Synchronous positioning outdoor parking lot intelligent surveying and mapping method, system and equipment

Abstract

The invention discloses a synchronous positioning outdoor parking lot intelligent surveying and mapping method, system and device, and relates to the technical field of surveying and mapping, and the method comprises the steps: after a vehicle enters a parking lot, obtaining the position information of the vehicle in real time through a positioning device, and obtaining the behavior monitoring data of the vehicle through a vehicle-mounted electronic system, the behavior monitoring data comprises at least one of vehicle-mounted sensor data and driving operation data; determining a driving track of the vehicle according to the position information, and determining a parking position of the vehicle according to the driving track; determining a parking posture of the vehicle based on a reference parking space according to the behavior monitoring data and the driving track; and determining parking line data of the vehicle at the parking position according to the parking posture, and updating a parking space surveying and mapping map of the parking lot according to the parking line data. The method has the effect of improving the intelligent level of parking lot surveying and mapping.

Description

Technical Field

[0001] The present invention relates to the technical field of surveying and mapping, and in particular to a synchronously positioned outdoor parking lot intelligent surveying and mapping method, system and equipment. Background Art

[0002] With the acceleration of urbanization, the increase in urban population has led to a sharp increase in the number of motor vehicles, and the problem of parking difficulties has become increasingly prominent. In this context, traditional parking lot management methods have become increasingly ineffective. Many parking lots still rely on manual management and static maps, which cannot reflect the use of parking spaces in a timely manner. Existing surveying and mapping technologies mostly rely on manual measurement and simple electronic systems, lacking real-time and automation, resulting in delayed updates of parking space information. Users often face a dilemma when looking for parking spaces.

[0003] With the rapid development of technologies such as the Internet of Things, cloud computing, and big data analysis, some modern parking management systems have begun to use sensors and basic positioning technologies, and the intelligent transformation of parking lot mapping and management has become a possibility. However, most parking lots have not yet fully realized this transformation. The popularity of intelligent configuration and technology is low. Many systems still rely on static mapping information and lack rapid response and dynamic management of parking space usage. Therefore, the current level of intelligent mapping in parking lots is low, resulting in low management efficiency of parking lots. Summary of the invention

[0004] In order to improve the intelligence level of parking lot mapping, the present invention provides a method, system and device for intelligent mapping of outdoor parking lots with synchronous positioning.

[0005] In the first aspect, the present invention provides a synchronous positioning outdoor parking lot intelligent mapping method, which adopts the following technical solutions: A synchronous positioning outdoor parking lot intelligent mapping method, comprising: After the vehicle enters the parking lot, the location information of the vehicle is obtained in real time through a positioning device, and the behavior monitoring data of the vehicle is obtained through an on-board electronic system, wherein the behavior monitoring data includes at least one of on-board sensor data and driving operation data; Determining a driving trajectory of the vehicle according to the position information, and determining a parking position of the vehicle according to the driving trajectory; Based on a reference parking space and according to the behavior monitoring data and the driving trajectory, determining a parking posture of the vehicle, wherein the parking posture includes a parking angle; The parking line data of the vehicle at the parking position is determined according to the parking posture, and the parking space mapping map of the parking lot is updated according to the parking line data.

[0006] By adopting the above technical solution, after the vehicle enters the parking lot, the location information of the vehicle is obtained in real time through the positioning device, and the behavior monitoring data of the vehicle is obtained through the on-board electronic system, wherein the behavior monitoring data includes at least one of the on-board sensor data and the driving operation data. Then, the driving trajectory of the vehicle is determined according to the location information, and the parking position of the vehicle is determined according to the driving trajectory. Then, based on the reference parking space, the parking posture of the vehicle is determined according to the behavior monitoring data and the driving trajectory, wherein the parking posture includes the parking angle. Finally, the parking line data of the vehicle at the parking position is determined according to the parking posture, and the parking space mapping map of the parking lot is updated according to the parking line data. Through the above method, the parking space can be mapped through the data collected by the vehicle entering the parking lot itself, and there is no need to install additional data acquisition devices in the parking lot, thereby improving the real-time mapping of the parking lot, and improving the intelligence level of the parking lot mapping and the management efficiency of the parking lot. In addition, the monitoring of vehicles in the parking lot is realized, and the safety during parking is improved.

[0007] Optionally, the step of determining the driving trajectory of the vehicle according to the position information includes: Based on a Kalman filter algorithm, Kalman position information is generated according to the position information; The Kalman position information is subjected to trajectory interpolation according to the Kalman position information to obtain a driving trajectory of the vehicle.

[0008] By adopting the above technical solution, in order to determine the driving trajectory of the vehicle according to the position information, firstly based on the Kalman filter algorithm, Kalman position information is generated according to the position information, and then the Kalman position information is interpolated according to the Kalman position information to obtain the driving trajectory of the vehicle.

