embodiments of the present application, a method for determining road state is provided, comprising: obtaining at least one collection image obtained by at least one collection device collecting images in a road of a target area, and a positioning position corresponding to the collection image, the positioning position corresponding to the collection image being used to indicate the position of the collection device when collecting the collection image; determining the collection image with the positioning position in a target road of the target area and / or the collection image with the positioning position in an associated road connected with the target road as a target image; performing image recognition on the target image, determining the road state displayed by the target image according to the image recognition result; and determining whether the target road is closed according to the road state displayed by at least one target image.

[0005] According to a second aspect of embodiments of the present application, a device for determining road state is provided, comprising: an obtaining module, configured to obtain at least one collection image obtained by at least one collection device collecting images in a road of a target area, and a positioning position corresponding to the collection image, the positioning position corresponding to the collection image being used to indicate the position of the collection device when collecting the collection image; an image positioning module, configured to determine the collection image with the positioning position in a target road of the target area and / or the collection image with the positioning position in an associated road connected with the target road as a target image; an image recognition module, configured to perform image recognition on the target image, and determine the road state displayed by the target image according to the image recognition result; and an aggregation judgment module, configured to determine whether the target road is closed according to the road state displayed by at least one target image.

[0006] According to a third aspect of the embodiments of the present application, an electronic device is provided, comprising a processor, a memory, a communication interface and a communication bus, the processor, the memory and the communication interface complete communication with each other through the communication bus; the memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform the operation corresponding to the method for determining the road state according to the first aspect.

[0007] According to a fourth aspect of the embodiments of the present application, a storage medium is provided, and the storage medium stores a computer program, and the program is executed by a processor to implement the method for determining the road state according to the first aspect.

[0008] According to a fifth aspect of the embodiments of the present application, a computer program product is provided, and the computer program product is executed by a processor to implement the method for determining the road state according to the first aspect.

[0009] The method for determining the road state, the device, the storage medium and the computer program product provided by the embodiments of the present application, at least one acquisition image obtained by at least one acquisition device in the target area of the road for image acquisition and the positioning position corresponding to the acquisition image are obtained, and the positioning position corresponding to the acquisition image is used to indicate the position of the acquisition device when the acquisition image is collected; the acquisition image of the positioning position in the target road of the target area and / or the acquisition image of the positioning position in the associated road connected with the target road is determined as the target image; the target image is subjected to image recognition, and the road state displayed by the target image is determined according to the image recognition result; and whether the target road is closed is determined according to the road state displayed by at least one target image. The image recognition is performed in combination with the image of the target road and the associated road connected with the target road, which does not depend on a single image, improves the accuracy of judging whether the road is closed, utilizes image recognition for judgment, has better real-time performance, does not need high-definition image, and can identify a more extensive road range. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments described in the embodiments of the present application, and other drawings can also be obtained by those skilled in the art according to these drawings.

[0011] Figure 1 A scene schematic diagram of a method for determining a road state provided by the first embodiment of the present application;

[0012] Figure 2 A flowchart of a method for determining a road state provided by the first embodiment of the present application;

[0013] Figure 3A schematic diagram of image acquisition provided for Embodiment One of the present application;

[0014] Figure 4 Another scene schematic diagram of determining road state provided for Embodiment One of the present application;

[0015] Figure 5 Structure diagram of a device for determining road state provided for Embodiment Two of the present application;

[0016] Figure 6 Structure diagram of an electronic device provided for Embodiment Three of the present application. DETAILED DESCRIPTION

[0017] In order to make the personnel in the art better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the embodiments of the present application shall belong to the scope of protection of the embodiments of the present application.

[0018] The specific implementation of the embodiments of the present application will be further described below in conjunction with the drawings of the embodiments of the present application.

[0019] Embodiment One

[0020] Embodiment One of the present application provides a method for determining road state, applied to an electronic device. In order to facilitate understanding, the application scenario of the method for determining road state provided by Embodiment One of the present application is described, referring to Figure 1 , as shown in the figure, Figure 1 A scene schematic diagram of the method for determining road state provided for Embodiment One of the present application. Figure 1 The scene shown in the figure includes an electronic device 101, which can be a device for executing the method for determining road state provided by Embodiment One of the present application.

[0021] The electronic device 101 can be a terminal device such as a smart phone, a tablet computer, a notebook computer, a vehicle-mounted terminal, etc. The electronic device 101 can also be a network device such as a server, etc. Of course, this is only an exemplary description, and the present application is not limited thereto.

