Method for drawing road intersection, related device and computer program product

Abstract

The invention provides a method for drawing a road intersection, a related device and a computer program product, and relates to the technical field of artificial intelligence such as high-precision maps, intelligent driving and intelligent transportation. A specific embodiment of the method comprises the following steps: extracting a target position of a single-side mounted lane line from an electronic map; drawing a target line segment based on the lane line group mounted at the target position; two ends of the target line segment are endpoints of two outermost lane lines in the lane line group; based on the distance between the target line segments, clustering the target line segments to obtain a clustering result; based on the target line segment included in the clustering result, drawing a map block corresponding to the clustering result in the electronic map; the map blocks are used for indicating road intersections. Therefore, the position and the range of the road intersection can be more accurately marked in the electronic map, so that a user and an automatic driver can formulate a passing strategy of the road intersection more specifically and finely, and the traffic efficiency and the traffic safety are improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, in particular to the technical field of artificial intelligence such as high-definition map, intelligent driving and intelligent transportation, and especially relates to a method and device for drawing a road intersection, an electronic device, a computer readable storage medium and a computer program product. BACKGROUND

[0002] With the gradual improvement of user requirements for navigation quality and the rapid development of intelligent and autonomous driving technology, high-definition map (HD Map) as one of the core technologies plays a vital role.

[0003] High-definition map not only provides high-resolution road information for users and intelligent driving vehicles, but also provides higher accuracy than traditional positioning systems, supporting accurate positioning and efficient path planning for vehicles. Therefore, it is worth paying attention to and urgently needed to further improve the quality of high-definition map so that users and autonomous driving can better utilize high-definition map to assist and complete driving. SUMMARY

[0004] Embodiments of the present disclosure provide a method and device for drawing a road intersection, an electronic device, a computer readable storage medium and a computer program product.

[0005] In a first aspect, a method for drawing a road intersection is provided, including: extracting a target position of a single-side mounted lane line from an electronic map; drawing a target line segment based on a lane line group mounted at the target position; wherein two ends of the target line segment are endpoints of two outermost lane lines in the lane line group; clustering the target line segments based on distances between the target line segments to obtain a clustering result; and drawing a map block corresponding to the clustering result in the electronic map based on the target line segments included in the clustering result; wherein the map block is used to indicate the road intersection.

[0006] In a second aspect, a device for drawing a road intersection is provided, including: a position extraction unit configured to extract a target position of a single-side mounted lane line from an electronic map; a line segment drawing unit configured to draw a target line segment based on a lane line group mounted at the target position; wherein two ends of the target line segment are endpoints of two outermost lane lines in the lane line group; a line segment clustering unit configured to cluster the target line segments based on distances between the target line segments to obtain a clustering result; and a block drawing unit configured to draw a map block corresponding to the clustering result in the electronic map based on the target line segments included in the clustering result; wherein the map block is used to indicate the road intersection.

[0007] In a third aspect, an electronic device is provided, and the electronic device includes at least one processor, and a memory connected with the at least one processor in communication; 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 implement the method for drawing a road intersection as described in any implementation manner of the first aspect.

[0008] In a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, and the computer instructions are used to enable a computer to implement the method for drawing a road intersection as described in any implementation manner of the first aspect.

[0009] In a fifth aspect, a computer program product including a computer program is provided, and the computer program is executable by a processor to implement the method for drawing a road intersection as described in any implementation manner of the first aspect.

[0010] The method for drawing a road intersection, the device, the electronic device, the computer-readable storage medium, and the computer program product provided in the embodiments of the present disclosure first extract a target position of a single-side mounted lane line from an electronic map; then draw a target line segment based on a lane line group mounted at the target position; wherein two ends of the target line segment are end points of two outermost lane lines in the lane line group; next, cluster the target line segments based on distances between the target line segments to obtain a clustering result; finally, draw a map block corresponding to the clustering result in the electronic map based on the target line segments included in the clustering result; wherein the map block is used to indicate a road intersection.

[0011] The present disclosure can more accurately label the position and range of a road intersection in an electronic map, so that a user or an autonomous vehicle can more specifically and finely formulate a traffic strategy for the road intersection, and improve traffic efficiency and traffic safety. For example, in an autonomous driving scenario, a control party (of a vehicle) can determine whether to use a more targeted traffic strategy configured for the scenario of a road intersection to control the vehicle, by identifying whether the autonomous vehicle has entered a road intersection that can lack lane lines or guide lines. In this way, the autonomous vehicle can differentially select a traffic strategy different from other scenarios to more efficiently and safely pass through the road intersection when passing through this special scenario.

[0012] It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0013] Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments thereof as taken in conjunction with the accompanying drawings: Figure 1 is an exemplary system architecture to which the present disclosure can be applied; Figure 2 a flowchart of a method for drawing a road intersection provided by an embodiment of the present disclosure; Figures 3a to 3c an effect schematic diagram of an electronic map in an application scenario provided by an embodiment of the present disclosure; Figure 4 a flowchart of a process for re-executing clustering to obtain an updated clustering result provided by an embodiment of the present disclosure; Figures 5a to 5b an effect schematic diagram of an electronic map in another application scenario provided by an embodiment of the present disclosure; Figure 6 a structural block diagram of a device for drawing a road intersection provided by an embodiment of the present disclosure; Figure 7 a structural schematic diagram of an electronic device suitable for executing a method for drawing a road intersection provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0014] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, which should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize 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, descriptions of well-known functions and structures are omitted in the following description for clarity and conciseness. It should be noted that the embodiments in the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0015] In addition, the technical solutions involved in the present disclosure involve the acquisition (such as the electronic map and the like involved in the subsequent disclosure of the present disclosure), storage, use, processing, transportation, provision and disclosure of user personal information, which comply with relevant laws and regulations and do not violate public order and good customs.

