Unmanned aerial vehicle outdoor parking lot surveying and mapping method and system

Abstract

The invention discloses an outdoor parking lot surveying and mapping method and system for an unmanned aerial vehicle, and relates to the technical field of data processing, and the method comprises the steps: obtaining an area where an outdoor parking lot is located, dividing the area into a plurality of dynamic coverage areas, obtaining the center position of each dynamic coverage area, obtaining the information of a vehicle in current movement, and obtaining the information of the vehicle; acquiring occupied vehicle information and non-occupied vehicle information, acquiring a visibility weight, acquiring a non-shielding parameter, and acquiring a priority index; obtaining to-be-mapped areas, sequentially arranging the to-be-mapped areas according to the descending order of the priority indexes, forming an initial mapping queue, obtaining a plurality of dynamic coverage areas with the priority indexes smaller than or equal to a preset threshold value, taking the dynamic coverage areas as delayed areas, and merging the delayed areas into the tail end of the initial mapping queue to form a target mapping queue; and configuring the unmanned aerial vehicle to sequentially complete coverage and perform surveying and mapping according to the target surveying and mapping queue. The method has the advantages of stability, reliability, high surveying and mapping efficiency and good surveying and mapping effect.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an outdoor parking lot mapping method and system using an unmanned aerial vehicle. Background Art

[0002] With the surge in the number of motor vehicles in cities, the demand for large-scale and dynamic management of outdoor parking lots is becoming increasingly urgent. Traditional parking lot mapping relies on manual inspections or fixed monitoring equipment, and has problems such as large blind spots and long update cycles.

[0003] Although drone technology has been introduced to improve surveying and mapping efficiency, there are still significant technical bottlenecks when dealing with complex dynamic scenes: First, existing drone surveying and mapping solutions mostly adopt fixed flight paths or static zoning strategies, which are difficult to adapt to the real-time changes in parking space status caused by frequent vehicle movement. For example, the parking space occupancy in high-mobility areas such as parking lot entrances and exits during peak hours changes rapidly, and existing technologies cannot predict regional dynamic trends, which causes drones to repeatedly scan these areas but miss other areas; second, low-altitude flight during drone surveying and mapping is easily interfered by occlusion caused by moving vehicles, but existing technologies only evaluate occlusion based on static spatial distance, ignoring the impact of vehicle motion characteristics on occlusion duration. Instantaneous occlusion caused by vehicle motion may cause the loss of key parking space information, resulting in a large number of invalid frames in the collected images, reducing the accuracy of parking space recognition; finally, existing solutions use equalized area division (such as grid method) and fixed priority sorting, and do not optimize the task queue in combination with regional dynamic characteristics. Drones always perform tasks in a fixed order, resulting in additional invalid collection, making it difficult to balance surveying and mapping accuracy and efficiency. Summary of the invention

[0004] In view of the defects in the prior art, the present invention provides an outdoor parking lot mapping method and system using an unmanned aerial vehicle.

[0005] A method for mapping an outdoor parking lot using a drone comprises: obtaining an area where an outdoor parking lot is located, dividing the area where the outdoor parking lot is located into a plurality of dynamic coverage areas, obtaining the center position of each dynamic coverage area, and obtaining information about currently moving vehicles in the area where the outdoor parking lot is located according to the drone, obtaining information about occupied vehicles in an i-th dynamic coverage area and information about unoccupied vehicles outside the i-th dynamic coverage area according to the currently moving vehicle information, and obtaining a visibility weight corresponding to the i-th dynamic coverage area according to the information about occupied vehicles in the i-th dynamic coverage area, and obtaining a visibility weight corresponding to the i-th dynamic coverage area according to the information about unoccupied vehicles and Obtain non-occlusion parameters corresponding to the ith dynamic coverage area at the center position, and obtain the priority index corresponding to the ith dynamic coverage area according to the visibility weight and non-occlusion parameters corresponding to the ith dynamic coverage area; obtain multiple dynamic coverage areas whose priority indexes are greater than a preset threshold and use them as areas to be surveyed, arrange the multiple areas to be surveyed in descending order according to the priority indexes to form an initial surveying and mapping queue, obtain multiple dynamic coverage areas whose priority indexes are less than or equal to the preset threshold and use them as delayed areas, and merge the multiple delayed areas into the end of the initial surveying and mapping queue to form a target surveying and mapping queue; configure the drone to complete coverage and conduct surveying in sequence according to the target surveying and mapping queue.

[0006] Optionally, obtaining the visibility weight corresponding to the ith dynamic coverage area based on the information of occupied vehicles in the ith dynamic coverage area includes: obtaining the number of occupied vehicles and the speed of each occupied vehicle in the ith dynamic coverage area based on the information of occupied vehicles in the ith dynamic coverage area, and obtaining the area of ​​the ith dynamic coverage area; obtaining the visibility weight corresponding to the ith dynamic coverage area based on the number of occupied vehicles in the ith dynamic coverage area, the speed of each occupied vehicle and the area of ​​the ith dynamic coverage area.

[0007] Optionally, the visibility weight corresponding to the ith dynamic coverage area is obtained according to the number of occupied vehicles in the ith dynamic coverage area, the speed of each occupied vehicle, and the area of ​​the ith dynamic coverage area, and is expressed as: , ;in, is the visibility weight corresponding to the i-th dynamic coverage area, is the number of occupied vehicles in the i-th dynamic coverage area, is the speed of the jth occupied vehicle in the i-th dynamic coverage area, is the area of ​​the ith dynamic coverage area, is the scaling factor.

