An autonomous driving assistance method and system

Abstract

The application relates to the technical field of automatic driving and provides an automatic driving assistance method and system, which comprises the following steps: acquiring point cloud data, wherein the point cloud data is data information acquired by a detection signal emitted by a laser radar installed on a first vehicle; generating a two-dimensional image according to the point cloud data, wherein the two-dimensional image is a two-dimensional image of the surrounding environment of the first vehicle perceived by the laser radar installed on the first vehicle; performing feature extraction on the two-dimensional image by using a neural network model to obtain feature information, wherein the feature information comprises feature information of each foreground point in the two-dimensional image; performing clustering on each foreground point in the two-dimensional image based on the feature information to obtain an instance segmented two-dimensional image; and assisting a user in taking over the first vehicle according to the instance segmented two-dimensional image, so that the automatic driving vehicle can accurately and quickly perceive the surrounding environment, the driving personnel can take over the vehicle in the automatic driving according to the perception result, and the safety of the automatic driving is improved.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and more specifically, to an autonomous driving assistance method and system. Background Technology

[0002] With the rapid development of the autonomous vehicle industry, autonomous driving technology is becoming increasingly mature and the degree of automation is also increasing. When a vehicle is driving autonomously, it needs to perceive the surrounding environment to assist the vehicle in driving and avoid accidents to the driver. Currently, onboard sensors are usually used to identify vehicles around the autonomous vehicle. However, this method has problems such as low recognition accuracy and slow detection speed. Therefore, there is an urgent need for an autonomous driving assistance method that can accurately and quickly identify the surrounding environment of the autonomous vehicle to assist the driver. Summary of the Invention

[0003] The purpose of this invention is to provide an autonomous driving assistance method and system to improve the above-mentioned problems.

[0004] To achieve the above objectives, the embodiments of this application provide the following technical solutions:

[0005] On one hand, embodiments of this application provide an autonomous driving assistance method, the method comprising:

[0006] Acquire point cloud data, which is data information obtained from the detection signal emitted by the lidar installed on the first vehicle, and the first vehicle is a vehicle in autonomous driving;

[0007] A two-dimensional image is generated based on the point cloud data. The two-dimensional image is a two-dimensional image of the environment around the first vehicle perceived by the lidar installed on the first vehicle.

[0008] The two-dimensional image is used to extract features using a neural network model to obtain feature information, which includes feature information of each foreground point in the two-dimensional image;

[0009] Based on the feature information, each foreground point in the two-dimensional image is clustered to obtain the instance-segmented two-dimensional image;

[0010] The two-dimensional image segmented from the example helps the user take over the first vehicle.

[0011] Secondly, embodiments of this application provide an autonomous driving assistance system, the system comprising:

[0012] The acquisition module is used to acquire point cloud data, which is data information obtained from the detection signal emitted by the lidar installed on the first vehicle, and the first vehicle is a vehicle in autonomous driving.

[0013] A generation module is used to generate a two-dimensional image based on the point cloud data. The two-dimensional image is a two-dimensional image of the environment around the first vehicle perceived by the lidar installed on the first vehicle.

[0014] The first processing module is used to extract features from the two-dimensional image using a neural network model to obtain feature information, wherein the feature information includes feature information of each foreground point in the two-dimensional image;

[0015] The second processing module is used to cluster each foreground point in the two-dimensional image based on the feature information to obtain the instance-segmented two-dimensional image.

[0016] The third processing module is used to assist the user in taking over the first vehicle based on the two-dimensional image segmented from the instance.

[0017] Thirdly, embodiments of this application provide an autonomous driving assistance device, the device including a memory and a processor. The memory is used to store a computer program; the processor is used to execute the computer program to implement the steps of the above-described autonomous driving assistance method.

[0018] Fourthly, embodiments of this application provide a readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described autonomous driving assistance method.

[0019] The beneficial effects of this invention are as follows:

[0020] This invention acquires point cloud data of the surrounding environment using vehicle-mounted LiDAR, converts the point cloud data into a dense two-dimensional image, and then uses an instance segmentation algorithm to segment the two-dimensional image to obtain a segmented two-dimensional image. This enables autonomous vehicles to accurately and quickly detect and perceive the surrounding environment. Finally, based on the perception results, it assists the driver in taking over the autonomous vehicle, thereby improving the safety of autonomous driving, preventing the driver from causing danger, and ensuring the driver's personal safety.

