Method, device, storage medium and product for determining validity of lane guide sign

Abstract

The present disclosure provides a method, device, storage medium and product for determining the effectiveness of a lane guide sign, relates to the technical field of ground transportation, and particularly relates to the technical field of the specification / effectiveness arrangement of ground guide arrows of road traffic markings. The specific implementation scheme is as follows: an image of a target lane is recognized, and a guide sign of the target lane in the image is extracted; the key feature dimensions of the guide sign contour are calculated; and the effectiveness of the guide sign is determined based on the key feature dimensions. The present disclosure can improve the road data production efficiency.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of ground transportation, in particular to the technical field of specification / effectiveness arrangement of road traffic marking ground guide arrows, and more particularly to a method and device for determining effectiveness of lane guide signs, a storage medium and a product. BACKGROUND

[0002] Road traffic marking ground guide can play a role in regulating and guiding traffic. The integrity of the ground guide standard can also better guarantee traffic safety and guide civilized driving.

[0003] However, the ground road is constantly being revised, such as paving asphalt, which may cover the ground guide signs. SUMMARY

[0004] The present disclosure provides a method and device for determining effectiveness of lane guide signs, a storage medium and a product.

[0005] According to a first aspect of the present disclosure, a method for determining effectiveness of lane guide signs is provided, the method comprising:

[0006] identifying an image containing a lane and extracting a guide sign of a target lane in the image; calculating a key feature dimension of a contour of the guide sign; and determining effectiveness of the guide sign based on the key feature dimension.

[0007] According to a second aspect of the present disclosure, a device for determining effectiveness of lane guide signs is provided, the device comprising:

[0008] an extraction module configured to identify an image containing a lane and extract a guide sign of a target lane in the image; a calculation module configured to calculate a key feature dimension of a contour of the guide sign; and a determination module configured to determine effectiveness of the guide sign based on the key feature dimension.

[0009] According to a third aspect of the present disclosure, an electronic device is provided, comprising:

[0010] at least one processor; and a memory communicatively connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of the first aspect.

[0011] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to perform the method of the first aspect.

[0012] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method according to the first aspect.

[0013] It should be understood that the matters described herein are intended to be illustrative rather than limiting. For example, while the application is described in terms of specific embodiments of a system, those skilled in the art will recognize that the application is not limited to the embodiments specifically described. Indeed, any suitable method, apparatus, or material described herein can be used with the application. BRIEF DESCRIPTION OF DRAWINGS

[0014] The accompanying drawings are included to provide a further understanding of the application, and are incorporated in and constitute a part of this specification. In the drawings:

[0015] Figure 1 A schematic diagram of a lane guide sign according to an embodiment of the present disclosure is shown;

[0016] Figure 2 A schematic diagram of a lane guide sign according to an embodiment of the present disclosure is shown;

[0017] Figure 3 A schematic diagram of a lane guide sign according to an embodiment of the present disclosure is shown;

[0018] Figure 4 A flowchart of a method of determining lane guide sign validity according to an embodiment of the present disclosure is shown;

[0019] Figure 5 A schematic diagram of lane division line recognition according to an embodiment of the present disclosure is shown;

[0020] Figure 6 A schematic diagram of determining a partial image containing a lane according to an embodiment of the present disclosure is shown;

[0021] Figure 7 A flowchart of a method of determining lane guide sign validity according to an embodiment of the present disclosure is shown;

[0022] Figure 8 A schematic diagram of determining a lane division line slope according to an embodiment of the present disclosure is shown;

[0023] Figure 9 A schematic diagram of extracting a guide sign within a target lane according to an embodiment of the present disclosure is shown;

[0024] Figure 10 A schematic diagram of combining guide signs according to an embodiment of the present disclosure is shown;

[0025] Figure 11 A schematic diagram of guide sign recognition according to an embodiment of the present disclosure is shown;

[0026] Figure 12 Fig. 6 shows a schematic diagram of another lane guide sign according to an embodiment of the present disclosure;

[0027] Figure 13 Fig. 7 shows a flowchart of a method for determining the validity of the lane guide sign according to an embodiment of the present disclosure;

[0028] Figure 14 Fig. 8 shows a structural diagram of an apparatus for determining the validity of the lane guide sign according to an embodiment of the present disclosure;

[0029] Figure 15 Fig. 9 is a block diagram of an electronic device for implementing the method for determining the validity of the lane guide sign according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] Exemplary embodiments of the present disclosure are described herein with reference to the accompanying drawings, in which various details of the embodiments of the present disclosure are set forth to assist in the understanding of the present disclosure. It will be apparent to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, the description herein omits well-known functions and constructions in order to make the present disclosure more apparent and concise.