[0008] Optionally, obtaining non-obstruction parameters corresponding to the ith dynamic coverage area based on the information of unoccupied vehicles outside the ith dynamic coverage area and the center position includes: obtaining the number of unoccupied vehicles, the speed of each unoccupied vehicle and the position of each unoccupied vehicle within the ith dynamic coverage area based on the information of unoccupied vehicles outside the ith dynamic coverage area; obtaining the distance between the position of each unoccupied vehicle and the center position of the ith dynamic coverage area and using it as the calculated distance of each unoccupied vehicle; obtaining the non-obstruction parameters corresponding to the ith dynamic coverage area based on the number of unoccupied vehicles outside the ith dynamic coverage area, the speed of each unoccupied vehicle and the calculated distance of each unoccupied vehicle.

[0009] Optionally, the non-blocking parameter corresponding to the i-th dynamic coverage area is obtained according to the number of unoccupied vehicles outside the i-th dynamic coverage area, the speed of each unoccupied vehicle, and the calculated distance of each unoccupied vehicle, and is expressed as: ;in, is the non-occlusion parameter corresponding to the ith dynamic coverage area, is the number of unoccupied vehicles outside the i-th dynamic coverage area, is the calculated distance of the number of k-th unoccupied vehicles outside the ith dynamic coverage area, is the speed of the kth unoccupied vehicle outside the ith dynamic coverage area.

[0010] Optionally, the priority index corresponding to the ith dynamic coverage area is obtained according to the visibility weight and non-occlusion parameter corresponding to the ith dynamic coverage area, expressed as: ;in, is the priority indicator corresponding to the ith dynamic coverage area, is the visibility weight corresponding to the i-th dynamic coverage area, is the non-occlusion parameter corresponding to the i-th dynamic coverage area.

[0011] Optionally, the method further includes: obtaining an interval time period, and re-obtaining current moving vehicle information in the area where the outdoor parking lot is located every interval time period, wherein the moving vehicle information includes the number of moving vehicles, the speed of the moving vehicles, and the position of the moving vehicles.

[0012] A drone-based outdoor parking lot mapping system is also provided, characterized in that the system comprises: an acquisition module for acquiring the area where the outdoor parking lot is located, and dividing the area where the outdoor parking lot is located into a plurality of dynamic coverage areas, and acquiring the center position of each dynamic coverage area, and acquiring the current moving vehicle information in the area where the outdoor parking lot is located according to the drone; a calculation and analysis module for acquiring the occupied vehicle information in the i-th dynamic coverage area and the unoccupied vehicle information outside the i-th dynamic coverage area according to the current moving vehicle information, and acquiring the visibility weight corresponding to the i-th dynamic coverage area according to the occupied vehicle information in the i-th dynamic coverage area, and acquiring the visibility weight corresponding to the unoccupied vehicle information outside the i-th dynamic coverage area according to the unoccupied vehicle information in the i-th dynamic coverage area; and The vehicle information and center position obtain the non-occlusion parameters corresponding to the ith dynamic coverage area, and obtain the priority index corresponding to the ith dynamic coverage area according to the visibility weight and non-occlusion parameters corresponding to the ith dynamic coverage area; the sequence generation module is used to obtain multiple dynamic coverage areas whose priority index is greater than a preset threshold and use them as areas to be surveyed, arrange the multiple areas to be surveyed in order from large to small according to the priority index and form an initial surveying and mapping queue, and obtain multiple dynamic coverage areas whose priority index is less than or equal to the preset threshold and use them as delayed areas, and merge the multiple delayed areas into the end of the initial surveying and mapping queue to form a target surveying and mapping queue; the surveying and mapping execution module is used to configure the UAV to complete coverage and perform surveying in sequence according to the target surveying and mapping queue.

[0013] Optionally, the calculation and analysis module is also used to: obtain the number of occupied vehicles in the i-th dynamic coverage area and the speed of each occupied vehicle based on the information of occupied vehicles in the i-th dynamic coverage area, and obtain the area of ​​the i-th dynamic coverage area; obtain the visibility weight corresponding to the i-th dynamic coverage area based on the number of occupied vehicles in the i-th dynamic coverage area, the speed of each occupied vehicle and the area of ​​the i-th dynamic coverage area.

[0014] Optionally, the calculation and analysis module is also used to: obtain the number of unoccupied vehicles, the speed of each unoccupied vehicle and the position of each unoccupied vehicle within the i-th dynamic coverage area based on the information of unoccupied vehicles outside the i-th dynamic coverage area; obtain the distance between the position of each unoccupied vehicle and the center position of the i-th dynamic coverage area and use it as the calculated distance of each unoccupied vehicle; obtain the non-occupied parameters corresponding to the i-th dynamic coverage area based on the number of unoccupied vehicles outside the i-th dynamic coverage area, the speed of each unoccupied vehicle and the calculated distance of each unoccupied vehicle.

