Map generation method and apparatus

Abstract

Embodiments of the present specification provide a map generation method and device, wherein the map generation method comprises: obtaining an initial map containing a target road, and determining a parking space corresponding to the target road in the initial map; determining a pole position in the initial map according to the parking space and a pole condition, wherein the pole position is used to configure a device for monitoring a parking state of the parking space; marking the pole position in the initial map to obtain a target map, and performing three-dimensional reconstruction on the target map to obtain a three-dimensional target map. By identifying the parking space in the map, the pole position is determined according to the pole condition and the position of the parking space, so as to automatically generate a three-dimensional map containing the pole position, thereby avoiding manual adjustment of the pole position and regeneration of the three-dimensional map, and improving the efficiency of planning and design of a parking system.

Description

TECHNICAL FIELD

[0001] Embodiments of the present specification relate to the technical field of data processing, in particular to a map generation method. BACKGROUND

[0002] With the rapid development of social economy and the continuous increase of automobile ownership, parking demand is increasingly booming, and "difficult parking and random parking" seriously affects the travel of citizens and the urban traffic environment. The road traffic pressure faced by the city increases year by year, and the phenomenon of urban traffic congestion and congestion is becoming increasingly serious. It is manifested as "difficult driving" in dynamic traffic and "difficult parking" in static traffic. For a long time, more attention has been paid to the development of dynamic traffic in the development of urban traffic, and insufficient attention has been paid to the development of static traffic, resulting in an increasingly prominent contradiction between supply and demand of parking. The problem of parking of urban vehicles has become a thorny problem and one of the biggest "urban diseases" in China's large and medium-sized cities.

[0003] In the current road parking system, simple charts and monitoring dashboards cannot meet the user's perception of the real physical world. Road parking customers are very concerned about the real-time status of the on-site road section (even back to a certain past time). Therefore, a three-dimensional reconstruction of the physical world is necessary, but the construction of a 3D model is time-consuming and labor-intensive. When planning the location of a stand, a change in one stand position often leads to the redesign of all adjacent areas, consuming a large amount of manpower and resulting in low design efficiency. SUMMARY

[0004] Therefore, the embodiments of the present specification provide a map generation method. One or more embodiments of the present specification also relate to a map generation device, a computing device, a computer-readable storage medium, and a computer program to solve the technical defects in the prior art.

[0005] According to a first aspect of the embodiments of the present specification, a map generation method is provided, comprising:

[0006] obtaining an initial map containing a target road, and determining a parking space corresponding to the target road in the initial map;

[0007] determining a stand position in the initial map according to the parking space and stand conditions, wherein the stand position is used to configure a device for monitoring the parking state of the parking space;

[0008] annotating the stand position in the initial map to obtain a target map, and performing three-dimensional reconstruction on the target map to obtain a three-dimensional target map.

[0009] According to a second aspect of the embodiments of the present specification, a map generation device is provided, comprising:

[0010] a data obtaining module configured to obtain an initial map containing a target road, and determine a parking space corresponding to the target road in the initial map;

[0011] a determining module configured to determine a pole position in the initial map according to the parking space and a pole condition, wherein the pole position is used to configure a device for monitoring a parking state of the parking space;

[0012] a generating module configured to mark the pole position in the initial map to obtain a target map, and perform three-dimensional reconstruction on the target map to obtain a three-dimensional target map.

[0013] According to a third aspect of the embodiments of the present specification, a computing device is provided, comprising:

[0014] a memory and a processor;

[0015] The memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions, and the computer executable instructions, when executed by the processor, implement the steps of the above map generation method.

[0016] According to a fourth aspect of the embodiments of the present specification, a computer readable storage medium is provided, which stores computer executable instructions, and the instructions, when executed by a processor, implement the steps of the above map generation method.

[0017] According to a fifth aspect of the embodiments of the present specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer program causes the computer to execute the steps of the above map generation method.

[0018] The embodiments of the present specification provide a map generation method and device, wherein the map generation method comprises: obtaining an initial map containing a target road, and determining a parking space corresponding to the target road in the initial map; determining a pole position in the initial map according to the parking space and a pole condition, wherein the pole position is used to configure a device for monitoring a parking state of the parking space; marking the pole position in the initial map to obtain a target map, and performing three-dimensional reconstruction on the target map to obtain a three-dimensional target map. By identifying the parking space in the map, the pole position is determined according to the pole condition and the position of the parking space, so as to automatically generate a three-dimensional map containing the pole position, thereby avoiding manual adjustment of the pole position and regeneration of the three-dimensional map, and improving the efficiency of planning and design of the parking system. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 is a flowchart of a map generation method provided by an embodiment of the present specification;

[0020] Figure 2a is a stand position diagram of a map generation method provided by an embodiment of the present specification;

[0021] Figure 2b is another stand position diagram of a map generation method provided by an embodiment of the present specification;

[0022] Figure 3 is a road splitting diagram of a map generation method provided by an embodiment of the present specification;

[0023] Figure 4 is a process flow diagram of a map generation method provided by an embodiment of the present specification;

[0024] Figure 5 is a structural diagram of a map generation apparatus provided by an embodiment of the present specification;

[0025] Figure 6 is a structural block diagram of a computing device provided by an embodiment of the present specification. DETAILED DESCRIPTION

[0026] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present specification. However, the present specification can be practiced without the specific details, other than in the examples provided herein, and it is understood that the scope of the present specification is not limited to the details below.

