Parking lot-based lidar monitoring method, system, device, and storage medium

Abstract

The application provides a parking lot-based laser radar monitoring method, system, device and storage medium, wherein the method comprises the following steps: collecting point cloud data in a parking lot and dividing the point cloud data into a static point cloud set and a dynamic point cloud set, dividing target dynamic point cloud sets to be tracked from the static point cloud set and the dynamic point cloud set, obtaining a coincidence coefficient of a first projection area of a preset parking space and a second projection area of the target dynamic point cloud set, and updating the target dynamic point cloud set to a static point cloud when the target dynamic point cloud set is static in the range of a parking space point cloud and the coincidence coefficient meets a preset threshold, and determining that a collision is sent when the nearest distance between the second contour of the target dynamic point cloud set and the third contour of the static point cloud representing all vehicles parked on the parking space is 0. The application can solve the problem of car safety protection after parking, confirm the danger and capture the relevant image, and provide the greatest vehicle safety guarantee for the owner.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence and parking lot management, and in particular to a parking lot-based laser radar monitoring method, system, equipment and storage medium. Background Art

[0002] Parking lots are places where vehicles are parked. They range from simple parking lots with marked spaces but no staff or fees, to paid parking lots equipped with entry and exit gates, parking attendants, and timekeepers. Modern parking lots often feature automated timekeeping systems, closed-circuit television, and video recorders, effectively safeguarding vehicles. Currently, when a vehicle is struck by another vehicle while parked in a parking lot, it's not immediately known, resulting in financial losses. Furthermore, parking lot security and theft prevention are poor, making it vulnerable to theft by outsiders, further compounding losses.

[0003] In view of this, the present invention proposes a parking lot-based lidar monitoring method, system, device and storage medium.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute prior art known to ordinary technicians in this field. Summary of the Invention

[0005] In response to the problems in the prior art, the purpose of the present invention is to provide a parking lot-based lidar monitoring method, system, equipment and storage medium, which overcomes the difficulties of the prior art and can use the user's various personal data to determine whether the abnormal body temperature is caused by a common cold or there is a high risk of infection with the new coronavirus, thereby accurately identifying dangerous users and reducing the risk of misjudgment.

[0006] An embodiment of the present invention provides a parking lot-based laser radar monitoring method, comprising the following steps:

[0007] Collecting point cloud data in the parking lot for modeling, dividing the point cloud data into a static point cloud set and a dynamic point cloud set, and projecting the static point cloud set onto a horizontal plane;

[0008] Segmenting a plurality of target dynamic point cloud sets of dynamic targets to be tracked from the dynamic point cloud set and projecting them onto a horizontal plane;

[0009] When the target dynamic point cloud set is stationary within the range of a parking space point cloud, and the obtained overlap coefficient between a first projection area of ​​a preset parking space and a second projection area of ​​the target dynamic point cloud set meets a preset threshold, the target dynamic point cloud set is updated to a static point cloud;

[0010] Obtain the closest distance between the second contour point cloud of the target dynamic point cloud set and the third contour point cloud representing the static point cloud of all vehicles parked in the parking spaces. When the closest distance is 0, it is determined to have sent a collision, and the camera is driven to shoot a video of the corresponding position.

[0011] Preferably, the collecting point cloud data in the parking lot for modeling, dividing the point cloud data into a static point cloud set and a dynamic point cloud set, and projecting the static point cloud set onto a horizontal plane comprises:

[0012] Collect and denoise point cloud data in the parking lot;

[0013] Modeling based on the point cloud data of the parking lot;

[0014] The point cloud data is divided into a static point cloud matrix and a dynamic point cloud matrix.

[0015] Preferably, a laser radar is used to collect point cloud data in the parking lot.

[0016] Preferably, the step of segmenting a plurality of target dynamic point cloud sets of the dynamic targets to be tracked from the dynamic point cloud set and projecting the target point cloud sets onto a horizontal plane comprises:

[0017] Segmenting a plurality of target dynamic point cloud sets and corresponding labels of dynamic targets to be tracked from the dynamic point cloud set through point cloud recognition;

[0018] Each target dynamic point cloud set is projected onto a horizontal plane.

[0019] Preferably, when the target dynamic point cloud set is stationary within the range of a parking space point cloud, and an overlap coefficient between a first projected area of ​​a preset parking space and a second projected area of ​​the target dynamic point cloud set satisfies a preset threshold, updating the target dynamic point cloud set to a static point cloud includes:

[0020] When the target dynamic point cloud set stops within a preset parking space point cloud range, a first projection area C of a first contour of the preset parking space is obtained. a The second projection area Y of the second contour of the target dynamic point cloud set a ;

[0021] Get the first projected area C a and the second projected area Y a The coincidence coefficient β is:

[0022]

[0023] When the overlap coefficient is greater than a preset threshold, and the value range of the preset threshold is 0.7 to 0.9, the dynamic point cloud corresponding to the target dynamic point cloud set is removed from the dynamic point cloud set, and added to the static point cloud set as the static point cloud marked as the vehicle parked in the parking space.

