Obstacle detection method and device, vehicle, storage medium and electronic device

Abstract

The invention discloses an obstacle detection method and device, a vehicle, a storage medium and an electronic device, and relates to the technical field of vehicles. The method comprises the steps that the vehicle door opening degree and the obstacle distance of a target vehicle door in a target vehicle are obtained; vehicle door corner information of the target vehicle door is determined based on the vehicle door opening degree, and initial obstacle corner information of the target obstacle is determined based on the obstacle distance; performing coordinate conversion on the initial obstacle corner information to obtain target obstacle corner information; determining a target distance based on the target obstacle corner information and the vehicle door corner information; and detecting the target obstacle based on the target distance and a preset safety distance. According to the invention, the technical problem that the position of the obstacle is difficult to accurately calculate so as to cause potential safety hazards in driving in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to an obstacle detection method, device, vehicle, storage medium and electronic device. Background Art

[0002] With the development of intelligent vehicles, the automatic opening and closing function of car doors has become an important direction to improve the driving experience. However, in a complex and changeable driving environment, the car doors may encounter pedestrians, bicycles or other obstacles during the automatic opening or closing process, causing safety hazards. Due to factors such as cost, general automatic car doors, such as automatic scissor doors and automatic side-opening doors, generally rely on a single sensor for detection, so the calculation of the position of obstacles is particularly important. Summary of the invention

[0003] The embodiments of the present invention provide an obstacle detection method, device, vehicle, storage medium and electronic device to at least solve the technical problem in the related art that it is difficult to accurately calculate the position of an obstacle, thereby causing hidden dangers to driving safety.

[0004] According to one embodiment of the present invention, there is provided an obstacle detection method, comprising: obtaining a door opening and an obstacle distance of a target door in a target vehicle, wherein the obstacle distance is used to represent the distance between the target obstacle and the target door within a preset range of the target door; determining door corner point information of the target door based on the door opening, and determining initial obstacle corner point information of the target obstacle based on the obstacle distance, wherein the door corner point information is used to represent contour features of the target door, and the initial obstacle corner point information is used to predict contour features of the target obstacle; performing coordinate transformation on the initial obstacle corner point information to obtain target obstacle corner point information, wherein the target obstacle corner point information and the door corner point information are located in the same coordinate system; determining the target distance based on the target obstacle corner point information and the door corner point information; and detecting the target obstacle based on the target distance and a preset safety distance.

[0005] Optionally, detecting the target obstacle based on the target distance and the preset safety distance includes: in response to the target distance being greater than or equal to the preset safety distance, obtaining a first detection result, wherein the first detection result is used to indicate that there is no target obstacle during the opening and closing process of the target door; in response to the target distance being less than the preset safety distance, obtaining a second detection result, and reporting a prompt message, wherein the second detection result is used to indicate that there is a target obstacle during the opening and closing process of the target door, and the prompt message is used to indicate that there is a target obstacle outside the target door.

[0006] Optionally, the door corner point information includes: the center point coordinates of the radar on the target door, the preset lower corner point coordinates of the target door, the outermost point coordinates of the target door in the first direction, the preset upper corner point coordinates of the target door, the glass water cut position corner point coordinates of the target door, the top corner point coordinates of the glass, the preset upper corner point coordinates of the front end of the target door, the preset lower corner point coordinates of the front end of the target door and the outermost point coordinates of the rearview mirror corresponding to the target door in the first direction.

[0007] Optionally, determining the initial obstacle corner point information of the target obstacle based on the obstacle distance includes: determining a first field of view angle and a second field of view angle of the radar, wherein the first field of view angle is half of the horizontal field of view angle of the radar, and the second field of view angle is half of the vertical field of view angle of the radar; determining the initial obstacle corner point information according to the obstacle distance, the sine value of the first field of view angle, the cosine value of the first field of view angle, the sine value of the second field of view angle, and the cosine value of the second field of view angle.

[0008] Optionally, performing coordinate transformation on the initial obstacle corner point information to obtain the target obstacle corner point information includes: when the target door is closed, determining the normal point and the horizontal point of the radar based on a preset distance; determining a conversion relationship between a first coordinate system and a second coordinate system based on the normal point and the horizontal point of the radar, wherein the first coordinate system is the coordinate system where the initial obstacle corner point information is located, and the second coordinate system is the coordinate system where the target obstacle corner point information is located; performing coordinate transformation on the initial obstacle corner point information based on the conversion relationship to obtain the target obstacle corner point information.