[0027] The terminology used in one or more embodiments of the present specification is for the purpose of describing particular embodiments only and is not intended to be limiting of one or more embodiments of the present specification. As used in one or more embodiments of the present specification and the accompanying claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in one or more embodiments of the present specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0028] It is to be understood that the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. It is to be further understood that the terms "comprises," "comprising," "includes," "including," "has," "having" and the like, when used in one or more embodiments of the present specification, specify the presence of stated features, integers, steps, operations, elements, and / or components but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It is to be understood that the terms "even number" and "odd number" include the number zero unless the context clearly dictates otherwise.

[0029] First, the nomenclature terms related to one or more embodiments of the present specification are explained.

[0030] Three-dimensional reconstruction: refers to the establishment of a mathematical model suitable for computer representation and processing of a three-dimensional object, which is the basis for processing, operating and analyzing its properties in a computer environment, and is also a key technology for establishing a virtual reality representing the objective world in a computer.

[0031] Stand: is a component of engineering construction-scaffolding engineering, as the literal interpretation, is a stand-up rod.

[0032] GeoJSON: is a format for encoding various geographic data structures, based on Javascript (JavaScript is a lightweight, interpreted or just-in-time compiled programming language with first-class functions) object notation (JavaScript Object Notation, abbreviated as JSON) geospatial information data exchange format.

[0033] CAD: use computer and its graphics equipment to help designers to carry out design work.

[0034] Three.js: is a 3D engine running in the browser.

[0035] Digital twin: is to make full use of physical model, sensor update, operation history and other data, integrate multi-disciplinary, multi-physical quantity, multi-scale, multi-probability simulation process, complete mapping in virtual space, and reflect the whole life cycle process of the corresponding entity equipment.

[0036] In the present specification, a map generation method is provided, and the present specification also relates to a map generation device, a computing device, and a computer readable storage medium, which are described in detail one by one in the following embodiments.

[0037] Reference Figure 1 , Figure 1 A flowchart of a map generation method according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0038] Step 102: obtaining an initial map containing a target road, and determining a parking space corresponding to the target road in the initial map.

[0039] Wherein, the target road can be understood as the road where the parking space to be monitored is located; the initial map can be a map obtained through an application programming interface, or a pre-established map; the parking space corresponding to the target road can be understood as the parking space beside the target road.

[0040] In actual application, before the map generation method in the specification is executed, a marker of a target road needs to be manually added, and a parking space marker beside the road can also be manually added. Specifically, for a map obtained through an application program interface, the target road can be located in the obtained map and a screenshot can be taken, a scale of the current map is obtained, map coordinates are converted into container coordinates, and container coordinates of the screenshot area are obtained. The screenshot obtained from the map is taken as a base map, wherein the unit of the container can be consistent with the size unit of the base map, for example, 1 unit in the base map represents 1 meter. It is also necessary to manually draw roads, draw parking spaces, draw obstructions (for example, trees, traffic signs, etc.), and draw areas where poles cannot be erected (for example, passages, gateways, manhole covers, underground pipelines, fire fighting facilities, etc.).

[0041] For example, a base map is obtained, the base map includes a target road, a parking space of the target road, trees, traffic signs, passages, gateways, manhole covers, underground pipelines, and fire fighting facilities, the position of the target road is determined from the map, and the parking space of the target road is determined.

[0042] In a possible implementation, the determining of the parking space corresponding to the target road in the initial map includes:

[0043] The parking space marker is searched in the initial map.

[0044] The parking space corresponding to the target road is determined according to the parking space marker.

[0045] In actual application, there are marked roads and positions of parking spaces beside the marked roads in the base map, and then the position of the parking space can be determined according to the parking space marker.

[0046] For example, the parking space identifier is searched in the base map, the parking space identifier A can be found, and the area where the parking space is located is determined according to the parking space identifier A.

[0047] The embodiment of the specification automatically determines the area where the parking space is located according to the parking space identifier, and the design efficiency is improved.

[0048] Step 104: determining a pole position according to the parking space and the pole condition in the initial map, wherein the pole position is used to configure a device for monitoring a parking state of the parking space.

[0049] The determining of the pole position according to the parking space and the pole condition can be understood as determining the position of the pole according to the parking space and a set rule, and the device for monitoring the parking state of the parking space can be a camera or the like.