[0024] Preferably, obtaining the closest distance between the second contour point cloud of the target dynamic point cloud set and the third contour point cloud representing the static point cloud of all vehicles parked in the parking spaces, and determining that a collision is initiated when the closest distance is 0, and driving the camera to capture a video of the corresponding position, includes:

[0025] Obtaining the shortest distance between the point cloud of the second outline of the target dynamic point cloud set and the point cloud of the third outline of the static point cloud representing all vehicles parked in the parking spaces;

[0026] When the closest distance is 0, it is determined to send a collision, and the relative spatial position of the point cloud that produces the closest distance is obtained;

[0027] The camera is driven to capture the video of the relative spatial position and upload it to trigger an alarm operation.

[0028] Preferably, after obtaining the closest distance between the second contour point cloud of the target dynamic point cloud set and the third contour point cloud representing the static point cloud of all vehicles parked in the parking spaces, determining that a collision is sent when the closest distance is 0 and driving the camera to capture a video of the corresponding position, the method further includes:

[0029] The closest distance between the second contour point cloud of the target dynamic point cloud set labeled as a pedestrian and the third contour point cloud of the static point cloud representing all vehicles parked in the parking spaces is obtained. When the closest distance is greater than 0 and less than a preset distance threshold and continues to exceed a preset time threshold, where the preset time threshold ranges from 4 to 10 seconds, it is determined to be a theft, and the camera is driven to capture video of the corresponding location.

[0030] An embodiment of the present invention further provides a parking lot-based laser radar monitoring system for implementing the above-mentioned parking lot-based laser radar monitoring method. The parking lot-based laser radar monitoring system includes:

[0031] A point cloud acquisition module collects point cloud data in the parking lot for modeling, divides the point cloud data into a static point cloud set and a dynamic point cloud set, and projects the static point cloud set onto a horizontal plane;

[0032] a point cloud segmentation module, which segments a plurality of target dynamic point cloud sets of dynamic targets to be tracked from the dynamic point cloud set and projects the target dynamic point cloud sets onto a horizontal plane;

[0033] a point cloud updating module, when the target dynamic point cloud set is static within the range of a parking spot point cloud, obtaining an overlap coefficient of a first projection area of a preset parking spot and a second projection area of the target dynamic point cloud set, and updating the target dynamic point cloud set to a static point cloud when the overlap coefficient meets a preset threshold value;

[0034] a collision detection module, obtaining the nearest distance between the point cloud of the second contour of the target dynamic point cloud set and the point cloud of the third contour of the static point cloud representing all vehicles parked in the parking spots, and determining that a collision is sent when the nearest distance is 0, and driving the camera to shoot a video of the corresponding position.

[0035] Embodiments of the present application also provide a parking lot-based laser radar monitoring device, comprising:

[0036] a processor;

[0037] a memory, wherein executable instructions of the processor are stored in the memory;

[0038] The processor is configured to execute the steps of the above-mentioned parking lot-based laser radar monitoring method by executing the executable instructions.

[0039] Embodiments of the present application also provide a computer-readable storage medium for storing a program, which is executed to implement the steps of the above-mentioned parking lot-based laser radar monitoring method.

[0040] The present application aims to provide a parking lot-based laser radar monitoring method, system, device and storage medium, which can solve the problem of car safety protection after parking, confirm the danger and capture the relevant images, and provide the greatest vehicle safety guarantee for the owner. BRIEF DESCRIPTION OF DRAWINGS

[0041] Other features, objects and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments with reference to the attached drawings.

[0042] Figure 1 is a flowchart of an embodiment of the parking lot-based laser radar monitoring method of the present application.

[0043] Figure 2 is a flowchart of step S110 of the parking lot-based laser radar monitoring method of the present application.

[0044] Figure 3 is a flowchart of step S120 of the parking lot-based laser radar monitoring method of the present application.

[0045] Figure 4 is a flowchart of step S130 of the parking lot-based laser radar monitoring method of the present application.

[0046] Figure 5 is a flowchart of the middle step S140 of the parking lot based lidar monitoring method of the present application.

[0047] Figure 6 is a module diagram of an embodiment of the parking lot based lidar monitoring system of the present application.

[0048] Figure 7 is a module diagram of the point cloud collection module in the parking lot based lidar monitoring system of the present application.

[0049] Figure 8 is a module diagram of the point cloud segmentation module in the parking lot based lidar monitoring system of the present application.

[0050] Figure 9 is a module diagram of the point cloud update module in the parking lot based lidar monitoring system of the present application.

[0051] Figure 10 is a module diagram of the collision detection module in the parking lot based lidar monitoring system of the present application.

