Vehicle driving assistance system and method based on 360-degree looking-around device

Abstract

The invention discloses a vehicle driving assistance system and method based on a 360-degree looking-around device, and relates to the technical field of driving assistance. The vehicle driving assistance system comprises an image acquisition module, a path planning module, a real-time monitoring module, a parking planning module, an early warning terminal and a database. Then, according to each piece of information in the panoramic image, selecting each available parking space for a driver to select, planning a driving route from the vehicle to the parking space, then monitoring whether the vehicle is separated from the planned driving route in real time, if so, re-planning the driving route, if not, re-planning the driving route, and finally planning a parking driving range of the vehicle. According to the method, the parking space of the vehicle can be quickly and effectively selected, whether the parking of the vehicle is standard or not is analyzed, if not, early warning is conducted, a driver is reminded of the standard parking position, the driver can quickly and effectively select the parking space, the safety of the vehicle arriving at the parking space and the parking safety are guaranteed, and the standard parking of the vehicle is also guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of driving assistance technology, and in particular to a vehicle driving assistance system and method based on a 360-degree surround view device. Background Art

[0002] In modern society, the demand for driving safety and convenience is constantly increasing. Vehicle parking is an important part of the driving process, and its intelligence directly affects the user experience. Therefore, it is particularly urgent to develop a system that can fully perceive the vehicle's surrounding environment, accurately plan parking paths, and provide auxiliary information in real time.

[0003] Traditional vehicle driving assistance systems and methods install a camera at the rear of the vehicle. When the vehicle is in reverse gear, the camera will automatically turn on to capture real-time images of the rear of the vehicle and transmit the images to the display screen inside the vehicle. The driver parks the car through the display screen. Obviously, this vehicle driving assistance system and method has the following shortcomings: 1. Traditional vehicle driving assistance systems and methods lack the selection of parking spaces. The driver selects a parking space based on the observed parking space conditions, which cannot guarantee that the driver can select a parking space quickly and effectively.

[0004] 2. Traditional vehicle driving assistance systems and methods rely on a camera installed at the rear of the vehicle to observe the situation behind the vehicle. The camera at the rear of the vehicle has a certain visual blind spot, and the driver cannot observe the situation in the blind spot, which cannot ensure the driver's safety during the parking process. Summary of the Invention

[0005] In view of the above-mentioned technical deficiencies, the object of the present invention is to provide a vehicle driving assistance system and method based on a 360-degree surround view device.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions: First, the present invention provides a vehicle driving assistance system based on a 360-degree surround view device, including the following modules: an image acquisition module, a path planning module, a real-time monitoring module, a parking planning module, an early warning terminal and a database.

[0007] The image acquisition module is used to collect images of the vehicle's surroundings and generate a 360-degree panoramic image, while identifying and marking parking spaces and obstacles around the vehicle.

[0008] The path planning module is used to analyze the available parking spaces and unavailable parking spaces based on the information in the panoramic image, mark the unavailable parking spaces in red and the available parking spaces in green in the panoramic image, and feedback the information to the user interface. The driver randomly selects an available parking space based on the feedback panoramic image information, which is called the target parking space, and plans the driving path according to the vehicle position and the position of the target parking space.

[0009] The real-time monitoring module is used to monitor in real time whether the vehicle's position is on the planned route when the driver is driving according to the planned route. If not, the route is replanned according to the vehicle's current position.

[0010] The parking planning module is used to collect the vehicle's position in real time and calculate the distance between the vehicle and the target parking space. When the distance between the vehicle and the target parking space is less than a preset value, parking planning is carried out and an analysis is made as to whether the vehicle is parked in a standard manner. If not, an early warning is issued and the parking position is marked in a panoramic view. At the same time, feedback is fed back to the user interface, and the driver makes adjustments based on the feedback information.

[0011] The early warning terminal is used to issue an early warning when the vehicle is not on the planned driving route or the vehicle is parked unsafely.

[0012] The database is used to store preset thresholds for various data and vehicle dimensions.

[0013] In the second aspect, the present invention provides a vehicle driving assistance method based on a 360-degree surround view device, comprising the following steps: Step 1, image acquisition: capturing images of the vehicle's surroundings and generating a 360-degree panoramic image, while identifying and marking parking spaces and obstacles around the vehicle.