[0050] In practical applications, the stand position is planned according to an algorithm, corresponding monitoring rods, cameras and other models are automatically drawn, and the association relationship between the camera and the parking space is output. See Figure 2a , Figure 2a A stand position schematic diagram of a map generation method according to an embodiment of the present specification is shown, which includes a road, a parking area, and a stand position. The parking area is provided with a plurality of parking spaces divided along the road, the stand position is on one side of the road, the parking spaces are on the other side of the road, the stand position is the placement position of the stand, and a camera can be placed on the stand. The camera can monitor the parking state of the parking space. For example, three cameras are arranged on the stand at the stand position, and the three cameras monitor the parking state of the three sections of the parking area. For example, in practical applications, if the parking area has 9 parking spaces, each camera can monitor 3 parking spaces in turn. These cameras can have a networking function, and the camera sends the captured image to the server through the network. The server analyzes and identifies the image to achieve the purpose of monitoring the parking space in the image. The camera can also have a processing function, that is, the camera can be provided with a processor to process the captured image, analyze and identify the image, and achieve the purpose of monitoring the parking space in the image. The stand position can be arranged on the opposite side of the parking space or on the same side of the parking space, and the embodiment of the present specification is not limited, as long as it can achieve the function of monitoring the state of the parking space.

[0051] In another implementable manner, see Figure 2b , Figure 2b Another stand position schematic diagram of a map generation method according to an embodiment of the present specification is shown, which includes a parking area 202, the parking area 202 includes a plurality of parking spaces 204, and the parking area 202 includes a plurality of stand positions 206. Each stand position 206 can place a stand 208, and a camera 210 can be arranged on each stand 208. The camera 210 is used to monitor the parking state of the parking space 204, such as whether there is a vehicle in the parking space 204 or a vehicle enters the parking space 204.

[0052] It should be noted that after the stand position is determined, CAD drawings, parking space association tables, equipment lists and other design files or GeoJSON format data can be derived to manually adjust the stand position.

[0053] Specifically, the stand position is determined in the initial map according to the parking space and stand condition, comprising:

[0054] determining a planning area of the target road according to the parking space;

[0055] segmenting the target road in the planning area using dichotomy to obtain a segmented road segment;

[0056] merging the segmented road segment according to a preset merging rule to obtain a merged road segment;

[0057] splitting the merged road segment according to a preset splitting rule to obtain a solving road segment;

[0058] solving the solving road segment to obtain a pole position.

[0059] The planning area refers to an area containing the target road.

[0060] In actual application, whether the equipment at the pole position can monitor the parking space needs to be considered, and then the road segment needs to be divided more accurately.

[0061] For example, the planning area of the target road A is determined, the target road A is cut in the planning area using dichotomy to obtain a target road A1 and a target road A2, whether the target road A1 and the target road A2 need to be merged is determined according to the merging rule, if not, the target road A1 and the target road A2 are both merged road segments, and whether the merged road segment needs to be split is determined, and the split road segment can be used as a solving road segment.

[0062] The embodiments of the present specification cut, merge, split and the like of the target road, so that the target road forms a final solving road, and the degree of refinement is improved, and the effect of the pole is improved.

[0063] In a possible implementation manner, the planning area of the target road is determined according to the parking space, including:

[0064] A planning road is determined by extending a preset length at both ends of the parking space.

[0065] A planning area containing the planning road is determined from the initial map.

[0066] The preset length can be 40 meters to 50 meters.

[0067] In actual application, a part of the road segment needs to be reserved in the planning area to facilitate the completion of other design planning, for example, the pole position is set at both ends of the planning road, and then the conditions of the road segments at both ends need to be known.

[0068] For example, the target road A is 40 meters, and 40 meters is extended at both ends of the target road A as a planning road, and an area containing the planning road is determined from the initial map as a planning area.

[0069] In a possible implementation, the merging the segmented road sections according to a preset merging rule to obtain a merged road section comprises:

[0070] Determining an included angle between adjacent segmented road sections, and merging the adjacent segmented road sections to obtain a merged road section in a case where the included angle is greater than a preset threshold.

[0071] The included angle between the segmented road sections can be understood as an included angle between straight lines where the segmented road sections are located, and the included angle is less than 180°.

[0072] It should be noted that, after the road is segmented by the bisection method, the included angle of the adjacent two road sections can be relatively large, and the adjacent two road sections can be regarded as a straight line and share a same vertical pole. In actual application, the road section with a turn is segmented, and the adjacent line sections are gradually merged, wherein the first and last line sections are merged in a case where an included angle between the adjacent line sections is less than a set value (any value between 150° and 160°), and each line section after the merging is a solution domain.

[0073] For example, a planning area of a target road A is determined, the target road A is cut by the bisection method in the planning area to obtain a target road A1 and a target road A2, and it is determined whether the target road A1 and the target road A2 need to be merged according to a merging rule. If an included angle between the target road A1 and the target road A2 is greater than 160°, it is determined that the target road A1 and the target road A2 need to be merged to obtain a merged road section.

[0074] For another example, a planning area of a target road A is determined, the target road A is cut by the bisection method in the planning area to obtain a target road A1 and a target road A2, and it is determined whether the target road A1 and the target road A2 need to be merged according to a merging rule. If an included angle between the target road A1 and the target road A2 is less than or equal to 160°, the target road A1 and the target road A2 are respectively taken as merged road sections.

[0075] The embodiments of the present specification can improve the utilization rate of the vertical pole by merging the adjacent road sections with a small included angle, that is, regarding the two adjacent road sections as a solution road section.