[0022] The electronic device 101 can access a network, connect with the cloud through the network, and perform data interaction, or the electronic device 101 can be a device of the cloud. In this application, the network includes a local area network (Local Area Network, LAN), a wide area network (Wide Area Network, WAN), a mobile communication network, such as the World Wide Web (World Wide Web, WWW), a Long Term Evolution (Long Term Evolution, LTE) network, a 2G network (2th Generation Mobile Network), a 3G network (3th Generation Mobile Network), a 5G network (5th Generation Mobile Network), and the like. The cloud can include various devices connected through the network, such as servers, relay devices, device-to-device (Device-to-Device, D2D) devices, and the like. Of course, this is only an example and does not limit the application.

[0023] In combination Figure 1 The method for determining the road state provided by the first embodiment of the application is described in detail in the scenario shown, and it should be noted that Figure 1 is only one application scenario of the method for determining the road state provided by the first embodiment of the application, and does not mean that the method for determining the road state must be applied to Figure 1 The scenario shown, which can be applied to an electronic device, is described with reference to Figure 2 , Figure 2 A flowchart of the method for determining the road state provided by the first embodiment of the application is shown, and the method includes the following steps:

[0024] Step 201, obtaining at least one collection image obtained by at least one collection device in the road of the target area, and a positioning position corresponding to the collection image.

[0025] The positioning position corresponding to the collection image is used to indicate the position of the collection device when collecting the collection image. It should be noted that in this application, the collection device can be an image shooting device on the vehicle, such as a vehicle-mounted camera. For example, in the process of driving the vehicle, the collection device shoots the collection image at different positions. As Figure 3 shown, Figure 3 An example of image collection provided by the first embodiment of the application is shown. Figure 3The trajectory of the data acquisition device is shown by the dotted line. Different images were captured at different locations along the trajectory, thus establishing a correspondence between the captured images and the location. It should also be noted that the target area can be any map region; this application only uses a target area as an example for illustration.

[0026] Step 202: The images acquired with the location within the target road in the target area and / or the images acquired with the location within an associated road connected to the target road are identified as target images.

[0027] It should be noted that in this application, the road can be a directional road or a two-way road. For example, a road containing one or more lanes, all with the same direction of travel, is a directional road; similarly, a road containing two or more lanes, with at least two lanes having different directions of travel, is a two-way road. It should also be noted that the number of target images can be one or more. Target images can include images captured at the location within the target road; or images captured at the location within the target road and associated roads connected to the target road; or images captured at the location within associated roads connected to the target road. For example, the target image can include images captured at the location within the target road in the target area and / or images captured at the location within associated roads connected to the target road within a preset time period. The preset time period can be 5 minutes, 30 minutes, or 1 hour prior to the current time, etc., and this is merely an example.

[0028] Step 203: Perform image recognition on the target image and determine the road condition displayed in the target image based on the image recognition results.

[0029] The road status displayed in the target image can include closed, open, and unverifiable states. A closed state means the road shown in the target image is closed; an open state means the road shown in the target image is unobstructed; and unverifiable means it is impossible to determine whether the road shown in the target image is closed. It should be noted that if there are multiple target images, image recognition must be performed on each target image. Taking target image A and target image B as examples, if the location corresponding to target image A is within the target road, then the road status displayed in target image A is the status of the target road; if the location corresponding to target image B is within an associated road connected to the target road, then the road status displayed in target image B is the status of that associated road.

[0030] Here, three specific examples are provided to further illustrate the point.

[0031] Optionally, in the first example, the target image is subjected to image recognition, and the road state displayed by the target image is determined according to the image recognition result, including: the target image is subjected to image recognition, and it is determined whether there is an obstacle on the target road in the target image according to the image recognition result; if there is an obstacle on the target road in the target image, it is determined that the road state displayed by the target image is closed.

[0032] Optionally, in the second example, based on the first example, the road state displayed by the target image is determined according to the image recognition result, including: if there is no obstacle on the target road in the target image, it is determined that the road state displayed by the target image is not closed.

[0033] Optionally, in the third example, the target image is subjected to image recognition, and the road state displayed by the target image is determined according to the image recognition result, including: the target image is subjected to image recognition, and if it is determined that the target image does not contain a road image according to the image recognition result, it is determined that the road state displayed by the target image is unverifiable. If the target image does not contain a road image, it means that the target image does not have an image that can represent the road condition, and cannot be used as a basis for determining the road condition.

