Positioning method and apparatus, electronic device, and storage medium

Abstract

The application provides a positioning method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a road sign in an environment image, wherein the road sign comprises a plurality of contour points and a plurality of code points located in a convex hull formed by the plurality of contour points; determining the identity of the road sign according to the shape of the convex hull and / or the position of the plurality of code points relative to the convex hull; and determining the geographical position information corresponding to the road sign according to the identity of the road sign. The positioning method of the application is widely applicable and the recognition algorithm is simple.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a positioning method, device, electronic device and storage medium. Background Technology

[0002] Currently, with the rapid development of computer technology, artificial intelligence is widely used in various fields. Among them, visual positioning technology in indoor environments has brought convenience to people's lives and industrial production. For example, robots achieve visual positioning by recognizing landmarks (tags) at fixed locations, and then plan their movement trajectories.

[0003] In related technologies, road signs are set up with specific visual features, and location is achieved by recognizing these features. However, for civilian scenarios where aesthetics are a certain requirement, such as restaurants and hotels, it is not suitable to paste such road signs over a large area, and the applicability is not wide enough. In addition, the road sign recognition algorithm based on feature recognition is complex. Summary of the Invention

[0004] This application aims to at least partially address one of the technical problems in the related art.

[0005] Therefore, the first objective of this application is to propose a positioning method that is widely applicable and has a simple recognition algorithm.

[0006] The second objective of this application is to provide a positioning device.

[0007] The third objective of this application is to propose an electronic device.

[0008] The fourth objective of this application is to provide a computer-readable storage medium.

[0009] To achieve the above objectives, a first aspect of this application proposes a positioning method, comprising: acquiring a landmark in an environmental image, the landmark including multiple contour points and multiple coded points located within a convex hull formed by the multiple contour points; determining an identifier of the landmark based on the shape of the convex hull and / or the position of the multiple coded points relative to the convex hull; and determining the geographical location information corresponding to the landmark based on the identifier of the landmark.

[0010] The positioning method proposed in this application acquires road signs in an environmental image. Each road sign includes multiple contour points and multiple coded points located within a convex hull formed by these contour points. Based on the shape of the convex hull and / or the positions of the coded points relative to it, the road sign's identifier is determined. The corresponding geographical location information is then determined based on the road sign's identifier. This type of road sign consists of only a few scattered points, barely affecting the aesthetics of the environment. Even in civilian scenarios where aesthetics are important, such as restaurants and hotels, it is suitable for large-scale application of these road signs, offering wide applicability and a simple recognition algorithm.

[0011] According to one embodiment of this application, determining the identifier of the landmark based on the position of the plurality of coding points relative to the convex hull includes: determining the code corresponding to the position of the plurality of coding points relative to the convex hull; and determining the identifier of the landmark based on the code.

[0012] According to one embodiment of this application, determining the identifier of the road sign based on the shape of the convex hull includes: determining the code corresponding to the shape of the convex hull; and determining the identifier of the road sign based on the code.

[0013] According to one embodiment of this application, determining the identifier of the road sign based on the shape of the convex hull and the positions of the plurality of coding points relative to the convex hull includes: determining the code corresponding to the shape of the convex hull and the positions of the plurality of coding points relative to the convex hull; and determining the identifier of the road sign based on the code.

[0014] According to one embodiment of this application, determining the identifier of the road sign based on the shape of the convex hull and the positions of the plurality of coding points relative to the convex hull includes: determining the code corresponding to the position of the plurality of coding points relative to the convex hull; verifying the code based on the shape of the convex hull; and if the verification passes, determining the identifier of the road sign based on the code.

[0015] According to one embodiment of this application, the step of verifying the code based on the shape of the convex hull includes: verifying the number of the plurality of coding points corresponding to the code based on the shape of the convex hull.

[0016] According to one embodiment of this application, acquiring road signs in an environmental image includes: acquiring a set of marker points in the environmental image; determining the shape of the convex hull corresponding to the set of marker points; and determining whether the set of marker points is a road sign based on the shape of the convex hull.

[0017] According to one embodiment of this application, determining whether the set of marker points is the road sign based on the shape of the convex hull includes: determining whether the set of marker points is the road sign based on the shape of the convex hull and a preset convex hull shape.