[0076] In a possible implementation, the merging the segmented road sections according to a preset merging rule to obtain a merged road section comprises:

[0077] In a case where a width of the merged road section is greater than a preset threshold, the merged road section is split to obtain a first direction road section and a second direction road section;

[0078] The first direction road section and the second direction road section are split to obtain a solution road section according to a vertical pole marking area in the first direction road section and the second direction road section.

[0079] wherein the width of the merging road section can be understood as the lane width of the road; the preset threshold value can be any value between 26 meters and 30 meters; the first direction road section and the second direction road section can be understood as the lanes of two directions of a section of road; and the pole installation area can be understood as a position where a pole is prohibited to be installed.

[0080] In actual application, if the width of the road is too large and the device on the pole cannot accurately identify the state of the parking space, the pole position needs to be set on both sides of the road. The road can be vertically split according to the width of the road: if the width of the road is greater than a set value (any value between 26 meters and 30 meters), the two sides of the road are regarded as independent solving domains. See Figure 3 Figure 3 A road splitting schematic diagram of a map generation method according to one embodiment of the present specification is shown. A road with a horizontal distance greater than a set value (any value between 16 meters and 20 meters) between adjacent two parking spaces and an intersection, a gate, etc. that cannot install a pole needs to be split into two sub-solving domains. For example, if the width of the intersection between two parking spaces is greater than 18 meters, the parking spaces on both sides of the intersection are split into sub-solving domain 1 and sub-solving domain 2. Or a road with a horizontal distance greater than a set value (any value between 46 meters and 50 meters) needs to be split.

[0081] For example, the preset threshold value is 28 meters, the planning area of the target road A is determined, the target road A is cut using the bisection method in the planning area, the target road A1 and the target road A2 are obtained, whether the target road A1 and the target road A2 need to be merged is judged according to the merging rule, if the included angle between the target road A1 and the target road A2 is less than or equal to 160°, the target road A1 and the target road A2 are regarded as merging road sections, the width of the target road A1 and the target road A2 is judged, if the width of the target road A1 and the target road A2 is greater than 28 meters, the target road A1 and the target road A2 are split into southward target road A1, northward target road A1, southward target road A2 and northward target road A2, further, whether there is a non-pole installation area in the southward target road A1, the northward target road A1, the southward target road A2 and the northward target road A2 needs to be determined, for example, there is a gate of a small community in the southward target road A1, the gate of the small community separates the parking spaces therein and the distance between them is greater than 18 meters, then the southward target road A1 is further split into first southward target road A1 and second southward target road A1, finally, the solving road sections obtained are the first southward target road A1 and the second southward target road A1, and the northward target road A1, the southward target road A2 and the northward target road A2.

[0082] ​It should be noted that there may be no area where a pole cannot be erected between two adjacent parking spaces, but the distance is too large to enable a pole to monitor, so the road also needs to be split, for example, there is a 50-meter gap between the two parking spaces in the south target road A1, and the south target road A1 is split into the first south target road A1 and the second south target road A1 at the left and right ends of the 50-meter gap. Finally, the solving road sections obtained are the first south target road A1 and the second south target road A1, and the north target road A1, the south target road A2, and the north target road A2.

[0083] The embodiment of the present specification determines the pole position by considering the road width, the area where a pole cannot be erected in the road, and the length between the parking spaces in the road, thereby improving the accuracy of the pole position.

[0084] In a possible implementation, the solving the solving road sections to obtain the pole position comprises:

[0085] determining the first number of cameras required for each of the solving road sections;

[0086] determining whether the parking spaces are continuous, and in the case that the parking spaces are not continuous, determining the interval distance between the discontinuous parking spaces;

[0087] determining a virtual parking space according to the interval distance;

[0088] allocating a camera to each parking space according to the virtual parking space, the number of parking spaces, and the first number of cameras to obtain the pole position, wherein the camera is installed on the pole at the pole position.

[0089] The first number of cameras can be the minimum number of cameras required; whether the parking spaces are continuous can be understood as whether there is a gap between the parking spaces; and the virtual parking space can be understood as a gap regarded as a parking space.

[0090] In actual application, the minimum number of cameras required to cover all parking spaces is calculated, the number of parking spaces is divided by the maximum number of parking spaces that can be monitored by a single camera, the gap between non-continuous parking spaces is regarded as a virtual parking space, and then the cameras are allocated to the parking spaces to determine the pole position.

[0091] It should be noted that the closest distance, the farthest distance, and the field of view angle of different cameras are different, and the maximum number of parking spaces that can be monitored by a single camera needs to be determined according to the model of the camera.

[0092] For example, there are 15 parking spaces in the south target road A2, and the maximum number of parking spaces watched by each camera is 4. Therefore, at least 4 cameras are needed to watch the 15 parking spaces in the south target road A2. If the 15 parking spaces are continuous, 4 cameras can be arranged. The first camera watches parking spaces numbered one, two, three, and four. The second camera watches parking spaces numbered five, six, seven, and eight. The third camera watches parking spaces numbered nine, ten, eleven, and twelve. The fourth camera watches parking spaces numbered thirteen, fourteen, and fifteen.