[0009] Optionally, the step of determining the parking position of the vehicle according to the driving trajectory includes: Acquire timestamp data corresponding to the driving trajectory according to the driving trajectory, and create an initial window according to a preset time length, the driving trajectory and the timestamp data; Sliding the initial window according to a preset time sliding unit to obtain at least one intermediate window; For each of the intermediate windows, determine whether the distances between all adjacent position points in the intermediate window are less than a preset distance based on the intermediate window, and determine whether multiple position points stay at the same position for more than a preset time. If so, determine the parking data of the vehicle based on the intermediate window, wherein the parking data includes the parking position, parking time period and parking duration.

[0010] By adopting the above technical solution, in order to determine the parking position of the vehicle according to the driving trajectory, the timestamp data corresponding to the driving trajectory is obtained according to the driving trajectory, and an initial window is created according to the preset time length, the driving trajectory and the timestamp data, and then the initial window is slid according to the preset time sliding unit to obtain at least one intermediate window. Finally, for each intermediate window, it is determined according to the intermediate window whether the distances between all adjacent position points in the intermediate window are less than the preset distance, and whether there are multiple position points that stay at the same position for more than the preset time. If so, the parking data of the vehicle is determined according to the intermediate window, wherein the parking data includes the parking position, parking time period and parking duration.

[0011] Optionally, the step of determining the parking posture of the vehicle based on a reference parking space and according to the behavior monitoring data and the driving trajectory includes: Acquiring parking line data of the reference parking space based on the reference parking space, wherein the parking line data includes direction data of the parking line; Acquire model training data, and divide the model training data into a training set and a test set according to a preset ratio, wherein the model training data includes the parking line data, historical behavior detection data, and historical driving trajectory; The hyperparameters of the pre-built deep learning model were set according to the random network search algorithm, and the root mean square error RMSE and the coefficient of determination R 2 As an evaluation indicator; Training the deep learning model according to the training set to obtain a trained deep learning model; Testing the trained deep learning model according to the test set, and judging whether the error is within a preset range according to the evaluation index, and if so, using the trained deep learning model as a parking posture prediction model; Based on a parking posture prediction model, the parking posture of the vehicle is generated according to the behavior monitoring data and the driving trajectory.

[0012] By adopting the above technical solution, in order to determine the parking posture of the vehicle, the parking line data of the reference parking space is obtained based on the reference parking space, wherein the parking line data includes the direction data of the parking line, and then the model training data is obtained, and the model training data is divided into a training set and a test set according to a preset ratio, wherein the model training data includes the parking line data, the historical behavior detection data and the historical driving trajectory, and then the hyperparameters of the pre-built deep learning model are set according to the random network search algorithm, and the root mean square error RMSE and the determination coefficient R 2As an evaluation indicator, the deep learning model is then trained according to the training set to obtain a trained deep learning model, and then the trained deep learning model is tested according to the test set, and whether the error is within the preset range is judged according to the evaluation indicator. If the error is within the preset range, the trained deep learning model is used as the parking posture prediction model. Finally, based on the parking posture prediction model, the parking posture of the vehicle is generated according to the behavior monitoring data and driving trajectory.

[0013] Optionally, the parking posture prediction model includes an input layer, a first feature extraction layer, a second feature extraction layer, a splicing layer, and an output layer. The step of generating the parking posture of the vehicle based on the parking posture prediction model according to the behavior monitoring data and the driving trajectory includes: Generate a first data feature vector according to the behavior monitoring data through the input layer; Generate a second data feature vector according to the driving trajectory through the input layer; generating a third data feature vector according to the first data feature vector through the first feature extraction layer; generating a fourth data feature vector according to the second data feature vector through the second feature extraction layer; The third data feature vector and the fourth data feature vector are concatenated through the concatenation layer to obtain a fifth data feature vector; Generate an output vector through the output layer according to the fifth data feature vector, wherein the output vector includes a first element, a second element, a third element and a fourth element, the first element is used to characterize the deflection angle between the front line of the vehicle and the first side of the reference parking space, the second element is used to characterize the deflection angle between the left side line of the vehicle and the second side of the reference parking space, the third element is used to characterize the deflection angle between the rear side line of the vehicle and the third side of the reference parking space, and the fourth element is used to characterize the deflection angle between the right side line of the vehicle and the fourth side of the reference parking space; A parking posture of the vehicle is generated based on the first element, the second element, the third element, and the fourth element.