[0016] Figure 1 An exemplary system architecture 100 is shown, which can apply embodiments of the method, device, electronic device and computer readable storage medium for drawing a road intersection of the present disclosure.

[0017] As Figure 1As shown, the system architecture 100 can include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is a medium for providing a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links, or optical fiber cables, and the like.

[0018] A user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, and the like. The terminal devices 101, 102, 103 and the server 105 can be installed with various applications for realizing information communication between the two, such as navigation applications, high-definition map maintenance applications, instant messaging applications, and the like.

[0019] The terminal devices 101, 102, 103 and the server 105 can be hardware or software. When the terminal devices 101, 102, 103 are hardware, they can be various electronic devices with a display screen, including but not limited to smartphones, tablet computers, laptop computers, desktop computers, and the like; when the terminal devices 101, 102, 103 are software, they can be installed in the above-mentioned electronic devices, and can be implemented as multiple software or software modules, or as a single software or software module, which is not specifically limited here. When the server 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server; when the server 105 is software, it can be implemented as multiple software or software modules, or as a single software or software module, which is not specifically limited here.

[0020] The server 105 can provide various services through various built-in applications. Taking a high-definition map maintenance application for an electronic map (e.g., a high-definition map) that can be provided for navigation as an example, the server 105 can achieve the following effects when running the high-definition map maintenance application: first, after obtaining the electronic map from the terminal devices 101, 102, 103 through the network 104, the server 105 can extract target positions of single-sided mounted lane lines from the electronic map; then, the server 105 can draw target line segments based on lane line groups mounted at the target positions; wherein the two ends of the target line segments are the endpoints of the two outermost lane lines in the lane line group; next, the server 105 can cluster the target line segments based on the distances between the target line segments to obtain clustering results; finally, the server 105 can draw map blocks corresponding to the clustering results in the electronic map based on the target line segments included in the clustering results; wherein the map blocks are used to indicate road intersections.

[0021] It should be noted that the electronic map can be pre-stored in the server 105 locally in various ways in addition to being acquired from the terminal devices 101, 102, 103 through the network 104. Therefore, when the server 105 detects that the data has been stored locally (for example, before starting the electronic map maintenance task left over from the previous processing), the data can be directly acquired from the local storage, and in this case, the exemplary system architecture 100 can also not include the terminal devices 101, 102, 103 and the network 104.

[0022] Since the operations such as extracting the target position and performing clustering of the target line segment often require a large amount of computing resources and strong computing power, the method for drawing a road intersection provided in each of the subsequent embodiments of the present disclosure is generally executed by the server 105 with strong computing power and a large amount of computing resources, and accordingly, the device for drawing a road intersection is generally also arranged in the server 105. However, it should also be noted that when the terminal devices 101, 102, 103 also have computing power and computing resources that meet the requirements, the terminal devices 101, 102, 103 can also complete the above-mentioned operations performed by the server 105 through the high-definition map maintenance application installed thereon, and then output the same result as the server 105. Especially in the case where there are multiple terminal devices with different computing power, but the high-definition map maintenance application determines that the terminal device has strong computing power and a large amount of remaining computing resources, the terminal device can be allowed to perform the above-mentioned operations, thereby appropriately reducing the computing pressure of the server 105, and accordingly, the device for drawing a road intersection can also be arranged in the terminal devices 101, 102, 103. In this case, the exemplary system architecture 100 can also not include the server 105 and the network 104.

[0023] It should be understood that Figure 1 the number of terminal devices, networks and servers inmay be only illustrative. According to the needs of implementation, there can be any number of terminal devices, networks and servers.

[0024] Please refer to Figure 2 , Figure 2 a flowchart of a process for drawing a road intersection provided by an embodiment of the present disclosure, which includes the process 200.

[0025] The process 200 can specifically include the following steps: Step 201: Extracting a target position of a single-side mounted lane line from an electronic map; In an embodiment of the present disclosure, this step is intended to acquire the electronic map by the execution subject of the method for drawing a road intersection (for example, the server 105 shown in Figure 1

[0026] In the electronic map, a "line" can be used to represent a road and a lane line in a real scene. For example, in the electronic map, a continuous line can be used to represent a road that actually exists in a physical space and an actual scene.

[0027] It should be noted that the electronic map can be obtained by the above execution subject directly from a local storage device, or from a non-local storage device (for example Figure 1 The terminal device 101, 102, and 103 shown in the figure). The local storage device can be a data storage module arranged in the above execution subject, such as a server hard disk, in which case the electronic map can be quickly read locally; the non-local storage device can also be any electronic device arranged for storing data, such as some user terminals, etc., in which case the execution subject can obtain the required electronic map by sending an acquisition command to the electronic device.

[0028] After obtaining the electronic map, the execution subject can extract a target position of a single-side mounted lane line from the electronic map. That is, the execution subject can extract a position with only one side mounted with a lane line as a target position. In an actual scene, the "target position" can usually be a position of an end of a road, a position of a stop line before a road intersection (for convenience, hereinafter referred to as "intersection"), and the like.