[0031] Road traffic marking ground guide can play a role in regulating and guiding traffic. The integrity of the ground guide standard can also better guarantee traffic safety and guide civilized driving.

[0032] However, the ground road is constantly being modified, such as paving asphalt, etc., which can cover the ground guide sign, resulting in the invalidation of the lane guide sign. For example, Figure 1 Fig. 4 shows a schematic diagram of a lane guide sign with complete guide arrows according to an embodiment of the present disclosure, as shown in Figure 1 The guide arrows on the road surface are clearly visible. When the road surface is repaved with asphalt, only a small part of the guide arrows remains. Figure 2 Fig. 5 shows a schematic diagram of a lane guide sign with partial guide arrows according to an embodiment of the present disclosure, as shown in Figure 2 The guide arrows are not complete and cannot clearly determine the driving direction indicated by the guide sign.

[0033] The guide sign can also be incomplete due to wear and tear of road vehicles. For example, Figure 3 Fig. 6 shows a schematic diagram of a lane guide sign with partial guide arrows according to an embodiment of the present disclosure, as shown in Figure 3 The wear and tear of the guide arrows is quite serious and close to invalidation.

[0034] In the related art, the effectiveness of the current lane guide sign is mainly determined by manual judgment, and the current lane guide sign needs to be determined manually, so the workload is very large.

[0035] Therefore, in order to improve the road data production efficiency, the present disclosure provides a method and device for determining the effectiveness of the lane guide sign. By collecting the image of the lane, the guide sign in the image is identified. According to the key feature dimension of the identified guide sign, the integrity of the guide sign is determined, thereby determining the effectiveness probability of the guide sign. The effectiveness of the guide sign is determined by calculating the effectiveness probability, which can improve the road data production efficiency.

[0036] The following embodiments will be described in conjunction with the accompanying drawings.

[0037] Figure 4 A flowchart of a method for determining the effectiveness of a lane guide sign according to an embodiment of the present disclosure is shown in FIG. 1. Figure 4 The method can include the following steps.

[0038] In step S110, an image containing a lane is identified, and a guide sign of a target lane in the image is extracted.

[0039] In the embodiment of the present disclosure, the target lane is determined by extracting the lane segmentation line of the image containing the lane. Figure 5 A schematic diagram of identifying a lane segmentation line according to an embodiment of the present disclosure is shown in FIG. 2. Figure 5 As shown in FIG. 2, an image of a target lane is identified to obtain an image marked with a lane segmentation line.

[0040] The part of the image containing the lane is determined, and the other part of the image except the part containing the lane is removed. Figure 6 A schematic diagram of determining the part of the image containing the lane according to an embodiment of the present disclosure is shown in FIG. 3. Figure 6 As shown in FIG. 3, the part of the image including the lane is selected. The part of the image including the lane is identified to obtain the guide sign of the target lane.

[0041] In step S120, the key feature dimension of the guide sign contour is calculated.

[0042] In the embodiment of the present disclosure, the key feature dimension of the guide sign contour is further determined according to the obtained guide sign of the target lane.

[0043] In the present disclosure, the key feature dimension at least includes a combination distribution feature, a gray mean value feature, a gradient change feature, and a contour area matching feature.

[0044] In step S130, the effectiveness of the guide sign is determined based on the key feature dimension.

[0045] In the present disclosure, the determined key features including the combination distribution feature, the gray mean value feature, the gradient change feature and the contour area matching feature are weighted and calculated, and the probability value of the effectiveness of the target lane guide sign is determined after normalization. The effectiveness of the target lane guide sign is determined according to the calculated probability value.