[0015] The beneficial effects of the present invention are embodied in: In the entire drone outdoor parking lot mapping method, the entire drone outdoor parking lot mapping method, first of all, the adaptive dynamic partitioning strategy based on vehicle motion characteristics solves the problems of repeated scanning and omissions caused by traditional fixed paths or static divisions: by real-time analysis of the speed, number and area of ​​occupied vehicles in the area, the visibility weight is generated, and the non-occlusion parameters are calculated in combination with the speed and distance of unoccupied vehicles outside the area to quantify the occlusion risk, so that the drone can give priority to covering areas with few moving vehicles, low occlusion rates and low visual interference in the area. Secondly, dynamic queue generation realizes the optimal allocation of resources: through threshold screening and queue sorting, the drone switches high-value areas on demand to avoid energy waste caused by equal division. At the same time, it can also be combined with real-time data refresh to ensure that sudden traffic changes (such as holiday peaks) can be included in the queue adjustment in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0017] Figure 1 A schematic diagram of some steps of an outdoor parking lot mapping method using a drone of the present invention in one embodiment; Figure 2 It is a schematic diagram of a part of the steps of S2 in the outdoor parking lot mapping method using a drone of the present invention; Figure 3 It is a schematic diagram of another part of the steps of S2 in the outdoor parking lot mapping method of the drone of the present invention; Figure 4 The figure is a schematic diagram of the steps of the outdoor parking lot mapping method using a drone of the present invention in another embodiment. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0019] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. In addition, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0021] like Figure 1 As shown, a method for mapping an outdoor parking lot using a drone is provided, comprising: S1. Obtain the area where the outdoor parking lot is located, and divide the area where the outdoor parking lot is located into multiple dynamic coverage areas, and obtain the center position of each dynamic coverage area, and obtain the current moving vehicle information in the area where the outdoor parking lot is located according to the drone. S2. Obtain the occupied vehicle information in the ith dynamic coverage area and the unoccupied vehicle information outside the ith dynamic coverage area according to the currently moving vehicle information, obtain the visibility weight corresponding to the ith dynamic coverage area according to the occupied vehicle information in the ith dynamic coverage area, obtain the non-occupied parameter corresponding to the ith dynamic coverage area according to the unoccupied vehicle information outside the ith dynamic coverage area and the center position, and obtain the priority index corresponding to the ith dynamic coverage area according to the visibility weight and non-occupied parameter corresponding to the ith dynamic coverage area; S3, obtaining multiple dynamic coverage areas whose priority index is greater than a preset threshold and using them as areas to be surveyed and mapped, arranging the multiple areas to be surveyed and mapped in descending order of priority index to form an initial surveying and mapping queue, obtaining multiple dynamic coverage areas whose priority index is less than or equal to the preset threshold and using them as delayed areas, and merging the multiple delayed areas into the end of the initial surveying and mapping queue to form a target surveying and mapping queue; S4. Configure the drone to complete coverage and perform mapping in sequence according to the target mapping queue.

[0022] In this embodiment, it should be noted that in S1, a dynamic perception framework for the area where the outdoor parking lot is located is constructed. First, the approximate geographical location of the parking lot is obtained through positioning (such as GPS or visual SLAM), that is, the area where the outdoor parking lot is located. This is a rough location that has not been surveyed, and the area where the outdoor parking lot is located is divided into multiple coverage areas based on a preset dynamic division rule; the partitioning strategy here is not a fixed grid division. For example, at the intersection of channels where vehicles frequently intersect, smaller partitions will be generated to capture high-frequency changes; while in the long-term parking area, larger partitions are used to reduce the computational load. The center position of each partition is determined by the geometric center algorithm as the reference point for the subsequent non-occlusion parameter calculation. Secondly, the drone collects dynamic information of moving vehicles in the parking lot in real time through multi-source sensors (such as cameras and millimeter-wave radars), including the real-time coordinates, movement speed and direction of the vehicles. These data are preliminarily cleaned and fused through edge computing nodes to form a mobile vehicle heat map covering the entire field, providing real-time input for subsequent weight calculations. Through the combination of dynamic partitioning and real-time perception, a flexible mapping unit system is established for the drone to ensure that the subsequent steps can accurately capture the spatiotemporal variation characteristics of the parking lot.

[0023] For example, suppose that the area where an open-air parking lot is located includes circulation ramps, temporary shopping parking areas, and fixed employee parking areas. When executing S1, the main circulation ramps in the area where the open-air parking lot is located are divided into 6 areas (ABCDEF), of which 2 small dynamic coverage areas (AB) only cover part of the circulation ramps, 2 medium dynamic coverage areas (CD) cover part of the circulation ramps and part of the shopping area, and 2 large dynamic coverage areas (EF) cover the employee area; the center coordinates of each area are generated by the polygon centroid algorithm; then, the drone uses visual recognition technology to track that there is a car moving at 10km / h in area A, a car moving at 10km / h in area B, a car moving at 10km / h and a car moving at 15km / h in area C, a car moving at 15km / h in area D, a car moving at 20km / h in area E, and a car moving at 20km / h in area F. These real-time motion states (speed, position) are integrated into structured data, laying the data foundation for S2's priority calculation.

[0024] In S2, the mapping value of each area is dynamically evaluated, and priority indicators are generated by integrating the vehicle movement characteristics inside and outside the area. First, for each dynamic coverage area, the distribution status of the occupied vehicles in the area is analyzed: based on the number of vehicles and the speed of movement, combined with the area of ​​the area, the visibility weight is calculated. A high visibility weight represents a small number of moving vehicles and a low occlusion rate in the area, and a low visibility weight represents a large number of moving vehicles and a high occlusion rate in the area. For example, the more vehicles in the area, the slower the moving speed, and the larger the area, the higher the occlusion rate of the area, the worse the mapping effect, and the lower the visibility weight; by quantifying the visibility characteristics in the area, it is possible to identify areas with high mapping effects, providing a key basis for subsequent queue sorting. Secondly, evaluate the occlusion effect of unoccupied vehicles outside the area on the current area, and calculate the non-occlusion parameter based on the speed, position and distance of the unoccupied vehicles from the center of the area. For example, if a high-speed vehicle is close to the boundary of the area and the drone is covering and mapping the area, the vehicle's moving trajectory may quickly pass through the drone's field of view, causing a brief but serious field of view occlusion, affecting the mapping effect, and the smaller the non-occlusion parameter; while the occlusion risk of low-speed vehicles in the distance to the current area is low, the mapping effect is relatively good, and the larger the non-occlusion parameter. Finally, the priority index is obtained through the visibility weight and the non-occlusion parameter, so that the areas with large priority indexes are mapped first, and the areas with small priority indexes are processed later.