[0029] For the convenience of understanding such a target position, reference can also be made to Figure 3a . Figure 3a An effect schematic diagram of an electronic map in an application scenario provided by the embodiments of the present disclosure is shown, which includes an electronic map 300a.

[0030] In the electronic map 300a, a "line" depicted in a style 310 can be used to represent, record, and depict a position of a lane (line) in a real scene.

[0031] After obtaining the electronic map 300a, the execution subject can determine target positions 301, 302, 303, and 304 with only one side mounted with a lane line. For example, the target position 301 has only "lane lines" mounted on the upper side, the target position 302 has only "lane lines" mounted on the left side, the target position 303 has only "lane lines" mounted on the lower side, and the target position 304 has only "lane lines" mounted on the right side.

[0032] Step 202: drawing a target line segment based on a lane line group mounted at the target position; In the embodiments of the present disclosure, after determining the target position based on the above step 201, the execution subject can draw a target line segment based on a lane line group mounted at the target position.

[0033] The target line segment can be a line segment that starts from and ends at the end points of two outermost lane lines in the lane line group to which the target line segment is mounted, and passes through each lane line included in the lane line group.

[0034] For the convenience of understanding such a target line segment, reference can also be made to Figure 3b . Figure 3b An effect schematic diagram of an electronic map in an application scenario provided by the embodiments of the present disclosure is shown in FIG. 3, which includes an electronic map 300b.

[0035] Based on the electronic map 300a shown in FIG. 3, the execution subject can draw a target line segment 311 corresponding to the target position 301 (for example, the target line segment 311 can be drawn based on the end points of the lane line 315 and the lane line 316), a target line segment 312 corresponding to the target position 302, a target line segment 313 corresponding to the target position 303, and a target line segment 314 corresponding to the target position 304 based on the lane lines mounted by the target positions 301, 302, 303 and 304, to obtain the electronic map 300b.

[0036] It should be understood that in different scenarios and requirements, the target line segment can be a "straight line segment" or a "curve line segment", and the present disclosure does not limit this. For example, in the case where the end points of each lane line in the lane line group in the electronic map are not aligned, the "target line segment" can also be a "curve line segment", a "polygon line segment" or a "curve line segment" for connecting the end points in sequence.

[0037] Step 203: clustering the target line segments based on the distances between the target line segments to obtain a clustering result; In the embodiments of the present disclosure, after the execution subject determines and draws the target line segments corresponding to each target position based on the above-mentioned step 203, the execution subject can cluster the target line segments based on the distances between the target line segments to obtain a clustering result.

[0038] For example, the execution subject can cluster the target line segments whose distances between the midpoints and the same side end points are less than or equal to a predetermined or preset distance threshold as one clustering result (or a clustering cluster or a clustering set) based on the distances. In some embodiments, the distance can be determined based on the distances of the target line segments that can be trusted to belong to the same "intersection".

[0039] Correspondingly, the "target line segments" belonging to the same clustering result can be "considered" by the execution subject to be from or belong to the same intersection.

[0040] In some embodiments, based on the size of the electronic map, the indicated range difference, the clustering result can not be limited to one, but also can be multiple (for example, in the case of including multiple intersections in the electronic map, multiple clustering results can be obtained in this step). But for the convenience of understanding, the following will mainly discuss one specific clustering result, and accordingly, in the case of multiple clustering results, the execution subject can similarly process each clustering result in a similar manner.

[0041] Step 204: Based on the target line segments included in the clustering result, draw the map package block corresponding to the clustering result in the electronic map.

[0042] In an embodiment of the present disclosure, based on the above step 203, in this step, the execution subject can generate a map package block corresponding to each clustering result for representing the part of the intersection in the electronic map.

[0043] The map package block can be a "closed area" formed by the execution subject connecting the end points of the target line segments included in the same clustering result in sequence.

[0044] For example, the execution subject can start from one end point of any target line segment in a clockwise or counterclockwise direction, and sequentially connect the end points of each target line segment (for example, using a "straight line" to connect the two end points) to form the "closed area", that is, the map package block.

[0045] Correspondingly, after completing the drawing, the execution subject can use the map package block to correspond to and indicate the "intersection" and "road crossing" mentioned above.

[0046] For the convenience of understanding, please continue to refer to Figure 3b In Figure 3b , the execution subject can exemplarily use line segment 321 to connect the "left end point" of target line segment 311 with the "upper end point" of target line segment 312 in a clockwise direction; then continue to use line segment 322 to connect the "lower end point" of target line segment 312 with the "left end point" of target line segment 313; then similarly connect target line segments 313 and 314 through line segment 323, and connect target line segments 314 and 311 through line segment 324.

[0047] Finally, a closed area formed by line segments 321, 322, 323, 324, and target line segments 311 to 314 is obtained, and a map package block 330 is obtained.

[0048] Correspondingly, the user, the controller of the autonomous driving vehicle, etc. can learn from the map tile 330 that the area corresponding to the "intersection" in the electronic map 300b (for example, the area indicated by the map tile 330) and correspondingly select the adjustment strategy when the vehicle enters the area to better pass through the intersection. For example, the controller of the autonomous driving vehicle can change the control strategy of tracing the "lane line" to the intersection passing strategy of planning the path based on the obstacles included in the scene image after the autonomous driving vehicle enters the map tile 330, determining the lane of the intersection based on the scene image, and so on.