[0021] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram of the autonomous driving assistance method described in an embodiment of the present invention.

[0024] Figure 2 This is a schematic diagram of the structure of the autonomous driving assistance system described in an embodiment of the present invention.

[0025] Figure 3 This is a schematic diagram of the structure of the autonomous driving assistance device described in an embodiment of the present invention.

[0026] The diagram is labeled as follows: 901, Acquisition Module; 902, Generation Module; 903, First Processing Module; 904, Second Processing Module; 905, Third Processing Module; 800, Autonomous Driving Assistance Equipment; 801, Processor; 802, Memory; 803, Multimedia Component; 804, I / O Interface; 805, Communication Component. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0028] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0029] Example 1:

[0030] This embodiment provides an autonomous driving assistance method. It can be understood that a scenario can be set up in this embodiment, such as: when a vehicle in autonomous driving mode is on a traffic road, and a vehicle is approaching from behind or to the side, the driver needs to take over the autonomous driving vehicle.

[0031] See Figure 1 The figure shows that the method includes steps S1, S2, S3, S4 and S5.

[0032] Step S1: Acquire point cloud data, which is the data information obtained from the detection signal emitted by the lidar installed on the first vehicle, and the first vehicle is a vehicle in autonomous driving.

[0033] It is understandable that LiDAR is installed on vehicles to emit detection signals to sense the surrounding environment and collect data.

[0034] Step S2: Generate a two-dimensional image based on the point cloud data. The two-dimensional image is a two-dimensional image of the environment around the first vehicle perceived by the lidar installed on the first vehicle.

[0035] It is understood that step S2 further includes steps S21, S22, and S23, which are specifically as follows:

[0036] Step S21: Obtain the horizontal and vertical angles of the lidar installation;

[0037] Step S22: Obtain the three-dimensional coordinates, depth, and reflectivity of each point based on the point cloud data;

[0038] Step S23: Generate a two-dimensional image corresponding to the point cloud data based on the coordinate value of each point, the depth value, the reflectivity, and the horizontal and vertical angles at which the lidar is installed.

[0039] In this embodiment, projecting point cloud data onto a two-dimensional plane to generate a two-dimensional image specifically involves:

[0040]

[0041] n = l

[0042] F(m,n)=[x,y,z,r,d,1] T

[0043] In the above formula, F represents the generated two-dimensional image, m and n are the coordinates of the three-dimensional point projected onto the two-dimensional image, x, y, and z are the three-dimensional coordinates of the three-dimensional point in the lidar coordinate system, l is the line number, α is the horizontal angle of the lidar installation, R is the horizontal angular resolution of the two-dimensional image, r is the reflection intensity, d is the depth value, and 1 is a marker. It should be noted that the number 1 is a marker, indicating that the pixel is projected onto the image. The marker 0 indicates that the pixel is not projected onto the image. The formulas for calculating x, y, and z are:

[0044] x = d*cos(β)cos(α)

[0045] y = d*cos(β)sin(α)

[0046] z = d*sin(β)

[0047] In the above formula, β is the vertical angle at which the lidar is installed. The three-dimensional coordinates of the point cloud data in the lidar coordinate system can be determined according to the above formula.

[0048] In this embodiment, the problem of subsequent feature extraction being hindered by converting point cloud data into sparse two-dimensional images in the prior art is effectively solved. By converting point cloud data into dense two-dimensional images, the features of the two-dimensional images can be fully extracted, thereby ensuring that autonomous vehicles can accurately perceive their surrounding environment.

[0049] Step S3: Use a neural network model to extract features from the two-dimensional image to obtain feature information, which includes feature information of each foreground point in the two-dimensional image;

[0050] It is understood that using neural network models to extract features from the two-dimensional image is a well-known technique in the art, and therefore will not be elaborated here.

[0051] Step S4: Based on the feature information, cluster each foreground point in the two-dimensional image to obtain the instance-segmented two-dimensional image;

[0052] Understandably, by clustering each foreground point in a two-dimensional image to obtain a segmented two-dimensional image, vehicles and obstacles on the road can be accurately identified, avoiding the problem in existing technologies where obstacles on the road are easily identified as foreground objects, resulting in incorrect identification.

[0053] Step S5: Use the segmented two-dimensional image of the instance to assist the user in taking over the first vehicle.

