A method, apparatus, device, and readable storage medium for identifying elevated structures.

Abstract

This application relates to an elevated road identification method, apparatus, device, and readable storage medium, belonging to the field of positioning technology. The method includes: when a vehicle is detected to be in an elevated area, acquiring greenery feature information of the elevated area where the vehicle is located via a camera; matching the greenery feature information of the elevated area with greenery feature information of non-elevated areas; if the greenery feature information of the elevated area and the non-elevated area successfully match, it is determined that the vehicle is on an elevated road; if the greenery feature information of the elevated area and the non-elevated area fail to match, it is determined that the vehicle is below an elevated road. This application can accurately determine whether the road where the vehicle is located is elevated by using greenery feature information, thereby accurately identifying whether the vehicle is on an elevated road, without needing to obtain vehicle speed, elevation changes, and parking status through GNSS signals and inertial navigation sensors, thus effectively improving the accuracy of elevated road identification results.

Description

Technical Field

[0001] This application relates to the field of positioning technology, and in particular to an elevated identification method, apparatus, device, and readable storage medium. Background Technology

[0002] Elevated roads, often simply called viaducts, are three-dimensional roads constructed to alleviate urban traffic congestion. When a car travels through an elevated area, the GPS (Global Positioning System) latitude and longitude coordinates of the upper and lower levels of the viaduct are very similar, often leading to errors in determining whether the car is on or below the viaduct. This can result in route matching errors, mis-deviations, and other problems, affecting the user's navigation experience and even driving safety.

[0003] In existing technologies, GNSS (Global Navigation Satellite System) signals and inertial navigation sensors are often used to obtain vehicle speed, elevation changes, and parking status to identify whether a vehicle is on an elevated road. However, in urban areas, obstructions from buildings and elevated bridges can weaken or even render GNSS signals unusable, resulting in poor accuracy of the acquired vehicle status information. This, in turn, affects the identification of whether a vehicle is on an elevated road, leading to lower accuracy in the identification results. Furthermore, although traffic regulations typically require vehicles to maintain a certain speed on elevated roads, congestion during rush hour often results in vehicles reaching zero speed on elevated roads. Therefore, relying on whether a vehicle is stopped to determine whether it is on an elevated road also tends to result in low accuracy. Summary of the Invention

[0004] This application provides an elevated road identification method, apparatus, device, and readable storage medium to solve the problem of low accuracy of elevated road identification results in related technologies.

[0005] Firstly, an elevated road identification method is provided, comprising the following steps:

[0006] When a vehicle is detected to be in an elevated area, the camera acquires information about the green features of the elevated area where the vehicle is located.

[0007] The greening feature information of the elevated area is matched with the greening feature information of the non-elevated area;

[0008] If the greening feature information of the elevated area matches the greening feature information of the non-elevated area, then it is determined that the vehicle is on the elevated road.

[0009] If the greening feature information of the elevated area does not match the greening feature information of the non-elevated area, the vehicle is determined to be below the elevated area.

[0010] In some embodiments, the elevated area greening feature information includes the elevated greening mean and elevated greening variance, and the non-elevated area greening feature information includes the non-elevated greening mean and non-elevated greening variance.

[0011] In some embodiments, if the greening feature information of the elevated area successfully matches the greening feature information of the non-elevated area, it includes:

[0012] If the difference between the average value of elevated greening and the average value of non-elevated greening is greater than the greening average threshold and the difference between the variance value of elevated greening and the variance value of non-elevated greening is greater than the greening variance threshold, then it is determined that the greening feature information of the elevated area and the greening feature information of the non-elevated area are successfully matched.

[0013] In some embodiments, before the step of acquiring the greening feature information of the elevated area where the vehicle is located via a camera when the vehicle is detected to be in an elevated area, the method further includes:

[0014] The camera acquires information about the greenery features of the non-elevated area when the vehicle is in a non-elevated area.

[0015] In some embodiments, after the step of acquiring the greening feature information of the non-elevated area corresponding to the vehicle being in a non-elevated area via the camera, the method further includes:

[0016] Weights are assigned to the mean and variance of non-elevated greening in the non-elevated area greening feature information based on the distance between the vehicle and the elevated area.

[0017] Based on the weights, the mean value of the non-elevated green space and the variance value of the non-elevated green space are subjected to weighted average filtering to obtain the updated mean value of the non-elevated green space and the updated variance value of the non-elevated green space.