[0014] Step 2: Path planning: Based on the information in the panoramic image, available and unavailable parking spaces are analyzed, unavailable parking spaces are marked red in the panoramic image, and available parking spaces are marked green in the panoramic image. This information is then fed back to the user interface. The driver randomly selects an available parking space based on the feedback panoramic image information, calling it the target parking space, and plans the driving path based on the vehicle position and the location of the target parking space.

[0015] Step 3: Real-time monitoring: When the driver is driving according to the planned route, the vehicle's position is monitored in real time to see if it is on the planned route. If not, the route is replanned based on the vehicle's current position.

[0016] Step 4: Parking planning: The vehicle's position is collected in real time, and the distance between the vehicle and the target parking space is calculated. When the distance between the vehicle and the target parking space is less than the preset value, parking planning is carried out, and analysis is performed to determine whether the vehicle is parked in a standard manner. If not, an early warning is issued, and the parking location is marked in the panoramic view. At the same time, feedback is fed back to the user interface, and the driver makes adjustments based on the feedback information.

[0017] The beneficial effects of the present invention are: 1. The present invention provides a vehicle driving assistance system and method based on a 360-degree surround view device, which first collects images of the vehicle's surroundings and generates a panoramic image. Then, based on the information in the panoramic image, the system selects available parking spaces for the driver to choose, and plans the vehicle's driving route to the parking space. After that, the system monitors in real time whether the vehicle deviates from the planned driving route. If it deviates, the system replans the driving route. Finally, the vehicle's parking range is planned, and it is analyzed whether the vehicle's parking is standard. If not, an early warning is issued, and the driver is prompted to the standard parking position. The driver can quickly and effectively select a parking space, ensuring the safety of the vehicle reaching the parking space and the safety of parking, and also ensuring the standardization of the vehicle parking.

[0018] 2. The present invention first determines whether the parking spaces around the vehicle can be parked based on the information in the panoramic view. The parking spaces that can be parked are marked green in the panoramic view, and the parking spaces that cannot be parked are marked red in the panoramic view. The information is then fed back to the user interface. The driver randomly selects a parking space based on the feedback information, ensuring that the driver can select a parking space quickly and effectively.

[0019] 3. After the driver selects a parking space, the present invention automatically generates various driving routes based on the coordinates of the selected parking space, the vehicle coordinates, and information surrounding the vehicle. A cost function is designed to calculate the costs of various driving routes, compare them, select the route with the lowest cost, and feed this route back to the user interface. While the driver is driving along the planned route, the system monitors in real time whether the vehicle deviates from the planned route. If so, the route is replanned and fed back to the user interface, ensuring the safety of the vehicle reaching the parking space.

[0020] 4. When a vehicle arrives near a parking space, the present invention plans the parking range of the vehicle based on various information about the parking space's surroundings, and simultaneously monitors in real time whether the vehicle exceeds the parking range during parking. If so, the emergency braking system is activated. At the same time, it monitors whether the vehicle is parked in a standard manner. If not, an early warning is issued, and the standard parking position is fed back to the user interface, thereby ensuring parking safety and standardization. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1This is a schematic diagram of the system structure connection of the present invention.

[0023] Figure 2 The figure is a schematic flow chart of the steps for implementing the method of the present invention. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0025] See also Figure 1 As shown, the present invention provides a vehicle driving assistance system based on a 360-degree surround view device, including the following modules: an image acquisition module, a path planning module, a real-time monitoring module, a parking planning module, an early warning terminal and a database.

[0026] The image acquisition module is connected to the path planning module, the path planning module is connected to the real-time monitoring module, the real-time monitoring module is connected to the parking planning module, the early warning terminal is connected to the real-time monitoring module and the parking planning module, and the book database is connected to the path planning module, the real-time monitoring module and the parking planning module.

[0027] The image acquisition module is used to collect images of the vehicle's surroundings and generate a 360-degree panoramic image, while identifying and marking parking spaces and obstacles around the vehicle.

[0028] It should be noted that the 360-degree surround view device consists of 4 or more cameras, which are installed on the front grille, bottom of the rearview mirror and rear of the vehicle to collect image information around the vehicle from different angles.

[0029] It should also be noted that the process of generating a 360-degree panoramic image is as follows: first, each image captured by each camera is subjected to denoising, color correction, and brightness adjustment processing, and then a feature extraction algorithm is used to extract the feature points and feature descriptors of each processed image. By comparing the feature descriptors of each image, matching feature point pairs are found. Then, based on the matching feature point pairs, the transformation matrix between adjacent images is calculated, and the adjacent images are projected according to the calculated transformation matrix to map them to the same plane. Finally, the images are fused and optimized to obtain a 360-degree panoramic image.