[0052] Figure 11 、 12 is a flowchart of the implementation process of the parking lot based lidar monitoring method of the present application.

[0053] Figure 13 is a schematic diagram of the parking lot based lidar monitoring device of the present application. DETAILED DESCRIPTION

[0054] The present application is described herein with reference to specific embodiments thereof, which are illustrative of the principles of the present application. Other advantages and embodiments of the present application will become apparent to those skilled in the art after considering the following detailed description in conjunction with the accompanying drawings. The detailed description set forth below in connection with the appended drawings is intended as a description of the present application and is not intended to represent the only embodiments in which the present application can be practiced. The detailed description includes specific details for the purpose of providing a thorough understanding of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced without these specific details. In some instances, well-known structures and functions have not been described in detail in order to avoid obscuring the concept of the present application.

[0055] The embodiments of the present application will be described below in detail with reference to the accompanying drawings. The present application can be embodied in many different forms, and is not limited to the embodiments described herein.

[0056] In the description of this application, reference to the terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of this application. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. In addition, those skilled in the art may combine and integrate different embodiments or examples described in this application, as well as features of different embodiments or examples, unless otherwise contradictory.

[0057] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature identified as "first" or "second" may explicitly or implicitly include at least one such feature. In the context of this application, "plurality" means two or more, unless otherwise specifically defined.

[0058] In order to clearly describe the present application, components not related to the description are omitted, and the same or similar components throughout the specification are given the same reference numerals.

[0059] Throughout this specification, when a device is said to be "connected" to another device, this includes not only "direct connection" but also "indirect connection" with other elements interposed therebetween. Furthermore, when a device is said to "include" a certain component, unless otherwise stated, this does not exclude the inclusion of other components but rather implies that the device may include other components.

[0060] When a device is said to be "on" another device, it may be directly on the other device, but there may also be other devices between it. In contrast, when a device is said to be "directly on" another device, there are no other devices between it.

[0061] Although the terms first, second, etc. are used in some instances herein to represent various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, the first interface and the second interface, etc. are represented. Furthermore, as used in this article, the singular forms "one," "an," and "the" are intended to also include the plural forms, unless there is a contrary indication in the context. It should be further understood that the terms "comprise," "include," and "include" indicate the presence of features, steps, operations, elements, components, items, types, and / or groups, but do not exclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, types, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or mean any one or any combination. Therefore, "A, B, or C" or "A, B, and / or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B, and C." Exceptions to this definition only occur when the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.

[0062] The technical terms used herein are intended only to refer to specific embodiments and are not intended to limit this application. The singular form used herein also includes the plural form unless the statement explicitly indicates otherwise. The term "comprising" as used in this specification is intended to specify specific features, regions, integers, steps, operations, elements, and / or components and does not exclude the presence or addition of other features, regions, integers, steps, operations, elements, and / or components.

[0063] Although not defined differently, all terms used herein, including technical and scientific terms, have the same meanings as those generally understood by those skilled in the art to which this application belongs. Terms defined in commonly used dictionaries are to be interpreted as having meanings consistent with the relevant technical literature and current teachings, and unless otherwise defined, they should not be overly interpreted as ideal or highly formalized meanings.

[0064] Figure 1 FIG. 1 is a flow chart of an embodiment of the parking lot-based laser radar monitoring method of the present invention. Figure 1 As shown, the parking lot-based laser radar monitoring method of the present invention includes:

[0065] S110 , collecting point cloud data in the parking lot for modeling, dividing the point cloud data into a static point cloud set and a dynamic point cloud set, and projecting the static point cloud set onto a horizontal plane.

[0066] S120 , dividing a plurality of target dynamic point cloud sets of dynamic targets to be tracked from the dynamic point cloud set, and projecting the target point cloud sets onto a horizontal plane.

[0067] S130. When the target dynamic point cloud set is stationary within the range of a parking space point cloud, and an overlap coefficient between a first projection area of ​​a preset parking space and a second projection area of ​​the target dynamic point cloud set satisfies a preset threshold, the target dynamic point cloud set is updated to a static point cloud.

[0068] S140. Obtain the closest distance between the second contour point cloud of the target dynamic point cloud set and the third contour point cloud representing the static point cloud of all vehicles parked in the parking spaces. When the closest distance is 0, determine that a collision has been sent, and drive the camera to capture a video of the corresponding position.

[0069] The present invention can solve the problem of car safety protection after parking. It can predict danger, confirm danger, accurately capture graphics and images, and can be combined with other extended accessories to warn of possible crimes and provide car owners with maximum vehicle safety protection.