[0018] According to one embodiment of this application, the brightness of the contour points and the coded points is higher than a preset brightness threshold, and the step of obtaining a set of marker points in the environmental image includes: obtaining the set of marker points in the environmental image whose brightness is higher than the brightness threshold.

[0019] According to one embodiment of this application, there are multiple preset convex hull shapes, and any one of the preset convex hull shapes does not overlap with other preset convex hull shapes by rotation and / or scaling.

[0020] According to one embodiment of this application, the convex hull corresponding to the road sign does not have rotational symmetry.

[0021] To achieve the above objectives, a second aspect of this application provides a positioning device, comprising: an acquisition module for acquiring road signs in an environmental image, the road signs including multiple contour points and multiple coded points located within a convex hull formed by the multiple contour points; a first determination module for determining the identifier of the road sign based on the shape of the convex hull and / or the position of the multiple coded points relative to the convex hull; and a second determination module for determining the geographical location information corresponding to the road sign based on the identifier of the road sign.

[0022] The positioning device proposed in this application acquires road signs in an environmental image. Each road sign includes multiple contour points and multiple coded points located within a convex hull formed by the contour points. Based on the shape of the convex hull and / or the positions of the coded points relative to the convex hull, the device determines the road sign's identifier and the corresponding geographical location information based on the identifier. This type of road sign consists of only a few scattered points, hardly affecting the aesthetics of the environment. Even in civilian scenarios where aesthetics are important, such as restaurants and hotels, it is suitable for large-area application of these road signs, offering wide applicability and a simple recognition algorithm.

[0023] To achieve the above objectives, a third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the positioning method as described in the first aspect of this application.

[0024] To achieve the above objectives, a fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the positioning method as described in the first aspect of this application. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating a positioning method according to an embodiment of this application;

[0026] Figure 2This is a schematic diagram of a road sign template according to one embodiment of this application;

[0027] Figure 3 This is a flowchart illustrating a positioning method according to another embodiment of this application;

[0028] Figure 4 This is a flowchart illustrating a positioning method according to another embodiment of this application;

[0029] Figure 5 This is a flowchart illustrating a positioning method according to another embodiment of this application;

[0030] Figure 6 This is a flowchart illustrating a positioning method according to another embodiment of this application;

[0031] Figure 7 This is a flowchart illustrating a positioning method according to another embodiment of this application;

[0032] Figure 8 This is a schematic diagram of the convex hull shape according to an embodiment of this application;

[0033] Figure 9 This is a schematic diagram of another convex hull shape according to one embodiment of this application;

[0034] Figure 10 This is a schematic diagram of another convex hull shape according to one embodiment of this application;

[0035] Figure 11 This is a schematic diagram of another convex hull shape according to one embodiment of this application;

[0036] Figure 12 This is a schematic diagram of a road sign according to an embodiment of this application;

[0037] Figure 13 This is a schematic diagram of the actual deployment of road signs according to one embodiment of this application;

[0038] Figure 14 This is a schematic diagram of the actual deployment of road signs according to another embodiment of this application;

[0039] Figure 15 This is a block diagram of a positioning device according to an embodiment of this application.

[0040] Figure 16 This is a block diagram of an electronic device according to an embodiment of the present application. Detailed Implementation

[0041] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0042] The positioning method, apparatus, electronic device, and storage medium of this application are described below with reference to the accompanying drawings.

[0043] Figure 1 This is a flowchart illustrating a positioning method according to an embodiment of this application, as shown below. Figure 1 As shown, the positioning method in this application embodiment may specifically include the following steps:

[0044] S101, acquire landmarks in the environment image, the landmarks include multiple contour points and multiple encoded points located within the convex hull formed by the multiple contour points.

[0045] In this embodiment of the application, the positioning method can be executed by the positioning device provided in this embodiment. The positioning device can be a hardware device with data information processing capabilities and / or the necessary software to drive the hardware device to work. Specifically, this positioning device can be applied to intelligent devices such as robots.