[0014] By adopting the above technical solution, in order to generate the parking posture of the vehicle, a first data feature vector is generated according to the behavior monitoring data through the input layer, and a second data feature vector is generated according to the driving trajectory through the input layer, and then a third data feature vector is generated according to the first data feature vector through the first feature extraction layer, and then a fourth data feature vector is generated according to the second data feature vector through the second feature extraction layer, and then the third data feature vector and the fourth data feature vector are spliced ​​through the splicing layer to obtain a fifth data feature vector, and then an output vector is generated according to the fifth data feature vector through the output layer, wherein the output vector includes a first element, a second element, a third element and a fourth element, the first element is used to characterize the deflection angle between the front line of the vehicle and the first side of the reference parking space, the second element is used to characterize the deflection angle between the left side line of the vehicle and the second side of the reference parking space, the third element is used to characterize the deflection angle between the rear side line of the vehicle and the third side of the reference parking space, and the fourth element is used to characterize the deflection angle between the right side line of the vehicle and the fourth side of the reference parking space, and finally the parking posture of the vehicle is generated based on the first element, the second element, the third element and the fourth element.

[0015] Optionally, the first feature extraction layer includes a first fully connected layer, a second fully connected layer, and a third fully connected layer, the ratio of the number of neurons in the first fully connected layer, the second fully connected layer, and the third fully connected layer is 5:2:1, and the step of generating a third data feature vector according to the first data feature vector through the first feature extraction layer includes: Inputting the first data feature vector into the first fully connected layer to obtain a first intermediate feature vector; Inputting the first intermediate feature vector into the second fully connected layer to obtain a second intermediate feature vector; The second intermediate feature vector is input into the third fully connected layer to obtain a third data feature vector.

[0016] By adopting the above technical solution, in order to generate the third data feature vector, the first data feature vector is first input into the first fully connected layer to obtain the first intermediate feature vector, and then the first intermediate feature vector is input into the second fully connected layer to obtain the second intermediate feature vector, and finally the second intermediate feature vector is input into the third fully connected layer to obtain the third data feature vector.

[0017] Optionally, the step of determining parking line data of the vehicle at the parking position according to the parking posture includes: Acquire size information of the vehicle, wherein the size information includes length and width; Based on the parking space standard data of the parking lot and according to the size information, determining the parking space specification of the vehicle; Based on the parking posture of the vehicle and according to the parking space specification, parking line data of the vehicle at the parking position is determined.

[0018] By adopting the above technical solution, in order to determine the parking line data of the vehicle at the parking position according to the parking posture, the size information of the vehicle is obtained, wherein the size information includes the length and width, and then based on the parking space standard data of the parking lot and according to the size information, the parking space specifications of the vehicle are determined, and finally based on the parking posture of the vehicle and according to the parking space specifications, the parking line data of the vehicle at the parking position is determined.

[0019] In a second aspect, the present invention also provides a synchronous positioning outdoor parking lot intelligent mapping system, which adopts the following technical solutions: A synchronous positioning outdoor parking lot intelligent mapping system, comprising: A data acquisition module, used to acquire the position information of the vehicle in real time through a positioning device after the vehicle enters the parking lot, and to acquire the behavior monitoring data of the vehicle through an on-board electronic system, wherein the behavior monitoring data includes at least one of on-board sensor data and driving operation data; a position information processing module, used to determine the driving trajectory of the vehicle according to the position information, and determine the parking position of the vehicle according to the driving trajectory; A parking posture generating module, configured to determine the parking posture of the vehicle based on a reference parking space and according to the behavior monitoring data and the driving trajectory, wherein the parking posture includes a parking angle; The parking space mapping map updating module is used to determine the parking line data of the vehicle at the parking position according to the parking posture, and update the parking space mapping map of the parking lot according to the parking line data.

[0020] The position information processing module includes: A Kalman filter submodule, for generating Kalman position information based on a Kalman filter algorithm and according to the position information; The trajectory interpolation submodule is used to perform trajectory interpolation on the Kalman position information according to the Kalman position information to obtain the driving trajectory of the vehicle.

[0021] In a third aspect, the present invention further provides a computer device, which adopts the following technical solution: A computer device comprises a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor implements the method described in the first aspect when executing the computer program.

[0022] In summary, the present invention includes at least the following beneficial technical effects: after a vehicle enters a parking lot, the location information of the vehicle is obtained in real time through a positioning device, and the behavior monitoring data of the vehicle is obtained through a vehicle-mounted electronic system, wherein the behavior monitoring data includes at least one of vehicle-mounted sensor data and driving operation data; then the driving trajectory of the vehicle is determined according to the location information, and the parking position of the vehicle is determined according to the driving trajectory; then the parking posture of the vehicle is determined based on a reference parking space and according to the behavior monitoring data and the driving trajectory, wherein the parking posture includes a parking angle; finally, the parking line data of the vehicle at the parking position is determined according to the parking posture, and the parking space mapping map of the parking lot is updated according to the parking line data; through the above method, the parking space can be mapped through the data collected by the vehicle entering the parking lot itself, and there is no need to install an additional data acquisition device in the parking lot, thereby improving the real-time mapping of the parking lot, and improving the intelligence level of the parking lot mapping and the management efficiency of the parking lot. In addition, the monitoring of vehicles in the parking lot is realized, and the safety during parking is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of the overall process of an embodiment of the present invention.