[0070] Figure 2 It is a flow chart of step S110 in the parking lot-based lidar monitoring method of the present invention. Figure 3 It is a flow chart of step S120 in the parking lot-based lidar monitoring method of the present invention. Figure 4 It is a flow chart of step S130 in the parking lot-based lidar monitoring method of the present invention. Figure 5 This is a flow chart of step S140 in the parking lot-based laser radar monitoring method of the present invention. Figure 1 In the embodiment, on the basis of steps S110, S120, and S130, step S110 is replaced by S111, S112, and S113, step S120 is replaced by S121 and S122, step S130 is replaced by S131, S132, and S133, step S140 is replaced by S141, S142, and S143, and step S150 is added after step S140. Each step is described below:

[0071] S111. Use laser radar to collect point cloud data in the parking lot.

[0072] S112. Modeling is performed based on the point cloud data of the parking lot.

[0073] S113 , dividing the point cloud data into a static point cloud matrix and a dynamic point cloud matrix.

[0074] S121. Target dynamic point cloud sets and corresponding labels are segmented from the dynamic point cloud set using point cloud recognition. In this embodiment, a conventional point cloud recognition neural network is used to label dynamic targets (e.g., moving cars or pedestrians) in the dynamic point cloud set, and the point cloud sets belonging to these dynamic targets are combined into a target dynamic point cloud set.

[0075] S122. Project each target dynamic point cloud set onto a horizontal plane.

[0076] S131: When the target dynamic point cloud set stops within a preset parking space point cloud range, a first projection area C of a first contour of the preset parking space is obtained. a The second projection area Y of the second contour of the target dynamic point cloud set a .

[0077] S132, obtain the first projection area C a and the second projection area Y a The coincidence coefficient β is:

[0078]

[0079] S133. When the overlap coefficient is greater than a preset threshold value, and the preset threshold value range is 0.7 to 0.9, the dynamic point cloud corresponding to the target dynamic point cloud set is removed from the dynamic point cloud set, and is added to the static point cloud set as a static point cloud marked as a vehicle parked in the parking space.

[0080] S141 : Obtain the shortest distance between the second contour point cloud of the target dynamic point cloud set and the third contour point cloud of the static point cloud representing all vehicles parked in the parking spaces.

[0081] S142: When the closest distance is 0, it is determined that a collision is sent, and the relative spatial position of the point cloud that produces the closest distance is obtained.

[0082] S143: Drive the camera to capture a video of the relative spatial position and upload it to trigger an alarm operation. The camera in this embodiment is a camera of a monitoring table that has been calibrated with the laser radar, so that the image can be rotated toward the target direction (relative spatial position).

[0083] S150: Obtain the closest distance between the second contour point cloud of the target dynamic point cloud set labeled as a pedestrian and the third contour point cloud of the static point cloud representing all vehicles parked in the parking spaces. If the closest distance is greater than 0 and less than a preset distance threshold, and continues to exceed a preset time threshold (the preset time threshold ranges from 4 to 10 seconds), it is determined to be a theft, and the camera is activated to capture video at the corresponding location. This allows the present invention to not only detect collisions between vehicles in a garage, but also detect whether pedestrians are stealing vehicles, greatly expanding the functionality of parking lot monitoring and improving the safety of parking processes.

[0084] Figure 6 FIG. 1 is a schematic diagram of a module of an embodiment of a parking lot-based laser radar monitoring system of the present invention. Figure 6As shown, the parking lot-based laser radar monitoring system of the present application comprises but is not limited to:

[0085] The point cloud collection module 51 collects point cloud data in the parking lot for modeling, and divides the point cloud data into a static point cloud set and a dynamic point cloud set, and projects the static point cloud set onto a horizontal plane.

[0086] The point cloud segmentation module 52 segments a target dynamic point cloud set of a plurality of dynamic targets to be tracked from the dynamic point cloud set, and projects the target dynamic point cloud set onto a horizontal plane.

[0087] The point cloud updating module 53 updates the target dynamic point cloud set to a static point cloud when a coincidence coefficient of a first projection area of a preset parking space and a second projection area of the target dynamic point cloud set meets a preset threshold.

[0088] The collision detection module 54 obtains the nearest distance between the second contour point cloud of the target dynamic point cloud set and the third contour point cloud of the static point cloud representing all vehicles parked in the parking space, and determines that a collision occurs when the nearest distance is 0, and drives the camera to shoot a video of the corresponding position.

[0089] The implementation principle of the above modules is described in the related description of the parking lot-based laser radar monitoring method, which will not be repeated here.

[0090] The parking lot-based laser radar monitoring system of the present application can solve the problem of car safety protection after parking, confirm the danger and capture the relevant image, and provide the greatest vehicle safety protection for the owner.