[0054] Understandably, the two-dimensional images obtained through instance segmentation can accurately and quickly perceive and identify the environment around the first vehicle. Finally, based on the perception results, the driver can take over the vehicle in autonomous driving to improve the safety of autonomous driving, avoid danger to the driver, and ensure the driver's personal safety.

[0055] It is understood that step S5 further includes steps S51 and S52, which are specifically as follows:

[0056] Step S51: Obtain the driving information of the second vehicle based on the segmented two-dimensional image of the instance. The second vehicle includes vehicles perceived around the first vehicle. The driving information includes the trajectory information, speed information, and position information of the second vehicle.

[0057] It is understandable that the position and speed information of the vehicles around the first vehicle can be obtained accurately and quickly based on the two-dimensional image after instance segmentation. Based on the two-dimensional image after instance segmentation of multiple consecutive frames of the second vehicle, the trajectory information of the vehicle can be inferred according to the vehicle trajectory prediction model. It should be noted that the vehicle trajectory prediction model is a technical solution well known to those in the art, so it will not be described in detail here.

[0058] Step S52: Determine whether there is a contact point between the first vehicle and the second vehicle based on the trajectory information of the second vehicle. If there is a contact point between the first vehicle and the second vehicle, calculate the contact time between the first vehicle and the second vehicle based on the speed and position information of the second vehicle. If there is no contact point between the first vehicle and the second vehicle, the first vehicle does not require driver intervention.

[0059] It is understandable that the trajectory information of the second vehicle can be used to determine whether the second vehicle intersects with the first vehicle, i.e., makes contact. The trajectory information of the second vehicle can be used to make a preliminary judgment on whether the autonomous vehicle needs to be taken over by the driver.

[0060] It is understood that step S52 further includes steps S521, S522, S523, and S524, which are specifically as follows:

[0061] Step S521: Obtain the preset speed information of the first vehicle;

[0062] It is understandable that the preset speed information of the first vehicle is the speed value at each moment when the vehicle is driving autonomously.

[0063] Step S522: Determine the first orientation information of the second vehicle based on the location information of the second vehicle, wherein the first orientation information includes that the second vehicle is located behind or to the side of the first vehicle.

[0064] It is understandable that the coordinates of the second vehicle can be obtained based on the location information of the second vehicle, and the position of the second vehicle relative to the first vehicle can be obtained based on the coordinates of the second vehicle, that is, whether the second vehicle is behind or to the side of the first vehicle. At the same time, the distance between the second vehicle and the first vehicle can also be obtained.

[0065] Step S523: Calculate the relative speed information between the first vehicle and the second vehicle based on the preset speed information of the first vehicle and the speed information of the second vehicle;

[0066] It is understandable that the speed information of the second vehicle includes the speed value of the second vehicle at each moment. Based on the speed values ​​of the first vehicle and the second vehicle at each moment during autonomous driving, the relative speed between the first vehicle and the second vehicle at each moment can be calculated, thus obtaining the relative speed information between the first vehicle and the second vehicle.

[0067] Step S524: Calculate the first contact time information or the second contact time information based on the relative speed information between the first vehicle and the second vehicle and the first orientation information of the second vehicle. The first contact time information includes the contact time when the second vehicle is behind the first vehicle, and the second contact time information includes the contact time when the second vehicle is to the side of the first vehicle.

[0068] Understandably, since the relative speed between the first and second vehicles at each moment is known, the contact time between the first and second vehicles can be calculated based on the distance between them. It should be noted that when the second vehicle is behind the first vehicle, the contact time between the first and second vehicles only needs to be calculated as the longitudinal contact time, i.e., the first contact time; when the second vehicle is to the side of the first vehicle, the contact time between the first and second vehicles only needs to be calculated as the lateral contact time, i.e., the second contact time.

[0069] It is understood that step S524 is followed by steps S525, S526, and S527, which specifically include:

[0070] Step S525: Obtain the takeover time information of the driver of the first vehicle;

[0071] It is understood that step S525 further includes steps S5251, S5252, and S5253, which are specifically as follows:

[0072] Step S5251: Obtain historical takeover time information and current meteorological data;

[0073] Step S5252: Send the meteorological data at the current moment to the trained weather prediction model to obtain the weather information at the current moment;

[0074] It is understandable that training weather prediction models is a well-known technical solution, so it will not be elaborated here. By sending the current meteorological data to the trained weather prediction model, the current weather can be predicted. By taking into account the impact of weather conditions on the driver takeover time, the accuracy of the takeover time selection is effectively improved, thereby improving the safety of driver-controlled autonomous driving.