[0093] In a possible implementation, the virtual parking space is determined according to the interval distance, including:

[0094] If the interval distance is less than or equal to a first distance, it is determined that there is no virtual parking space.

[0095] If the interval distance is greater than the first distance, the number of virtual parking spaces is determined according to a difference between the interval distance and the first distance.

[0096] The first distance can be a distance without virtual parking space, for example, 3 meters.

[0097] In actual application, a distance less than or equal to 3 meters is regarded as 0 virtual parking space, a distance greater than 3 meters and less than or equal to 9 meters is regarded as 1 virtual parking space, and a distance greater than 9 meters and less than or equal to 15 meters is regarded as 2 virtual parking spaces.

[0098] For example, there are 15 parking spaces in the south target road A2, and the maximum number of parking spaces watched by each camera is 4. Therefore, at least 4 cameras are needed to watch the 15 parking spaces in the south target road A2. If there are discontinuous parking spaces in the 15 parking spaces, the interval between the adjacent discontinuous parking spaces is determined. If the interval between the adjacent discontinuous parking spaces is 2 meters, it is determined that there are 0 virtual parking spaces.

[0099] For example, there are 15 parking spaces in the south target road A2, and the maximum number of parking spaces watched by each camera is 4. Therefore, at least 4 cameras are needed to watch the 15 parking spaces in the south target road A2. If there are discontinuous parking spaces in the 15 parking spaces, the interval between the adjacent discontinuous parking spaces is determined. If the interval between the adjacent discontinuous parking spaces is 2 meters, it is determined that there are 0 virtual parking spaces.

[0100] In a possible implementation, the number of virtual parking spaces is determined according to the difference between the interval distance and the first distance, including:

[0101] The ratio of the difference value to a preset distance threshold is determined.

[0102] The number of virtual parking spaces is determined according to the ratio.

[0103] The preset distance threshold can be a distance threshold for determining a virtual parking space, for example, 6 meters.

[0104] For example, in the case where the first distance is 3 meters and the distance threshold is 6 meters, there are 15 parking spaces in the southbound target road A2, and the maximum number of parking spaces watched by each camera is 4, so at least 4 cameras are needed for the 15 parking spaces in the southbound target road A2. There are discontinuous parking spaces in the 15 parking spaces, and the numbers of the adjacent discontinuous parking spaces are three and four. The interval between the adjacent discontinuous parking spaces is determined. If the interval between the adjacent discontinuous parking spaces is 6 meters, 6 minus 3 and then divided by 6 is 0.5, and the virtual parking space is determined to be 1 by rounding up.

[0105] In a possible implementation, the method further includes:

[0106] According to the ratio of the number of virtual parking spaces and the number of parking spaces to the number of first cameras, the parking space corresponding to each camera is determined.

[0107] The stand pole positions are generated according to the correspondence between the parking spaces and the cameras.

[0108] For example, there are 15 parking spaces in the southbound target road A2, and the maximum number of parking spaces watched by each camera is 4, so at least 4 cameras are needed for the 15 parking spaces in the southbound target road A2. There are discontinuous parking spaces in the 15 parking spaces, and the numbers of the adjacent discontinuous parking spaces are three and four. The interval between the adjacent discontinuous parking spaces is determined. If the interval between the adjacent discontinuous parking spaces is 2 meters, then 4 cameras can be set. The first camera watches parking spaces numbered one, two, three, and four, the second camera watches parking spaces numbered five, six, seven, and eight, the third camera watches parking spaces numbered nine, ten, eleven, and twelve, and the fourth camera watches parking spaces numbered thirteen, fourteen, and fifteen. A stand pole can be set between the parking space numbered four and the parking space numbered five, and a stand pole can be set between the parking space numbered twelve and the parking space numbered thirteen. Two cameras can be set on each stand pole.

[0109] For example, there are 15 parking spaces in the southbound target road A2, and each camera can monitor up to 4 parking spaces. Therefore, at least 4 cameras are needed to monitor the 15 parking spaces in the southbound target road A2. There are discontinuous parking spaces in the 15 parking spaces, and the adjacent discontinuous parking spaces are numbered three and four. The interval between the adjacent discontinuous parking spaces is determined. If the interval between the adjacent discontinuous parking spaces is 6 meters, a virtual parking space is determined. Therefore, 4 cameras can be set up. The first camera monitors parking spaces numbered one, two, three, the second camera monitors parking spaces numbered four, five, six, and seven, the third camera monitors parking spaces numbered eight, nine, ten, and eleven, and the fourth camera monitors parking spaces numbered twelve, thirteen, fourteen, and fifteen. A stand can be set up between the parking space numbered four and the virtual parking space, and a stand can be set up between the parking space numbered eleven and the parking space numbered twelve. Two cameras can be set up on each stand.