[0091] Figure 7 is a module schematic diagram of the point cloud collection module in the parking lot-based laser radar monitoring system of the present application. Figure 8 is a module schematic diagram of the point cloud segmentation module in the parking lot-based laser radar monitoring system of the present application. Figure 9 is a module schematic diagram of the point cloud updating module in the parking lot-based laser radar monitoring system of the present application. Figure 10 is a module schematic diagram of the collision detection module in the parking lot-based laser radar monitoring system of the present application. Figure 7 、 8 、9、10 as shown in Figure 6Based on the device embodiment, the parking lot-based lidar monitoring system of the present invention replaces the point cloud acquisition module 51 with the radar acquisition module 511, the point cloud modeling module 512, and the point cloud matrix module 513. The point cloud segmentation module 52 is replaced by the point cloud recognition module 521 and the point cloud projection module 522. The point cloud update module 53 is replaced by the projection area module 531, the area overlap module 532, and the attribute update module 533. The collision detection module 54 is replaced by the contour ranging module 541, the collision detection module 542, and the monitoring trigger module 543. A theft judgment module is also added, and each module is described below:

[0092] The radar acquisition module 511 uses a laser radar to collect point cloud data in the parking lot.

[0093] The point cloud modeling module 512 performs modeling based on the point cloud data of the parking lot.

[0094] The point cloud matrix module 513 divides the point cloud data into a static point cloud matrix and a dynamic point cloud matrix.

[0095] The point cloud recognition module 521 segments a plurality of target dynamic point cloud sets of dynamic targets to be tracked from the dynamic point cloud set through point cloud recognition.

[0096] The point cloud projection module 522 projects each target dynamic point cloud set onto a horizontal plane.

[0097] The projection area module 531 obtains a first projection area C of a first outline of a preset parking space when the target dynamic point cloud set stops within the range of a preset parking space point cloud. a The second projection area Y of the second contour of the target dynamic point cloud set a .

[0098] The area overlap module 532 obtains the first projection area C a and the second projection area Y a The coincidence coefficient β is:

[0099]

[0100] The attribute update module 533 removes the dynamic point cloud corresponding to the target dynamic point cloud set from the dynamic point cloud set when the overlap coefficient is greater than a preset threshold value, and the preset threshold value range is 0.7 to 0.9, and adds the static point cloud set as the static point cloud of the vehicle marked as parked in the parking space.

[0101] The contour distance measurement module 541 obtains the shortest distance between the second contour point cloud of the target dynamic point cloud set and the third contour point cloud representing the static point cloud of all vehicles parked in the parking spaces.

[0102] The collision detection module 542 determines that a collision is sent when the closest distance is 0, and obtains the relative spatial position of the point cloud that generates the closest distance.

[0103] The monitoring trigger module 543 drives the camera to capture the video of the relative spatial position and upload it to trigger an alarm operation.

[0104] The theft determination module obtains the closest distance between the second contour point cloud of the target dynamic point cloud set and the third contour point cloud representing all vehicles parked in the parking spaces. If the closest distance is greater than 0 and less than a preset distance threshold and continues to exceed a preset time threshold (the preset time threshold ranges from 4 to 10 seconds), it is determined to be a theft and the camera is driven to capture video of the corresponding location.

[0105] The implementation principle of the above modules can be found in the relevant introduction of the parking lot-based lidar monitoring method, which will not be repeated here.

[0106] Figure 11 、 12 This is a schematic diagram of the implementation process of the parking lot-based laser radar monitoring method of the present invention. Figure 11 As shown, the purpose of the present invention is to provide a parking lot lidar protection system that can solve the problem of car safety protection after parking, can predict danger, confirm danger, accurately capture graphics and images, and can be used with other extended accessories to warn of possible crimes and provide car owners with maximum vehicle safety protection; in order to solve the problems raised in the above background technology.

[0107] To achieve the above-mentioned objectives, the present invention adopts the following technical solutions: a parking lot laser radar protection system, comprising a power supply module, a laser radar system, a control module, an alarm module, a sensing module, an infrared laser module, a camera, an image acquisition module, an object recognition module, a camera communication module, a camera storage module and an algorithm module. The laser radar system acquires data of the monitored object through multiple laser radars so as to monitor vehicles in parking spaces on a large scale and acquire more data; the acquired data is sent to a terminal on the control module so as to analyze the acquired data, and then, based on the analyzed data results, it is determined whether the camera is started; if the camera is started, the power supply module is controlled to power the camera through the laser radar system to start it for operation and acquire image data of the monitored object monitored by the camera, so as to determine whether an accident has occurred with the monitored object, so as to protect the vehicle; the image acquisition module can acquire images in the parking lot, and then identify dynamic objects and static objects in the parking lot through the object recognition module; the camera communication module can feed back the recorded images to a mobile phone so as to observe the situation in the parking lot anytime and anywhere, and the camera storage module can mainly store and place the collected images and recorded videos.