[0075] Step S5253: Determine the takeover time information of the driver of the first vehicle based on the weather information at the current moment. If the weather information is severe weather, extract the maximum takeover time from the historical takeover time information to obtain the takeover time information of the first vehicle. The severe weather includes snow, fog and rain. If the environment in which the first vehicle is located is normal weather, calculate the average takeover time based on the historical takeover time information and use the average takeover time as the takeover time information of the driver of the first vehicle.

[0076] Understandably, when the weather forecast based on the current meteorological data indicates normal weather, the average takeover time is obtained by adding up each takeover time and taking the mean, thus serving as the takeover time for the first vehicle. This effectively ensures that the driver can safely take over the vehicle in normal weather. In severe weather, the maximum takeover time from the historical takeover time information is selected as the takeover time for the first vehicle. This effectively ensures that the driver has sufficient time to safely take over the vehicle in severe weather. It should be noted that severe weather includes, but is not limited to, rainy, foggy, and rainy days.

[0077] Step S526: Determine whether the first vehicle is in a dangerous area based on the takeover time information of the first vehicle driver, the first contact time information, and the second contact time information, and obtain a first judgment result;

[0078] Understandably, when the second vehicle is behind the first vehicle, the first contact time between the first and second vehicles is calculated and denoted as t1, and the takeover time of the driver of the first vehicle is denoted as t0. When t1 ≤ t0, the first vehicle is in an extremely dangerous area. When the second vehicle is to the side of the first vehicle, the second contact time between the first and second vehicles is calculated and denoted as t2. When t2 ≤ t0, the first vehicle is in an extremely dangerous area.

[0079] Step S527: Send a warning message to the driver of the first vehicle based on the first judgment result. The warning message is used to assist the driver in taking over the first vehicle.

[0080] It is understood that step S52 further includes steps S528, S529, S5210, and S5211, which are specifically as follows:

[0081] Step S528: Obtain the preset speed information of the first vehicle;

[0082] Step S529: Determine the second orientation information of the second vehicle based on the position information of the second vehicle, wherein the second orientation information includes that the second vehicle is located to the side and rear of the first vehicle;

[0083] Step S5210: Calculate the relative speed information between the first vehicle and the second vehicle based on the preset speed information of the first vehicle and the speed information of the second vehicle;

[0084] Step S5211: Calculate the third contact time information based on the relative speed information between the first vehicle and the second vehicle and the second orientation information of the second vehicle. The third contact time information includes the contact time when the second vehicle is located to the side and rear of the first vehicle.

[0085] Understandably, when the second vehicle is located to the side and rear of the first vehicle, the contact time between the first and second vehicles needs to be calculated simultaneously as the longitudinal contact time and the lateral contact time as the third contact time information. The driver can determine whether the driver needs to take over the vehicle based on the third contact time between the first and second vehicles.

[0086] It is understood that step S5211 is followed by steps S5212, S5213, and S5214, which are specifically as follows:

[0087] Step S5212: Obtain the takeover time information of the driver of the first vehicle;

[0088] Step S5213: Based on the takeover time information of the driver of the first vehicle and the third contact time information, determine whether the first vehicle is in a dangerous area, and obtain a second judgment result;

[0089] Understandably, when the second vehicle is located to the side and rear of the first vehicle, the longitudinal contact time between the first and second vehicles is calculated and denoted as t1, the lateral contact time as t2, and the takeover time of the driver of the first vehicle as t0. When t1≤t0 and t2≤t0, the first vehicle is in an extremely dangerous area; when t1≤t0 and t2>t0, the first vehicle is in a normal dangerous area; and when t1>t0 and t2≤t0, the first vehicle is in a normal dangerous area.

[0090] Step S5214: Send a warning message to the driver of the first vehicle based on the second judgment result. The warning message is used to assist the driver in taking over the first vehicle.

[0091] Understandably, different methods are used to warn the driver when the vehicle is in an extremely dangerous area and a normally dangerous area. Specifically, when the vehicle is in a normally dangerous area, the autonomous vehicle's intelligent voice system provides a voice reminder; when the vehicle is in an extremely dangerous area, a preset color is displayed in a preset area of ​​the autonomous vehicle to stimulate the driver's driving awareness, while the intelligent voice system provides a voice reminder. By displaying a preset color in a preset area of ​​the autonomous vehicle to stimulate the driver's driving awareness, the driver can be effectively reminded to quickly take over the autonomous vehicle.