[0046] In this embodiment, multiple fixed-location landmarks to be identified are pre-set in the geographic environment to be located, each landmark corresponding to a geographic location. Each landmark can be viewed as a two-dimensional region, containing multiple contour points and multiple coded points located within the convex hull formed by these contour points. These contour points and coded points are arranged according to certain rules within the two-dimensional region. The lines connecting the contour points form a convex polygon, and the coded points are scattered within this polygon according to certain rules; this convex polygon is called the convex hull. In a real vector space V, for a given set X, the intersection S of all convex sets containing X is called the convex hull of X. The convex hull of X can be constructed using the convex combination of all points (X1, ..., Xn) within X. In two-dimensional Euclidean space, the convex hull can be imagined as a rubber band that just encloses all the points.

[0047] Specifically, road signs in the surrounding environment can be obtained through image acquisition devices such as cameras.

[0048] S102, determine the sign of the road sign based on the shape of the convex hull and / or the position of multiple coding points relative to the convex hull.

[0049] In this embodiment, based on the multiple contour points and multiple coded points in the road sign obtained in step S101, the shape of the convex hull and the positions of the multiple coded points relative to the convex hull are determined, thereby determining the road sign's identifier, i.e., which road sign it is. It should be noted that the convex hull in this embodiment does not possess rotational symmetry; that is, the convex hull can be correctly oriented from different angles, thus determining the orientation of the local reference system of the road sign itself formed by the contour points. The positions of the aforementioned multiple coded points relative to the convex hull are determined based on this local coordinate system. The road sign's identifier is used to mark the uniqueness of the road sign and can be used to represent a specific road sign.

[0050] It should be noted that when determining the markings of road signs, they can be determined solely based on the shape of the convex hull, solely based on the positions of multiple coding points relative to the convex hull, or they can be determined by a combination of the shape of the convex hull and the positions of multiple coding points relative to the convex hull.

[0051] S103, determine the geographical location information corresponding to the road sign based on the road sign's markings.

[0052] In this embodiment of the application, the geographical location information corresponding to the road sign is determined based on the road sign identifier obtained in step S102, thereby achieving accurate positioning.

[0053] It should be noted here that a road sign template can be pre-designed to generate the road signs in the embodiments of this application. This road sign template is an imaginary two-dimensional area. On this area, some predefined positions are used to paste marker points, forming outline points or coded points. By pasting marker points in different positions according to rules, different road signs can be generated.

[0054] Available Bit: The position on the marker template used to paste marker points. Includes encoding bits and outline bits.

[0055] Encoding Bit: The location on the sign template used to paste encoding points. The marker points pasted at these locations on each sign are the encoding points.

[0056] ContourBit: The location on the sign template used to paste the contour point. The marker point pasted at these locations on each sign is the contour point.

[0057] Figure 2 This is a schematic diagram of a road sign template. (For example...) Figure 2 As shown, the dashed circles represent all available bits, the thicker dashed circles represent outline bits, and the thinner dashed circles represent encoded bits. Figure 2 It includes 8 contour bits and 18 encoding bits.

[0058] The positioning method proposed in this application acquires road signs in an environmental image. Each road sign includes multiple contour points and multiple coded points located within a convex hull formed by these contour points. Based on the shape of the convex hull and / or the positions of the coded points relative to it, the road sign's identifier is determined. The corresponding geographical location information is then determined based on the road sign's identifier. This type of road sign consists of only a few scattered points, barely affecting the aesthetics of the environment. Even in civilian scenarios where aesthetics are important, such as restaurants and hotels, it is suitable for large-scale application of these road signs, offering wide applicability and a simple recognition algorithm.

[0059] Figure 3 This is a flowchart illustrating a positioning method according to another embodiment of this application. Figure 3 As shown above, in the above Figure 1 Based on the illustrated embodiments, the positioning method of this application may specifically include the following steps:

[0060] The above Figure 1 Step S101 in the illustrated embodiment may specifically include the following steps S301-S303.

[0061] S301, Obtain a set of marker points in the environmental image.

[0062] In this embodiment, to facilitate the identification of marker points (including contour points and coded points) in road signs, the marker points can be points with brightness higher than a preset brightness threshold, i.e., high-brightness points. It is easy to understand that an environmental image may contain multiple road signs. In this embodiment, each road sign can be considered as a group of mutually adjacent marker points. Therefore, a group of mutually adjacent marker points with brightness higher than the brightness threshold in the environmental image can be obtained as the aforementioned group of marker points.