[0108] The LiDAR system connects to the sensing module via wireless communication, enabling the sensing module to detect parked vehicles in the parking lot and confirm whether any are parked. The LiDAR system consists of multiple radars to expand the range of the radar laser scanning. Once a vehicle is parked, the LiDAR monitoring system activates. Furthermore, the LiDARs can be installed on top of the parking lot, on the front, or at a 45-degree angle, enabling comprehensive monitoring of vehicles in parking spaces and enhancing parking safety. In a preferred embodiment, an infrared laser module performs infrared laser scanning of parking spaces within the parking lot. This allows the LiDAR to pre-label the parking data by scanning and modeling the parking environment, clearly distinguishing the monitored locations and facilitating real-time monitoring of each parking space once monitoring is activated. Once the LiDAR locks onto a parking space, it scans the vehicle model in seconds, quickly obtaining the vehicle's exterior features and a high-precision, centimeter-level point cloud model. Using an algorithm module, the system then recovers the vehicle's edge data. The camera captures images of vehicles in parking spaces and feeds them back to the algorithm module, which can effectively calculate and determine the distance and speed of dynamic objects from the vehicle. Furthermore, the object recognition module within the camera facilitates the identification of dynamic objects, so that the specific type of object approaching the vehicle can be quickly determined.

[0109] In addition, the object recognition module can accurately and clearly identify the shape characteristics of the object. If the distance of a dynamic object is less than 30cm, it will prompt that an object is approaching, record the time and shape of the dynamic object, and review the surveillance video recording at the same time; the control module is connected to the alarm module through communication to use the alarm prompt; if the approaching object does not leave quickly (within 5 seconds), an alarm of suspected peeping and possible theft will be issued; if the laser radar's recognition of the car's stationary state causes edge coordinate deviation, a collision alarm will be issued, the highest level alarm will be pushed directly, and personnel will be guided to handle it on the spot.

[0110] like Figure 12 As shown, the algorithm module is composed of four groups of algorithm modules, so as to calculate the distance between the dynamic object and the parked vehicle, and can also accurately calculate the data of the vehicle edge. Finally, through the output module, the calculated data is fed back to the terminal. The process of implementing the algorithm of the parking lot-based laser radar monitoring method of the present invention is as follows:

[0111] 1. Data cleaning

[0112] (1) De-noising the collected data

[0113] (2) Segmenting the data

[0114] 1) Segment the static point cloud and mark it as X

[0115] 2) Segment the dynamic point cloud and mark it as Y

[0116] 3) The final point cloud space matrix of the two states is as follows:

[0117]

[0118]

[0119] 2. Euclidean distance calculation for point cloud (function of algorithm module 2):

[0120] Spatial Euclidean distance formula:

[0121]

[0122] The distance from any point in the X point cloud to any point in the Y point cloud:

[0123]

[0124] Then the distance matrix from the first point of X to all points of Y is:

[0125] Dx1y=(dx1y1 dx1y2...dx1ym) T

[0126] The distance matrix from the second point in X to all points in Y is

[0127] Dx2y=(dx2y1 dx2y2...dx2ym) T

[0128] The distance matrix from the nth point in X to all points in Y is

[0129] Dxny=(dxny1 dxny2...dxnym) T

[0130] The final Euclidean distance matrix between all points in X and Y is:

[0131] D(X,Y)=(Dx1y Dx2y...Dxny)............③

[0132] 3. Two-dimensional projection processing of parking spaces and vehicles in parking spaces on the x0y plane (function of algorithm module 3)

[0133] (1) Let the spatial matrix of the segmented and marked parking lot cloud be C

[0134]

[0135] (2) The point cloud of the dynamic vehicle is Y

[0136] (3) When a dynamic vehicle is parked in a parking space, project the dot matrix of the vehicle and the parking space onto the xoy plane and calculate its area.

[0137] 1) The projection of the parking space on xoy is:

[0138] Recorded as ---> x,y are the coordinates of the point in the xoy plane

[0139] 2) The projection of the vehicle on xoy is:

[0140] Recorded as --->

[0141] Among them, x,y are the coordinate points of the xoy plane

[0142] 3) Sort the contour points and calculate the area of ​​the contour

[0143] The area is calculated as:

[0144]

[0145] According to the above calculation method, the area of ​​the parking space is C a , the vehicle's projected area Y a .

[0146] when Y is divided into vehicles parked in the parking spaces, wherein the value range of the β overlap coefficient can be 0<β<1.

[0147] 4. Collision and theft algorithms for vehicle Y and dynamic point cloud X (function of algorithm module No. 4)

[0148] 1) Get the contour point of Y and X and record it as Y edge ,X edge

[0149] 2) Introduce parameters δ, γ, and τ, which are the Euclidean distance between the two point cloud contours, the number of points that meet the conditions, and the dwell time.