[0034] Optionally, in combination with the above three examples, the object in the target image can be identified, if it is identified that the target image does not contain a road, the road state displayed by the target image is unverifiable; if it is identified that the target image contains a road and an obstacle, the road state displayed by the target image is closed; if it is identified that the target image contains a road and does not contain an obstacle, the road state displayed by the target image is not closed. It should be noted that, in this application, the obstacle is an object that indicates that the road is closed and prohibits passing, for example, the obstacle can include a conical bucket roadblock, a road closure fence, etc.

[0035] It should be further noted that, step 202 can be performed first, and then step 203 can be performed, or step 203 can be performed first, and then step 202 can be performed, that is, the collected image is subjected to image recognition, and the road state displayed by the collected image is determined according to the recognition result, and then the collected image whose positioning position is in the target road in the target area and / or the collected image whose positioning position is in the associated road connected with the target road is determined as the target image, and the road state displayed by the target image is used to determine whether the target road is closed.

[0036] Step 204: determining whether the target road is closed according to the road state displayed by at least one target image.

[0037] Because the road state displayed by the target road is not necessarily accurate, determining whether the target road is closed based on the road state displayed by the at least one target image is more accurate. Here, an embodiment is listed for illustration. Optionally, determining whether the target road is closed based on the road state displayed by the at least one target image comprises: performing operation on the road state displayed by the target image by using a preset aggregation model, and determining whether the target road is closed based on an operation result of the aggregation model. The aggregation model can be an algorithm model, which calculates the result of whether the target road is closed based on the road state displayed by the target image. The aggregation model can be a neural network model, or a mathematical function, etc.

[0038] Further optionally, performing operation on the road state displayed by the target image by using a preset aggregation model, and determining whether the target road is closed based on an operation result of the aggregation model comprises: determining a closed parameter of the target image based on the road state displayed by the target image by using the aggregation model; calculating a weighted average of the closed parameter of the target image by using the confidence of the target image to obtain a closed probability of the target road as the operation result of the aggregation model; and determining whether the target road is closed based on the closed probability of the target road. It should be noted that the closed parameter of the target image is used to represent whether the road displayed by the target image is closed. For example, the closed parameter of the target image can be 0 or 1, 0 representing not closed and 1 representing closed. The closed probability of the target road is used to represent the possibility of the closed state of the target road, and the greater the closed probability, the greater the possibility of the target road being closed.

[0039] Optionally, in an embodiment, whether the target road is closed is determined based on the closed probability and the size of a preset threshold value. If the closed probability is greater than or equal to the preset threshold value, the target road is closed, and if the closed probability is less than the preset threshold value, the target road is not closed. The preset threshold value can be a number in (0, 1], and the preset threshold value can be 0.6, 0.5, 0.7, etc. Generally, the preset threshold value can be greater than or equal to 0.5.

[0040] Optionally, the confidence of a target image can represent a reliability degree of a road state shown by the target image. For example, the closer the collection time of the target image is to the current time, the higher the confidence of the target image is; for another example, the higher the definition of the target image is, the higher the confidence of the target image is; for another example, the closer the positioning position of the target image is to the target road, the higher the confidence of the target image is. In an implementation manner, the method further includes: calculating the confidence of the target image according to at least one of the collection time of the target image, the definition of the target image, and the positioning position of the target image. Here, only exemplary description is given, and other factors that affect the confidence can also exist, which are not limited in the present application. The confidence calculated by comprehensively considering multiple factors can more accurately reflect the reliability degree of the target image, and can further improve the accuracy of judging whether the target road is closed.