[0024] Figure 2 It is a schematic diagram of the structure of the system of the present invention.

[0025] Figure 3 It is a structural block diagram of the computer device of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the present invention more clear, the following Figure 1-Figure 3 It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0027] The embodiment of the present invention discloses a synchronous positioning outdoor parking lot intelligent mapping method.

[0028] Reference Figure 1 , a synchronous positioning outdoor parking lot intelligent mapping method, comprising: Step S11, after the vehicle enters the parking lot, the location information of the vehicle is obtained in real time through the positioning device, and the behavior monitoring data of the vehicle is obtained through the vehicle electronic system.

[0029] Wherein, the behavior monitoring data includes at least one of vehicle-mounted sensor data and driving operation data; It should be noted that in step S11, the real-time monitoring of the vehicle is achieved through the positioning device and / or the vehicle-mounted electronic system. The vehicle is usually equipped with a GPS module or other positioning system (such as GNSS) to ensure that accurate location information can be obtained in the parking lot. It can also be combined with base station positioning or Wi-Fi positioning and other technologies to improve positioning accuracy; the vehicle-mounted electronic system is connected to the vehicle-mounted sensors (such as accelerometers, gyroscopes, radar sensors, etc.), which can collect vehicle status information in real time, or monitor the driver's operation data (i.e. driving operation data), including throttle, brake, steering wheel angle, gear position and other information. These data can be read through the OBD-II interface or the vehicle-mounted controller; then the monitored behavior data is uploaded to the cloud platform through the vehicle-mounted communication system (such as 4G / 5G, V2X communication), or the data is transmitted to the parking lot management system through Wi-Fi for subsequent processing.

[0030] Step S12, determining the driving trajectory of the vehicle according to the position information, and determining the parking position of the vehicle according to the driving trajectory.

[0031] Step S13, determining the parking posture of the vehicle based on the reference parking space, behavior monitoring data and driving trajectory.

[0032] Among them, the parking posture includes the parking angle.

[0033] It should be noted that the parking posture of a vehicle is used to indicate the posture or state of the vehicle relative to a reference parking space. For example, if the parking lot is a flat land, the parking posture may include the parking angle of the vehicle relative to the reference parking space. If the parking lot includes two flat lands of different heights, the parking posture may include the parking height of the vehicle relative to the reference parking space.

[0034] Step S14, determining parking line data of the vehicle at the parking position according to the parking posture, and updating the parking space mapping map of the parking lot according to the parking line data.

[0035] It is understandable that when surveying and mapping is just started, the parking space surveying and mapping map is usually an initial map that does not include parking lines. During the surveying and mapping process, the parking space surveying and mapping map is a map formed by adding a part of parking lines to the initial map.

[0036] In the above embodiment, after the vehicle enters the parking lot, the location information of the vehicle is obtained in real time through the positioning device, and the behavior monitoring data of the vehicle is obtained through the on-board electronic system, wherein the behavior monitoring data includes at least one of the on-board sensor data and the driving operation data. Then, the driving trajectory of the vehicle is determined according to the location information, and the parking position of the vehicle is determined according to the driving trajectory. Then, based on the reference parking space, the parking posture of the vehicle is determined according to the behavior monitoring data and the driving trajectory, wherein the parking posture includes the parking angle. Finally, the parking line data of the vehicle at the parking position is determined according to the parking posture, and the parking space mapping map of the parking lot is updated according to the parking line data. Through the above method, the parking space can be mapped through the data collected by the vehicle entering the parking lot itself, and there is no need to install additional data acquisition devices in the parking lot, thereby improving the real-time mapping of the parking lot, and improving the intelligence level of the parking lot mapping and the management efficiency of the parking lot. In addition, the monitoring of vehicles in the parking lot is realized, and the safety during the parking process is improved.

[0037] As a further implementation of the method, the step of determining the driving trajectory of the vehicle according to the position information includes: Step S21, based on the Kalman filter algorithm, generates Kalman position information according to the position information.