[0150] According to formula ③, collision and theft are calculated as follows:

[0151] D(X edge ,Y edge ) edge =(Dx1y Dx2y...Dxny) edge

[0152] F(D(X edge ,Yedge ) edge )<=δ

[0153] H(δ)>=γ

[0154] T(δ)<=τ

[0155] The F function is the edge point that meets the δ threshold, the H function is the edge point that meets the γ threshold, and the T function is the edge point that meets the τ threshold. For example:

[0156] δ<=10,γ>=20 is judged as a collision between two objects

[0157] δ<=10,γ>=20,τ>=10 is considered theft

[0158] Note: xn1, xn2, xn3 are the projections of the three-dimensional space vector of the n-th point in X on the three coordinate axes; yn1, yn2, yn3 are the projections of the three-dimensional space vector of the n-th point in Y on the three coordinate axes; dxiyj is X.

[0159] The actual distance between any two points in Y; Dxny is the distance matrix from X to all points in Y; D(X,Y) is the distance matrix between all points in X and Y.

[0160] An embodiment of the present invention further provides a parking lot-based laser radar monitoring device, comprising a processor and a memory storing executable instructions for the processor. The processor is configured to execute the executable instructions to perform the steps of a parking lot-based laser radar monitoring method.

[0161] As shown above, the parking lot-based lidar monitoring system of this embodiment of the present invention can solve the problem of car safety protection after parking, identify dangers and capture relevant images, and provide car owners with maximum vehicle safety protection.

[0162] Those skilled in the art will appreciate that various aspects of the present invention may be implemented as systems, methods, or program products. Accordingly, various aspects of the present invention may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, microcode, etc.), or in a combination of hardware and software, collectively referred to herein as "circuits," "modules," or "platforms."

[0163] Figure 13 This is a schematic diagram of the laser radar monitoring device based on the parking lot of the present invention. Figure 13 An electronic device 600 according to this embodiment of the present invention is described. Figure 13 The electronic device 600 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0164] like Figure 13 As shown, electronic device 600 is implemented as a general-purpose computing device. Components of electronic device 600 may include, but are not limited to, at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including storage unit 620 and processing unit 610), and a display unit 640.

[0165] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 executes the steps according to various exemplary embodiments of the present invention described in the electronic prescription circulation processing method section of this specification. For example, the processing unit 610 can execute the following steps: Figure 1 Follow the steps shown in .

[0166] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0167] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: a processing system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0168] Bus 630 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0169] The electronic device 600 can also communicate with one or more external devices 700 (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 600, and / or any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). Such communication can occur via an input / output (I / O) interface 650. Furthermore, the electronic device 600 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 660. The network adapter 660 can communicate with other modules of the electronic device 600 via the bus 630. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the electronic device 600, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0170] An embodiment of the present invention further provides a computer-readable storage medium for storing a program that, when executed, implements the steps of the parking lot-based lidar monitoring method. In some possible implementations, various aspects of the present invention may also be implemented in the form of a program product, which includes program code. When the program product is executed on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the electronic prescription circulation processing method section above.

[0171] As shown above, the parking lot-based lidar monitoring system of this embodiment of the present invention can solve the problem of car safety protection after parking, identify dangers and capture relevant images, and provide car owners with maximum vehicle safety protection.

[0172] According to an embodiment of the present invention, a program product 800 for implementing the above method can be implemented in a portable compact disc read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0173] The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0174] Computer-readable storage media may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0175] The program code for performing the processes of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0176] In summary, the purpose of the present invention is to provide a parking lot-based lidar monitoring method, system, equipment and storage medium, which can solve the problem of car safety protection after parking, identify dangers and capture relevant images, and provide car owners with maximum vehicle safety protection.

[0177] The above is a further detailed description of the present invention in conjunction with specific preferred embodiments, and the specific implementation of the present invention should not be considered to be limited to these descriptions. For those skilled in the art of the present invention, without departing from the concept of the present invention, several simple deductions or substitutions can be made, which should be considered to fall within the scope of protection of the present invention.

Claims

1. A parking lot-based laser radar monitoring method, characterized in that: The following steps are involved: Collecting point cloud data in the parking lot for modeling, dividing the point cloud data into a static point cloud set and a dynamic point cloud set, and projecting the static point cloud set onto a horizontal plane; Segmenting a plurality of target dynamic point cloud sets of dynamic targets to be tracked from the dynamic point cloud set and projecting them onto a horizontal plane; When the target dynamic point cloud set is stationary within the range of a parking space point cloud, and the obtained overlap coefficient between a first projection area of ​​a preset parking space and a second projection area of ​​the target dynamic point cloud set meets a preset threshold, the target dynamic point cloud set is updated to a static point cloud; Obtain the closest distance between the second contour point cloud of the target dynamic point cloud set and the third contour point cloud representing the static point cloud of all vehicles parked in the parking spaces. When the closest distance is 0, it is determined that a collision has occurred, and the camera is driven to capture a video of the corresponding position.