[0063] S302, Determine the shape of the convex hull corresponding to a set of marker points.

[0064] In this embodiment of the application, the shape of the convex hull of a set of marker points obtained in step S301 is determined.

[0065] S303, determine whether a set of marker points are road signs based on the shape of the convex hull.

[0066] In this embodiment of the application, as a feasible implementation method, a set of marker points can be determined as road signs based on the shape of the convex hull and a preset convex hull shape. The preset convex hull shape can be one or more. Furthermore, to ensure the uniqueness of different convex hull shapes, any preset convex hull shape should not coincide with other preset convex hull shapes through rotation and / or scaling. Additionally, to ensure correct orientation of the road sign when viewed from different angles, the convex hull corresponding to the road sign should not have rotational symmetry. Rotational symmetry can be illustrated with an example: if a planar figure L is rotated α (0 < α < 360) degrees around a point O on the plane, and the resulting new figure L* completely coincides with L, then L is said to be a planar rotationally symmetric figure, and L is said to have rotational symmetry.

[0067] In practice, one or more convex hull shapes can be pre-defined for road signs and stored in a convex hull shape library for determining whether a set of marker points is a road sign. The convex hull shape determined in step S302 is matched with the convex hull shapes in the library. If a convex hull shape exists in the library that matches the shape determined in step S302, the set of marker points obtained in step S301 is considered a road sign. If no convex hull shape exists in the library that matches the shape determined in step S302, the set of marker points obtained in step S301 is not considered a road sign. By analyzing the shape of the convex hull, a rapid determination of whether a set of marker points is a road sign can be achieved, enabling fast road sign detection. Furthermore, detecting road signs based on convex hull matching requires that the correct convex hull shape be matched only after all marker points of a road sign have been completely observed, thus preventing road sign recognition errors due to incomplete observation.

[0068] S304, Determine the signage based on the shape of the convex hull and / or the position of multiple coding points relative to the convex hull.

[0069] S305 determines the geographical location information corresponding to the road sign based on the road sign markings.

[0070] In this embodiment, steps S304-S305 are implemented in the same way as steps S302-S303 in the previous embodiment, and will not be described again here.

[0071] Furthermore, the specific implementation of step S304 "based on the shape of the convex hull and / or the position of multiple coding points relative to the convex hull" will be described in detail in the following four embodiments.

[0072] like Figure 4 As shown, step S304 above, "determining the marker of a landmark based on the position of multiple coding points relative to the convex hull," may specifically include the following steps:

[0073] S401, determine the encoding corresponding to the position of multiple encoding points relative to the convex hull.

[0074] In this embodiment, contour points are used only for landmark detection, while coded points are used for landmark recognition. The code corresponding to each of the multiple coded points is determined based on their position relative to the convex hull. Specifically, all coded points in a single landmark correspond to one code.

[0075] S402, determine the signage identifier based on the code.

[0076] In this embodiment of the application, a correspondence table between different codes and different road sign identifiers is pre-stored. Based on the codes corresponding to multiple code points obtained in step S401, the identifier of the road sign corresponding to the code is searched in the above correspondence table.

[0077] like Figure 5 As shown, step S304 above, "determining the road sign identifier based on the shape of the convex hull," may specifically include the following steps:

[0078] S501, determine the code corresponding to the shape of the convex hull.

[0079] In this embodiment, in addition to being used for rapid road sign detection as shown in the above embodiments, contour points can also be used for road sign recognition, that is, different convex hull shapes can be used as different encoding information.

[0080] The code corresponding to multiple contour points is determined based on the shape of the convex hull. Each contour point in a landmark corresponds to one code.

[0081] S502, determine the identification of road signs based on codes.

[0082] In this embodiment of the application, a correspondence table between different codes and different road sign identifiers is pre-stored. Based on the codes corresponding to multiple contour points obtained in step S501, the identifier of the road sign corresponding to the code is searched in the above correspondence table.

[0083] like Figure 6 As shown, step S304 above, "determining the marker of the road sign based on the shape of the convex hull and the positions of multiple coding points relative to the convex hull," may specifically include the following steps:

[0084] S601, determine the shape of the convex hull and the codes corresponding to the positions of multiple coding points relative to the convex hull.