[0009] Optionally, determining the target distance based on the target obstacle corner point information and the door corner point information includes: determining the distance between any target obstacle corner point in the target obstacle corner point information and any door corner point in the door corner point information to obtain distance information; and determining the target distance based on the minimum distance in the distance information.

[0010] Optionally, the method further includes: updating the second coordinate system based on an inertial measurement unit of the target vehicle.

[0011] Optionally, obtaining the door opening of a target door in the target vehicle includes: obtaining a Hall count of the target door based on a Hall sensor; and determining the door opening of the target door based on the Hall count.

[0012] According to one embodiment of the present invention, there is also provided an obstacle detection device, comprising: an acquisition module, used to acquire the door opening and obstacle distance of a target door in a target vehicle, wherein the obstacle distance is used to represent the distance between the target obstacle and the target door within a preset range of the target door; a first determination module, used to determine the door corner point information of the target door based on the door opening, and to determine the initial obstacle corner point information of the target obstacle based on the obstacle distance, wherein the door corner point information is used to represent the contour features of the target door, and the initial obstacle corner point information is used to predict the contour features of the target obstacle; a conversion module, used to perform coordinate conversion on the initial obstacle corner point information to obtain the target obstacle corner point information, wherein the target obstacle corner point information and the door corner point information are located in the same coordinate system; a second determination module, used to determine the target distance based on the target obstacle corner point information and the door corner point information; and a detection module, used to detect the target obstacle based on the target distance and the preset safety distance.

[0013] Optionally, the detection module is also used to obtain a first detection result in response to the target distance being greater than or equal to a preset safety distance, wherein the first detection result is used to indicate that there is no target obstacle during the opening and closing process of the target door; in response to the target distance being less than a preset safety distance, obtain a second detection result and report a prompt message, wherein the second detection result is used to indicate that there is a target obstacle during the opening and closing process of the target door, and the prompt message is used to indicate that there is a target obstacle outside the target door.

[0014] Optionally, the first determination module is also used to determine the center point coordinates of the radar on the target door, the preset lower corner point coordinates of the target door, the outermost point coordinates of the target door in the first direction, the preset upper corner point coordinates of the target door, the glass water cut position corner point coordinates of the target door, the top corner point coordinates of the glass, the preset upper corner point coordinates of the front end of the target door, the preset lower corner point coordinates of the front end of the target door and the outermost point coordinates of the rearview mirror corresponding to the target door in the first direction.

[0015] Optionally, the first determination module is also used to determine the first field of view angle and the second field of view angle of the radar, wherein the first field of view angle is half of the horizontal field of view angle of the radar, and the second field of view angle is half of the vertical field of view angle of the radar; and determine the initial obstacle corner point information according to the obstacle distance, the sine value of the first field of view angle, the cosine value of the first field of view angle, the sine value of the second field of view angle, and the cosine value of the second field of view angle.

[0016] Optionally, the conversion module is also used to determine the normal point and horizontal point of the radar based on a preset distance when the target door is closed; determine the conversion relationship between the first coordinate system and the second coordinate system based on the normal point and horizontal point of the radar, wherein the first coordinate system is the coordinate system where the initial obstacle corner point information is located, and the second coordinate system is the coordinate system where the target obstacle corner point information is located; and perform coordinate conversion on the initial obstacle corner point information based on the conversion relationship to obtain the target obstacle corner point information.

[0017] Optionally, the second determination module is further used to determine the distance between any target obstacle corner point in the target obstacle corner point information and any door corner point in the door corner point information to obtain distance information; and determine the target distance based on the minimum distance in the distance information.

[0018] Optionally, the first determination module is further configured to update the second coordinate system based on an inertial measurement unit of the target vehicle.

[0019] Optionally, the acquisition module is further used to acquire a Hall count of the target door based on the Hall sensor; and determine the door opening of the target door based on the Hall count.

[0020] According to one embodiment of the present invention, a vehicle is provided, and the vehicle is used to execute any of the above obstacle detection methods.

[0021] According to one embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute any of the above obstacle detection methods when running on a computer or a processor.

[0022] According to one embodiment of the present invention, there is further provided an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the above obstacle detection methods.

[0023] According to one embodiment of the present invention, a computer program product is further provided, including a computer program, and when the computer program is executed by a processor, the obstacle detection method in any one of the above items is implemented.