[0049] In some embodiments, in order to more accurately determine the range of the intersection and improve the accuracy of the map tile (for example, reduce the area included in the map tile 330 that does not belong to the "road"), the execution subject can also select to connect the target line segments based on the Bezier curve in the process of drawing the map tile based on the target line segments included in the clustering result. That is, the above-mentioned line segments 321, 322, 323 and 324 are drawn using the Bezier curve to avoid that the map tile drawn and depicted by the "straight line segment" cannot accurately fit the actual road scene.

[0050] Specifically, the execution subject can select to construct a second-order Bezier curve for connecting adjacent target line segments in the clustering result based on the pre-determined control point parameters (for example, the control point parameters determined based on the "arc" and "radius" of each lane in the intersection in the real scene).

[0051] Then, the execution subject draws the map tile corresponding to the clustering result by connecting the target line segments in the clustering result and the second-order Bezier curve.

[0052] For the convenience of understanding such a process, reference can also be made to Figure 3c . Figure 3c The effect schematic diagram of the electronic map in an application scenario provided by the embodiments of the present disclosure is shown, which includes the electronic map 300c.

[0053] In the electronic map 300c, the execution subject distinguishes from the above-mentioned electronic map 300b, and draws the map tile 330' in a manner similar to the above-mentioned electronic map 300b, taking the line segment 321' as the replacement of the above-mentioned line segment 321, taking the line segment 322' as the replacement of the above-mentioned line segment 322, taking the line segment 323' as the replacement of the above-mentioned line segment 323, and taking the line segment 324' as the replacement of the above-mentioned line segment 324.

[0054] In the electronic map 300c, taking the line segment 321' as an example, the execution subject can construct a "second-order Bezier curve" based on the extension lines of the outer sides of the lanes (for example, the extension line 342 of the leftmost lane of the lane line group hanging on the target line segment 311, and the extension line 341 of the uppermost lane of the lane line group hanging on the target line segment 312), and the adjustment line segment 343 determined based on the predetermined control point parameter, and then determine the line segment 321'.

[0055] In this way, in this way, not only can the edges of the drawn map blocks be smoothed, but also the area depicted by the map blocks can be closer to the real road conditions in the real scene, and the range of the intersection in the real scene can be more accurately depicted.

[0056] The method for drawing a road intersection provided in the embodiments of the present disclosure extracts a target position of a single-side hanging lane line from an electronic map; draws a target line segment based on a lane line group hanging on the target position; the two ends of the target line segment are the endpoints of the two outermost lane lines in the lane line group; clusters the target line segments based on the distance between the target line segments to obtain a clustering result; and draws a map block corresponding to the clustering result in the electronic map based on the target line segments included in the clustering result; the map block is used to indicate a road intersection. In this way, the position and range of the road intersection can be more accurately labeled in the electronic map, so that the user or the automatic driving can more specifically and granularly formulate a traffic strategy for the road intersection, and the traffic efficiency and safety are improved.

[0057] In this way, the position and range of the road intersection can be more accurately labeled in the electronic map, so that the user or the automatic driving can more specifically and granularly formulate a traffic strategy for the road intersection, and the traffic efficiency and safety are improved. For example, in an automatic driving scenario, the control party can determine whether to use a more targeted traffic strategy configured for the scenario of the road intersection to control the vehicle by identifying whether the automatic driving vehicle has entered the road intersection that may lack lane lines and guide lines. In this way, the automatic driving vehicle can differentially select a traffic strategy different from other scenarios when passing through the special scenario of the road intersection, so as to more efficiently and safely pass through the road intersection.

[0058] In some embodiments, after clustering based on the distance in the above process, in order to avoid excessive clustering or, in other words, low-quality clustering (for example, two or more intersections are mistakenly clustered as one intersection) due to the proximity of the intersections, the execution subject can also determine whether such "low-quality clustering" occurs by detecting the number of target line segments included in the process of drawing the map block.

[0059] Specifically, the execution subject can first determine whether the number of target line segments included in the clustering result is less than or equal to a number threshold (e.g., the number threshold can be determined based on an upper limit of the number of target line segments included in an intersection, which can be considered as a number threshold allowing the execution subject to perform the mapping). Accordingly, if the number of target line segments included in the clustering result is less than or equal to the number threshold, the execution subject can further select the map block corresponding to the clustering result to be mapped in the electronic map. Thus, the mapping error caused by the low-quality clustering or the poor clustering result can be avoided.

[0060] In some embodiments, the execution subject can also determine whether the clustering error occurs based on the area of the mapped map block. For example, the execution subject can determine whether the range corresponding to the map block is "reasonable" (e.g., whether the range is "too large" because multiple different intersections are fused) after the mapping is completed.

[0061] In such a case, the execution subject can first map an initial map block corresponding to the clustering result in the electronic map based on the target line segments included in the clustering result.

[0062] Then, if the area of the initial map block is less than or equal to an area threshold (e.g., the area threshold can be determined based on an upper limit of the area of a "intersection" that can be considered as a "reasonable" area), the execution subject can further select the initial map block as the map block corresponding to the clustering result in response. Thus, the mapping error caused by the low-quality clustering or the poor clustering result can be avoided.