[0085] In this embodiment, contour points are used not only for road sign detection but also, together with coded points, for road sign recognition. The corresponding code is determined based on the shape of the convex hull and the positions of multiple coded points relative to the convex hull. Multiple contour points, arranged according to certain rules, can form different convex hull shapes, and these different convex hull shapes can be used as different coded information, thereby expanding the number of codes. For example, Figure 2 The road sign template shown has 18 coding positions. Each coding position can have a marker point either pasted or not, resulting in a total of 2... 18 There are only a maximum of m possible combinations, resulting in a maximum of m*2 different codes. Assuming m convex hull shapes are predefined, expanding the code using convex hull shapes will yield a maximum of m*2 different codes. 18 There are several different codes. In a single landmark, all coded points and contour points correspond to one code.

[0086] S602, determine the road sign identifier based on the code.

[0087] In this embodiment of the application, a correspondence table between different codes and different road sign identifiers is pre-stored. Based on the codes corresponding to multiple code points and multiple contour points obtained in S601, the identifier of the road sign corresponding to the code is searched in the above correspondence table.

[0088] like Figure 7 As shown, step S304 above, "determining the marker of the road sign based on the shape of the convex hull and the positions of multiple coding points relative to the convex hull," may specifically include the following steps:

[0089] S701, determine the encoding corresponding to the position of multiple encoding points relative to the convex hull.

[0090] In this embodiment, the coded points are used for road sign recognition, and the contour points are used to verify the recognized road signs. This step is the same as step S401 in its specific implementation, and will not be repeated here.

[0091] S702 verifies the code based on the shape of the convex hull.

[0092] In this embodiment, the shape of the convex hull is determined based on the position of the contour point, and the code determined in step S701 is verified based on the shape of the convex hull. A pre-stored correspondence table between different codes and different convex hull shapes is used. Based on the code determined in S701, the table is searched to see if a convex hull shape corresponding to that code exists. If it exists and the shape of the convex hull matches the shape of the convex hull determined by the current contour point, the verification passes. If it does not exist, or if it exists but the shape of the convex hull does not match the shape of the convex hull determined by the current contour point, the verification fails.

[0093] It should be noted that various methods can be used to verify the code using contour points in specific implementations, and this application does not limit the methods.

[0094] S703 If the verification passes, the signpost identifier is determined based on the code.

[0095] In this embodiment, if the verification passes, it indicates that the code is correctly identified, and the landmark can be identified based on the code. It should be noted that if the verification fails, the current code is considered incorrectly identified, and the landmark cannot be identified based on the code. This improves the road sign recognition's resistance to environmental interference and further enhances the reliability of positioning.

[0096] Furthermore, step S702 "verifying the code based on the shape of the convex hull" may specifically include: verifying the number of multiple coding points corresponding to the code based on the shape of the convex hull.

[0097] In this embodiment, when verifying the encoding based on the positions of multiple contour points, the number of multiple encoding points can be verified. Different correspondences between the number of encoding points and convex hull shapes are pre-defined. For example, there are four pre-defined convex hull shapes: when the number of encoding points k modulo 4 is greater than or equal to 1, it corresponds to convex hull shape 1; when the number of encoding points k modulo 4 is greater than or equal to 2, it corresponds to convex hull shape 2; when the number of encoding points k modulo 4 is greater than or equal to 3, it corresponds to convex hull shape 3; and when the number of encoding points k is divisible by 4, it corresponds to convex hull shape 4. The corresponding convex hull shape is determined based on the positions of multiple contour points. The number of encoding points corresponding to that convex hull shape is determined based on the convex hull shape and the above-described number of encoding points. If the number of encoding points matches the actual number of encoding points, the verification passes; otherwise, the verification fails.

[0098] The following is based on Figure 2 Taking the road sign template shown as an example, a detailed description is provided. Figure 7 The process of generating road signs in the illustrated embodiment. Based on Figure 2 The template shown indicates that road signs are only allowed to use the following templates: Figures 8-11 The four convex hull shapes shown correspond to convex hull shapes 1-4, respectively. Figures 8-11 The solid circle represents the outline where the marker points are pasted.