[0024] In an embodiment of the present invention, the door opening and obstacle distance of a target door in a target vehicle are obtained, wherein the obstacle distance is used to represent the distance between the target obstacle and the target door within a preset range of the target door; the door corner point information of the target door is determined based on the door opening, and the initial obstacle corner point information of the target obstacle is determined based on the obstacle distance, wherein the door corner point information is used to represent the contour features of the target door, and the initial obstacle corner point information is used to predict the contour features of the target obstacle; coordinate conversion is performed on the initial obstacle corner point information to obtain the target obstacle corner point information, wherein, The target obstacle corner point information and the door corner point information are located in the same coordinate system; the target distance is determined based on the target obstacle corner point information and the door corner point information; the target obstacle is detected based on the target distance and the preset safety distance, so as to achieve the purpose of accurately calculating the specific position of the obstacle and the actual distance between the obstacle and the door, thereby achieving the technical effect that the vehicle can detect whether the environment around the vehicle is safe when the door is automatically opened and closed, thereby reducing the hidden dangers to driving safety, and further solving the technical problem in related technologies that it is difficult to accurately calculate the position of the obstacle, thereby causing hidden dangers to driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0026] Figure 1 is a basic structural diagram of an automatic door according to one embodiment of the present invention;

[0027] Figure 2 is a schematic diagram of vehicle body coordinate system modeling according to one embodiment of the present invention;

[0028] Figure 3 is a schematic diagram of marking information of nine door corner points in a vehicle body coordinate system according to one embodiment of the present invention;

[0029] Figure 4 is a schematic diagram of a local coordinate system 1MP of an ultrasonic radar according to one embodiment of the present invention;

[0030] Figure 5 is a schematic diagram of the distribution position and envelope surface of an ultrasonic radar according to one embodiment of the present invention;

[0031] Figure 6 is a schematic diagram of determining information of five obstacle corner points in an ultrasonic local coordinate system according to one embodiment of the present invention;

[0032] Figure 7 is a flowchart of early warning obstacle avoidance processing according to one embodiment of the present invention;

[0033] Figure 8 is a flow chart of an obstacle detection method according to one embodiment of the present invention;

[0034] Fig. 9 is a structural block diagram of an obstacle detection device according to one embodiment of the present invention. DETAILED DESCRIPTION

[0035] For ease of understanding, some concepts related to the embodiments of the present invention are exemplarily described for reference, as shown below:

[0036] Integrated Inertial Measurement Unit (IMU): used to measure the acceleration and angular velocity of an object. IMU is usually composed of sensors such as accelerometers, gyroscopes and magnetometers, which can measure and track the motion state and direction of an object in real time. IMU is commonly used in drones, cars, ships and other equipment that requires precise positioning and navigation.

[0037] Electric drive unit: A device used to control a motor or actuator by providing an electric power signal to the motor to control its movement or operation. Electric drive units usually include components such as power modules, controllers, drivers, and sensors, which can achieve precise control of parameters such as the speed, direction, and position of the motor, thereby achieving motion control of various industrial automation and mechanical equipment.

[0038] Door movement mechanism: A device installed on the side of the vehicle to control the opening and closing of the door. It usually includes door locks, door handles, door shafts, door hinges and other components, and is driven by power devices such as electric motors, hydraulic devices or pneumatic devices to achieve the opening and closing of the door.

[0039] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 creative work should fall within the scope of protection of the present invention.

[0040] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In the description of this embodiment, unless otherwise specified, the meaning of "multiple" is two or more. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0041] According to one embodiment of the present invention, an embodiment of an obstacle detection method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0042] The method embodiment can be executed in an electronic device including a memory and a processor, a similar control device or a system. Taking an electronic device as an example, the electronic device may include one or more processors and a memory for storing data. Optionally, the electronic device may also include a communication device and a display device for communication functions. It can be understood by a person of ordinary skill in the art that the above structural description is only illustrative and does not limit the structure of the above electronic device. For example, the electronic device may also include more or fewer components than the above structural description, or have a configuration different from the above structural description.

[0043] The processor may include one or more processing units. For example, the processor may include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microcontroller unit (MCU), a field-programmable gate array (FPGA), a neural-network processing unit (NPU), a tensor processing unit (TPU), an artificial intelligence (AI) type processor, and other processing devices. Among them, different processing units may be independent components or integrated into one or more processors. In some instances, the electronic device may also include one or more processors.