[0046] By calculating the key features of the guide sign in the present disclosure, the effectiveness probability of the guide sign can be calculated, and the effectiveness probability of the guide sign can be obtained by calculating the weight of each key feature. The effectiveness of the lane guide sign can be automatically analyzed without manual judgment, the road data production efficiency is improved, and the effectiveness of the lane sign can be determined.

[0047] Figure 7 A flowchart of a method for determining the effectiveness of a lane guide sign according to an embodiment of the present disclosure is shown in FIG. 1. As shown in FIG. 1, the method can include the following steps. Figure 7

[0048] In step S210, lane division markings in the image are identified, and the target lane is determined based on the slope of the lane division markings.

[0049] In the present disclosure, the lane division markings in the image can be identified, and the slope of each lane division line can be determined. Figure 8 A schematic diagram of determining the slope of a lane division line according to an embodiment of the present disclosure is shown in FIG. 2. As shown in FIG. 2, lane division lines with the same slope are determined as a set, the lane division lines in the set are on the same straight line, and the target lane is determined based on the lane division lines. Wherein, the left and right lane division lines are determined as a lane unit. Figure 8

[0050] In the present disclosure, the lane guide sign identified can be a lane unit or the entire lane.

[0051] In step S220, the guide sign in the target lane is extracted.

[0052] In the present disclosure, after the target lane is determined, the guide sign in the target lane is extracted. Figure 9 A schematic diagram of extracting the guide sign in the target lane according to an embodiment of the present disclosure is shown in FIG. 3. As shown in FIG. 3, after determining that there is a guide sign in the lane, the guide sign contour edge in the lane is extracted based on the color difference between the road surface color and the guide sign color. Figure 9

[0053] In the present disclosure, the key feature dimension includes the combination distribution feature. In the present disclosure, the combination feature refers to the presence of multiple guide signs at the same position in the same lane unit.

[0054] ​​​For example, Figure 10 A schematic diagram of a combined guide sign is shown in the embodiment of the present disclosure, as shown in Figure 10 As shown in the embodiment of the present disclosure, there are two straight guide signs in the same lane, i.e., there are multiple guide signs of different sizes in the same position within a lane range.

[0055] In the present disclosure, the distribution of guide signs in the same lane is identified, and the combined distribution characteristics of the guide signs are calculated based on the distribution.

[0056] In the embodiment of the present disclosure, the key feature dimension includes the gray mean feature. That is, the average gray value of the guide arrow profile needs to be identified in the present disclosure.

[0057] For example, Figure 11 A schematic diagram of identifying a guide sign is shown in the embodiment of the present disclosure, as shown in Figure 11 As shown in the embodiment of the present disclosure, part of the profile of the guide sign has been missing. Figure 12 A schematic diagram of identifying a guide sign is shown in the embodiment of the present disclosure, as shown in Figure 12 As shown in the embodiment of the present disclosure, there are two guide signs of straight and left turn. The guide signs of straight and left turn are identified, the gray values of different positions of each guide sign are determined, and the gray mean features of each guide sign are calculated. It is determined that the gray mean of the guide sign of left turn is greater than that of the guide sign of straight. Thus, it is determined that the guide sign of left turn has high clarity.

[0058] In the embodiment of the present disclosure, the key feature dimension includes the gradient change feature. That is, in the present disclosure, the gradient change of the guide sign profile edge pixel points in multiple lanes needs to be identified.

[0059] In the embodiment of the present disclosure, the guide signs of the adjacent lanes of the target lane are determined, and the pixel values of all the guide signs are determined. Based on the pixel values corresponding to each guide sign, the gradient change feature of the guide sign of the target lane is determined. For example, by judging the gradient change trend of 10 pixel points in the profile edge of each guide sign, the gradient change feature of the guide sign of the target lane is determined. As shown in Figure 9 The guide sign is an arrow, the paint surface of the arrow 1 has a clear boundary with the ground paint surface, the tip of the arrow 2 has a slow transition, and the right part of the arrow 3 has a significant slow transition.