[0063] It should be understood that, whether for the number of target line segments or the area of the map block, the execution subject can select any one of the two judgment methods or jointly use the two judgment methods in different embodiments to more accurately determine whether the low-quality clustering occurs. For example, the execution subject can first determine the number of target line segments included in the clustering result. If the number is less than or equal to the number threshold, the execution subject can correspondingly map an initial map block. Then, the execution subject can compare the area of the initial map block with the area threshold to determine whether the initial map block is selected as the map block.

[0064] Then, if the area of the initial map block is greater than the area threshold or the number of target line segments included in the clustering result is greater than the number threshold, the execution subject can select the way of re-executing the clustering to "solve" the low-quality clustering.

[0065] To better discuss the process of re-clustering, please refer to Figure 4 . Figure 4A flowchart of a process of re-executing clustering to obtain an updated clustering result is provided for embodiments of the present disclosure, which includes process 400.

[0066] Process 400 can specifically include the following steps: Step 401: determining a representative point corresponding to the target line segment based on the lane line group mounted on the target line segment; Specifically, the execution subject can first determine a representative point corresponding to the target line segment based on the lane line group mounted on the target line segment. If the lane corresponding to the lane line group is composed of separate lane directions (for example, only composed of an entering lane line group and a leaving lane line group at an intersection), in such a case, the representative point of the target line segment can be a single point. For example, it can be the midpoint of the target line segment.

[0067] In some scenarios, if the lane line group is composed of two parts (for example, composed of a first lane subgroup of an entering direction entering the intersection and a second lane subgroup of a leaving direction leaving the intersection), in such a case, the target line segment can be correspondingly determined to have two representative points for the first lane subgroup and the second lane subgroup, respectively.

[0068] For example, the target line segment can be first split into two target sub-line segments of equal length, and then the midpoints of the two target sub-line segments are taken as the representative points (correspondingly, each representative point represents the part of the lane subgroup mounted on the target sub-line segment).

[0069] For the convenience of understanding such a case, reference can also be made to Figure 5a and 5b . Figure 5a and 5b An effect schematic diagram of an electronic map in another application scenario is provided for embodiments of the present disclosure, wherein Figure 5a includes electronic map 500, Figure 5b includes electronic map 500'. Correspondingly, in electronic maps 500 and 500', the positions of the lanes (lines) in the real scene can continue to be recorded and depicted by using the "line" depicted by style 310.

[0070] First, in Figure 5a the electronic map 500 shown, the execution subject erroneously draws the map block 520 due to "low-quality clustering". For example, the error of the map block 520 is caused by erroneously clustering and using the target line segment 514.

[0071] Correspondingly, the exemplary execution subject can determine that re-clustering is needed by determining that the area of the map block 520 is greater than the area threshold.

[0072] Correspondingly, the execution body can firstly determine the representative points 531 and 532 of the target line segment 511, the representative points 533 and 534 of the target line segment 512, the representative points 535 and 536 of the target line segment 513, and the representative points 537 and 538 of the target line segment 514.

[0073] Step 402: for each target line segment, determining the moving direction of the representative point pair based on the lane direction of the lane line group; Specifically, after determining the representative points of each target line segment based on the above steps, the execution body can further determine the moving direction of the representative points based on the lane direction of the lane line group.

[0074] The moving direction of the representative points is actually consistent with the lane direction of the lane line group. For example, the moving direction of the representative points for the lane line group representing the lane entering the intersection can be the direction moving towards the intersection, and the moving direction of the representative points for the lane line group representing the lane leaving the intersection can be the direction moving away from the intersection.

[0075] It should be understood that if the lane line group includes two moving directions, for example, the lane line group is composed of a first lane sub-group and a second lane sub-group, in such a case, the execution body can correspondingly determine the moving direction of the representative points based on whether the representative points are associated with the first lane sub-group or the second lane sub-group. That is, two different representative points for representing the same target line segment can have different moving directions based on whether they are associated with the first lane sub-group or the second lane sub-group.

[0076] In this regard, it can be continued to refer to Figure 5a , the execution body can determine the moving direction of each representative point based on the lane line group corresponding to the target line segment 511, 512, 513 and 514. For example, the representative points 531, 533, 535 and 537 can be moving in the direction of the intersection (for example, in the direction of approaching or entering the map block 520), and the representative points 532, 534, 536 and 538 can be moving in the direction away from the intersection (for example, in the direction of moving away or leaving the map block 520).

[0077] Step 403: updating the position of each representative point based on the mean shift method to obtain the updated position of each representative point; Specifically, after determining the position of each representative point based on the above step 403, the execution body can update and move the position of each representative point in the mean shift (or Mean Shift) manner based on the predetermined Gaussian kernel function (i.e., continuously and iteratively update the position of each representative point according to the above moving direction).

[0078] In the mean shift mode, the execution subject can move each representative point in rounds. In each round, the execution subject can move each representative point by using a predetermined moving range limit, or by using a bandwidth parameter determined based on the current distribution of the representative points.

[0079] Then, the execution subject calculates the weighted average of other representative points in the neighborhood of each representative point after moving, and then performs the next round of movement based on the calculation result, so that each representative point can move to the area with higher density according to the moving direction.

[0080] For this purpose, reference can be made to Figure 5b The electronic map 500' shown in FIG. 5B shows the results of moving the representative points 531-538 in the mean shift mode.

[0081] Step 404: clustering the updated positions based on the area density of the updated positions to obtain a position clustering result; Specifically, after moving each representative point in the above manner, the execution subject can cluster each updated position based on the area density of the updated position after moving each representative point, to obtain a position clustering result. The position clustering result can include a number of representative points whose density meets the clustering requirement. Accordingly, the execution subject can consider that the updated positions included in the position clustering result belong to the same "intersection".