[0025] In S3, a mapping task queue is constructed that takes into account both real-time needs and resource optimization. First, high-priority dynamic coverage areas are screened out by preset thresholds. These areas usually have high visibility weights (indicating that there are few moving vehicles in the area and low occlusion rates) and low occlusion risks (such as low risk of interference from surrounding vehicles), indicating that their current mapping value is significant; these areas are arranged in descending order according to priority indicators to form an initial mapping queue to ensure that drones prioritize areas that are most likely to release vacancies or have data update needs. Secondly, low-priority areas (priority indicators do not reach the preset threshold) are classified as deferred areas and attached to the end of the initial queue in sequence. Such areas usually have low visibility weights (indicating that there are many moving vehicles in the area and high occlusion rates) and high occlusion risks (such as high risk of interference from surrounding vehicles), and have low real-time mapping needs. By dynamically merging high and low priority areas, the target mapping queue not only ensures real-time coverage of key areas, but also avoids the waste of battery life caused by excessive attention to low-value areas. For example, when the drone completes the mapping of the employee parking area, it automatically turns to deferred areas such as circulation lanes, effectively balancing the mapping response speed and global resource allocation efficiency.

[0026] For example: Assume that a parking lot is divided into six dynamic areas (AF). After calculation by S2, the priority indicators of areas B, D, and F are 1.3, 1.5, and 1.4 respectively (all higher than the preset threshold 1). They are included in the queue to be surveyed and arranged in descending order as D→F→B; the priority indicators of areas A, C, and E are 0.7, 0.8, and 0.6, and they are delayed areas. Therefore, the final arrangement order is D→F→B→C→A→E.

[0027] In S4, the dynamically generated task queue is converted into the actual mapping action of the UAV to achieve accurate and efficient regional coverage. The UAV flies to each area to be mapped in turn according to the order of the target mapping queue, and starts sensors (such as cameras and lidar) for data collection. In this process, the UAV dynamically adjusts the flight parameters in combination with real-time environmental feedback: for example, when flying to a high-priority area, if it detects that a sudden moving vehicle may cause path obstruction, it will automatically increase the flight altitude or fine-tune the route angle to avoid instantaneous field of view interference and ensure the effectiveness of the collected image. At the same time, the hovering time will be adaptively adjusted according to the area and complexity of the area. A fast scanning mode is used for small, highly dynamic areas, while the fine-grained mapping time is extended for large and complex areas, thereby maximizing the endurance utilization while ensuring data quality.

[0028] In summary, in the entire drone outdoor parking lot mapping method, first of all, the adaptive dynamic partitioning strategy based on vehicle motion characteristics solves the problems of repeated scanning and omissions caused by traditional fixed paths or static divisions: by real-time analysis of the speed, number and area of ​​occupied vehicles in the area, visibility weights are generated, and non-occlusion parameters are calculated in combination with the speed and distance of unoccupied vehicles outside the area to quantify the occlusion risk, so that drones can give priority to covering areas with few moving vehicles, low occlusion rates and low visual interference. Secondly, dynamic queue generation realizes optimal resource allocation: through threshold screening and queue sorting, drones switch high-value areas on demand to avoid energy waste caused by equal division. At the same time, they can also be combined with real-time data refresh to ensure that sudden changes in traffic flow (such as holiday peaks) can be included in queue adjustments in a timely manner.

[0029] like Figure 2 As shown, in one embodiment, obtaining the visibility weight corresponding to the i-th dynamic coverage area according to the occupied vehicle information in the i-th dynamic coverage area in S2 includes: S21. Obtain the number of occupied vehicles in the i-th dynamic coverage area and the speed of each occupied vehicle according to the information of occupied vehicles in the i-th dynamic coverage area, and obtain the area of ​​the i-th dynamic coverage area; S22. Obtain a visibility weight corresponding to the ith dynamic coverage area according to the number of occupied vehicles in the ith dynamic coverage area, the speed of each occupied vehicle, and the area of ​​the ith dynamic coverage area.

[0030] In this embodiment, it should be noted that, specifically, in S21, the number of occupied vehicles in the dynamic coverage area is first counted, and the real-time movement speed of each vehicle is recorded, and the area of ​​the area is obtained at the same time. For example, if there are multiple low-speed vehicles in a certain area, it means that the parking spaces are in a continuous occupied state, and the dense distribution of vehicles may form a blind spot; if the number of vehicles in the area is small and they move at high speed, it may be a short-term stay area. These data provide basic parameters for the subsequent visibility weight calculation, which is used to evaluate the potential degree of occlusion in the area.

[0031] S22 calculates the visibility weight through a nonlinear mapping relationship based on the parameters collected by S21. The core logic of this weight is that the more vehicles there are in the area, the slower the vehicle movement speed, and the smaller the area, the denser the vehicles are and the longer they stay, the more significant the occlusion effect on the drone's field of view, and the lower the visibility weight; conversely, when the number of vehicles is small, the moving speed is fast, or the area is large, the occlusion risk is reduced and the visibility weight increases. For example, in the temporary parking strip of the shopping area, if there are multiple slow-moving vehicles in the area and the area is small, it will be judged that its visibility weight is low, and the drone needs to adjust the scanning strategy to avoid occlusion; in the fixed parking area for employees, if the vehicle is stationary but the area is large, the visibility weight is relatively high, and the mapping can be completed quickly.