[0030] It should also be noted that the process of identifying parking spaces and obstacles around the vehicle is as follows: first, the 360-degree panoramic image is grayscaled, denoised, and image enhanced. Then, an edge detection operator is used to extract edge information in the image, and a corner detection algorithm is used to extract corner information in the image. Then, a template matching algorithm is used to find areas in the extracted edge image or feature image that match the shape of the parking space. Finally, a pre-trained machine learning model is used to classify and identify the extracted features to determine whether the area in the image is an obstacle.

[0031] The path planning module is used to analyze the available parking spaces and unavailable parking spaces based on the information in the panoramic image, mark the unavailable parking spaces in red and the available parking spaces in green in the panoramic image, and feedback the information to the user interface. The driver randomly selects an available parking space based on the feedback panoramic image information, which is called the target parking space, and plans the driving path according to the vehicle position and the position of the target parking space.

[0032] In a specific embodiment, the path planning process is as follows: S11, obtaining the coordinates of each surrounding vehicle, the coordinates of each obstacle, the coverage range of each parking space and the size of each parking space in the vehicle panoramic view, and calling the surrounding vehicles as blocking vehicles, and analyzing whether each parking space is an available parking space based on the coordinates of each blocking vehicle, the coordinates of each obstacle, the coverage range of each parking space, the size of each parking space and the size of the vehicle, and obtaining each available parking space and each unavailable parking space, marking each unavailable parking space in red in the panoramic view, marking each available parking space in green in the panoramic view, and feeding back to the user interface.

[0033] It should be noted that the process of obtaining the positions of the surrounding vehicles and obstacles in the vehicle panoramic image is as follows: first, a coordinate system is established in the panoramic image, and the pixel coordinates of the surrounding vehicles and obstacles in the image are determined according to their positions in the image.

[0034] It should also be noted that the specific process of obtaining the coverage range and size of each parking space is as follows: first, morphological operations are performed on the panoramic image, then the contours in the image are extracted, and these contours are analyzed to screen out contours that meet the characteristics of the parking space. Then, Hough transform detection is used to determine the four boundary lines of each parking space. According to the intersection of the four boundary lines, the four vertices of each parking space can be determined, and then the coverage range of each parking space can be determined. Finally, the size of each parking space is calculated based on the various parameters of the camera and the four transformed pixels of each parking space.

[0035] It should also be noted that the dimensions of the vehicle are set by the manufacturer of the vehicle and stored in the database.

[0036] S12. The driver randomly selects an available parking space based on the panoramic image feedback, which is called the target parking space. The driver plans a driving area based on the vehicle coordinates and the coordinates of the target parking space. Within the driving area, the driver divides the driving area into sub-areas according to a preset area threshold. The center point of each sub-area is used as each node, the vehicle position is used as the starting point, and the target parking space is used as the end point. At the same time, the driver determines whether each node is passable, removes the inaccessible nodes, and obtains the passable nodes. Based on the passable nodes, several driving routes are automatically generated.

[0037] It should be noted that a rectangular driving area is planned with the vehicle position and the target parking space position as diagonals.

[0038] It should also be noted that the preset area threshold is set by the staff.

[0039] S13. Design a cost function, calculate the driving cost of each driving route, compare them, select the driving route with the minimum cost, use this driving route as the driver's driving route to the parking space, and feed it back to the user interface.

[0040] In the above, the specific process of analyzing whether each parking space is an available parking space is as follows: S21, obtaining the coordinates of each surrounding vehicle, the coordinates of each obstacle and the coverage range of each parking space in the vehicle panoramic view, and calling the surrounding vehicles each blocking vehicle.

[0041] S22. Compare the coordinates of each obstructing vehicle and each obstacle with the coverage range of each parking space. If the coordinates of an obstructing vehicle are within the coverage range of a parking space, or the coordinates of an obstacle are within the coverage range of the parking space, it means that the parking space is occupied and the parking space is called an unavailable parking space. If the coordinates of all obstructing vehicles are not within the coverage range of a parking space, and the coordinates of all obstacles are not within the coverage range of the parking space, it means that the parking space is not occupied and the parking space is called a passable parking space. In this way, the unavailable parking spaces and the passable parking spaces are obtained.