[0110] It should be noted that when the difference between the number of parking spaces monitored by the adjacent two cameras is greater than 2, the parking space closest to the fewer one is allocated to the fewer one. For example, there are 5 parking spaces in the southbound target road A2, and each camera can monitor up to 4 parking spaces. Therefore, at least 2 cameras are needed to monitor the 5 parking spaces in the southbound target road A2. There are no discontinuous parking spaces in the 5 parking spaces. Therefore, 2 cameras can be set up. The first camera monitors parking spaces numbered one, two, three, and four, and the second camera monitors parking space numbered five. In order to evenly distribute the pressure of each camera, the first camera can be assigned to monitor parking spaces numbered one, two, and three, and the second camera can be assigned to monitor parking spaces numbered four and five.

[0111] Step 106: labeling the stand positions in the initial map to obtain a target map, and performing three-dimensional reconstruction on the target map to obtain a three-dimensional target map.

[0112] The target map can be a map with added stand positions.

[0113] In actual applications, the obtained GeoJSON format data information can be used to draw a model using the Three.js front-end open source library.

[0114] In one possible implementation, after the three-dimensional target map is obtained by performing three-dimensional reconstruction on the target map, the method further includes:

[0115] The video data is obtained, and the three-dimensional target map is updated according to the video data.

[0116] In actual applications, the update of the three-dimensional target map can be triggered by the parking space state monitored by the camera, the digital twin of the parking space can be realized, and the rotation of the camera can be controlled.

[0117] For example, after a vehicle enters a parking space, the update of the three-dimensional target map is triggered.

[0118] The embodiment of the present specification provides a map generation method and device, wherein the map generation method comprises: obtaining an initial map containing a target road, and determining a parking space corresponding to the target road in the initial map; determining a pole position in the initial map according to the parking space and a pole condition, wherein the pole position is used to configure a device for monitoring the parking state of the parking space; marking the pole position in the initial map to obtain a target map, and performing three-dimensional reconstruction on the target map to obtain a three-dimensional target map. By identifying the parking space in the map, the pole position is determined according to the pole condition and the position of the parking space, so as to automatically generate a three-dimensional map containing the pole position, thereby avoiding manual adjustment of the pole position and re-generation of the three-dimensional map, and improving the efficiency of the planning and design of the parking system.

[0119] The following describes the embodiment of the present specification in conjunction with the accompanying Figure 4 The map generation method provided in the present specification is taken as an example to further illustrate the map generation method. Wherein, Figure 4 A processing process flow diagram of a map generation method provided by an embodiment of the present specification is shown, which specifically comprises the following steps.

[0120] Step 402: The server obtains an initial map containing a target road, and determines a parking space corresponding to the target road in the initial map.

[0121] Step 404: The server determines a planning road by extending a preset length at both ends of the parking space, and determines a planning area containing the planning road from the initial map.

[0122] Step 406: The server divides the target road in the planning area to obtain a divided road section using bisection method.

[0123] Step 408: The server determines an included angle between adjacent divided road sections, and in the case that the included angle is greater than a preset threshold, the adjacent divided road sections are merged to obtain a merged road section.

[0124] Step 410: The server splits the merged road section to obtain a first direction road section and a second direction road section in the case that the width of the merged road section is greater than a preset threshold.

[0125] Step 412: The server splits the first direction road section and the second direction road section to obtain a solving road section according to a pole marking area in the first direction road section and the second direction road section.

[0126] Step 414: The server solves the solving road section to obtain a pole position.

[0127] Step 416: The server labels the pole position in the initial map to obtain a target map, and performs three-dimensional reconstruction on the target map to obtain a three-dimensional target map.

[0128] By identifying the parking space in the map, the pole position is determined according to the pole condition and the position of the parking space, so as to automatically generate a three-dimensional map containing the pole position, thereby avoiding manual adjustment of the pole position and regeneration of the three-dimensional map, and improving the efficiency of the parking system planning and design.

[0129] Corresponding to the method embodiments described above, the present specification also provides map generation device embodiments, Figure 5 The structure of a map generation device provided by an embodiment of the present specification is shown in a structural schematic diagram. As shown in the figure, Figure 5 The device comprises:

[0130] The data acquisition module 502 is configured to acquire an initial map containing a target road, and determine a parking space corresponding to the target road in the initial map;

[0131] The determination module 504 is configured to determine a pole position in the initial map according to the parking space and a pole condition, wherein the pole position is used to configure a device for monitoring the parking state of the parking space;

[0132] The generation module 506 is configured to label the pole position in the initial map to obtain a target map, and perform three-dimensional reconstruction on the target map to obtain a three-dimensional target map.

[0133] Further, the data acquisition module 502 is further configured to:

[0134] Find a parking space marker in the initial map;

[0135] Determine the parking space corresponding to the target road according to the parking space marker.

[0136] Further, the determination module 504 is further configured to:

[0137] Determine a planning area of the target road according to the parking space;

[0138] Segment the target road in the planning area using the bisection method to obtain a segmented road section;

[0139] Merge the segmented road section according to a preset merging rule to obtain a merged road section;

[0140] Split the merged road section according to a preset splitting rule to obtain a solving road section;

[0141] solving the solving path segment to obtain a pole position.

[0142] Further, the determining module 504 is further configured to:

[0143] determining an included angle between adjacent segmented path segments, and merging the adjacent segmented path segments to obtain a merged path segment when the included angle is greater than a preset threshold.