[0082] It should be understood that such a re-clustering process can also be understood as a process of splitting the above-mentioned clustering result, so in such a process, the updated clustering result is usually two or more results split from the clustering result.

[0083] For this purpose, reference can be made to Figure 5b After moving, the execution subject can cluster the representative points 531, 533, and 535 (corresponding to the updated positions) into a position clustering result based on the area density. Accordingly, because the representative point 537 is not clustered in the position clustering result, the position clustering result actually achieves the purpose of moving the target line segment 514 corresponding to the representative point 537 out of the clustering result (e.g., the clustering result corresponding to the map tile 520).

[0084] Step 405: obtaining an updated clustering result based on the position clustering result.

[0085] Specifically, the execution subject can take the target line segment corresponding to the representative point of the updated position in the position clustering result as the updated clustering result to complete the re-clustering process.

[0086] Thus, not only can the re-clustering and updating of the clustering result be achieved in the case that the clustering result is not actually composed of several "intersections", but also the execution subject can re-cluster by mainly referring to the lane line (group) entering the intersection and distancing the lane line (group) leaving the intersection, so as to reduce the clustering difficulty and improve the clustering effect by converging the lane lines in the same direction.

[0087] In some embodiments, if the representative point cannot be clustered into an updated clustering result because the lane line group only has the direction leaving the intersection, the execution subject can attribute it to an updated clustering result by distance-based judgment and whether the target line segment corresponding to the target line segment represented by the representative point is included in the updated clustering result (for example, only the lane line group in the direction entering the intersection) when the updated clustering result is available and reliable (i.e., the updated clustering result corresponds to and includes an intersection) in subsequent determination, so as to avoid data loss in the above-mentioned single-direction clustering.

[0088] In some embodiments, after obtaining the updated clustering result, the execution subject can similarly continue to compare the number of target line segments included in the updated clustering result with the number threshold based on the above discussion, and / or compare the area of the updated map block corresponding to the updated clustering result with the area threshold after redrawing the updated map block in the electronic map based on the updated clustering result, to determine whether the updated clustering result is still a "low-quality clustering".

[0089] Correspondingly, if the execution subject determines that the updated clustering result is no longer a "low-quality clustering" (i.e., the area of the updated map block is less than or equal to the area threshold, and the number of target line segments included in the updated clustering result is less than or equal to the number threshold), the execution subject can respond accordingly, similarly, take the above-mentioned updated map block as the map block corresponding to the updated clustering result when judging by the updated map block, or draw the map block corresponding to the updated clustering result in the electronic map based on the target line segments included in the updated clustering result when not judging by the updated map block.

[0090] Thus, in the case that the above-mentioned clustering result is determined to be a "low-quality clustering", the more accurate map block is drawn by the updated clustering result through re-clustering, so as to improve the representation accuracy of the map block.

[0091] In some embodiments, if the updated clustering result is still determined to be a "low-quality clustering", the execution subject can further re-cluster the updated clustering result again based on the K-order clustering algorithm to further and continuously optimize the updated clustering result. In this way, the execution subject can realize the coarse and fine two-level re-clustering or clustering optimization for the "low-quality clustering" by means of the above-mentioned mean shift and K-order clustering algorithm to balance the relationship between the operation resource consumption and the clustering accuracy and clustering quality.

[0092] The K-order clustering algorithm is also known as the K-means clustering algorithm. Under the K-order clustering algorithm, the execution subject can divide the updated clustering result into K clusters, each of which is represented by a centroid, and perform clustering by minimizing the sum of squared errors of the samples (i.e., target line segments) in the cluster to their centroids.

[0093] The execution subject can first split the updated clustering result or re-cluster the target line segments in the updated clustering result with K being 2. In this process, the execution subject can first determine 2 centroids, and then assign the target line segments in the updated clustering result to the corresponding centroids based on the distance to each centroid to form two different clusters.

[0094] Then, in the two clusters, the execution subject can re-calculate new centroids based on the assigned target line segments (e.g., based on mean value calculation).

[0095] Then, in the case where the two clusters no longer change or the centroid movement is less than a threshold value, or the maximum number of iterations is reached, two updated clustering sub-results (i.e., new clustering results split from the updated clustering result) are obtained.

[0096] Then, the execution subject can continue to determine whether the two updated clustering sub-results are both satisfactory (i.e., neither of them is a "low-quality clustering") in a similar manner.

[0097] Correspondingly, if neither of them is a "low-quality clustering", the execution subject can determine the map block and intersection of each of them as a new updated clustering sub-result.

[0098] If at least one of them is a "low-quality clustering", the execution subject can adjust K to 3 to re-cluster the updated clustering result again to obtain three updated clustering sub-results, and judge whether they are "low-quality clustering" in a similar manner.

[0099] Subsequently, if at least one of the three is a "low-quality cluster", the execution subject can continue to repeat the above steps by changing the way of K, until all the determined update cluster sub-results are not "low-quality clusters".

[0100] In this way, by such a way, the execution subject can use the K-order clustering algorithm to continuously split in an iterative manner until there is no longer a "low-quality cluster". In this way, the quality of the map block is affected by the appearance of the "low-quality cluster", so that the map block is misaligned.