[0099] based on Figure 2 The template for the road sign shown is as follows: Figure 12 The diagram shows the selection of two code positions to paste marker points (thin solid circles represent code positions with pasted marker points), meaning the number of code points k = 2, and k modulo 4 leaves a remainder of 2. Therefore, the selection is... Figure 9 The convex hull shape 2 shown (the thicker solid circle represents the outline where marker points are pasted) is as follows: After removing the imaginary border and dashed circle, the actual road sign deployed in the scene looks like... Figure 13 As shown.

[0100] based on Figure 2 The template for the road sign shown is as follows: Figure 14 The diagram shows the selection of 3 code positions to paste marker points (thin solid circles represent code positions with pasted marker points), meaning the number of code points k = 3, and k modulo 4 leaves a remainder of 3. Therefore, the selection is... Figure 10 The convex hull shape 3 shown is illustrated (the thicker solid circle represents the outline where marker points are pasted). After removing the imaginary border and dashed circle, the actual road sign deployed in the scene looks like... Figure 14 As shown.

[0101] The positioning method proposed in this application acquires road signs in an environmental image. Each road sign includes multiple contour points and multiple coded points located within a convex hull formed by these contour points. Based on the shape of the convex hull and / or the positions of the coded points relative to it, the road sign's identifier is determined. The corresponding geographical location information is then determined based on the road sign's identifier. This type of road sign consists of only a few scattered points, barely affecting the aesthetics of the environment. Even in civilian scenarios where aesthetics are important, such as restaurants and hotels, it is suitable for large-scale application of these road signs, offering wide applicability and a simple recognition algorithm.

[0102] To implement the above embodiments, this application also proposes a positioning device that can implement the positioning method of any of the above embodiments. For example... Figure 15 As shown, the positioning device proposed in this application embodiment may specifically include: an acquisition module 151, a first determination module 152, and a second determination module 153. Wherein:

[0103] The acquisition module 151 is used to acquire landmarks in the environmental image. The landmarks include multiple contour points and multiple coded points located within the convex hull formed by the multiple contour points.

[0104] The first determining module 152 is used to determine the identifier of the landmark based on the shape of the convex hull and / or the position of multiple coding points relative to the convex hull.

[0105] The second determining module 153 is used to determine the geographical location information corresponding to the road sign based on the road sign's identifier.

[0106] Furthermore, in one possible implementation of this application embodiment, the first determining module 152 can be specifically used to: determine the codes corresponding to the positions of multiple coding points relative to the convex hull; and determine the identifiers of road signs based on the codes.

[0107] Furthermore, in one possible implementation of this application embodiment, the first determining module 152 can be specifically used to: determine the code corresponding to the shape of the convex hull; and determine the identifier of the road sign based on the code.

[0108] Furthermore, in one possible implementation of this application embodiment, the first determining module 152 can be specifically used to: determine the shape of the convex hull and the encoding corresponding to the positions of multiple encoding points relative to the convex hull; and determine the identifier of the landmark based on the encoding.

[0109] Furthermore, in one possible implementation of this application embodiment, the first determining module 152 can be specifically used to: determine the codes corresponding to the positions of multiple coding points relative to the convex hull; verify the codes according to the shape of the convex hull; and if the verification passes, determine the signpost identifier according to the code.

[0110] Furthermore, in one possible implementation of this application embodiment, the first determining module 152 can be specifically used to: verify the number of multiple coding points corresponding to the coding based on the shape of the convex hull.

[0111] Furthermore, in one possible implementation of this application embodiment, the acquisition module 151 can be specifically used to: acquire a set of marker points in an environmental image; determine the shape of the convex hull corresponding to the set of marker points; and determine whether the set of marker points are road signs based on the shape of the convex hull.

[0112] Furthermore, in one possible implementation of this application embodiment, the acquisition module 151 can be specifically used to: determine whether a set of marker points are road signs based on the shape of the convex hull and a preset convex hull shape.

[0113] Furthermore, in one possible implementation of this application embodiment, if the brightness of the contour points and the coding points is higher than a preset brightness threshold, the acquisition module 151 can be specifically used to: acquire a set of marker points in the environmental image whose brightness is higher than the brightness threshold.