[0018] The updated mean value of non-elevated green space and the updated variance value of non-elevated green space are used as new green space feature information for non-elevated areas. Based on the new green space feature information for non-elevated areas, the step of obtaining the elevated area green space feature information of the vehicle's location through a camera when a vehicle is detected to be in an elevated area is executed.

[0019] In some embodiments, acquiring the greening feature information of the non-elevated area corresponding to when the vehicle is in a non-elevated area via the camera includes:

[0020] The starting position of the non-elevated area is determined based on the preset distance and the starting position of the elevated area;

[0021] The camera acquires information about the greening features of the non-elevated area when the vehicle is located between the starting position of the non-elevated area and the starting position of the elevated area.

[0022] In some embodiments, after the step of determining that the vehicle is on an elevated road, the method further includes:

[0023] When the vehicle is detected to re-enter the non-elevated area, the greening feature information of the non-elevated area is deleted, and the greening feature information of the non-elevated area is extracted again.

[0024] Secondly, an elevated identification device is provided, comprising:

[0025] The acquisition unit is used to acquire, through a camera, the greening feature information of the elevated area where the vehicle is located when the vehicle is detected to be in an elevated area.

[0026] A matching unit is used to match the greening feature information of the elevated area with the greening feature information of the non-elevated area;

[0027] The identification unit is used to determine that the vehicle is on the elevated road if the greening feature information of the elevated area matches the greening feature information of the non-elevated area; and to determine that the vehicle is below the elevated road if the greening feature information of the elevated area does not match the greening feature information of the non-elevated area.

[0028] Thirdly, an elevated road identification device is provided, comprising: a memory and a processor, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the aforementioned elevated road identification method.

[0029] Fourthly, a computer-readable storage medium is provided, the computer storage medium storing a computer program that, when executed by a processor, implements the aforementioned elevated road identification method.

[0030] The beneficial effects of the technical solution provided in this application include: it can accurately identify whether a vehicle is on an elevated road, thus improving the accuracy of elevated road identification results.

[0031] This application provides an elevated road identification method, apparatus, device, and readable storage medium. The method includes: when a vehicle is detected to be in an elevated area, acquiring greenery feature information of the elevated area where the vehicle is located via a camera; matching the greenery feature information of the elevated area with greenery feature information of non-elevated areas; if the greenery feature information of the elevated area and the non-elevated area successfully match, determining that the vehicle is on an elevated road; if the greenery feature information of the elevated area and the non-elevated area fail to match, determining that the vehicle is below an elevated road. This application can accurately determine whether the road where the vehicle is located is elevated or not through greenery feature information, thus accurately identifying whether the vehicle is on an elevated road, without needing to obtain vehicle operating condition information such as vehicle speed, elevation changes, and parking status through GNSS signals and inertial navigation sensors, thereby effectively improving the accuracy of elevated road identification results. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 A flowchart illustrating an elevated road identification method provided in an embodiment of this application;

[0034] Figure 2 This is a schematic diagram of the structure of an elevated identification device provided in an embodiment of this application;

[0035] Figure 3 This is a structural schematic diagram of an elevated identification device provided in an embodiment of this application. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0037] This application provides an elevated road identification method, apparatus, device, and readable storage medium, which can solve the problem of low accuracy of elevated road identification results in related technologies.

[0038] To achieve the above objectives, the overall approach of this application is as follows:

[0039] An elevated road identification method, the method comprising the following steps:

[0040] Step S10: When a vehicle is detected to be in an elevated area, the greening feature information of the elevated area where the vehicle is located is obtained through a camera;

[0041] Step S20: Match the greening feature information of the elevated area with the greening feature information of the non-elevated area;

[0042] Step S30: If the greening feature information of the elevated area matches the greening feature information of the non-elevated area, then it is determined that the vehicle is on the elevated road;

[0043] Step S40: If the greening feature information of the elevated area does not match the greening feature information of the non-elevated area, then it is determined that the vehicle is under the elevated road.

[0044] The embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0045] See Figure 1 As shown in the figure, this application provides an elevated road identification method, including the following steps:

[0046] Step S10: When a vehicle is detected to be in an elevated area, the greening feature information of the elevated area where the vehicle is located is acquired through a camera; wherein, the greening feature information of the elevated area includes the mean value and variance value of the elevated greening.

[0047] As an example, it is understandable that with the development of major cities in China, roadside greening in urban areas has become increasingly standardized and widespread, resulting in large shrub beds or trees typically lining both sides of roads. However, on elevated roads, due to environmental constraints, the amount of greenery on both sides is limited and the plants are short, showing a significant difference from the greening of ordinary roads. Therefore, this embodiment uses greening information as a starting point to determine whether a vehicle is on or below an elevated road.