[0101] Further referring to Figure 6 , as an implementation of the method shown in the above figures, the present disclosure provides an embodiment of a device for drawing a road intersection, which corresponds to the method embodiment shown in Figure 2 , and the device can be applied to various electronic devices.

[0102] As shown in Figure 6 , the device 600 for drawing a road intersection in this embodiment can include a position extraction unit 601, a line segment drawing unit 602, a line segment clustering unit 603, and a block drawing unit 604. The position extraction unit 601 is configured to extract a target position of a single-side mounted lane line from an electronic map; the line segment drawing unit 602 is configured to draw a target line segment based on a lane line group mounted at the target position; wherein the two ends of the target line segment are the endpoints of the two outermost lane lines in the lane line group; the line segment clustering unit 603 is configured to cluster the target line segments based on the distance between the target line segments to obtain a clustering result; and the block drawing unit 604 is configured to draw a map block corresponding to the clustering result in the electronic map based on the target line segments included in the clustering result; wherein the map block is used to indicate a road intersection.

[0103] In this embodiment, in the device 400 for drawing a road intersection: the specific processing of the position extraction unit 601, the line segment drawing unit 602, the line segment clustering unit 603, and the block drawing unit 604 and the technical effects brought by them can be respectively referred to the related descriptions of steps 201-204 in the corresponding embodiments, which will not be repeated here. Figure 2 The corresponding embodiments in the corresponding embodiments, the corresponding embodiments in the corresponding embodiments, which will not be repeated here.

[0104] In some optional implementations of this embodiment, the block drawing unit 604 includes an initial drawing sub-unit configured to draw an initial map block corresponding to the clustering result in the electronic map based on the target line segments included in the clustering result; and a first block determination sub-unit configured to determine the initial map block as the map block corresponding to the clustering result in response to the area of the initial map block being less than or equal to an area threshold.

[0105] In some optional implementations of the present embodiment, the package block drawing unit 604 further includes a first re-clustering subunit configured to, in response to the area of the initial map package block being greater than the area threshold, re-perform clustering based on the target line segments included in the clustering result to obtain an updated clustering result; a package block redrawing subunit configured to redraw, based on the target line segments included in the updated clustering result, an updated map package block corresponding to the updated clustering result in the electronic map; and a second package block determination subunit configured to, in response to the area of the updated map package block being less than or equal to the area threshold, determine the updated map package block as the map package block corresponding to the updated clustering result.

[0106] In some optional implementations of the present embodiment, the package block drawing unit 604 is further configured to, in response to the number of the target line segments included in the clustering result being less than or equal to the number threshold, draw, based on the target line segments included in the clustering result, a map package block corresponding to the clustering result in the electronic map.

[0107] In some optional implementations of the present embodiment, the package block drawing unit 604 includes a second re-clustering subunit configured to, in response to the number of the target line segments included in the clustering result being greater than the number threshold, re-perform clustering based on the target line segments included in the clustering result to obtain an updated clustering result; and a package block drawing subunit configured to, in response to the number of the target line segments included in the updated clustering result being less than or equal to the number threshold, draw, based on the target line segments included in the updated clustering result, a map package block corresponding to the updated clustering result in the electronic map.

[0108] In some optional implementations of the present embodiment, re-performing clustering based on the target line segments included in the clustering result to obtain an updated clustering result includes: determining a representative point corresponding to each target line segment based on a lane line group mounted on the target line segment; determining a moving direction corresponding to the representative point based on a lane direction of the lane line group for each target line segment, wherein the moving direction is consistent with the lane direction; updating the position of each representative point based on a mean shift manner to obtain an updated position of each representative point; clustering the updated positions based on the area density of the updated positions to obtain a position clustering result; and obtaining the updated clustering result based on the position clustering result.

[0109] In some optional implementations of the present embodiment, the apparatus 600 further includes a first re-re-clustering module configured to, in response to the area of the updated map package block being still greater than the area threshold after the corresponding updated map package block is redrawn based on the updated clustering result, re-re-cluster the updated clustering result based on a K-order clustering algorithm.

[0110] In some optional implementation forms of the embodiment, the apparatus 600 further includes a second re-clustering module configured to, in response to the number of target line segments included in the updated clustering result still being greater than the number threshold, re-cluster the updated clustering result based on the K-order clustering algorithm.

[0111] In some optional implementation forms of the embodiment, the package block drawing unit 604 includes a curve construction sub-unit configured to construct a second-order Bezier curve for connecting adjacent target line segments in the clustering result based on predetermined control point parameters; and a line segment and curve connection sub-unit configured to draw a map package block corresponding to the clustering result by connecting the target line segments in the clustering result with the second-order Bezier curve.

[0112] The embodiment provides the device for drawing a road intersection, and the device can more accurately mark the position and range of the road intersection in the electronic map, so that the user and the automatic driving can more specifically and finely formulate a traffic strategy of the road intersection, and the traffic efficiency and the traffic safety are improved.

[0113] 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.

[0114] Figure 7 A schematic block diagram of an example electronic device 700 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 assistants, cellular telephones, smartphones, 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 meant to limit implementations of the present disclosure described and / or claimed in this document.