[0044] The memory can be used to store computer programs, such as storing the computer program corresponding to the obstacle detection method in the embodiment of the present invention. The processor implements the above-mentioned obstacle detection method by running the computer program stored in the memory. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include a memory remotely arranged relative to the processor, and these remote memories can be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0045] The communication device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the communication device includes a network adapter (network interface controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the communication device can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0046] The display device may be, for example, a touch screen type liquid crystal display (LCD) and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display may enable a user to interact with the user interface of the mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), and a user may interact with the GUI by finger contact and / or gestures on the touch-sensitive surface. The human-computer interaction functions here may optionally include the following interactions: creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital videos, playing digital music and / or web browsing, etc. The executable instructions for executing the above human-computer interaction functions are configured / stored in a computer program product or readable storage medium executable by one or more processors.

[0047] Figure 1 FIG. 1 is a basic structural diagram of an automatic door according to one embodiment of the present invention. Figure 1 As shown, the basic structure of the automatic door mainly includes the body (integrated IMU unit), electric drive unit, door movement mechanism, door, door sensor, algorithm processing software and early warning unit.

[0048] Body (integrated IMU unit): The body coordinate system is as follows Figure 2 The method shown is set up to establish the front upper left body coordinate system OXY, i.e., b_{body coordinate system}, with the origin being the projection point of the rear wheel axle center on the ground, the front of the vehicle being +X, and the left of the vehicle being +Y. The IMU is integrated into the vehicle body, and the IMU can output the accelerations ax, ay, and az of the x-axis, y-axis, and z-axis in the body coordinate system in real time, as well as the body coordinate system attitude, i.e., roll angle roll, pitch angle pitch, and heading angle yaw.

[0049] Electric drive unit: One end is connected to the vehicle body and the other end is connected to the door movement mechanism. It drives the door movement mechanism to open and close the door. The actuator is generally an electric strut with an integrated Hall sensor. It can record the value of the Hall counter corresponding to the movement length of the strut in real time, thereby reflecting the opening of the door. As shown in Table 1, the larger the value of the Hall counter, the larger the door opening. The electric drive unit generally also includes a software part that controls the electric strut motor to execute instructions such as opening, closing, and stopping.

[0050] Table 1 Hall counter value record

[0051]

[0052] Door movement mechanism: generally a multi-link mechanism, which converts the linear motion of the electric strut into the rotational motion of the door around a certain rotation axis. The electric side opening door is generally an axis that is approximately perpendicular to the upper and lower hinges of the door, while the scissor door, butterfly door, etc. are a certain instantaneous axis in space.

[0053] Door: Passengers enter and exit the vehicle through a passageway, usually with glass that can be raised and lowered, rearview mirrors for observing the rear view, water-cut structures for cleaning the glass, etc. Doors generally contain complex three-dimensional curved surface structures. In this example, taking a certain model as an example, we filter out Figure 3 The 9 corner points shown are: 1. The center point of the radar; 2. The dangerous lower corner point of the door; 3. The point farthest from the door in the Y direction; 4. The corner point at the upper end of the door; 5. The corner point at the water cut position of the glass; 6. The top corner point of the glass; 7. The corner point at the upper end of the front end of the door; 8. The corner point at the lower end of the front end of the door; 9. The outermost point in the Y direction of the rearview mirror. In the early stage of project development, the digital model information of the vehicle can be obtained. By simulating the door motion, the three-dimensional coordinate information of the above 9 corner points under the vehicle body coordinate system OXY at different door openings can be obtained. At the same time, in order to obtain the conversion relationship between the p_{ultrasonic local coordinate system} (with the outer surface where the ultrasonic radar is located, the normal through the center as the +Y axis, the direction towards the front of the vehicle as +X, and the right-hand rule to obtain the +Z axis) and the vehicle body coordinate system (R (rotation matrix), S (scaling) and T (translation matrix)), as follows Figure 4 As shown, two points (ie, P and M) are added. For example, the local coordinates 1MP of the ultrasonic radar are established. Assuming that the car door is closed, P: adds a radar normal point |1P|=100mm, M: adds a radar horizontal point |1M|=100mm, which is not limited here.