[0144] Further, the determining module 504 is further configured to:

[0145] splitting the merged path segment to obtain a first direction path segment and a second direction path segment when a width of the merged path segment is greater than a preset threshold;

[0146] splitting the first direction path segment and the second direction path segment to obtain a split path segment according to a pole marking area in the first direction path segment and the second direction path segment;

[0147] solving the split path segment to obtain a pole position.

[0148] Further, the determining module 504 is further configured to:

[0149] extending a preset length at both ends of the parking space to determine a planning road;

[0150] determining a planning area containing the planning road from the initial map.

[0151] Further, the determining module 504 is further configured to:

[0152] determining a first camera number required by a parking space in each of the solving path segments;

[0153] determining whether the parking spaces are continuous, and determining an interval distance between discontinuous parking spaces when the parking spaces are discontinuous;

[0154] determining a virtual parking space according to the interval distance;

[0155] allocating a camera to each parking space according to the virtual parking space, a number of the parking spaces, and the first camera number to obtain a pole position, wherein the camera is installed on a pole at the pole position.

[0156] Further, the determining module 504 is further configured to:

[0157] determining that the virtual parking space does not exist when the interval distance is less than or equal to a first distance;

[0158] In a case that the interval distance is greater than the first distance, the number of the virtual parking spaces is determined according to a difference between the interval distance and the first distance.

[0159] Further, the determining module 504 is further configured to:

[0160] determine a ratio of the difference and a preset distance threshold;

[0161] determine the number of the virtual parking spaces according to the ratio.

[0162] Further, the determining module 504 is further configured to:

[0163] determine the parking space corresponding to each camera according to a ratio of the number of the virtual parking spaces and the number of the cameras;

[0164] generate the pole position according to the correspondence between the parking space and the camera.

[0165] Further, the generating module 506 is further configured to:

[0166] obtain the video data, and update the three-dimensional target map according to the video data.

[0167] The embodiment of the present specification provides a map generation method and device, wherein the map generation device obtains an initial map containing a target road, and determines a parking space corresponding to the target road in the initial map; determines a pole position in the initial map according to the parking space and a pole condition, wherein the pole position is used to configure a device for monitoring the parking state of the parking space; labels the pole position in the initial map to obtain a target map, and performs three-dimensional reconstruction on the target map to obtain a three-dimensional target map. By identifying the parking space in the map, the pole position is determined according to the pole condition and the position of the parking space, so as to automatically generate a three-dimensional map containing the pole position, thereby avoiding manual adjustment of the pole position and regeneration of the three-dimensional map, and improving the efficiency of planning and design of the parking system.

[0168] The above is a schematic scheme of the map generation device of the embodiment. It should be noted that the technical scheme of the map generation device belongs to the same concept as the technical scheme of the above-mentioned map generation method, and the details of the technical scheme of the map generation device which are not described in detail can be referred to the description of the technical scheme of the above-mentioned map generation method.

[0169] Figure 6A structural block diagram of a computing device 600 according to one embodiment of this specification is shown. The components of the computing device 600 include, but are not limited to, a memory 610 and a processor 620. The processor 620 is connected to the memory 610 via a bus 630, and a database 650 is used to store data.

[0170] The computing device 600 also includes an access device 640, which enables the computing device 600 to communicate via one or more networks 660. Examples of these networks include a Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 640 may include one or more of any type of wired or wireless network interface (e.g., a Network Interface Card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) interface, a Wi-MAX interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, and so on.

[0171] In one embodiment of this specification, the above-described components of the computing device 600 and Figure 6 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 6 The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0172] The computing device 600 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or PCs. The computing device 600 can also be a mobile or stationary server.

[0173] The processor 620 is configured to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the map generation method described above.

[0174] The above is an illustrative scheme of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the map generation method described above belong to the same concept. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solution of the map generation method described above.

[0175] The embodiment of the present specification also provides a computer readable storage medium, which stores computer executable instructions, and the computer executable instructions realize the steps of the above map generation method when executed by a processor.

[0176] The above is a schematic scheme of the computer readable storage medium of the embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above map generation method belong to the same concept, and the details of the technical scheme of the storage medium which are not described in detail can be referred to the description of the technical scheme of the above map generation method.

[0177] The embodiment of the present specification also provides a computer program, which causes a computer to execute the steps of the above map generation method when the computer program is executed in the computer.

[0178] The above is a schematic scheme of the computer program of the embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the above map generation method belong to the same concept, and the details of the technical scheme of the computer program which are not described in detail can be referred to the description of the technical scheme of the above map generation method.

[0179] The above describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims can be performed in a different order than those in the embodiments and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing can be advantageous.

[0180] The computer instructions include computer program code, which can be in the form of source code, object code, executable code, or some intermediate form. The computer readable medium can include any entity or apparatus capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0181] It should be noted that, for the aforementioned method embodiments, the sequences of the described actions are not necessarily required to implement the present application, and certain actions can be performed in other sequences, or even at the same time, in accordance with the present application. Furthermore, certain actions can not be required to implement the present application. Additionally, the described embodiments are not necessarily the only possible implementation of the present application.