[0115] As shown in Figure 7 The device 700 includes a computing unit 701 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 702 or a computer program loaded into a random access memory (RAM) 703 from a storage unit 708. Various programs and data required for the operation of the device 700 can also be stored in the RAM 703. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0116] A plurality of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0117] The computing unit 701 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 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, etc. The computing unit 701 performs various methods and processes described above, such as the method of mapping a road intersection. For example, in some embodiments, the method of mapping a road intersection can be implemented as a computer software program, which is tangibly embodied in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded onto the RAM 703 and executed by the computing unit 701, one or more steps of the method of mapping a road intersection described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the method of mapping a road intersection by any other appropriate means, such as by means of firmware.

[0118] Various implementations of the systems and techniques described above herein 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 (CPLD), 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.

[0119] 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 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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 arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of large management difficulty and weak business scalability in traditional physical host and virtual private server (VPS, Virtual Private Server) services. The server can also be a server of a distributed system, or a server combined with a blockchain.

[0124] According to the technical scheme of the embodiment of the present disclosure, the road intersection position and range can be more accurately labeled in the electronic map, so that the user and the automatic driving can more specifically and finely formulate the traffic strategy of the road intersection, and the traffic efficiency and the traffic safety are improved.

[0125] It should be understood that various forms of flow shown above can be used to reorder, add or delete steps. For example, each step described in the present disclosure can be executed in parallel, sequentially or in different order, as long as the desired results of the technical scheme provided by the present disclosure can be achieved, which is not limited herein.

[0126] The above detailed description does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent replacement and improvement within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A method for drawing road intersections, comprising: Extract the target location of the single-sided lane line from the electronic map; The target line segment is drawn based on the lane line group mounted on the target location; wherein, the two ends of the target line segment are the endpoints of the two outermost lane lines in the lane line group; Based on the distance between the target line segments, the target line segments are clustered to obtain the clustering results; Based on the target line segments included in the clustering results, map blocks corresponding to the clustering results are drawn in the electronic map; wherein, the map blocks are used to indicate road intersections.

2. The method according to claim 1, wherein, The step of drawing map blocks corresponding to the clustering results in the electronic map based on the target line segments included in the clustering results includes: Based on the target line segments included in the clustering results, an initial map block corresponding to the clustering results is drawn in the electronic map; In response to the initial map block having an area less than or equal to an area threshold, the initial map block is used as the map block corresponding to the clustering result.

3. The method according to claim 2, further comprising: In response to the initial map packet having an area greater than the area threshold, clustering is re-executed based on the target line segments included in the clustering results to obtain updated clustering results; Based on the target line segments included in the updated clustering results, the updated map blocks corresponding to the updated clustering results are redrawn in the electronic map; In response to the updated map block having an area less than or equal to the area threshold, the updated map block is used as the map block corresponding to the updated clustering result.

4. The method according to claim 1, wherein, The step of drawing map blocks corresponding to the clustering results in the electronic map based on the target line segments included in the clustering results includes: In response to the fact that the number of target line segments included in the clustering result is less than or equal to a number threshold, a map block corresponding to the clustering result is drawn in the electronic map based on the target line segments included in the clustering result.

5. The method according to claim 4, further comprising: If the number of target line segments included in the clustering result is greater than the number threshold, clustering is re-executed based on the target line segments included in the clustering result to obtain an updated clustering result; In response to the fact that the number of target line segments included in the updated clustering result is less than or equal to the number threshold, a map block corresponding to the updated clustering result is drawn in the electronic map based on the target line segments included in the updated clustering result.

6. The method according to claim 3 or 5, wherein re-clustering based on the target line segments included in the clustering results to obtain updated clustering results includes: The representative point corresponding to the target line segment is determined based on the lane line group attached to the target line segment; For each target line segment, the movement direction corresponding to the representative point is determined based on the lane direction of the lane line group; wherein, the movement direction is consistent with the lane direction; The positions of each representative point are updated based on the mean shift method to obtain the updated positions of each representative point. Based on the region density of the updated location, the updated location is clustered to obtain the location clustering result; The updated clustering result is obtained based on the location clustering result.

7. The method according to claim 6, further comprising: In response to the situation where, after the corresponding updated map block is redrawn based on the updated clustering result, the area of ​​the updated map block is still greater than the area threshold, the updated clustering result is re-clustered based on the K-order clustering algorithm.

8. The method according to claim 6, further comprising: If the number of target line segments included in the updated clustering result is still greater than the number threshold, the updated clustering result is re-clustered based on the K-order clustering algorithm.

9. The method according to claim 1, wherein, The step of drawing map blocks corresponding to the clustering results in the electronic map based on the target line segments included in the clustering results includes: Based on predetermined control point parameters, a second-order Bézier curve is constructed to connect adjacent target line segments in the clustering results; By connecting the target line segment in the clustering result with the second-order Bézier curve, the map block corresponding to the clustering result is drawn.

10. An apparatus for drawing road intersections, comprising: The location extraction unit is configured to extract the target location of the single-sided attached lane line from the electronic map; The line segment drawing unit is configured to draw a target line segment based on the lane line group mounted at the target location; wherein the two ends of the target line segment are the endpoints of the two outermost lane lines in the lane line group; A line segment clustering unit is configured to cluster the target line segments based on the distances between them, thereby obtaining a clustering result. A block drawing unit is configured to draw map blocks corresponding to the clustering results in the electronic map based on the target line segments included in the clustering results; wherein the map blocks are used to indicate road intersections.

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 for drawing road intersections as described in any one of claims 1-9.

12. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of drawing a road intersection as described in any one of claims 1-9.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method for drawing road intersections according to any one of claims 1-9.

Images