[0041] Based on Figure 1 As shown in the scenario, in combination with steps 201-204, here, another specific application scenario is enumerated to illustrate the method for determining the road state. As shown in the scenario, Figure 4 As shown in the scenario, Figure 4 Another scenario diagram of a method for determining a road state provided by Embodiment One of the present application. Figure 4The electronic device 101 and the collection device 102 are shown. In this embodiment, the road is a one-way road, and the collection device can be arranged on a vehicle. The collection device can take pictures during the driving of the vehicle to obtain collection images. The collection device 102 transmits the collection images and the corresponding positioning positions when the collection images are taken to the electronic device 101. The electronic device 101 determines the collection images and the positioning positions in the target road in the target area and the collection images and the positioning positions in the associated road connected with the target road as target images according to the collection images and the positioning positions. The number of target images can be multiple. Image recognition is performed on each target image to determine the road state displayed by each target image. Exemplarily, only a preset number of target images taken most recently can be taken, for example, the preset number can be 20. If a new target image is obtained, 20 target images taken most recently are still taken. Alternatively, only target images obtained in a preset time period before the current time can be taken to ensure that the judgment result can reflect the latest road condition and improve the real-time performance. The road states displayed by multiple target images are combined to determine whether the target road is closed by using an aggregation model. The target images of the target road and the target images of the upstream road and the downstream road of the target road are combined to consider the road network structure and make an overall judgment, which is more accurate. In this embodiment, because the road is a one-way road, the upstream road of the target road is the road leading to the target road, and the downstream road of the target road is the road leading from the target road. Exemplarily, the confidence of the target image of the target road is 0.6, the confidences of the target images of the upstream road and the downstream road of the target road are 0.4 respectively, if the road state displayed by the target image of the target road is closed, which is represented by 1, and the road states displayed by the target images of the upstream road and the downstream road of the target road are non-closed, which are represented by 0, the weighted average value can be calculated as 0.2, that is, the closing probability of the target road is 0.2. The preset threshold can be 0.5. Because 0.2 is less than 0.5, it can be determined that the target road is not closed. If the target image of the target road displays that the target road is closed, and the target images of the upstream road and the downstream road of the target road display that the target road is not closed, it is indicated that the target road is likely not closed, and the target image of the target road can have a large error. This is only an example. In some other examples, if the target image of the target road displays that the target road is not closed, and the target images of the upstream road and the downstream road of the target road display that the target road is closed, it is determined that the target road is closed. Alternatively, in some other examples, if the target images of the target road and the upstream road and the downstream road of the target road all display that the target road is closed, it is determined that the target road is closed, and if all the target images display that the target road is not closed, it is determined that the target road is not closed. If the number of target images is insufficient, the position is not good, and the whole cannot be judged, when new target images of the target road and the associated road connected with the target road are obtained subsequently, the new target images can be added together for judgment to improve the judgment accuracy.In combination with the positioning location of the target image, the road state displayed by the target image, and the road network structure, the target road is comprehensively judged whether to be closed, which is more accurate and ensures high real-time performance, does not need high-definition map, and has more comprehensive coverage. The judgment result of whether the target road is closed can be transmitted to other devices in the cloud or terminal devices, so that the user can master the real-time road conditions.

[0042] The method for determining a road state provided in the embodiments of the present application comprises the following steps: acquiring at least one collection image obtained by at least one collection device in a target area of a road, and a positioning location corresponding to the collection image, the positioning location corresponding to the collection image being used to indicate the position of the collection device when the collection image is collected; determining the collection image with the positioning location in a target road in the target area and / or the collection image with the positioning location in an associated road connected with the target road as a target image; performing image recognition on the target image, determining the road state displayed by the target image according to the image recognition result; and determining whether the target road is closed according to the road state displayed by at least one target image. In combination with the images of the target road and the associated road connected with the target road, the image recognition is performed without relying on a single image, the accuracy of determining whether the road is closed is improved, the image recognition is used for judgment, the real-time performance is better, and the road range that can be recognized is more extensive without high-definition images.

[0043] Embodiment two

[0044] Based on the method described in the above embodiment one, the second embodiment of the present application provides a device for determining a road state, which is used to execute the method described in the above embodiment one, and refers to FIG. 5. Figure 5 As shown in FIG. 5, the device 50 for determining a road state comprises:

[0045] The acquisition module 501 is configured to acquire at least one collection image obtained by at least one collection device in a target area of a road, and a positioning location corresponding to the collection image, the positioning location corresponding to the collection image being used to indicate the position of the collection device when the collection image is collected.

[0046] The image positioning module 502 is configured to determine the collection image with the positioning location in a target road in the target area and / or the collection image with the positioning location in an associated road connected with the target road as a target image.

[0047] The image recognition module 503 is configured to perform image recognition on the target image, and determine the road state displayed by the target image according to the image recognition result.

[0048] The aggregation judgment module 504 is configured to determine whether the target road is closed according to the road state displayed by at least one target image.