[0042] S23. Obtain the length and width of each parking space, as well as the length and width of the vehicle, then:

[0043]

[0044] Where A a represents the length of the a-th parking space, B a represents the width of the a-th parking space, A′ represents the length of the vehicle, B′ represents the width of the vehicle, α a Represents the availability coefficient of the ath accessible parking space, a represents the number of each accessible parking space, a=1,2,3,...,b, b represents the total number of accessible parking spaces, and both a and b are positive integers.

[0045] S24. When the availability coefficient of a certain parking space is 1, it means that the vehicle can be parked in the parking space, and the parking space is called an available parking space. When the availability coefficient of a certain parking space is 0, it means that the vehicle cannot be parked in the parking space, and the parking space is called an unavailable parking space.

[0046] According to step S21 to step S24 , it is analyzed whether each parking space is an available parking space.

[0047] In the above, the specific process of determining whether each node is passable is as follows: obtain the coordinates of each node and the coordinates of each obstacle, and calculate the distance between each node and each obstacle, then:

[0048]

[0049] In the formula represents the distance between the cth node and the dth obstacle, represents the preset distance threshold, β c represents the pass value of the cth node, c represents the number of each node, c = 1, 2, 3, ..., f, f represents the total number of nodes, d represents the number of each obstacle, d = 1, 2, 3, ..., g, g represents the total number of obstacles, and c, f, d and g are all positive integers.

[0050] When β c =1, it means there are no obstacles around the cth node, and the node is passable. c =0, it means that there are obstacles around the cth node, and the node is not passable. This method is used to determine whether each node is passable.

[0051] It should be noted that

[0052] It should also be noted that the preset distance threshold is set by the staff and is used to evaluate whether each obstacle can affect the passage of each node.

[0053] In the above, the calculation of the driving cost of each driving route is as follows: S31, calculating the distance between each obstacle and each driving route, and comparing it with a preset first distance threshold. If the distance between an obstacle and a driving route is less than the preset first distance threshold, then the obstacle is regarded as an influencing obstacle for the driving route. In this way, the influencing obstacles of each driving route are obtained, and the total number of influencing obstacles of each driving route and the distance between each driving route and its influencing obstacles are counted.

[0054] It should be noted that the preset first distance threshold is set by the staff and is used to evaluate the impact of various obstacles on the passage of each driving path.

[0055] S32. Obtain the distance of each driving route and normalize the distance between each driving route and its influencing obstacles. Then:

[0056]

[0057] In the formula represents the distance between the hth driving route and the ith influencing obstacle, E h represents the total number of obstacles affecting the h-th driving route, χ h represents the driving cost of the hth driving route, F h represents the distance of the hth driving route, F′ represents the distance between the vehicle and the target parking space, then Where (x1, y1) represents the coordinates of the vehicle, (x2, y2) represents the location of the target parking space, h represents the number of each driving route, h = 1, 2, 3, ..., k, k represents the total number of driving routes, i represents the number of each influencing obstacle, i = 1, 2, 3, ..., j, j represents the total number of influencing obstacles, and h, k, i and j are all positive integers.

[0058] The real-time monitoring module is used to monitor in real time whether the vehicle's position is on the planned route when the driver is driving according to the planned route. If not, the route is replanned according to the vehicle's current position.

[0059] In a specific embodiment, the real-time monitoring is specifically carried out as follows: when the driver is driving according to the planned driving route, the vehicle coordinates are collected in real time, and the vehicle coordinates are compared with the range covered by the planned driving route. If the vehicle coordinates are not within the range covered by the planned driving path, it means that the vehicle has deviated from the driving path. At this time, the degree of deviation of the vehicle is analyzed. If the degree of deviation of the vehicle is low, the driver is prompted. If the degree of deviation of the vehicle is high, an early warning is issued, and the vehicle's driving route is replanned, and the re-planned driving route is fed back to the user interface.

[0060] It should be noted that the vehicle's location is obtained using GPS.

[0061] It should also be noted that the range covered by the planned driving route is obtained from the database.

[0062] In the above, the specific process of analyzing the degree of deviation of the vehicle is as follows: using the gyroscope sensor to obtain the vehicle's driving angle, and obtaining the vehicle's coordinates, the driving angle on the planned driving route, and the vehicle's coordinates at this time, then:

[0063]

[0064] Where G represents the driving angle of the vehicle, G′ represents the driving angle on the planned driving route, (x1′, y1′) represents the coordinates of the vehicle, and (x′, y′) represents the coordinates of the vehicle at this time on the planned driving route. represents the preset first boundary threshold, δ represents the deviation coefficient of the vehicle. When the deviation coefficient of the vehicle is 1, it means that the degree of deviation of the vehicle is low. When the deviation coefficient of the vehicle is 0, it means that the degree of deviation of the vehicle is high.