2. The parking lot-based laser radar monitoring method according to claim 1, characterized in that: The collecting point cloud data in the parking lot for modeling, dividing the point cloud data into a static point cloud set and a dynamic point cloud set, and projecting the static point cloud set onto a horizontal plane includes: Collect and denoise point cloud data in the parking lot; Modeling based on the point cloud data of the parking lot; The point cloud data is divided into a static point cloud matrix and a dynamic point cloud matrix.

3. The parking lot-based laser radar monitoring method according to claim 2, characterized in that: LiDAR is used to collect point cloud data in the parking lot.

4. The parking lot-based laser radar monitoring method according to claim 1, wherein: The step of segmenting a plurality of target dynamic point cloud sets of dynamic targets to be tracked from the dynamic point cloud set and projecting the target point cloud sets onto a horizontal plane includes: Segmenting a plurality of target dynamic point cloud sets and corresponding labels of dynamic targets to be tracked from the dynamic point cloud set through point cloud recognition; Each target dynamic point cloud set is projected onto a horizontal plane.

5. The parking lot-based laser radar monitoring method according to claim 1, wherein: When the target dynamic point cloud set is stationary within a range of a parking space point cloud, and an overlap coefficient between a first projection area of ​​a preset parking space and a second projection area of ​​the target dynamic point cloud set satisfies a preset threshold, updating the target dynamic point cloud set to a static point cloud includes: When the target dynamic point cloud set stops within a preset parking space point cloud range, a first projection area C of a first contour of the preset parking space is obtained. a The second projection area Y of the second contour of the target dynamic point cloud set a ; Get the first projected area C a and the second projected area Y a The coincidence coefficient β is: When the overlap coefficient is greater than a preset threshold, and the value range of the preset threshold is 0.7 to 0.9, the dynamic point cloud corresponding to the target dynamic point cloud set is removed from the dynamic point cloud set, and added to the static point cloud set as the static point cloud marked as the vehicle parked in the parking space.

6. The parking lot-based laser radar monitoring method according to claim 5, characterized in that: The method further comprises: obtaining a minimum distance between a point cloud of a second contour of the target dynamic point cloud set and a point cloud of a third contour representing a static point cloud of all vehicles parked in the parking spaces; determining that a collision has occurred when the minimum distance is 0; and driving a camera to capture a video of the corresponding position. Obtaining the shortest distance between the point cloud of the second outline of the target dynamic point cloud set and the point cloud of the third outline of the static point cloud representing all vehicles parked in the parking spaces; When the closest distance is 0, it is determined that a collision has occurred, and the relative spatial position of the point cloud that produces the closest distance is obtained; The camera is driven to capture the video of the relative spatial position and upload it to trigger an alarm operation.

7. The parking lot-based laser radar monitoring method according to claim 1, wherein: After obtaining the closest distance between the second contour point cloud of the target dynamic point cloud set and the third contour point cloud representing the static point cloud of all vehicles parked in the parking spaces, determining that a collision has occurred when the closest distance is 0, and driving the camera to capture a video of the corresponding position, the method further includes: The closest distance between the second contour point cloud of the target dynamic point cloud set labeled as a pedestrian and the third contour point cloud of the static point cloud representing all vehicles parked in the parking spaces is obtained. When the closest distance is greater than 0 and less than a preset distance threshold and continues to exceed a preset time threshold, where the preset time threshold ranges from 4 to 10 seconds, it is determined to be a theft, and the camera is driven to capture video of the corresponding location.

8. A laser radar monitoring system based on a parking lot, characterized in that: include: A point cloud acquisition module collects point cloud data in the parking lot for modeling, divides the point cloud data into a static point cloud set and a dynamic point cloud set, and projects the static point cloud set onto a horizontal plane; a point cloud segmentation module, which segments a plurality of target dynamic point cloud sets of dynamic targets to be tracked from the dynamic point cloud set and projects the target dynamic point cloud sets onto a horizontal plane; a point cloud updating module, configured to update the target dynamic point cloud set to a static point cloud when the target dynamic point cloud set is stationary within a parking space point cloud and an overlap coefficient between a first projection area of ​​a preset parking space and a second projection area of ​​the target dynamic point cloud set satisfies a preset threshold; The collision detection module obtains the closest distance between the second contour point cloud of the target dynamic point cloud set and the third contour point cloud representing the static point cloud of all vehicles parked in the parking spaces. When the closest distance is 0, it is determined that a collision has occurred and the camera is driven to capture a video of the corresponding position.

9. A laser radar monitoring device based on a parking lot, characterized in that: include: processor; a memory storing executable instructions for the processor; Wherein, the processor is configured to perform the steps of the parking lot-based lidar monitoring method described in any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium for storing a program, characterized in that: When the program is executed by a processor, the steps of the parking lot-based lidar monitoring method described in any one of claims 1 to 7 are implemented.

Images