[0049] Optionally, in a specific example, the aggregation judging module 504 is configured to use a preset aggregation model to calculate the road state shown in the target image, and determine whether the target road is closed according to the calculation result of the aggregation model.

[0050] Optionally, in a specific example, the aggregation judging module 504 is configured to use an aggregation model to determine a closure parameter of the target image according to the road state shown in the target image, calculate a weighted average of the closure parameter of the target image by using the confidence of the target image to obtain a closure probability of the target road as the calculation result of the aggregation model, and determine whether the target road is closed according to the closure probability of the target road.

[0051] Optionally, in a specific example, the aggregation judging module 504 is further configured to calculate the confidence of the target image according to at least one of the acquisition time of the target image, the definition of the target image, and the positioning position of the target image.

[0052] Optionally, in a specific example, the image recognizing module 503 is configured to perform image recognition on the target image, determine whether there is an obstacle on the target road in the target image according to the image recognition result, and determine that the road state shown in the target image is closed if there is an obstacle on the target road in the target image.

[0053] Optionally, in a specific example, the image recognizing module 503 is configured to determine that the road state shown in the target image is not closed if there is no obstacle on the target road in the target image.

[0054] Optionally, in a specific example, the image recognizing module 503 is configured to perform image recognition on the target image, and determine that the road state shown in the target image is unverifiable if it is determined according to the image recognition result that the target image does not contain a road image.

[0055] The device for determining a road state provided in the embodiments of the present application obtains at least one collection image obtained by at least one collection device in the road in the target area, and a positioning position corresponding to the collection image. The positioning position corresponding to the collection image is used to indicate the position of the collection device when the collection image is collected. The collection image of the positioning position in the target road in the target area and / or the collection image of the positioning position in the associated road communicated with the target road is determined as a target image. The target image is subjected to image recognition, and the road state displayed by the target image is determined according to the image recognition result. Whether the target road is closed is determined according to the road state displayed by at least one target image. The image recognition is performed in combination with the images of the target road and the associated road communicated with the target road, does not depend on a single image, improves the accuracy of determining whether the road is closed, uses image recognition to determine, has better real-time performance, does not need high-definition images, and can identify a wider range of roads.

[0056] Embodiment three

[0057] Based on the method described in the above embodiment one, the embodiment three of the present application provides an electronic device for executing the method described in the above embodiment one. Refer to Figure 6 , a structural schematic diagram of an electronic device according to the embodiment three of the present application is shown, and the specific implementation of the electronic device is not limited in the embodiments of the present application.

[0058] As shown in Figure 6 , the electronic device 60 can include a processor 602, a communications interface 604, a memory 606, and a communications bus 608.

[0059] Among them:

[0060] The processor 602, the communications interface 604, and the memory 606 complete the communication among each other through the communications bus 608.

[0061] The communications interface 604 is configured to communicate with other electronic devices or servers.

[0062] The processor 602 is configured to execute the program 610, and specifically can execute the related steps in the above method embodiments for determining a road state.

[0063] Specifically, the program 610 can include program code including computer operation instructions.

[0064] The processor 602 can be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement one or more embodiments of the application. The one or more processors of the smart device can be of the same type, such as one or more CPUs; or can be of different types, such as one or more CPUs and one or more ASICs.

[0065] The memory 606 is configured to store a program 610. The memory 606 can include a high-speed RAM memory, and can further include a non-volatile memory, such as at least one disk memory.

[0066] The program 610 can be specifically configured to cause the processor 602 to perform the method of determining a road state described in Embodiment One. The specific implementation of each step in the program 610 can refer to the corresponding description of the corresponding step and unit in the method of determining a road state described above, and will not be described here. It can be clearly understood by those skilled in the art that, for the convenience and brevity of description, the specific working process of the device and the module described above can refer to the corresponding process description in the foregoing method embodiments, and will not be described here.

[0067] The electronic device provided in the embodiments of the application acquires at least one acquisition image obtained by at least one acquisition device performing image acquisition in a road in a target area, and a positioning position corresponding to the acquisition image, the positioning position corresponding to the acquisition image being used to indicate a position of the acquisition device when the acquisition image is acquired; determines the acquisition image of the positioning position in a target road in the target area and / or the acquisition image of the positioning position in an associated road connected with the target road as a target image; performs image recognition on the target image, determines a road state displayed by the target image according to an image recognition result, and determines whether the target road is closed according to the road state displayed by at least one target image. The image recognition is performed in combination with the images of the target road and the associated road connected with the target road, does not rely on a single image, improves the accuracy of determining whether the road is closed, and uses image recognition to determine, which is better in real time, does not require a high-definition image, and can recognize a wider range of roads.