[0060] In the embodiment of the present disclosure, the key feature dimension includes the profile area matching feature.

[0061] In the present disclosure, the size information of the corresponding guide sign can be obtained from Table 2, the size of the standard guide sign area in the image is determined based on the conversion relationship between the picture pixel distance and the actual distance value. The contour actual area of the identified guide sign is matched with the contour standard area, and the contour area matching feature is calculated. For example, the pixel width of one lane in the track picture identified on the highway is 100 pixel points, and the width of one standard lane is 3.75 meters.

[0062] Table 2

[0063]

[0064]

[0065] Figure 13 A flowchart of a method for determining the validity of the guide sign is shown, as shown in Figure 13 The method can include the following steps:

[0066] In step S310, the validity probability of the guide sign is calculated based on the combined distribution feature, the gray mean feature, the gradient change feature and the contour area matching feature.

[0067] In the present disclosure, the calculation formula obtained by pre-training is obtained, the combined distribution feature, the gray mean feature, the gradient change feature and the contour area matching feature are determined as the input of the calculation formula, the output is obtained, and the validity probability of the guide sign is determined.

[0068] In the present disclosure, the expression of the calculation formula is as follows:

[0069]

[0070] Further, the calculation formula can be expressed as:

[0071] y1=w1*x1+w2*x2+w3*x3+w4*x4+b

[0072] Wherein, x represents the key feature of each dimension, for example, x1 represents the combined distribution feature, x2 represents the gray mean feature, x3 represents the gradient change feature, and x4 represents the contour area matching feature. b represents the initial offset. w1*x1 represents the probability of guide sign combined distribution, w2*x2 represents the probability of guide sign gray mean, w3*x3 represents the probability of guide sign gradient change, and w4*x4 represents the probability of guide sign contour area matching.

[0073] In the present disclosure, the initial offset corresponding to the device can be determined according to the device for collecting images.

[0074] In the embodiments of the present disclosure, the implementation of the pre-trained calculation formula is as follows: sample images with standard specification guide signs and sample images with abnormal distribution guide signs are obtained. Among them, the sample images with abnormal distribution guide signs are relatively more.

[0075] The combined distribution feature, the gray mean value feature, the gradient change feature, and the contour area matching feature in the sample image are identified, the combined distribution feature, the gray mean value feature, the gradient change feature, and the contour area matching feature of the sample image are taken as input, and the output is the actual effectiveness probability of the sample image. The calculation formula is trained to obtain a calculation formula for calculating the effectiveness of the guide sign.

[0076] In step S320, the effectiveness of the guide sign is determined based on the effectiveness probability.

[0077] In the embodiments of the present disclosure, the effectiveness of the guide sign is determined based on the effectiveness probability calculated by the calculation formula.

[0078] In the embodiments of the present disclosure, if the effectiveness probability is higher than the preset probability threshold, the guide sign can be processed and displayed at the corresponding position in the map. If the effectiveness probability is lower than or equal to the preset probability threshold, the guide sign can be sent to the traffic-related department to determine whether the guide sign of the lane needs to be updated.

[0079] Based on the same principle as the method shown in Figure 1 Figure 14 The structure schematic diagram of a device for determining the effectiveness of a lane guide sign provided by the embodiments of the present disclosure is shown, as shown in Figure 14 The device 100 for determining the effectiveness of a lane guide sign can include:

[0080] The extraction module 101 is configured to identify an image of a target lane and extract a guide sign of the target lane in the image. The calculation module 102 is configured to calculate a key feature dimension of a contour of the guide sign. The determination module 103 is configured to determine the effectiveness of the guide sign based on the key feature dimension.

[0081] In the embodiments of the present disclosure, the extraction module 101 is configured to identify lane segmentation markings in the image and determine a target lane based on the slope of the lane segmentation markings. The guide sign in the target lane is extracted.

[0082] In the embodiments of the present disclosure, the key feature dimension includes a combined distribution feature.

[0083] The calculation module 102 is configured to identify the distribution of the guide sign and calculate the combined distribution feature of the guide sign based on the distribution.