[0048] It should be understood that this embodiment can obtain the real-time location information of the vehicle through GPS positioning, and determine whether the vehicle has entered the elevated area based on the real-time location information. If the vehicle is detected to be in the elevated area, the vehicle-mounted camera can capture images of the roadside near the vehicle and extract the greening information on both sides of the road. This greening information includes, but is not limited to, roadside greening such as flower beds and trees. Then, the green and non-green parts of the image are automatically segmented and divided, and semantic labels are added to each pixel of the two parts, i.e., green is 1 and non-green is 0. Then, feature extraction is performed through pixel proportion distribution or distribution analysis to obtain the elevated area greening feature information, including the elevated greening mean and elevated greening variance values ​​used to describe the greening features.

[0049] One specific method for feature extraction based on pixel proportion distribution is as follows: In elevated areas, calculate the pixel proportion of green areas in the image, set a distance threshold (e.g., 100 meters), construct a distance sliding window, and calculate the mean and variance of the pixel proportion data within the window; as the vehicle moves, gradually update the mean and variance; if the pixel proportion x obtained in a certain frame makes |x-mean|>3×sigma, it means that the green environment has changed significantly, record the vehicle coordinates at this time, and do not include the pixel proportion data of this frame in the sliding window; if the pixel proportion x makes |x-mean|>3×sigma for 100 meters consecutively, clear the sliding window data and recalculate the mean and variance. Distribution analysis can be performed as follows: Treat the green areas in the image as a two-dimensional Gaussian distribution, calculate the mean and covariance of the green pixels. The mean and covariance are analogous to the pixel proportion data, and their processing method is the same; for simplicity, it will not be elaborated further here.

[0050] Furthermore, before the step of acquiring the greenery feature information of the elevated area where the vehicle is located via a camera when the vehicle is detected to be in an elevated area, the method further includes:

[0051] The camera acquires the greening feature information of the non-elevated area when the vehicle is in a non-elevated area; wherein, the greening feature information of the non-elevated area includes the mean value of the non-elevated greening and the variance value of the non-elevated greening.

[0052] As an example, in this embodiment, based on the continuity and similarity of roadside greenery within the urban area, when it is determined that a vehicle has entered a non-elevated area based on its real-time location information, continuous shooting by the onboard camera can be used to extract greenery information on both sides of the road in the non-elevated area. The image is then automatically segmented and divided into green and non-green parts. Semantic labels are added to each pixel in both parts, i.e., green is 1 and non-green is 0. Feature extraction is then performed using methods such as pixel proportion distribution or two-dimensional Gaussian distribution, and recorded as the non-elevated area greenery feature information, which includes the mean and variance of the non-elevated greenery. It should be noted that if the vehicle is an autonomous vehicle, the greenery features can be directly output from the perception module.

[0053] Furthermore, the step of acquiring the greening feature information of the non-elevated area corresponding to the vehicle being in a non-elevated area through the camera includes:

[0054] The starting position of the non-elevated area is determined based on the preset distance and the starting position of the elevated area;

[0055] The camera acquires information about the greenery features of the non-elevated area when the vehicle is positioned between its starting position in the non-elevated area and its starting position in the elevated area.

[0056] Understandably, to avoid unnecessary calculations, and given the continuity and similarity of greening features, feature extraction can begin or end at a certain distance from the elevated area. For example, at a distance of 50 meters from the elevated area (i.e., a preset distance of 50 meters), the extraction and calculation of greening feature information for non-elevated areas outside the elevated area can begin, without needing to extract greening features for non-elevated areas beyond 50 meters from the elevated area. It should be noted that the specific value of the preset distance can be determined according to actual needs and is not limited here.

[0057] Furthermore, after the step of acquiring the greening feature information of the non-elevated area corresponding to the vehicle being in a non-elevated area via the camera, the method further includes:

[0058] Weights are assigned to the mean and variance of non-elevated greening in the non-elevated area greening feature information based on the distance between the vehicle and the elevated area.

[0059] Based on the weights, the mean value of the non-elevated green space and the variance value of the non-elevated green space are subjected to weighted average filtering to obtain the updated mean value of the non-elevated green space and the updated variance value of the non-elevated green space.