[0032] For example: suppose that a dynamic coverage area A is the entrance to a parking lot. Three cars are detected in the area looking for parking spaces at a very low speed, and the area is small. S21 counts a large number of vehicles, low speed, and a small area. Based on this, S22 calculates a low visibility weight, indicating that there is a high occlusion risk in this area. In contrast, area F is an employee parking area with only one stationary vehicle and a large area. The visibility weight calculated by S22 is higher, and the drone can efficiently complete the scan of this area. This differentiated weight assessment makes it possible to dynamically adjust the mapping strategy based on the occlusion characteristics of different areas.

[0033] In one embodiment, in S22, the visibility weight corresponding to the i-th dynamic coverage area is obtained according to the number of occupied vehicles in the i-th dynamic coverage area, the speed of each occupied vehicle, and the area of ​​the i-th dynamic coverage area, and is expressed as: , ;in, is the visibility weight corresponding to the i-th dynamic coverage area, is the number of occupied vehicles in the i-th dynamic coverage area, is the speed of the jth occupied vehicle in the i-th dynamic coverage area, is the area of ​​the ith dynamic coverage area, is the scaling factor.

[0034] In this embodiment, it should be noted that the vehicle speed The smaller the area, the longer it stays in the area, and the longer the obstruction effect on the drone's vision. Furthermore, the area The smaller the value, the denser the vehicle distribution, and the easier it is to form an occlusion blind spot. Furthermore, if the number of occupied vehicles in a dynamic coverage area is 0, the visibility weight is equal to 1 (maximum value), and the entire expression in this embodiment is based on >0, and at the same time, the number of vehicles The larger the number, the more significant the occlusion superposition effect. Specifically, the occlusion factor of a single vehicle is It indicates the coverage density of the area of ​​the vehicle under unit speed. The higher the vehicle speed ( The larger the area ( The larger the value, the smaller the occlusion effect. =100, =20, then =2000, indicating that the shading effect of high-speed vehicles in a large area is low; the average value of the total shading factor in the area , sum and average the occlusion factors of all vehicles in the area to quantify the overall occlusion intensity. Generally speaking, the number of vehicles The larger the value, the lower the vehicle speed in the area, and the smaller the average value of the total occlusion factor, which means the higher the occlusion intensity of the area. Map the sum value to the interval (0, 1) to ensure the weight Decreases as the occlusion strength increases. Scaling factor Used to adjust the sensitivity, generally between 0.001 and 0.0001, The larger it is, the steeper the effect of occlusion strength on the weight.

[0035] In summary, the traditional method only relies on the static distance and ignores the vehicle's motion characteristics; this expression introduces the speed , distinguish the occlusion differences of vehicles in different motion states; for example, The value is significantly lower than that of high-speed vehicles, which can more accurately reflect the risk of continuous occlusion, avoid invalid frames caused by occlusion, and improve the accuracy of parking space recognition. At the same time, combined with the area and number of vehicles , quantify the impact of regional density on occlusion; for example, even if there are few vehicles in a small area, the weight may drop sharply due to high density distribution; prioritize scanning low occlusion areas (high ), reduce the number of invalid collection times, and balance surveying and mapping efficiency and accuracy.

[0036] For example, based on the open-air parking lot in S1, assume that the area of ​​AB is 100, the area of ​​CD is 200, and the area of ​​EF is 300, in m 2 After the expression is entered, the visibility weight of area A is =0.622, visibility weight of area B =0.622, visibility weight of zone C =0.777, D zone visibility weight =0.817, visibility weight of zone E =0.953, visibility weight of zone F =0.953.

[0037] In summary, the high visibility weight areas (E, F) are large (300m²) and vehicles move at high speed (20km / h), so the occlusion risk is low. The medium visibility weight areas (C, D) are medium (200m²) but the vehicle speed difference is large (12.5km / h), and the dynamic changes are significant. The medium area (200m²) and a single medium-speed vehicle (15km / h) in D have a medium occlusion risk. The low visibility weight areas (A, B) are small (100m²) and vehicles move at low speeds (10km / h), so the occlusion risk is high.

[0038] like Figure 3 As shown, in one embodiment, obtaining the non-blocking parameters corresponding to the i-th dynamic coverage area according to the unoccupied vehicle information and the center position outside the i-th dynamic coverage area in S2 includes: S23, acquiring the number of unoccupied vehicles, the speed of each unoccupied vehicle, and the position of each unoccupied vehicle in the i-th dynamic coverage area according to the information of unoccupied vehicles outside the i-th dynamic coverage area; S24, obtaining the distance between the position of each unoccupied vehicle and the center position of the i-th dynamic coverage area and using it as the calculated distance of each unoccupied vehicle; S25. Obtain a non-blocking parameter corresponding to the i-th dynamic coverage area according to the number of unoccupied vehicles outside the i-th dynamic coverage area, the speed of each unoccupied vehicle, and the calculated distance of each unoccupied vehicle.

[0039] In this embodiment, it should be noted that in S23, the dynamic information of unoccupied vehicles outside the area is collected to evaluate their potential occlusion risk to the current area. First, the status data of all unoccupied vehicles outside the i-th dynamic coverage area are obtained through multi-source sensors (such as millimeter wave radar, camera), including the number of vehicles, real-time speed and position coordinates.