[0038] It should be noted that Kalman filtering is a recursive algorithm for estimating the state of linear dynamic systems and is widely used in signal processing and control systems. Its main advantage is that it can effectively process noisy measurement data and estimate the system state. Assuming that for a vehicle, our goal is to estimate its position (i.e. predict its position) through Kalman filtering. We obtain measurement values ​​from sensors (such as GPS), but these measurement values ​​often contain noise. Here are the specific steps: First, we make a state prediction. Assuming that the real position of the vehicle at a certain moment is (2,3), we can use Kalman filtering to predict the position of the vehicle at the next moment (for example, every second). Based on the previous position and speed, the predicted position (i.e., state estimation) may be (2.5,3.5). Then, we use the position information to obtain the corresponding measurement value. Due to the interference of the GPS signal, the measurement value we get may be (2.7,3.2). This measurement value has some deviation from the real position, but we hope to use it to correct our predicted position. Then, we use Kalman filtering to calculate the vehicle's position. The method will consider the predicted value (2.5, 3.5) and the measured value (2.7, 3.2) in the update step, and calculate a new estimated position based on the confidence of the two (by weighting), which can be achieved through weighted operations. Suppose we give the predicted value a weight of 0.7 and the measured value a weight of 0.3. We will calculate a weighted average: new position = 0.7×(2.5, 3.5)+0.3×(2.7, 3.2), which can make the new position estimate closer to the predicted value while also taking into account the small changes caused by the measured value. In the Kalman filter, we maintain a covariance matrix that represents uncertainty, and use the covariance matrix to update the accuracy of the state in the update step. For example, a smaller covariance value indicates a higher confidence in the prediction, so the predicted position weight is relatively increased during the update. Finally, after weighted calculation and covariance adjustment, the new vehicle position estimate we get may be (2.6, 3.4). This position better combines the past motion prediction and current measurement information, minimizing the deviation introduced by the measurement error.

[0039] Step S22, performing trajectory interpolation on the Kalman position information according to the Kalman position information to obtain the driving trajectory of the vehicle.

[0040] It can be understood that through trajectory interpolation, missing information can be filled between known data points to form a continuous and smooth trajectory without jumps or unnatural changes.

[0041] In the above implementation, in order to determine the driving trajectory of the vehicle according to the position information, Kalman position information is first generated based on the Kalman filter algorithm and according to the position information, and then the Kalman position information is interpolated according to the Kalman position information to obtain the driving trajectory of the vehicle.

[0042] As a further implementation of the method, the step of determining the parking position of the vehicle according to the driving trajectory includes: Step S31, obtaining timestamp data corresponding to the driving trajectory according to the driving trajectory, and creating an initial window according to the preset time length, the driving trajectory and the timestamp data.

[0043] Step S32: Slide the initial window according to a preset time sliding unit to obtain at least one intermediate window.

[0044] Step S33, for each intermediate window, determine whether the distances between all adjacent position points in the intermediate window are less than the preset distance, and determine whether there are multiple position points that stay at the same position for more than the preset time. If so, determine the parking data of the vehicle based on the intermediate window.

[0045] Among them, parking data includes parking location, parking time period and parking duration.

[0046] In the above embodiment, in order to determine the parking position of the vehicle according to the driving trajectory, the timestamp data corresponding to the driving trajectory is obtained according to the driving trajectory, and an initial window is created according to the preset time length, the driving trajectory and the timestamp data, and then the initial window is slid according to the preset time sliding unit to obtain at least one intermediate window. Finally, for each intermediate window, it is determined according to the intermediate window whether the distances between all adjacent position points in the intermediate window are less than the preset distance, and whether there are multiple position points that stay at the same position for more than the preset time. If so, the parking data of the vehicle is determined according to the intermediate window, wherein the parking data includes the parking position, parking time period and parking duration.

[0047] As a further implementation of the method, the step of determining the parking posture of the vehicle based on the reference parking space and according to the behavior monitoring data and the driving trajectory includes: Step S41, acquiring parking line data of the reference parking space based on the reference parking space, wherein the parking line data includes direction data of the parking line.

[0048] Step S42, obtaining model training data, and dividing the model training data into a training set and a test set according to a preset ratio.

[0049] Among them, the model training data includes parking line data, historical behavior detection data and historical driving trajectory.

[0050] Step S43, setting the hyperparameters of the pre-built deep learning model according to the random network search algorithm, and calculating the root mean square error RMSE and the coefficient of determination R 2 as an evaluation indicator.

[0051] It should be noted that random network search is a method of hyperparameter tuning. Compared with grid search, it randomly selects parameter combinations for model training and evaluation. Its advantages include high efficiency: when the parameter space is large, random selection is more effective than systematically traversing each parameter combination, and relatively good parameter settings can be quickly found. Broad exploration: it can cover a wider parameter space and reduce dependence on local optimality. In deep learning models, hyperparameters that often need to be tuned include: learning rate (such as 0.001, 0.01, 0.1), batch size (such as 16, 32, 64, 128), number of network layers and the number of neurons in each layer, activation functions (such as ReLU, Sigmoid, Tanh), and regularization parameters (such as dropout rate, L2 regularization, etc.) Step S44: train the deep learning model according to the training set to obtain a trained deep learning model.

[0052] Step S45, testing the trained deep learning model according to the test set, and judging whether the error is within a preset range according to the evaluation index, if so, using the trained deep learning model as a parking posture prediction model.

[0053] Specifically, the trained deep learning model is tested according to the test set, and whether the error is within the preset range is determined according to the evaluation index. If the error is within the preset range, the trained deep learning model is used as the parking posture prediction model.

[0054] Step S46, based on the parking posture prediction model, the parking posture of the vehicle is generated according to the behavior monitoring data and the driving trajectory.