[0182] In the above embodiments, the description of each embodiment is focused on a certain aspect, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0183] The preferred embodiments of the present application disclosed above are only used to help explain the present application. Alternative embodiments do not describe all the details of the present application, and the present application is not limited to the specific embodiments described. Obviously, according to the content of the present application, many modifications and changes can be made. The present application selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present application, so that those skilled in the art can well understand and use the present application. The present application is limited by the claims and their full scope and equivalents.

Claims

1. A method for generating a map, comprising: obtaining an initial map containing a target road, and determining a parking space corresponding to the target road in the initial map; determining a pole location in the initial map according to the parking space and a pole condition, wherein the pole location is used to configure a device for monitoring a parking state of the parking space; the determining of the pole location in the initial map according to the parking space and the pole condition comprises: dividing the target road in the initial map to obtain the pole location under a constraint that a device at the pole location can monitor the parking space; and labeling the pole location in the initial map to obtain a target map, and performing three-dimensional reconstruction on the target map to obtain a three-dimensional target map. 2.The method of claim 1, wherein the determining of the parking space corresponding to the target road in the initial map comprises: searching for a parking space mark in the initial map; and determining the parking space corresponding to the target road according to the parking space mark. 3.The method of claim 1, wherein the dividing of the target road in the initial map to obtain the pole location under the constraint that the device at the pole location can monitor the parking space comprises: determining a planning area of the target road according to the parking space; segmenting the target road in the planning area by using a bisection method to obtain segmented road segments; merging the segmented road segments according to a preset merging rule to obtain merged road segments; splitting the merged road segments according to a preset splitting rule to obtain solving road segments; and solving the solving road segments to obtain the pole location. 4.The method of claim 3, wherein the merging of the segmented road segments according to the preset merging rule to obtain the merged road segments comprises: determining an included angle between adjacent segmented road segments, and merging the adjacent segmented road segments to obtain a merged road segment in a case where the included angle is greater than a preset threshold. 5.The method of claim 4, wherein the splitting of the merged road segments according to the preset splitting rule to obtain the solving road segments comprises: splitting the merged road segment to obtain a first direction road segment and a second direction road segment in a case where a width of the merged road segment is greater than a preset threshold; and splitting the first direction road segment and the second direction road segment according to a pole identification area in the first direction road segment and the second direction road segment to obtain solving road segments. 6.The method of claim 3, wherein the determining of the planning area of the target road according to the parking space comprises: determining a planning road by extending a preset length at both ends of the parking space; and determining a planning area containing the planning road from the initial map. 7.The method of claim 3, wherein the solving of the solving road segments to obtain the pole location comprises: determining a first number of cameras required by the parking space in each solving road segment; determining whether the parking space is continuous, and determining an interval distance between discontinuous parking spaces in a case where the parking space is discontinuous; and determining a virtual parking space according to the interval distance. ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ According to the virtual parking space and the number of parking spaces, and the first camera number, a camera is assigned to each parking space to obtain a pole position, wherein the camera is installed on the pole of the pole position.

8. The method of claim 7, wherein the determining the virtual parking space according to the interval distance comprises: in a case that the interval distance is less than or equal to a first distance, determining that the virtual parking space does not exist; in a case that the interval distance is greater than the first distance, determining the number of virtual parking spaces according to a difference between the interval distance and the first distance.

9. The method of claim 8, wherein the determining the number of virtual parking spaces according to the difference between the interval distance and the first distance comprises: determining a ratio of the difference and a preset distance threshold; determining the number of virtual parking spaces according to the ratio.

10. The method of claim 7, wherein the assigning a camera to each parking space to obtain a pole position according to the virtual parking space and the number of parking spaces, and the first camera number comprises: determining a parking space corresponding to each camera according to a ratio of the virtual parking space and the number of parking spaces, and the first camera number; generating a pole position according to the correspondence between the parking space and the camera.

11. The method of claim 1, after the three-dimensional target map is obtained by performing three-dimensional reconstruction on the target map, further comprising: obtaining video data, and updating the three-dimensional target map according to the video data.

12. A map generation apparatus, comprising: a data obtaining module configured to obtain an initial map containing a target road, and determine a parking space corresponding to the target road in the initial map; a determining module configured to determine a pole position in the initial map according to the parking space and a pole condition, wherein the pole position is used to configure a device for monitoring a parking state of the parking space; the determining module is further configured to divide the target road under the constraint that the device at the pole position can monitor the parking space to obtain the pole position; a generating module configured to mark the pole position in the initial map to obtain a target map, and perform three-dimensional reconstruction on the target map to obtain a three-dimensional target map.

13. A computing device, comprising: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions, which, when executed by the processor, implement the steps of the map generation method of any one of claims 1 to 11.

14. A computer readable storage medium storing computer executable instructions, which, when executed by a processor, implement the steps of the map generation method of any one of claims 1 to 11.

15. A computer program product, characterised in that, including computer instructions, which, when executed by a processor, implement the steps of the map generation method of any one of claims 1 to 11.

Images