[0060] The updated mean value of non-elevated green space and the updated variance value of non-elevated green space are used as new green space feature information for non-elevated areas. Based on the new green space feature information for non-elevated areas, the step of obtaining the elevated area green space feature information of the vehicle's location through a camera when a vehicle is detected to be in an elevated area is executed.

[0061] As an example, in this embodiment, feature extraction is performed using pixel proportion distribution: Before a vehicle enters the elevated area, the mean and variance sequence of the pixel proportion of the green features in the non-elevated area are obtained. At this time, a weighted average filtering method can be used to filter the mean and variance sequences, and weights are set according to the distance of the vehicle from the elevated area. As the distance decreases, the weights increase, thus obtaining the weighted mean and variance. The weighted mean and variance are then used as the final green feature information of the non-elevated area, making the extracted green features of the non-elevated area more accurate and more in line with the actual road conditions.

[0062] Step S20: Match the greening feature information of the elevated area with the greening feature information of the non-elevated area;

[0063] Exemplary and understandable, after obtaining the greening feature information of elevated areas corresponding to elevated areas and the greening feature information of non-elevated areas corresponding to non-elevated areas, the mean value of elevated greening in the greening feature information of elevated areas will be matched with the mean value of non-elevated greening in the greening feature information of non-elevated areas, and the variance value of elevated greening in the greening feature information of elevated areas will be matched with the variance value of non-elevated greening in the greening feature information of non-elevated areas to obtain the matching result. Based on the matching result, it is possible to accurately identify whether a vehicle is on an elevated road.

[0064] Step S30: If the greening feature information of the elevated area matches the greening feature information of the non-elevated area, then it is determined that the vehicle is on the elevated road;

[0065] Specifically, if the greening feature information of the elevated area successfully matches the greening feature information of the non-elevated area, it includes:

[0066] If the difference between the average value of elevated greening and the average value of non-elevated greening is greater than the greening average threshold and the difference between the variance value of elevated greening and the variance value of non-elevated greening is greater than the greening variance threshold, then it is determined that the greening feature information of the elevated area and the greening feature information of the non-elevated area are successfully matched.

[0067] In this exemplary embodiment, the difference between the average greening value of elevated roads and the average greening value of non-elevated roads is obtained by subtracting the average greening value of elevated roads. Similarly, the difference between the variance of elevated roads and the variance of non-elevated roads is obtained by subtracting the variance of elevated roads. These differences represent the deviation between the vehicle's location and the non-elevated area, indicating whether the vehicle is on an elevated road or not. Therefore, when both the difference between the average greening value and the variance of the greening value are greater than the average greening value threshold and the variance of the greening value are greater than the variance of the greening value threshold, it indicates a significant deviation between the greening characteristics of the elevated area and the non-elevated area. This confirms a successful match between the greening characteristics of the elevated area and the non-elevated area, thus determining that the vehicle is on an elevated road. It should be noted that the specific values ​​of the average greening value threshold and the variance of the greening value threshold can be determined according to actual needs and are not limited here.

[0068] Step S40: If the greening feature information of the elevated area does not match the greening feature information of the non-elevated area, then it is determined that the vehicle is under the elevated road.

[0069] Exemplary and understandable, when the difference in greening mean is less than or equal to the greening mean threshold and / or the difference in greening variance is less than or equal to the greening variance threshold, that is, as long as at least one of the difference in greening mean and the difference in greening variance is not greater than its corresponding threshold, it indicates that the deviation between the greening characteristics of the elevated area where the vehicle is located and the greening characteristics of the non-elevated area is very small, that is, the vehicle is on the lower level of the elevated area. Therefore, it can be determined that the greening characteristic information of the elevated area and the greening characteristic information of the non-elevated area have not been successfully matched, and thus it can be determined that the vehicle is under the elevated area.

[0070] Furthermore, after the step of determining that the vehicle is on an elevated road, the following steps are also included:

[0071] When the vehicle is detected to re-enter the non-elevated area, the greening feature information of the non-elevated area is deleted, and the greening feature information of the non-elevated area is extracted again.

[0072] As an example, in this embodiment, when it is determined that the vehicle has exited the elevated road and re-entered the non-elevated area based on the vehicle's real-time location information, the greening feature information of the non-elevated area will be cleared, and the extraction of greening information on both sides of the road in the non-elevated area will start again to maintain the optimal local greening features, thereby effectively improving the accuracy of the elevated road recognition results.