[0068] Embodiment Four

[0069] Based on the method described in Embodiment One, Embodiment Four of the application provides a computer storage medium having a computer program stored thereon, the program being executed by a processor to implement the method described in Embodiment One.

[0070] Embodiment Five

[0071] Based on the method described in the above embodiment one, the embodiment four of the present application provides a computer program product, which, when executed by a processor, implements the method described in the embodiment one.

[0072] It should be noted that, according to the needs of implementation, each component / step described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or part of the operation of the components / steps can be combined into a new component / step, to achieve the purpose of the embodiments of the present application.

[0073] The above method according to the embodiments of the present application can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium such as a CD ROM, a RAM, a floppy disk, a hard disk or an optical disk, or downloaded through a network and stored in a remote recording medium or a non-transitory machine readable medium and then stored in a local recording medium, so that the method described herein can be processed by such software on a recording medium using a general computer, a special purpose processor or programmable or special hardware such as an ASIC or an FPGA. It can be understood that the computer, the processor, the microprocessor controller or the programmable hardware includes a storage component (for example, RAM, ROM, flash memory, etc.) that can store or receive software or computer code, when the software or computer code is accessed and executed by the computer, the processor or the hardware, the navigation method described herein is implemented. In addition, when the general computer accesses the code for implementing the navigation method shown herein, the execution of the code will convert the general computer into a special computer for executing the navigation method shown herein.

[0074] Those of ordinary skill in the art can realize that the units and method steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of the present application.

[0075] The above embodiments are only used to illustrate the embodiments of the present application, and not to limit the embodiments of the present application. Those skilled in the related art can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application, therefore all equivalent technical solutions also belong to the scope of the embodiments of the present application, the patent protection scope of the embodiments of the present application should be defined by the claims.

Claims

1. A method of determining a road condition, wherein, The method comprises the following steps: acquiring at least one acquisition image obtained by at least one acquisition device in a target area and a positioning position corresponding to the acquisition image, the positioning position corresponding to the acquisition image indicating the position of the acquisition device when the acquisition image is acquired; determining the acquisition image of the positioning position in a target road of the target area and / or the acquisition image of the positioning position in an associated road connected with the target road as a target image; performing image recognition on the target image, and determining the road state displayed by the target image according to the image recognition result; determining whether the target road is closed according to the road state displayed by at least one target image, comprising: performing operation on the road state displayed by the target image by using a preset aggregation model, and determining whether the target road is closed according to the operation result of the aggregation model.

2. The method of claim 1, wherein, The method comprises the following steps: determining the closure parameter of the target image according to the road state displayed by the target image by using the aggregation model; calculating the weighted average of the closure parameter of the target image by using the confidence of the target image to obtain the closure probability of the target road as the operation result of the aggregation model; determining whether the target road is closed according to the closure probability of the target road.

3. The method of claim 2, wherein, The method further comprises the following steps: calculating the confidence of the target image according to at least one of the acquisition time of the target image, the definition of the target image, and the positioning position of the target image.

4. The method of claim 1, wherein, The method comprises the following steps: performing image recognition on the target image, and determining whether there is an obstacle on the target road in the target image according to the image recognition result; if there is an obstacle on the target road in the target image, determining that the road state displayed by the target image is closed.

5. The method of claim 4, wherein, The method comprises the following steps: if there is no obstacle on the target road in the target image, determining that the road state displayed by the target image is not closed.

6. The method according to any one of claims 1 to 5, wherein, The method comprises the following steps: performing image recognition on the target image, and if it is determined that the target image does not contain the image of the road according to the image recognition result, determining that the road state displayed by the target image cannot be verified.

7. An electronic device comprising: a processor, a memory, a communication interface, and a communication bus, the processor, the memory, and the communication interface performing communication with each other through the communication bus; the memory is used to store at least one executable instruction, and the executable instruction makes the processor execute the operation corresponding to the method for determining the road state according to any one of claims 1-6.

8. A storage medium having stored thereon a computer program which, when executed by a processor, implements the method of determining a road condition according to any one of claims 1-6.

9. A computer program product which, when executed by a processor, implements the method of determining a road condition according to any one of claims 1-6.

Images