[0055] In the above implementation, in order to determine the parking posture of the vehicle, the parking line data of the reference parking space is obtained based on the reference parking space, wherein the parking line data includes the direction data of the parking line, and then the model training data is obtained, and the model training data is divided into a training set and a test set according to a preset ratio, wherein the model training data includes the parking line data, the historical behavior detection data and the historical driving trajectory, and then the hyperparameters of the pre-built deep learning model are set according to the random network search algorithm, and the root mean square error RMSE and the determination coefficient R 2 As an evaluation indicator, the deep learning model is then trained according to the training set to obtain a trained deep learning model, and then the trained deep learning model is tested according to the test set, and whether the error is within the preset range is judged according to the evaluation indicator. If the error is within the preset range, the trained deep learning model is used as the parking posture prediction model. Finally, based on the parking posture prediction model, the parking posture of the vehicle is generated according to the behavior monitoring data and driving trajectory.

[0056] As a further implementation of the method, the parking posture prediction model includes an input layer, a first feature extraction layer, a second feature extraction layer, a splicing layer, and an output layer. Based on the parking posture prediction model, according to the behavior monitoring data and the driving trajectory, the step of generating the parking posture of the vehicle includes: Step S51, generating a first data feature vector according to the behavior monitoring data through the input layer.

[0057] Step S52: Generate a second data feature vector through the input layer according to the driving trajectory.

[0058] It should be noted that in a deep learning model, the input layer is the first layer of the model, which is responsible for receiving external data and converting it into a format suitable for model processing. The input can be a feature vector, image, text, etc. Depending on the specific task, the input layer usually needs to specify the shape and dimension of the data so that the subsequent network layers can process it correctly.

[0059] Step S53: Generate a third data feature vector according to the first data feature vector through the first feature extraction layer.

[0060] Step S54: Generate a fourth data feature vector according to the second data feature vector through the second feature extraction layer.

[0061] Step S55, concatenating the third data feature vector and the fourth data feature vector through a concatenation layer to obtain a fifth data feature vector.

[0062] It should be noted that the concatenation layer is a layer commonly used in deep learning, especially in convolutional neural networks (CNN). Its main function is to connect multiple input tensors along the specified dimension to form a new tensor. This concatenation operation can help the model fuse the features of different layers and achieve stronger representation capabilities.

[0063] Step S56, generating an output vector according to the fifth data feature vector through the output layer.

[0064] Among them, the output vector includes a first element, a second element, a third element and a fourth element. The first element is used to characterize the deflection angle between the front line of the vehicle and the first side of the reference parking space, the second element is used to characterize the deflection angle between the left side line of the vehicle and the second side of the reference parking space, the third element is used to characterize the deflection angle between the rear side line of the vehicle and the third side of the reference parking space, and the fourth element is used to characterize the deflection angle between the right side line of the vehicle and the fourth side of the reference parking space.

[0065] It should be noted that the output layer is the last layer in the deep learning model. It is responsible for converting the features generated by the model into the final prediction results. Depending on the task type, the structure and activation function of the output layer will also be different.

[0066] Step S57, generating the parking posture of the vehicle based on the first element, the second element, the third element and the fourth element.

[0067] In the above embodiment, in order to generate the parking posture of the vehicle, a first data feature vector is generated according to the behavior monitoring data through the input layer, and a second data feature vector is generated according to the driving trajectory through the input layer, and then a third data feature vector is generated according to the first data feature vector through the first feature extraction layer, and then a fourth data feature vector is generated according to the second data feature vector through the second feature extraction layer, and then the third data feature vector and the fourth data feature vector are spliced ​​through the splicing layer to obtain a fifth data feature vector, and then an output vector is generated according to the fifth data feature vector through the output layer, wherein the output vector includes a first element, a second element, a third element and a fourth element, the first element is used to characterize the deflection angle between the front line of the vehicle and the first side of the reference parking space, the second element is used to characterize the deflection angle between the left side line of the vehicle and the second side of the reference parking space, the third element is used to characterize the deflection angle between the rear side line of the vehicle and the third side of the reference parking space, and the fourth element is used to characterize the deflection angle between the right side line of the vehicle and the fourth side of the reference parking space, and finally the parking posture of the vehicle is generated based on the first element, the second element, the third element and the fourth element.

[0068] As a further implementation of the method, the first feature extraction layer includes a first fully connected layer, a second fully connected layer and a third fully connected layer, the ratio of the number of neurons in the first fully connected layer, the second fully connected layer and the third fully connected layer is 5:2:1, and the step of generating a third data feature vector according to the first data feature vector through the first feature extraction layer includes: Step S61: input the first data feature vector into the first fully connected layer to obtain a first intermediate feature vector.

[0069] Step S62: input the first intermediate feature vector into the second fully connected layer to obtain a second intermediate feature vector.