[0073] Therefore, this embodiment fully utilizes the feature extraction function of the vehicle-mounted perception module to obtain descriptive parameters of green features (i.e., green feature information), which greatly reduces the computational load of elevated road recognition. Through the green feature information, it can accurately determine whether the road where the vehicle is located is elevated or not, and thus accurately identify whether the vehicle is on an elevated road. This eliminates the need to rely on environmentally sensitive sensors such as GNSS and barometers to obtain vehicle operating condition information such as vehicle speed, elevation changes, and parking status, thereby effectively improving the accuracy and precision of elevated road recognition results and providing better robustness.

[0074] See Figure 2 As shown in the figure, this application embodiment also provides an elevated road identification device, including:

[0075] The acquisition unit is used to acquire, through a camera, the greening feature information of the elevated area where the vehicle is located when the vehicle is detected to be in an elevated area.

[0076] A matching unit is used to match the greening feature information of the elevated area with the greening feature information of the non-elevated area;

[0077] The identification unit is used to determine that the vehicle is on the elevated road if the greening feature information of the elevated area matches the greening feature information of the non-elevated area; and to determine that the vehicle is below the elevated road if the greening feature information of the elevated area does not match the greening feature information of the non-elevated area.

[0078] Furthermore, the greening characteristic information of the elevated area includes the mean value and variance value of the elevated greening, and the greening characteristic information of the non-elevated area includes the mean value and variance value of the non-elevated greening.

[0079] Furthermore, the matching unit is specifically used for:

[0080] If the difference between the average value of elevated greening and the average value of non-elevated greening is greater than the greening average threshold and the difference between the variance value of elevated greening and the variance value of non-elevated greening is greater than the greening variance threshold, then it is determined that the greening feature information of the elevated area and the greening feature information of the non-elevated area are successfully matched.

[0081] Furthermore, the acquisition unit shown is also used for:

[0082] The camera acquires information about the greenery features of the non-elevated area when the vehicle is in a non-elevated area.

[0083] Furthermore, the acquisition unit shown is also used for:

[0084] Weights are assigned to the mean and variance of non-elevated greening in the non-elevated area greening feature information based on the distance between the vehicle and the elevated area.

[0085] Based on the weights, the mean value of the non-elevated green space and the variance value of the non-elevated green space are subjected to weighted average filtering to obtain the updated mean value of the non-elevated green space and the updated variance value of the non-elevated green space.

[0086] The updated mean value of non-elevated green space and the updated variance value of non-elevated green space are used as new green space feature information for non-elevated areas. Based on the new green space feature information for non-elevated areas, the step of obtaining the elevated area green space feature information of the vehicle's location through a camera when a vehicle is detected to be in an elevated area is executed.

[0087] Furthermore, the acquisition unit is specifically used for:

[0088] The starting position of the non-elevated area is determined based on the preset distance and the starting position of the elevated area;

[0089] The camera acquires information about the greening features of the non-elevated area when the vehicle is located between the starting position of the non-elevated area and the starting position of the elevated area.

[0090] Furthermore, the acquisition unit is also used for:

[0091] When the vehicle is detected to re-enter the non-elevated area, the greening feature information of the non-elevated area is deleted, and the greening feature information of the non-elevated area is extracted again.

[0092] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the device and each unit described above can be referred to the corresponding processes in the aforementioned embodiments of the elevated road identification method, and will not be repeated here.

[0093] The elevated identification device provided in the above embodiments can be implemented as a computer program, which can, for example, Figure 3 It operates on the elevated identification equipment shown.

[0094] This application also provides an elevated road identification device, including: a memory, a processor, and a network interface connected via a system bus. The memory stores at least one instruction, which is loaded and executed by the processor to implement all or part of the steps of the aforementioned elevated road identification method.

[0095] The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0096] A processor can be a CPU, or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor, or any conventional processor. The processor is the control center of a computer device, connecting all parts of the computer device through various interfaces and lines.

[0097] Memory can be used to store computer programs and / or modules. The processor performs various functions of the computer device by running or executing the computer programs and / or modules stored in the memory, and by accessing data stored in the memory. Memory can primarily include a program storage area and a data storage area. The program storage area can store the operating system, application programs required for at least one function (such as video playback, image playback, etc.), etc.; the data storage area can store data created based on the use of the mobile phone (such as video data, image data, etc.). Furthermore, memory can include high-speed random access memory (RAM), and can also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, SmartMedia Cards (SMC), Secure Digital Cards (SD cards), Flash Cards, at least one disk storage device, flash memory devices, or other volatile solid-state storage devices.