[0065] It should be noted that the preset first threshold is set by the staff and is used to assess the degree of deviation of the vehicle.

[0066] The parking planning module is used to collect the vehicle's position in real time and calculate the distance between the vehicle and the target parking space. When the distance between the vehicle and the target parking space is less than a preset value, parking planning is carried out and whether the parking of the vehicle is safe is analyzed. If it is unsafe, an early warning is issued and the parking position is marked in the panoramic view. At the same time, feedback is fed back to the user interface, and the driver makes adjustments based on the feedback information.

[0067] In a specific embodiment, the parking planning process is as follows: S41. When the driver drives according to the planned route, the vehicle's position is collected in real time, and the distance between the vehicle and the target parking space is calculated, which is called the parking planning distance. The parking planning distance is compared with a preset second distance threshold. If the parking planning distance is not greater than the preset distance threshold, the vehicle's position and the position of the vehicle in the parking space adjacent to the target parking space are obtained, and the parking range of the vehicle is planned.

[0068] It should be noted that the preset second distance threshold is set by the staff and is used to determine whether to perform parking planning for the vehicle.

[0069] It should also be noted that the distance between the edge of the parking driving range and the vehicle in the parking space adjacent to the target parking space is greater than the preset safety distance threshold, and the target parking space is within the parking driving range.

[0070] It should also be noted that the preset safety distance threshold is set by the staff and is used to determine whether the vehicle may collide with the vehicle in the adjacent parking space. If the distance between the edge of the parking driving range and the vehicle in the parking space adjacent to the target parking space is greater than the preset safety distance threshold, it means that the vehicle is likely to collide with the vehicle in the adjacent parking space. If the distance between the edge of the parking driving range and the vehicle in the parking space adjacent to the target parking space is less than the preset safety distance threshold, it means that the vehicle is unlikely to collide with the vehicle in the adjacent parking space.

[0071] S42. When the driver parks the vehicle within the parking range, the coordinates of the four tires of the vehicle are collected in real time and compared with the parking range. If the coordinates of any tire are not within the parking range, the emergency braking system is activated and a warning is issued, while reminding the driver to adjust the position of the vehicle until the vehicle is parked within the target parking space.

[0072] It should be noted that the coordinates of the vehicle tires are collected using a UWB tag and IMU combination device.

[0073] S43. When the vehicle is parked within the target parking space, the system analyzes whether the parking is standard. If not, a prompt is given and the standard parking position is marked in the panoramic image. The standard parking position is also fed back to the user interface, and the driver makes adjustments based on the feedback information.

[0074] In the above, the analysis of whether the vehicle is parked in a standard manner is as follows: the coordinates of the vehicle and the horizontal coordinates of the four tires of the vehicle are obtained, then:

[0075]

[0076] Where η represents the distance between the vehicle coordinates and the preset coordinates, (x3, y3) represents the vehicle coordinates, (x4, y4) represents the preset coordinates, x″ represents the horizontal coordinate of the upper right tire of the vehicle, x′ represents the horizontal coordinate of the lower right tire of the vehicle, η′ represents the preset second boundary threshold, and γ represents the standard indicator of the vehicle.

[0077] When the vehicle's standard index is 1, it means the vehicle is parked in a standard manner. When the vehicle's standard index is 0, it means the vehicle is not parked in a standard manner.

[0078] It should be noted that the preset coordinates are set by the staff and are the center point of the parking space.

[0079] It should also be noted that the preset second threshold value is set by the staff and is used to determine whether the vehicle parking position is correct. When the distance between the vehicle coordinates and the preset coordinates is not greater than the preset second threshold value, it means that the vehicle parking position is correct. When the distance between the vehicle coordinates and the preset coordinates is greater than the preset second threshold value, it means that the vehicle parking position is incorrect.

[0080] The early warning terminal is used to issue an early warning when the vehicle is not on the planned driving route or the vehicle is parked unsafely.

[0081] The database is used to store preset thresholds for various data and vehicle dimensions.

[0082] It should be noted that the preset thresholds for each data include a preset area threshold, a preset distance threshold, a preset first distance threshold, a preset second distance threshold, a preset first boundary value, a preset safety distance threshold and a preset second boundary value threshold.