[0070] Step S63: input the second intermediate feature vector into the third fully connected layer to obtain a third data feature vector.

[0071] In the above embodiment, in order to generate the third data feature vector, the first data feature vector is first input into the first fully connected layer to obtain the first intermediate feature vector, and then the first intermediate feature vector is input into the second fully connected layer to obtain the second intermediate feature vector, and finally the second intermediate feature vector is input into the third fully connected layer to obtain the third data feature vector.

[0072] As a further implementation of the method, the step of determining parking line data of the vehicle at the parking position according to the parking posture includes: Step S71, obtaining the size information of the vehicle.

[0073] The size information includes length and width.

[0074] Step S72, based on the parking space standard data of the parking lot and according to the size information, determine the parking space specification of the vehicle.

[0075] It should be noted that the parking space standard data is used to indicate the parking space specifications for different types of vehicles.

[0076] Step S73, based on the parking posture of the vehicle and according to the parking space specifications, determine the parking line data of the vehicle at the parking position.

[0077] In the above embodiment, in order to determine the parking line data of the vehicle at the parking position according to the parking posture, the size information of the vehicle is obtained, wherein the size information includes the length and width, and then based on the parking space standard data of the parking lot and according to the size information, the parking space specifications of the vehicle are determined, and finally based on the parking posture of the vehicle and according to the parking space specifications, the parking line data of the vehicle at the parking position is determined.

[0078] The embodiment of the present invention also discloses a synchronous positioning outdoor parking lot intelligent mapping system.

[0079] refer to Figure 2 , a synchronous positioning outdoor parking lot intelligent mapping system, comprising: A data acquisition module, used to acquire the location information of the vehicle in real time through a positioning device after the vehicle enters the parking lot, and to acquire the behavior monitoring data of the vehicle through an on-board electronic system, wherein the behavior monitoring data includes at least one of on-board sensor data and driving operation data; A position information processing module, used to determine the driving trajectory of the vehicle according to the position information, and determine the parking position of the vehicle according to the driving trajectory; A parking posture generating module, used to determine the parking posture of the vehicle based on a reference parking space and according to the behavior monitoring data and the driving trajectory, wherein the parking posture includes a parking angle; The parking space mapping map updating module is used to determine the parking line data of the vehicle at the parking position according to the parking posture, and update the parking space mapping map of the parking lot according to the parking line data.

[0080] The location information processing module includes: A Kalman filter submodule, for generating Kalman position information based on a Kalman filter algorithm and according to the position information; The trajectory interpolation submodule is used to perform trajectory interpolation on the Kalman position information according to the Kalman position information to obtain the driving trajectory of the vehicle.

[0081] The synchronous positioning outdoor parking lot intelligent mapping system of the present invention can implement any one of the synchronous positioning outdoor parking lot intelligent mapping methods, and the specific working process of the synchronous positioning outdoor parking lot intelligent mapping system of the present invention can refer to the corresponding process in the above-mentioned synchronous positioning outdoor parking lot intelligent mapping method.

[0082] The embodiment of the present invention also discloses a computer device.

[0083] refer to Figure 3 A computer device includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, any one of the above-mentioned synchronous positioning outdoor parking lot intelligent mapping methods is implemented.

[0084] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims

1. A synchronous positioning outdoor parking lot intelligent mapping method, characterized in that: include: After the vehicle enters the parking lot, the location information of the vehicle is obtained in real time through a positioning device, and the behavior monitoring data of the vehicle is obtained through an on-board electronic system, wherein the behavior monitoring data includes at least one of on-board sensor data and driving operation data; Determining a driving trajectory of the vehicle according to the position information, and determining a parking position of the vehicle according to the driving trajectory; Based on a reference parking space and according to the behavior monitoring data and the driving trajectory, determining a parking posture of the vehicle, wherein the parking posture includes a parking angle; The parking line data of the vehicle at the parking position is determined according to the parking posture, and the parking space mapping map of the parking lot is updated according to the parking line data.

2. According to claim 1, a synchronous positioning outdoor parking lot intelligent mapping method is characterized in that: The step of determining the driving trajectory of the vehicle according to the position information comprises: Based on a Kalman filter algorithm, Kalman position information is generated according to the position information; The Kalman position information is subjected to trajectory interpolation according to the Kalman position information to obtain a driving trajectory of the vehicle.

3. The method for intelligent mapping of outdoor parking lots with synchronous positioning according to claim 1, characterized in that: The step of determining the parking position of the vehicle according to the driving trajectory comprises: Acquire timestamp data corresponding to the driving trajectory according to the driving trajectory, and create an initial window according to a preset time length, the driving trajectory and the timestamp data; Sliding the initial window according to a preset time sliding unit to obtain at least one intermediate window; For each of the intermediate windows, determine whether the distances between all adjacent position points in the intermediate window are less than a preset distance based on the intermediate window, and determine whether multiple position points stay at the same position for more than a preset time. If so, determine the parking data of the vehicle based on the intermediate window, wherein the parking data includes the parking position, parking time period and parking duration.