[0040] In S24, the relative position relationship between the unoccupied vehicles and the target area is quantified through geometric calculation. Based on the coordinates of the center of the area and the real-time position of each unoccupied vehicle, the Euclidean distance between the two is calculated as the basic parameter for evaluating the impact of occlusion. For example, a high-speed vehicle close to the center of the area may cause the loss of key parking space information due to close occlusion even if it passes by briefly; while a vehicle far away has a lower actual occlusion risk even if it is at a faster speed. By introducing the distance parameter, the spatial position and motion characteristics can be combined to accurately characterize the interference range of the vehicle on the drone's field of view.

[0041] In S25, the non-blocking parameters are calculated based on the speed, distance and number, and the visual transparency of vehicles outside the area to the current area is dynamically measured. High-speed vehicles are given a higher risk weight, but the impact of distant vehicles is weakened by the inverse of the square of the distance. For example, a high-speed vehicle close to the boundary of the area has its speed contribution amplified, while the distance attenuation effect is weak, resulting in a significant reduction in the non-blocking parameters; on the contrary, even if the low-speed vehicle is closer, its speed contribution is low and the impact on the parameters is small. This calculation logic ensures that the drone preferentially scans the areas with the least external interference, thereby reducing invalid frames and improving data quality.

[0042] In one embodiment, in S25, the non-blocking parameter corresponding to the i-th dynamic coverage area is obtained according to the number of unoccupied vehicles outside the i-th dynamic coverage area, the speed of each unoccupied vehicle, and the calculated distance of each unoccupied vehicle, and is expressed as: ;in, is the non-occlusion parameter corresponding to the ith dynamic coverage area, is the number of unoccupied vehicles outside the i-th dynamic coverage area, is the calculated distance of the number of k-th unoccupied vehicles outside the ith dynamic coverage area, is the speed of the kth unoccupied vehicle outside the ith dynamic coverage area.

[0043] In this embodiment, it should be noted that the speed Located in the molecule, The faster it is, the shorter the time it takes to pass through the drone's field of view after entering the area, and the lower the instantaneous occlusion risk. The greater the positive contribution; The slower the speed, the longer the time spent in the field of vision after entering the area, and the higher the risk of occlusion. By using speed as the numerator, the drone is encouraged to prioritize scanning the areas affected by high-speed vehicles (because of their short occlusion time) and postpone scanning the areas disturbed by low-speed vehicles.

[0044] Further, distance The square is in the numerator to achieve attenuation. The occlusion effect decays inversely with the distance. For example, a vehicle 10 meters away from the center of the area has four times the impact of a vehicle 20 meters away. Close-range priority avoidance is achieved. The closer the distance, the higher the probability that the vehicle will block the drone's field of view. The negative impact of close-range vehicles is amplified by the square term in the denominator.

[0045] Furthermore, The dynamic impact of all unoccupied vehicles outside the area is combined to quantify the overall field of vision. The more, the higher the cumulative risk. The larger the value.

[0046] In summary, the traditional method only evaluates occlusion based on static distance, while this formula introduces speed to distinguish the impact of vehicles in different motion states. It accurately quantifies the contribution of vehicle position to occlusion through the inverse square of distance, and dynamically adjusts the priority based on speed, giving priority to scanning areas with the least interference from external vehicles and optimizing the mapping queue.

[0047] For example, according to the open-air parking lot in S1, taking the third area C as an example, the unoccupied vehicles outside the area are located in A, B, D, E, and F, and the Euclidean distances between them and the center of area C are 15m, 12m, 8m, 12m, and 15m respectively. After substituting into the expression for calculation, =0.044+0.069+0.234+0.138+0.088=0.573.

[0048] In one embodiment, the priority index corresponding to the ith dynamic coverage area is obtained according to the visibility weight and non-occlusion parameter corresponding to the ith dynamic coverage area in S2 and is expressed as: ;in, is the priority indicator corresponding to the ith dynamic coverage area, is the visibility weight corresponding to the i-th dynamic coverage area, is the non-occlusion parameter corresponding to the i-th dynamic coverage area.

[0049] In this embodiment, it should be noted that only when the internal occlusion of the region is low ( large) and small external interference ( When the Only then can it be significantly improved. Nonlinear suppression: If any parameter ( or ) is too low, the product result will be greatly suppressed to avoid a single indicator misleading the priority. The product operation requires that the surveying area must meet both low internal occlusion and low external interference, so as to accurately select the area with the best comprehensive conditions.

[0050] Furthermore, the traditional solution cannot distinguish the difference between internal and external occlusion due to fixed weights, resulting in repeated scanning of high dynamic areas (such as parking lot exits). This solution uses product operations to associate internal vehicle density with external vehicle movement and dynamically adjusts the priority. For example: during peak hours, the exit area: there are many vehicles inside ( low), but external vehicles pass quickly ( High), if If it is still below the threshold, the scan will be postponed to avoid invalid collection; during off-peak hours, the staff area: the internal vehicles are stationary ( High), no external interference ( High), priority scanning.

[0051] like Figure 4 As shown, in one embodiment, the entire drone outdoor parking lot mapping method further includes: S5. Obtain an interval time period, and re-obtain the current moving vehicle information in the area where the outdoor parking lot is located every interval time period, wherein the moving vehicle information includes the number of moving vehicles, the speed of the moving vehicles, and the position of the moving vehicles.

[0052] In this embodiment, it should be noted that S5 ensures that the drone mapping task always responds to the dynamic changes of the parking lot through a periodic data refresh mechanism. The system presets a fixed interval time (such as 5 minutes), and re-collects the information of all mobile vehicles (quantity, speed, location) after each interval, and triggers the priority calculation process from S1 to S3 to generate an updated target mapping queue. For example, if an area was marked as low priority due to stationary vehicles in the previous cycle, but multiple cars were detected to start and leave in the new cycle, the system will immediately increase its priority index and insert it to the front of the queue. This dynamic update mechanism solves the problem of repeated scanning or omissions caused by data lag in traditional solutions, and is particularly suitable for scenarios with sudden changes in traffic flow (such as holiday peaks and emergencies).