[0083] See also Figure 2 As shown, the present invention provides a vehicle driving assistance method based on a 360-degree surround view device, comprising the following steps: Step 1, image acquisition: acquiring images of the vehicle's surroundings and generating a 360-degree panoramic image, while identifying and marking parking spaces and obstacles around the vehicle.

[0084] Step 2: Path planning: The panoramic image is segmented to identify the parking spaces. Based on the information about each parking space, available and unavailable spaces are analyzed. Unavailable spaces are marked red in the panoramic image, and available spaces are marked green in the panoramic image. This information is then fed back to the user interface. The driver then randomly selects an available parking space based on the panoramic image information, calling it the target parking space. The driver then plans the driving path based on the vehicle's position and the target parking space's position.

[0085] Step 3: Real-time monitoring: When the driver is driving according to the planned route, the vehicle's position is monitored in real time to see if it is on the planned route. If not, the route is replanned based on the vehicle's current position.

[0086] Step 4: Parking planning: The vehicle's coordinates are collected in real time, and the distance between the vehicle and the target parking space is calculated. When the distance between the vehicle and the target parking space is less than the preset value, parking planning is performed, and analysis is performed to determine whether the vehicle is parked correctly. If not, an early warning is issued, and the parking location is marked in the panoramic view. Feedback is also provided to the user interface, and the driver makes adjustments based on the feedback information.

[0087] The embodiment of the present invention first captures an image of the vehicle's surroundings and generates a panoramic image. Then, based on the information in the panoramic image, it selects available parking spaces for the driver to choose from, and plans the vehicle's driving route to the parking space. It then monitors in real time whether the vehicle deviates from the planned driving route. If so, the driving route is replanned. Finally, the vehicle's parking range is planned, and it is analyzed whether the vehicle is parked in a standard manner. If not, an early warning is issued, and the driver is prompted to park in a standard position. The driver can quickly and effectively select a parking space, ensuring the safety of the vehicle reaching the parking space and the safety of parking, as well as the standardization of vehicle parking.

[0088] The above content is merely an example and explanation of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they should all fall within the scope of protection of the present invention.

Claims

1. A vehicle driving assistance system based on a 360-degree surround view device, characterized in that: Includes the following modules: The image acquisition module is used to collect images of the vehicle's surroundings and generate a 360-degree panoramic image. It also identifies and labels parking spaces and obstacles around the vehicle. The path planning module is used to analyze the available and unavailable parking spaces based on the information in the panoramic image, mark the unavailable parking spaces in red and the available parking spaces in green in the panoramic image, and feedback this to the user interface. The driver randomly selects an available parking space based on the feedback panoramic image information, calling it the target parking space, and plans the driving path based on the vehicle position and the location of the target parking space. The real-time monitoring module is used to monitor the vehicle's position in real time when the driver is driving according to the planned route. If it is not on the route, the route is replanned according to the vehicle's current position. The parking planning module is used to collect the vehicle's position in real time and calculate the distance between the vehicle and the target parking space. When the distance between the vehicle and the target parking space is less than the preset value, parking planning is carried out and the parking position is analyzed to see if the vehicle is parked in a standard manner. If not, an early warning is issued and the standard parking position is marked in the panoramic map. The feedback is also fed back to the user interface, and the driver can make adjustments based on the feedback information. The early warning terminal is used to issue an early warning when the vehicle is not on the planned driving route or the vehicle is parked unsafely; The database is used to store preset thresholds for various data and vehicle dimensions.

2. The vehicle driving assistance system based on the 360-degree surround view device according to claim 1, characterized in that: The specific process of path planning is as follows: S11. Obtain the coordinates of each vehicle, each obstacle, the coverage area of ​​each parking space, and the size of each parking space in the panoramic view of the vehicle. The surrounding vehicles are referred to as blocking vehicles. Based on the coordinates of each blocking vehicle, the coordinates of each obstacle, the coverage area of ​​each parking space, the size of each parking space, and the size of the vehicle, analyze whether each parking space is available. Obtain each available parking space and each unavailable parking space. Mark each unavailable parking space in red in the panoramic view and each available parking space in green in the panoramic view. Feedback is provided to the user interface. S12. The driver randomly selects an available parking space based on the panoramic image feedback, which is referred to as the target parking space. Based on the vehicle coordinates and the coordinates of the target parking space, the driver plans a driving area. Within the driving area, the driver divides the driving area into sub-areas according to a preset area. The center point of each sub-area is used as a node, the vehicle position is used as the starting point, and the target parking space is used as the end point. The driver also determines whether each node is passable. Inpassable nodes are removed to obtain passable nodes. Based on each passable node, a number of driving routes are automatically generated. S13. Design a cost function, calculate the driving cost of each driving route, compare them, select the driving route with the minimum cost, use this driving route as the driver's driving route to the parking space, and feed it back to the user interface.