[0114] Furthermore, in one possible implementation of the embodiments of this application, there are multiple preset convex hull shapes, and any one preset convex hull shape does not overlap with other preset convex hull shapes by rotation and / or scaling.

[0115] Furthermore, in one possible implementation of this application embodiment, the convex hull corresponding to the road sign does not have rotational symmetry.

[0116] It should be noted that the foregoing explanation of the positioning method embodiment also applies to the positioning device of this embodiment, and will not be repeated here.

[0117] The positioning device proposed in this application acquires road signs in an environmental image. Each road sign includes multiple contour points and multiple coded points located within a convex hull formed by the contour points. Based on the shape of the convex hull and / or the positions of the coded points relative to the convex hull, the device determines the road sign's identifier and the corresponding geographical location information based on the identifier. This type of road sign consists of only a few scattered points, hardly affecting the aesthetics of the environment. Even in civilian scenarios where aesthetics are important, such as restaurants and hotels, it is suitable for large-area application of these road signs, offering wide applicability and a simple recognition algorithm.

[0118] To implement the above embodiments, this application also proposes an electronic device 160, such as... Figure 16 As shown, the electronic device 160 may specifically include a memory 161, a processor 162, and a computer program stored on the memory 161 and executable on the processor 162. When the processor 162 executes the program, it implements the positioning method as shown in the above embodiment.

[0119] To implement the above embodiments, this application also proposes a computer-readable storage medium storing a computer program that is executed by a processor to implement the positioning method shown in the above embodiments.

[0120] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0121] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A positioning method, characterized in that, include: Obtain a set of marker points from the environmental image; Determine the shape of the convex hull corresponding to the set of marker points; Based on the shape of the convex hull and the preset convex hull shape, determine whether the set of marker points are road signs; There are multiple preset convex hull shapes, and any one of the preset convex hull shapes will not overlap with other preset convex hull shapes by rotation and / or scaling. If the shape of the convex hull is the same as the shape of the preset convex hull, then the set of marker points is determined as a road sign. The road sign includes multiple contour points and multiple coded points located in the convex hull formed by the multiple contour points. The convex hull is a convex polygon and does not have rotational symmetry. The identifier of the road sign is determined based on the shape of the convex hull and the position of the plurality of coding points relative to the convex hull; The geographical location information corresponding to the road sign is determined based on the sign's identifier; Determining the identifier of the road sign based on the shape of the convex hull and the positions of the plurality of coding points relative to the convex hull includes: Determine the codes corresponding to the positions of the plurality of coding points relative to the convex hull; The number of the plurality of coding points corresponding to the coding is verified according to the shape of the convex hull; If the verification passes, the identifier of the road sign is determined according to the encoding.

2. The method according to claim 1, characterized in that, The brightness of the contour points and the encoded points is higher than a preset brightness threshold, and the acquisition of a set of marker points in the environmental image includes: Obtain the set of marker points in the environmental image whose brightness is higher than the brightness threshold.

3. A positioning device, characterized in that, include: The acquisition module is used to acquire a set of marker points in the environmental image; Determine the shape of the convex hull corresponding to the set of marker points; Based on the shape of the convex hull and the preset convex hull shape, determine whether the set of marker points are road signs; There are multiple preset convex hull shapes, and any one of the preset convex hull shapes does not overlap with other preset convex hull shapes by rotation and / or scaling; if the shape of the convex hull is the same as the shape of the preset convex hull, then the set of marker points is determined as a road sign, the road sign includes multiple contour points and multiple coding points located in the convex hull formed by the multiple contour points, the convex hull is a convex polygon and does not have rotational symmetry; The first determining module is used to determine the identifier of the road sign based on the shape of the convex hull and the position of the plurality of coding points relative to the convex hull; The second determining module is used to determine the geographical location information corresponding to the road sign based on the road sign's identifier; The first determining module is specifically used for: Determine the codes corresponding to the positions of the plurality of coding points relative to the convex hull; The number of the plurality of coding points corresponding to the coding is verified according to the shape of the convex hull; If the verification passes, the identifier of the road sign is determined according to the encoding.

4. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the positioning method as described in any one of claims 1-2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the positioning method as described in any one of claims 1-2.

Images