[0053] An outdoor parking lot mapping system using a drone is also provided, wherein the system comprises: The acquisition module is used to obtain the area where the outdoor parking lot is located, and divide the area where the outdoor parking lot is located into multiple dynamic coverage areas, and obtain the center position of each dynamic coverage area, and obtain the current moving vehicle information in the area where the outdoor parking lot is located according to the drone. A calculation and analysis module, for obtaining information of occupied vehicles in the ith dynamic coverage area and information of unoccupied vehicles outside the ith dynamic coverage area based on information of currently moving vehicles, and obtaining a visibility weight corresponding to the ith dynamic coverage area based on information of occupied vehicles in the ith dynamic coverage area, and obtaining a non-occupied parameter corresponding to the ith dynamic coverage area based on information of unoccupied vehicles outside the ith dynamic coverage area and a center position, and obtaining a priority index corresponding to the ith dynamic coverage area based on the visibility weight and non-occupied parameter corresponding to the ith dynamic coverage area; A sequence generation module is used to obtain multiple dynamic coverage areas whose priority indicators are greater than a preset threshold and use them as areas to be surveyed and mapped, arrange the multiple areas to be surveyed and mapped in order from large to small according to the priority indicators and form an initial surveying and mapping queue, and obtain multiple dynamic coverage areas whose priority indicators are less than or equal to the preset threshold and use them as delayed areas, and merge the multiple delayed areas into the end of the initial surveying and mapping queue to form a target surveying and mapping queue; The surveying and mapping execution module is used to configure the drone to complete coverage and perform surveying in sequence according to the target surveying and mapping queue.

[0054] In one embodiment, the calculation and analysis module is also used to: obtain the number of occupied vehicles in the i-th dynamic coverage area and the speed of each occupied vehicle based on the information of occupied vehicles in the i-th dynamic coverage area, and obtain the area of ​​the i-th dynamic coverage area; obtain the visibility weight corresponding to the i-th dynamic coverage area based on the number of occupied vehicles in the i-th dynamic coverage area, the speed of each occupied vehicle and the area of ​​the i-th dynamic coverage area.

[0055] In one embodiment, the calculation and analysis module is also used to: obtain the number of unoccupied vehicles, the speed of each unoccupied vehicle and the position of each unoccupied vehicle within the i-th dynamic coverage area based on the information of unoccupied vehicles outside the i-th dynamic coverage area; obtain the distance between the position of each unoccupied vehicle and the center position of the i-th dynamic coverage area and use it as the calculated distance of each unoccupied vehicle; obtain the non-occupied parameters corresponding to the i-th dynamic coverage area based on the number of unoccupied vehicles outside the i-th dynamic coverage area, the speed of each unoccupied vehicle and the calculated distance of each unoccupied vehicle.

[0056] In this embodiment, it should be noted that regarding the outdoor parking lot mapping system of the above-mentioned drone, the specific method of performing the operation has been described in detail in the implementation of the outdoor parking lot mapping method of the drone, and will not be elaborated here.

[0057] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0058] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0059] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

[0060] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for mapping an outdoor parking lot using a drone, characterized in that: include: Obtain the area where the outdoor parking lot is located, divide the area where the outdoor parking lot is located into multiple dynamic coverage areas, obtain the center position of each dynamic coverage area, and obtain the current moving vehicle information in the area where the outdoor parking lot is located based on the drone. Obtain the occupied vehicle information within the ith dynamic coverage area and the unoccupied vehicle information outside the ith dynamic coverage area according to the currently moving vehicle information, obtain the visibility weight corresponding to the ith dynamic coverage area according to the occupied vehicle information within the ith dynamic coverage area, obtain the non-occupied parameter corresponding to the ith dynamic coverage area according to the unoccupied vehicle information outside the ith dynamic coverage area and the center position, and obtain the priority index corresponding to the ith dynamic coverage area according to the visibility weight and non-occupied parameter corresponding to the ith dynamic coverage area; Acquire multiple dynamic coverage areas whose priority index is greater than a preset threshold and use them as areas to be surveyed and mapped, arrange the multiple areas to be surveyed and mapped in descending order according to the priority index to form an initial surveying and mapping queue, acquire multiple dynamic coverage areas whose priority index is less than or equal to the preset threshold and use them as delayed areas, and merge the multiple delayed areas into the end of the initial surveying and mapping queue to form a target surveying and mapping queue; Configure the drones to complete coverage and conduct mapping in sequence according to the target mapping queue.

2. The outdoor parking lot mapping method using a drone according to claim 1, characterized in that: The obtaining of the visibility weight corresponding to the ith dynamic coverage area according to the occupied vehicle information in the ith dynamic coverage area comprises: According to the occupied vehicle information in the i-th dynamic coverage area, the number of occupied vehicles in the i-th dynamic coverage area and the speed of each occupied vehicle are obtained, and the area of ​​the i-th dynamic coverage area is obtained; Obtain a visibility weight corresponding to the ith dynamic coverage area according to the number of occupied vehicles in the ith dynamic coverage area, the speed of each occupied vehicle, and the area of ​​the ith dynamic coverage area.