3. The vehicle driving assistance system based on the 360-degree surround view device according to claim 2, characterized in that: The specific process of analyzing whether each parking space is an available parking space is as follows: S21. Obtain the coordinates of surrounding vehicles, the coordinates of obstacles, and the coverage of parking spaces in the vehicle panoramic image, and refer to the surrounding vehicles as blocking vehicles. S22. Compare the coordinates of each obstructing vehicle and each obstacle with the coverage range of each parking space. If the coordinates of an obstructing vehicle are within the coverage range of a parking space, or the coordinates of an obstacle are within the coverage range of the parking space, then the parking space is occupied and is referred to as an unavailable parking space. If the coordinates of all obstructing vehicles and all obstacles are not within the coverage range of the parking space, then the parking space is unoccupied and is referred to as a passable parking space. In this way, all unavailable parking spaces and passable parking spaces are obtained. S23. Obtain the length and width of each parking space, as well as the length and width of the vehicle, then: Where A a represents the length of the a-th parking space, B a represents the width of the a-th parking space, A′ represents the length of the vehicle, B′ represents the width of the vehicle, α a represents the availability coefficient of the ath parking space, where a represents the number of each parking space, a=1, 2, 3, ..., b, and b represents the total number of parking spaces. Both a and b are positive integers. S24. When the availability coefficient of a certain parking space is 1, it means that the vehicle can be parked in the parking space, and the parking space is called an available parking space. When the availability coefficient of a certain parking space is 0, it means that the vehicle cannot be parked in the parking space, and the parking space is called an unavailable parking space. According to step S21 to step S24 , it is analyzed whether each parking space is an available parking space.

4. The vehicle driving assistance system based on the 360-degree surround view device according to claim 2, characterized in that: The specific process of judging whether each node is passable is as follows: Get the coordinates of each node and each obstacle, and calculate the distance between each node and each obstacle, then: In the formula represents the distance between the cth node and the dth obstacle, represents the preset distance threshold, β c represents the pass value of the c-th node, c represents the node number, c = 1, 2, 3, ..., f, f represents the total number of nodes, d represents the obstacle number, d = 1, 2, 3, ..., g, g represents the total number of obstacles, c, f, d and g are all positive integers; When β c =1, it means there are no obstacles around the cth node, and the node is passable. c =0, it means that there are obstacles around the cth node, and the node is not passable. This method is used to determine whether each node is passable.

5. The vehicle driving assistance system based on the 360-degree surround view device according to claim 2, characterized in that: The calculation process of the travel cost of each route is as follows: S31. Calculate the distance between each obstacle and each driving route and compare it with a preset first distance threshold. If the distance between an obstacle and a driving route is less than the preset first distance threshold, then the obstacle is considered an influencing obstacle for the driving route. In this way, the influencing obstacles for each driving route are obtained, and the total number of influencing obstacles for each driving route and the distance between each driving route and its influencing obstacles are counted. S32. Obtain the distance of each driving route and normalize the distance between each driving route and its influencing obstacles. Then: In the formula represents the distance between the hth driving route and the ith influencing obstacle, E h represents the total number of obstacles affecting the h-th driving route, χ h represents the driving cost of the hth driving route, F h represents the distance of the hth driving route, F′ represents the distance between the vehicle and the target parking space, then Where (x1, y1) represents the coordinates of the vehicle, (x2, y2) represents the location of the target parking space, h represents the number of each driving route, h = 1, 2, 3, ..., k, k represents the total number of driving routes, i represents the number of each influencing obstacle, i = 1, 2, 3, ..., j, j represents the total number of influencing obstacles, and h, k, i and j are all positive integers.