[0092] Example 2:

[0093] like Figure 2 As shown, this embodiment provides an autonomous driving assistance system, which includes an acquisition module 901, a generation module 902, a first processing module 903, a second processing module 904, and a third processing module 905, specifically:

[0094] The acquisition module 901 is used to acquire point cloud data, which is data information acquired by the detection signal emitted by the lidar installed on the first vehicle, and the first vehicle is a vehicle in autonomous driving.

[0095] The generation module 902 is used to generate a two-dimensional image based on the point cloud data. The two-dimensional image is a two-dimensional image of the environment around the first vehicle perceived by the lidar installed on the first vehicle.

[0096] The first processing module 903 is used to extract features from the two-dimensional image using a neural network model to obtain feature information, wherein the feature information includes feature information of each foreground point in the two-dimensional image;

[0097] The second processing module 904 is used to cluster each foreground point in the two-dimensional image based on the feature information to obtain the instance segmented two-dimensional image.

[0098] The third processing module 905 is used to assist the user in taking over the first vehicle based on the two-dimensional image segmented from the instance.

[0099] Example 3:

[0100] Corresponding to the above method embodiments, this embodiment also provides an autonomous driving assistance device. The autonomous driving assistance device described below and the autonomous driving assistance method described above can be referred to each other.

[0101] Figure 3 This is a block diagram illustrating an autonomous driving assistance device 800 according to an exemplary embodiment. Figure 3 As shown, the autonomous driving assistance device 800 may include a processor 801 and a memory 802. The autonomous driving assistance device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0102] The processor 801 controls the overall operation of the autonomous driving assistance device 800 to complete all or part of the steps in the aforementioned autonomous driving assistance method. The memory 802 stores various types of data to support the operation of the autonomous driving assistance device 800. This data may include, for example, instructions for any application or method operating on the autonomous driving assistance device 800, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 802 or transmitted via communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 805 is used for wired or wireless communication between the autonomous driving assistance device 800 and other devices. Wireless communication may include Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of these. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0103] In an exemplary embodiment, the autonomous driving assistance device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the aforementioned autonomous driving assistance method.

[0104] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the above-described autonomous driving assistance method. For example, the computer-readable storage medium may be the memory 802 including program instructions, which may be executed by the processor 801 of the autonomous driving assistance device 800 to complete the above-described autonomous driving assistance method.

[0105] Example 4:

[0106] Corresponding to the above method embodiments, this embodiment also provides a readable storage medium. The readable storage medium described below can be referred to in conjunction with the autonomous driving assistance method described above.

[0107] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the autonomous driving assistance method described in the above method embodiments.

[0108] Specifically, the readable storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other readable storage medium capable of storing program code.

[0109] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0110] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An autonomous driving assistance method, characterized in that, include: Acquire point cloud data, which is data information obtained from the detection signal emitted by the lidar installed on the first vehicle, and the first vehicle is a vehicle in autonomous driving; A two-dimensional image is generated based on the point cloud data. The two-dimensional image is a two-dimensional image of the environment around the first vehicle perceived by the lidar installed on the first vehicle. The two-dimensional image is used to extract features using a neural network model to obtain feature information, which includes feature information of each foreground point in the two-dimensional image; Based on the feature information, each foreground point in the two-dimensional image is clustered to obtain the instance-segmented two-dimensional image; The user is assisted in taking over the first vehicle based on the segmented two-dimensional image of the instance, including: The driving information of the second vehicle is obtained from the segmented two-dimensional image of the instance. The second vehicle includes vehicles perceived around the first vehicle. The driving information includes the trajectory information, speed information and position information of the second vehicle. Based on the trajectory information of the second vehicle, it is determined whether there is a contact point between the first vehicle and the second vehicle. If there is a contact point between the first vehicle and the second vehicle, the contact time between the first vehicle and the second vehicle is calculated based on the speed and position information of the second vehicle. If there is no contact point between the first vehicle and the second vehicle, the first vehicle does not require driver intervention.

2. The autonomous driving assistance method according to claim 1, characterized in that, Generating a two-dimensional image based on the point cloud data includes: Obtain the horizontal and vertical angles of the lidar installation; The three-dimensional coordinates, depth, and reflectance of each point are obtained from the point cloud data. A two-dimensional image corresponding to the point cloud data is generated based on the coordinates, depth, reflectivity, and horizontal and vertical angles at which the lidar is installed for each point.