[0084] ​In the embodiments of the present disclosure, the key feature dimension includes a gray mean value feature.

[0085] The computing module 102 is configured to identify the gray value of the guide sign at different positions, and calculate the gray mean value feature of the guide sign.

[0086] In the embodiments of the present disclosure, the key feature dimension includes a gradient change feature.

[0087] The computing module 102 is configured to determine the guide sign of the adjacent lane of the target lane, and determine the pixel value of all guide signs; based on the pixel value corresponding to each guide sign, determine the gradient change feature of the guide sign of the target lane.

[0088] In the embodiments of the present disclosure, the key feature dimension includes a contour area matching feature.

[0089] The computing module 102 is configured to identify the actual contour area of the guide sign, and obtain the standard contour area corresponding to the guide sign; match the actual contour area with the standard contour area, and calculate the contour area matching feature.

[0090] In the embodiments of the present disclosure, the determining module 103 is configured to calculate the validity probability of the guide sign based on the combined distribution feature, the gray mean value feature, the gradient change feature and the contour area matching feature; and determine the validity of the guide sign based on the validity probability.

[0091] In the technical solution of the present disclosure, the acquisition, storage and application of user personal information comply with relevant laws and regulations, and do not violate public order and good customs.

[0092] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0093] Figure 15 A schematic block diagram of an example electronic device 200 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the present disclosure described and / or claimed in this document.

[0094] As Figure 15As shown, the device 200 includes a computing unit 201 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 202 or a computer program loaded into a random access memory (RAM) 203 from a storage unit 208. In the RAM 203, various programs and data required for the operation of the device 200 can also be stored. The computing unit 201, the ROM 202, and the RAM 203 are connected to each other through a bus 204. An input / output (I / O) interface 205 is also connected to the bus 204.

[0095] A plurality of components in the device 200 are connected to the I / O interface 205, including: an input unit 206, such as a keyboard, a mouse, and the like; an output unit 207, such as various types of displays, speakers, and the like; a storage unit 208, such as a magnetic disk, an optical disk, and the like; and a communication unit 209, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 209 allows the device 200 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0096] The computing unit 201 can be various general and / or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 201 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, and the like. The computing unit 201 performs the various methods and processes described above, such as the method of determining the validity of a lane guide sign. For example, in some embodiments, the method of determining the validity of a lane guide sign can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 208. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 200 via the ROM 202 and / or the communication unit 209. When the computer program is loaded into the RAM 203 and executed by the computing unit 201, one or more steps of the method of determining the validity of a lane guide sign described above can be performed. Alternatively, in other embodiments, the computing unit 201 can be configured to perform the method of determining the validity of a lane guide sign by any other appropriate means, such as by means of firmware.

[0097] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0098] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0099] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0100] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0101] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0102] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server is generally established by computer programs running on the respective computers and having a client-server relationship to each other. The servers can be cloud servers, servers of a distributed system, or servers combined with a blockchain.

[0103] It should be understood that various forms of flow shown above can be used, with steps reordered, added, or removed. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, without limitation herein, so long as the desired results of the technology disclosed in the present disclosure are achieved.

[0104] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Accordingly, the disclosure is not limited to the specific embodiments described above, but only by the scope of the appended claims.

Claims

1. A method for determining the validity of lane guidance signs, the method comprising: Identify an image containing lanes, identify lane dividing lines in the image, determine the slope of each lane dividing line, and identify two lane dividing lines with the same slope as a lane unit. After determining that there are guide signs in the lane unit, the guide signs in the lane unit are extracted based on the difference between the road surface color and the color of the guide signs. Calculate the key feature dimensions of the guide sign outline; the key feature dimensions include at least combined distribution features, gray-level mean features, gradient change features, and outline area matching features; the combined distribution features refer to the distribution of multiple guide signs at the same position in the same lane unit; the gradient change features include the gradient changes of the edge pixels of the guide sign outline within multiple lane units; The pre-trained calculation formula is obtained, and the combined distribution features, the gray-scale mean features, the gradient change features, and the contour area matching features are used as inputs to the calculation formula to obtain the output and determine the validity probability of the guide sign. The validity of the directional sign is determined based on the validity probability. The calculation formula is obtained by identifying the combined distribution features, gray-level mean features, gradient change features, and contour area matching features in the sample image, taking the combined distribution features, gray-level mean features, gradient change features, and contour area matching features of the sample image as input, and outputting the actual validity probability of the sample image. The sample image includes sample images with standard guide signs and sample images with abnormal distribution guide signs.