3. The outdoor parking lot mapping method using a drone according to claim 2, characterized in that: The visibility weight corresponding to the ith dynamic coverage area is obtained according to the number of occupied vehicles in the ith dynamic coverage area, the speed of each occupied vehicle and the area of ​​the ith dynamic coverage area as follows: , ;in, is the visibility weight corresponding to the i-th dynamic coverage area, is the number of occupied vehicles in the i-th dynamic coverage area, is the speed of the jth occupied vehicle in the i-th dynamic coverage area, is the area of ​​the ith dynamic coverage area, is the scaling factor.

4. The outdoor parking lot mapping method using a drone according to claim 1, characterized in that: The step of obtaining the non-blocking parameter corresponding to the i-th dynamic coverage area according to the unoccupied vehicle information and the center position outside the i-th dynamic coverage area includes: According to the information of unoccupied vehicles outside the i-th dynamic coverage area, the number of unoccupied vehicles, the speed of each unoccupied vehicle and the position of each unoccupied vehicle in the i-th dynamic coverage area are obtained; Obtain the distance between the position of each unoccupied vehicle and the center position of the i-th dynamic coverage area and use it as the calculated distance of each unoccupied vehicle; The non-blocking parameter corresponding to the ith dynamic coverage area is obtained according to the number of unoccupied vehicles outside the ith dynamic coverage area, the speed of each unoccupied vehicle, and the calculated distance of each unoccupied vehicle.

5. The outdoor parking lot mapping method using a drone according to claim 4, characterized in that: The non-blocking parameter corresponding to the i-th dynamic coverage area is obtained according to the number of unoccupied vehicles outside the i-th dynamic coverage area, the speed of each unoccupied vehicle and the calculated distance of each unoccupied vehicle as follows: ;in, is the non-occlusion parameter corresponding to the ith dynamic coverage area, is the number of unoccupied vehicles outside the i-th dynamic coverage area, is the calculated distance of the number of k-th unoccupied vehicles outside the ith dynamic coverage area, is the speed of the kth unoccupied vehicle outside the ith dynamic coverage area.

6. The outdoor parking lot mapping method using a drone according to claim 1, characterized in that: The priority index corresponding to the ith dynamic coverage area is obtained according to the visibility weight and non-occlusion parameter corresponding to the ith dynamic coverage area as follows: ;in, is the priority indicator corresponding to the ith dynamic coverage area, is the visibility weight corresponding to the i-th dynamic coverage area, is the non-occlusion parameter corresponding to the i-th dynamic coverage area.

7. The outdoor parking lot mapping method using a drone according to claim 1, characterized in that: Also includes: The interval time period is obtained, and the current moving vehicle information in the area where the outdoor parking lot is located is re-obtained every interval time period, wherein the moving vehicle information includes the number of moving vehicles, the speed of the moving vehicles, and the position of the moving vehicles.

8. An outdoor parking lot mapping system using a drone, characterized in that: The system comprises: The acquisition module is used to obtain the area where the outdoor parking lot is located, and divide the area where the outdoor parking lot is located into multiple dynamic coverage areas, and obtain the center position of each dynamic coverage area, and obtain the current moving vehicle information in the area where the outdoor parking lot is located according to the drone. A calculation and analysis module, for obtaining information of occupied vehicles in the ith dynamic coverage area and information of unoccupied vehicles outside the ith dynamic coverage area based on information of currently moving vehicles, and obtaining a visibility weight corresponding to the ith dynamic coverage area based on information of occupied vehicles in the ith dynamic coverage area, and obtaining a non-occupied parameter corresponding to the ith dynamic coverage area based on information of unoccupied vehicles outside the ith dynamic coverage area and a center position, and obtaining a priority index corresponding to the ith dynamic coverage area based on the visibility weight and non-occupied parameter corresponding to the ith dynamic coverage area; A sequence generation module is used to obtain multiple dynamic coverage areas whose priority indicators are greater than a preset threshold and use them as areas to be surveyed and mapped, arrange the multiple areas to be surveyed and mapped in order from large to small according to the priority indicators and form an initial surveying and mapping queue, and obtain multiple dynamic coverage areas whose priority indicators are less than or equal to the preset threshold and use them as delayed areas, and merge the multiple delayed areas into the end of the initial surveying and mapping queue to form a target surveying and mapping queue; The surveying and mapping execution module is used to configure the drone to complete coverage and perform surveying in sequence according to the target surveying and mapping queue.

9. The outdoor parking lot mapping system of a drone according to claim 8, characterized in that: The calculation and analysis module is also used for: According to the occupied vehicle information in the i-th dynamic coverage area, the number of occupied vehicles in the i-th dynamic coverage area and the speed of each occupied vehicle are obtained, and the area of ​​the i-th dynamic coverage area is obtained; Obtain a visibility weight corresponding to the ith dynamic coverage area according to the number of occupied vehicles in the ith dynamic coverage area, the speed of each occupied vehicle, and the area of ​​the ith dynamic coverage area.

10. The outdoor parking lot mapping system of a drone according to claim 8, characterized in that: The calculation and analysis module is also used for: According to the information of unoccupied vehicles outside the i-th dynamic coverage area, the number of unoccupied vehicles, the speed of each unoccupied vehicle and the position of each unoccupied vehicle in the i-th dynamic coverage area are obtained; Obtain the distance between the position of each unoccupied vehicle and the center position of the i-th dynamic coverage area and use it as the calculated distance of each unoccupied vehicle; The non-blocking parameter corresponding to the ith dynamic coverage area is obtained according to the number of unoccupied vehicles outside the ith dynamic coverage area, the speed of each unoccupied vehicle, and the calculated distance of each unoccupied vehicle.

Images