3. The autonomous driving assistance method according to claim 1, characterized in that, The contact time between the first and second vehicles is calculated based on the speed and position information of the second vehicle, including: Obtain the preset speed information of the first vehicle; The first orientation information of the second vehicle is determined based on the location information of the second vehicle, wherein the first orientation information includes that the second vehicle is located behind or to the side of the first vehicle. The relative speed information between the first vehicle and the second vehicle is calculated based on the preset speed information of the first vehicle and the speed information of the second vehicle. Based on the relative speed information between the first vehicle and the second vehicle and the first orientation information of the second vehicle, a first contact time information or a second contact time information is obtained. The first contact time information includes the contact time when the second vehicle is behind the first vehicle, and the second contact time information includes the contact time when the second vehicle is to the side of the first vehicle.

4. The autonomous driving assistance method according to claim 1, characterized in that, The contact time between the first and second vehicles is calculated based on the speed and position information of the second vehicle, including: Obtain the preset speed information of the first vehicle; The second vehicle's second orientation information is determined based on the second vehicle's location information, and the second orientation information includes that the second vehicle is located to the side and rear of the first vehicle; The relative speed information between the first vehicle and the second vehicle is calculated based on the preset speed information of the first vehicle and the speed information of the second vehicle. The third contact time information is calculated based on the relative speed information between the first vehicle and the second vehicle and the second orientation information of the second vehicle. The third contact time information includes the contact time when the second vehicle is located to the side and rear of the first vehicle.

5. The autonomous driving assistance method according to claim 3, characterized in that, After calculating the first contact time information or the second contact time information based on the relative speed information between the first vehicle and the second vehicle and the first orientation information of the second vehicle, the following steps are taken: Obtain the takeover time information of the driver of the first vehicle; Based on the takeover time information of the driver of the first vehicle, the first contact time information, and the second contact time information, it is determined whether the first vehicle is in a dangerous area, and a first judgment result is obtained; Based on the first judgment result, a warning message is sent to the driver of the first vehicle, and the warning message is used to assist the driver in taking over the first vehicle.

6. The autonomous driving assistance method according to claim 4, characterized in that, After calculating the third contact time information based on the relative speed information between the first vehicle and the second vehicle and the second orientation information of the second vehicle, the following information is included: Obtain the takeover time information of the driver of the first vehicle; Based on the takeover time information of the driver of the first vehicle and the third contact time information, and by determining whether the first vehicle is in a dangerous area, a second judgment result is obtained; Based on the second judgment result, a warning message is sent to the driver of the first vehicle, and the warning message is used to assist the driver in taking over the first vehicle.

7. An autonomous driving assistance system, characterized in that, include: The acquisition module is used to acquire point cloud data, which is data information obtained from the detection signal emitted by the lidar installed on the first vehicle, and the first vehicle is a vehicle in autonomous driving. A generation module is used to generate a two-dimensional image based on the point cloud data. The two-dimensional image is a two-dimensional image of the environment around the first vehicle perceived by the lidar installed on the first vehicle. The first processing module is used to extract features from the two-dimensional image using a neural network model to obtain feature information, wherein the feature information includes feature information of each foreground point in the two-dimensional image; The second processing module is used to cluster each foreground point in the two-dimensional image based on the feature information to obtain the instance-segmented two-dimensional image. The third processing module is used to assist the user in taking over the first vehicle based on the two-dimensional image segmented from the instance; and to obtain the driving information of the second vehicle based on the two-dimensional image segmented from the instance, wherein the second vehicle includes vehicles sensed around the first vehicle, and the driving information includes the trajectory information, speed information and position information of the second vehicle. Based on the trajectory information of the second vehicle, it is determined whether there is a contact point between the first vehicle and the second vehicle. If there is a contact point between the first vehicle and the second vehicle, the contact time between the first vehicle and the second vehicle is calculated based on the speed information and position information of the second vehicle. If there is no point of contact between the first vehicle and the second vehicle, then the first vehicle does not require driver intervention.

8. An autonomous driving assistance device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the autonomous driving assistance method as described in any one of claims 1 to 6.

9. A readable storage medium, characterized in that: The readable storage medium stores a computer program that, when executed by a processor, implements the steps of the autonomous driving assistance method as described in any one of claims 1 to 6.

Images