[0054] Door sensor: Figure 5 As shown in the middle left figure, the sensor and ultrasonic radar are integrated on the car door to detect obstacles around the door in real time, and send the obstacle distance information through the controller area network (CAN) or local interconnect network (LIN), so as to achieve real-time obstacle avoidance when the door is opened or closed. For cost considerations, it is generally a short-range ultrasonic radar with a detection distance of 0.02-3m. The horizontal field of view of the ultrasonic radar is about 100° and the vertical field of view is about 60°. The generated envelope surface is as follows Figure 5 As shown in the middle right figure, since the car door moves at a low speed and the main concern is close-range obstacles, a single ultrasonic radar has no directionality. After obtaining the distance information, it is approximately considered to be a sphere based on the horizontal and vertical field of view angles, and 5 corner points are abstracted. Figure 6As shown, the outer surface where the ultrasonic radar is located, the normal through the center is +Y axis, the direction toward the front of the vehicle is +X, and the right-hand rule gives +Z axis. Half of the horizontal field of view angle of the ultrasonic radar is θ, and half of the vertical field of view angle of the ultrasonic radar is β. Then in the p_{ultrasonic local coordinate system}, the detection distance is set to L, and the information of the five corner points of the initial obstacle can be obtained: point 1, the point in the normal direction (0, L, 0); point 2, the point in the forward direction of the horizontal field of view (L*sin(θ), L*cos(θ), 0); point 3, (-L*sin(θ), L*cos(θ), 0); point 4, (0, L*cos(β), L*sin(β)); point 5, (0, L*cos(β, -L*sin(β)). Calculate the conversion relationship R (rotation matrix), S (scaling) and T (translation matrix) with the body coordinate system. If you need to align two point clouds in the two coordinate systems and obtain the transformation matrix (RST) of the two coordinate systems, you can use the Iterative Closest Point algorithm (ICP). However, if you already know the exact correspondence between the two point sets, you can use the Umeyama algorithm to calculate the rotation and translation matrices between the two sets of data. Table 2 shows the R (rotation matrix) and T (translation matrix) calculated for different Hall counters. Since they are equal in proportion, the scaling ratio is set to 1. Then p_{ultrasonic local coordinate system point}*SR+T= b_{body coordinate system point}. In the actual matrix calculation process, it is necessary to ensure that the matrix is ​​multiplied by a homogeneous matrix.

[0055] Table 2 Rotation matrix (R) and translation matrix (T) under different Hall counts

[0056]

[0057] Algorithm processing software: The main obstacle avoidance information analysis unit of the side door determines whether there is a risk of collision with the door based on the calculated obstacle position information during the real-time opening of the door, and issues an early warning to avoid obstacles. The main processing flow chart is as follows Figure 7As shown: the algorithm processing software receives three main information inputs. First, the obstacle distance information detected by the door sensor. According to the previous part, the three-dimensional coordinate information of the five possible corner points in the p_{ultrasonic local coordinate system} can be obtained. Second, the electric drive unit, the Hall count value corresponding to the different door openings, can correspond to the coordinate information of the nine corner points in the body coordinate system through the Hall count value. Third, due to the body posture under full load, no load or air suspension, the position information of the door in the body coordinate system will also change, so it is necessary to borrow the IMU signal to update the coordinate information lookup table in real time. The specific algorithm model can borrow the current mature strapdown inertial algorithm to update the position and attitude. First, input the signal, then convert the five corner points in the p_{ultrasonic local coordinate system} to the b_{body coordinate system} based on the lookup table, and finally calculate the danger distance. The calculation of the dangerous distance is s=min_dist ({5 ultrasonic corner points} to {9 door corner points}), that is, the distances between the coordinate information of the 5 obstacles detected by ultrasonic detection and the 9 door corner points are calculated in sequence, and the minimum value is taken as the dangerous distance s. For example, when s < safe distance, the early warning unit issues an early warning. Generally, the safe distance is between 20-30cm, which is not limited here.

[0058] Early warning unit: After receiving the early warning information from the algorithm processing software, the result will be displayed on the central control screen or the user's mobile phone software, etc.

[0059] In this embodiment, an obstacle detection method running on an electronic device is provided. Figure 8 is a flow chart of an obstacle detection method according to one embodiment of the present invention. Figure 8 As shown, the process includes the following steps:

[0060] Step S1, obtaining a door opening and an obstacle distance of a target door in a target vehicle, wherein the obstacle distance is used to represent a distance between a target obstacle and the target door within a preset range of the target door;

[0061] In the embodiment of the present invention, the target vehicle can be understood as a vehicle equipped with doors that can open and close automatically.

[0062] The target door can be understood as a door that is used for passengers to get on and off the vehicle and can be opened and closed automatically.