2. The method according to claim 1, wherein, The key feature dimensions include combined distribution features; The calculation of the key feature dimensions of the guide sign outline includes: Identify the distribution of the directional signs and calculate the combined distribution characteristics of the directional signs based on the distribution.

3. The method according to claim 1, wherein, The key feature dimension includes the gray-level mean feature; The calculation of the key feature dimensions of the guide sign outline includes: Identify the grayscale values ​​at different positions of the directional sign and calculate the grayscale mean feature of the directional sign.

4. The method according to claim 1, wherein, The key feature dimension includes gradient change features; The calculation of the key feature dimensions of the guide sign outline includes: Determine the directional signs of the lanes adjacent to the lane unit, and determine the pixel values ​​of all directional signs; Based on the pixel value corresponding to each directional sign, the gradient change characteristics of the lane unit directional signs are determined.

5. The method according to claim 1, wherein, The key feature dimension includes contour area matching features; The calculation of the key feature dimensions of the guide sign outline includes: Identify the actual area of ​​the outline of the guide sign, and obtain the standard area of ​​the outline corresponding to the guide sign; The actual area of ​​the contour is matched with the standard area of ​​the contour, and the contour area matching feature is calculated.

6. An apparatus for determining the validity of a lane guidance sign, the apparatus comprising: The extraction module is used to identify images containing lanes, identify lane dividing lines in the image, determine the slope of each lane dividing line, and identify two lane dividing lines with the same slope as a lane unit; after determining that there are guide signs in the lane unit, the guide signs in the lane unit are extracted based on the difference between the road surface color and the color of the guide signs. The calculation module is used to calculate the key feature dimensions of the guide sign outline; the key feature dimensions include at least combined distribution features, gray-scale mean features, gradient change features, and outline area matching features; the combined distribution features refer to the distribution of multiple guide signs at the same position in the same lane unit; the gradient change features include the gradient changes of the edge pixels of the guide sign outline within multiple lane units; A determination module is used to acquire a pre-trained calculation formula, taking the combined distribution features, the gray-level mean features, the gradient change features, and the contour area matching features as inputs to the calculation formula, obtaining an output, and determining the validity probability of the guide sign; based on the validity probability, determining the validity of the guide sign; wherein, the calculation formula is obtained by identifying the combined distribution features, gray-level mean features, gradient change features, and contour area matching features in the sample image, taking the combined distribution features, gray-level mean features, gradient change features, and contour area matching features of the sample image as inputs, and outputting the actual validity probability of the sample image; the sample image includes sample images with standard guide signs and sample images with abnormally distributed guide signs.

7. The apparatus according to claim 6, wherein, The key feature dimensions include combined distribution features; The computing module is used for: Identify the distribution of the directional signs and calculate the combined distribution characteristics of the directional signs based on the distribution.

8. The apparatus according to claim 6, wherein, The key feature dimension includes the gray-level mean feature; The computing module is used for: Identify the grayscale values ​​at different positions of the directional sign and calculate the grayscale mean feature of the directional sign.

9. The apparatus according to claim 6, wherein, The key feature dimension includes gradient change features; The computing module is used for: Determine the directional signs of the lanes adjacent to the lane unit, and determine the pixel values ​​of all directional signs; Based on the pixel value corresponding to each directional sign, the gradient change characteristics of the lane unit directional signs are determined.

10. The apparatus according to claim 6, wherein, The key feature dimension includes contour area matching features; The computing module is used for: Identify the actual area of ​​the outline of the guide sign, and obtain the standard area of ​​the outline corresponding to the guide sign; The actual area of ​​the contour is matched with the standard area of ​​the contour, and the contour area matching feature is calculated.

11. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-5.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-5.

Images