[0098] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements all or part of the steps of the aforementioned elevated road identification method.

[0099] The embodiments of this application can implement all or part of the aforementioned processes, or they can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various methods described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0100] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, servers, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0101] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0102] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can 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 a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0103] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. An overhead identification method characterized by, The method comprises the following steps: when it is detected that the vehicle is in the elevated area, acquiring, by a camera, elevated area greening feature information of a position where the vehicle is located; matching the elevated area greening feature information with non-elevated area greening feature information, wherein the elevated area greening feature information comprises an elevated greening mean value and an elevated greening variance value, and the non-elevated area greening feature information comprises a non-elevated greening mean value and a non-elevated greening variance value; if the elevated area greening feature information and the non-elevated area greening feature information are successfully matched, determining that the vehicle is on the elevated area; if the elevated area greening feature information and the non-elevated area greening feature information are not successfully matched, determining that the vehicle is under the elevated area; wherein, before the step of acquiring, by the camera, the elevated area greening feature information of the position where the vehicle is located when it is detected that the vehicle is in the elevated area, the method further comprises: acquiring, by the camera, corresponding non-elevated area greening feature information when the vehicle is in the non-elevated area; setting weights for the non-elevated greening mean value and the non-elevated greening variance value in the non-elevated area greening feature information according to the distance between the vehicle and the elevated area; performing weighted average filtering on the non-elevated greening mean value and the non-elevated greening variance value based on the weights to obtain an updated non-elevated greening mean value and an updated non-elevated greening variance value; taking the updated non-elevated greening mean value and the updated non-elevated greening variance value as new non-elevated area greening feature information, and performing the step of acquiring, by the camera, the elevated area greening feature information of the position where the vehicle is located when it is detected that the vehicle is in the elevated area based on the new non-elevated area greening feature information.

2. The overhead identification method of claim 1, wherein, if the difference between the elevated greening mean value and the non-elevated greening mean value is greater than a greening mean value threshold value and the difference between the elevated greening variance value and the non-elevated greening variance value is greater than a greening variance threshold value, determining that the elevated area greening feature information and the non-elevated area greening feature information are successfully matched. determining a starting position of the non-elevated area according to a preset distance and a starting position of the elevated area; 3. The overhead identification method of claim 1, wherein, acquiring, by the camera, corresponding non-elevated area greening feature information when the vehicle is between the starting position of the non-elevated area and the starting position of the elevated area. after the step of determining that the vehicle is on the elevated area, the method further comprises: when it is detected that the vehicle reenters the non-elevated area, deleting the non-elevated area greening feature information and reextracting greening feature information of the non-elevated area.

4. The overhead identification method of claim 1, wherein, comprises: an acquisition unit configured to acquire, by a camera, elevated area greening feature information of a position where the vehicle is located when it is detected that the vehicle is in the elevated area; 5. An overhead identification device characterized by, ​ ​ The matching unit is configured to match the elevated area greening feature information and non-elevated area greening feature information, wherein the elevated area greening feature information comprises an elevated greening mean value and an elevated greening variance value, and the non-elevated area greening feature information comprises a non-elevated greening mean value and a non-elevated greening variance value; The recognition unit is configured to determine that the vehicle is on an elevated road if the elevated area greening feature information and the non-elevated area greening feature information are successfully matched, and determine that the vehicle is under an elevated road if the elevated area greening feature information and the non-elevated area greening feature information are not successfully matched. The acquisition unit is further configured to: acquire, by the camera, non-elevated area greening feature information corresponding to a situation in which the vehicle is in a non-elevated area; set weights for the non-elevated greening mean value and the non-elevated greening variance value in the non-elevated area greening feature information according to the distance between the vehicle and the elevated area; perform weighted average filtering on the non-elevated greening mean value and the non-elevated greening variance value based on the weights, to obtain an updated non-elevated greening mean value and an updated non-elevated greening variance value; use the updated non-elevated greening mean value and the updated non-elevated greening variance value as new non-elevated area greening feature information, and perform the step of acquiring, by the camera, elevated area greening feature information of a position where the vehicle is located when the vehicle is detected to be in an elevated area, based on the new non-elevated area greening feature information.

6. An overhead identification apparatus, characterized by The method comprises: a memory and a processor, wherein at least one instruction is stored in the memory, and the at least one instruction is loaded and executed by the processor to implement the elevated road recognition method in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer storage medium stores a computer program, and when the computer program is executed by the processor, the elevated road recognition method in any one of claims 1 to 4 is implemented.

Images