4. The method for intelligent mapping of outdoor parking lots with synchronous positioning according to claim 1, characterized in that: The step of determining the parking posture of the vehicle based on the reference parking space and according to the behavior monitoring data and the driving trajectory includes: Acquiring parking line data of the reference parking space based on the reference parking space, wherein the parking line data includes direction data of the parking line; Acquire model training data, and divide the model training data into a training set and a test set according to a preset ratio, wherein the model training data includes the parking line data, historical behavior detection data, and historical driving trajectory; The hyperparameters of the pre-built deep learning model were set according to the random network search algorithm, and the root mean square error RMSE and the coefficient of determination R 2 As an evaluation indicator; Training the deep learning model according to the training set to obtain a trained deep learning model; Testing the trained deep learning model according to the test set, and judging whether the error is within a preset range according to the evaluation index, and if so, using the trained deep learning model as a parking posture prediction model; Based on a parking posture prediction model, the parking posture of the vehicle is generated according to the behavior monitoring data and the driving trajectory.

5. The method for intelligent mapping of outdoor parking lots with synchronous positioning according to claim 4 is characterized in that: The parking posture prediction model includes an input layer, a first feature extraction layer, a second feature extraction layer, a splicing layer, and an output layer. The step of generating the parking posture of the vehicle based on the parking posture prediction model according to the behavior monitoring data and the driving trajectory includes: Generate a first data feature vector according to the behavior monitoring data through the input layer; Generate a second data feature vector according to the driving trajectory through the input layer; generating a third data feature vector according to the first data feature vector through the first feature extraction layer; generating a fourth data feature vector according to the second data feature vector through the second feature extraction layer; The third data feature vector and the fourth data feature vector are concatenated through the concatenation layer to obtain a fifth data feature vector; Generate an output vector through the output layer according to the fifth data feature vector, wherein the output vector includes a first element, a second element, a third element and a fourth element, the first element is used to characterize the deflection angle between the front line of the vehicle and the first side of the reference parking space, the second element is used to characterize the deflection angle between the left side line of the vehicle and the second side of the reference parking space, the third element is used to characterize the deflection angle between the rear side line of the vehicle and the third side of the reference parking space, and the fourth element is used to characterize the deflection angle between the right side line of the vehicle and the fourth side of the reference parking space; A parking posture of the vehicle is generated based on the first element, the second element, the third element, and the fourth element.

6. The method for intelligent mapping of outdoor parking lots with synchronous positioning according to claim 5, characterized in that: The first feature extraction layer includes a first fully connected layer, a second fully connected layer and a third fully connected layer, the ratio of the number of neurons in the first fully connected layer, the second fully connected layer and the third fully connected layer is 5:2:1, and the step of generating a third data feature vector according to the first data feature vector through the first feature extraction layer includes: Inputting the first data feature vector into the first fully connected layer to obtain a first intermediate feature vector; Inputting the first intermediate feature vector into the second fully connected layer to obtain a second intermediate feature vector; The second intermediate feature vector is input into the third fully connected layer to obtain a third data feature vector.

7. The method for intelligent mapping of outdoor parking lots with synchronous positioning according to claim 1, characterized in that: The step of determining the parking line data of the vehicle at the parking position according to the parking posture comprises: Acquire size information of the vehicle, wherein the size information includes length and width; Based on the parking space standard data of the parking lot and according to the size information, determining the parking space specification of the vehicle; Based on the parking posture of the vehicle and according to the parking space specification, parking line data of the vehicle at the parking position is determined.

8. A synchronous positioning outdoor parking lot intelligent mapping system, characterized in that: include: A data acquisition module, used to acquire the position information of the vehicle in real time through a positioning device after the vehicle enters the parking lot, and to acquire the behavior monitoring data of the vehicle through an on-board electronic system, wherein the behavior monitoring data includes at least one of on-board sensor data and driving operation data; a position information processing module, used to determine the driving trajectory of the vehicle according to the position information, and determine the parking position of the vehicle according to the driving trajectory; A parking posture generating module, configured to determine the parking posture of the vehicle based on a reference parking space and according to the behavior monitoring data and the driving trajectory, wherein the parking posture includes a parking angle; The parking space mapping map updating module is used to determine the parking line data of the vehicle at the parking position according to the parking posture, and update the parking space mapping map of the parking lot according to the parking line data.

9. The synchronous positioning outdoor parking lot intelligent mapping system according to claim 8 is characterized in that: The position information processing module includes: A Kalman filter submodule, for generating Kalman position information based on a Kalman filter algorithm and according to the position information; The trajectory interpolation submodule is used to perform trajectory interpolation on the Kalman position information according to the Kalman position information to obtain the driving trajectory of the vehicle.

10. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

Images