6. The vehicle driving assistance system based on the 360-degree surround view device according to claim 1, characterized in that: The specific process of real-time monitoring is as follows: When the driver is driving along the planned route, the vehicle's coordinates are collected in real time and compared with the range covered by the planned route. If the vehicle's coordinates are not within the range covered by the planned route, it means that the vehicle has deviated from the route. At this time, the degree of deviation of the vehicle is analyzed. If the degree of deviation is low, the driver is prompted. If the degree of deviation is high, an early warning is issued, and the vehicle's route is replanned. The re-planned route is fed back to the user interface.

7. The vehicle driving assistance system based on the 360-degree surround view device according to claim 6, characterized in that: The specific process of analyzing the degree of deviation of the vehicle is as follows: Use the gyrometer sensor to obtain the vehicle's driving angle, and obtain the vehicle's position, the driving angle on the planned driving route, and the vehicle coordinates at this time. Then: Where G represents the driving angle of the vehicle, G′ represents the driving angle on the planned driving route, (x1′, y1′) represents the coordinates of the vehicle, and (x′, y′) represents the coordinates of the vehicle at this time on the planned driving route. represents a preset first threshold value, δ represents the deviation coefficient of the vehicle. When the deviation coefficient of the vehicle is 1, it represents that the degree of deviation of the vehicle is low. When the deviation coefficient of the vehicle is 0, it represents that the degree of deviation of the vehicle is high.

8. The vehicle driving assistance system based on the 360-degree surround view device according to claim 1, characterized in that: The specific process of parking planning is as follows: S41. When the driver drives along the planned route, the vehicle's coordinates are collected in real time, and the distance between the vehicle and the target parking space is calculated, which is called the planned parking distance. The planned parking distance is compared with a preset distance threshold. If the planned parking distance is not greater than the preset distance threshold, the vehicle's coordinates and the coordinates of vehicles in parking spaces adjacent to the target parking space are obtained, and the vehicle's parking range is planned. S42. When the driver parks the vehicle within the parking range, the coordinates of the four tires of the vehicle are collected in real time and compared with the coordinates of the four tires of the vehicle within the parking range. If the coordinates of any tire are not within the parking range, the emergency braking system is activated, an early warning is issued, and the driver is reminded to adjust the position of the vehicle until the vehicle is parked within the target parking space. S43. When the vehicle is parked within the target parking space, the system analyzes whether the parking is standard. If not, a prompt is given and the standard parking position is marked in the panoramic image. The standard parking position is also fed back to the user interface, and the driver makes adjustments based on the feedback information.

9. The vehicle driving assistance system based on the 360-degree surround view device according to claim 8, characterized in that: The specific process of analyzing whether the parking of the vehicle is standard is as follows: Get the coordinates of the vehicle and the horizontal coordinates of the four tires of the vehicle, then: Where η represents the distance between the vehicle coordinates and the preset coordinates, (x3, y3) represents the vehicle coordinates, (x4, y4) represents the preset coordinates, x″ represents the horizontal coordinate of the right upper tire of the vehicle, x′ represents the horizontal coordinate of the right lower tire of the vehicle, η′ represents the preset second threshold value, and γ represents the standard index of the vehicle; When the vehicle's standard index is 1, it means the vehicle is parked in a standard manner. When the vehicle's standard index is 0, it means the vehicle is not parked in a standard manner.

10. A vehicle driving assistance method for executing the vehicle driving assistance system based on a 360-degree surround view device according to any one of claims 1 to 9, characterized in that: include: Step 1: Image acquisition: Capture images of the vehicle's surroundings and generate a 360-degree panoramic image. At the same time, identify and annotate parking spaces and obstacles around the vehicle. Step 2: Path Planning: Based on the information in the panoramic image, available and unavailable parking spaces are analyzed. Unavailable parking spaces are marked red in the panoramic image, and available parking spaces are marked green in the panoramic image. This information is then fed back to the user interface. The driver randomly selects an available parking space based on the feedback panoramic image information, calling it the target parking space, and plans a driving path based on the vehicle's position and the location of the target parking space. Step 3: Real-time monitoring: When the driver is driving according to the planned route, the vehicle's position is monitored in real time to see if it is on the planned route. If not, the route is replanned based on the vehicle's current position. Step 4: Parking planning: The vehicle's coordinates are collected in real time, and the distance between the vehicle and the target parking space is calculated. When the distance between the vehicle and the target parking space is less than the preset value, parking planning is performed, and analysis is performed to determine whether the vehicle is parked correctly. If not, an early warning is issued, and the parking location is marked in the panoramic view. At the same time, feedback is sent to the user interface, and the driver makes adjustments based on the feedback information.

Images