[0063] The door opening can be understood as the angle or distance of the door opening. For example, the electric drive unit in the target vehicle can be used to record the Hall count corresponding to the movement length of the electric support rod. The larger the Hall count value, the larger the corresponding door opening, which is not limited here.

[0064] The obstacle distance can be understood as the distance information between the obstacle around the target door and the target door. For example, a short-range ultrasonic radar can be used to detect the obstacle information around the door and record the obstacle distance, which is not limited here.

[0065] The preset range can be understood as a preset distance range between a detectable obstacle and a target door. For example, the preset range can be 0.02-3 meters, which is not limited here.

[0066] Obtaining the door opening and obstacle distance of the target door in the target vehicle can be understood as obtaining the angle or distance of the door opening in the target vehicle and the distance information between the surrounding obstacles and the target door. For example, the Hall count corresponding to the movement length of the electric strut can be recorded by the electric drive unit in the target vehicle. The larger the value of the Hall count, the larger the corresponding door opening. The obstacle information around the door is detected in real time by the short-range ultrasonic radar integrated in the door, and the obstacle distance information is sent through the controller area network (CAN) or the local interconnect network (LIN), which is not limited here.

[0067] In an embodiment of the present invention, by obtaining the opening angle or distance of the target door in the target vehicle, as well as the distance between the target obstacle and the target door within a preset range of the target door, it can be ensured that the door will not hit surrounding obstacles or other vehicles when opened, thereby reducing the risk of collision.

[0068] Step S2, determining the door corner point information of the target door based on the door opening, and determining the initial obstacle corner point information of the target obstacle based on the obstacle distance, wherein the door corner point information is used to represent the contour features of the target door, and the initial obstacle corner point information is used to predict the contour features of the target obstacle;

[0069] In the embodiment of the present invention, the door corner point information can be understood as information used to identify the shape and position of the door, and to perform edge detection or corner point detection of the door. Exemplarily, the door corner point information can be corner point coordinate information in b_{body coordinate system}, which is not limited here.

[0070] The target obstacle can be understood as an obstacle within a preset range. For example, a short-range ultrasonic radar is generally used to detect the distance of the obstacle, and obstacles within 0.02-3 meters from the target door can be used as target obstacles, which is not limited here.

[0071] The initial obstacle corner point information can be understood as the original corner point information of the obstacle without any processing, which is used to reflect the general contour characteristics of the obstacle. Exemplarily, the initial obstacle corner point information can be the three-dimensional coordinate information of the corner point in the p_{ultrasonic local coordinate system}, which is not limited here.

[0072] The door corner information of the target door determined based on the door opening can be understood as information for determining the shape and position of the target door based on the angle or distance of the door opening, and performing edge detection or corner detection of the door. Figure 3 As shown, the door corner point information of the target door determined based on the door opening may include: the center point of the radar, the dangerous lower corner point of the door, the outermost point in the Y direction of the door, the corner point at the upper end of the door, the corner point at the water cut position of the glass, the topmost corner point of the glass, the corner point at the upper end of the front end of the door, the corner point at the lower end of the front end of the door and the outermost point in the Y direction of the rearview mirror, which is not limited here.

[0073] Determining the initial obstacle corner point information of the target obstacle based on the obstacle distance can be understood as determining the original corner point information of the target obstacle based on the distance information between the detected obstacle and the target door. For example, Figure 6 As shown, when the length of the detection distance is L, the initial obstacle corner point information of the target obstacle may include: a point in the normal direction (0, L, 0), a point in the forward direction of the horizontal field of view angle (L*sin(θ), L*cos(θ), 0), (-L*sin(θ), L*cos(θ), 0), (0, L*cos(β), L*sin(β)) and (0, L*cos(β), -L*sin(β)), which is not limited here.

[0074] In an embodiment of the present invention, the shape of the target door and edge detection or corner point detection information are determined by acquiring the opening angle or distance of the door, and the initial obstacle corner point information and approximate contour features of the target obstacle are determined based on the distance information between the detected obstacle and the target door, thereby helping to improve the safety and efficiency of the target vehicle when opening and closing the door.

[0075] Step S3, performing coordinate conversion on the initial obstacle corner point information to obtain target obstacle corner point information, wherein the target obstacle corner point information and the door corner point information are located in the same coordinate system;

[0076] In the embodiment of the present invention, the target obstacle corner point information can be understood as information obtained after the initial obstacle corner point information is processed by coordinate transformation. Exemplarily, the target obstacle corner point information is obtained by transforming the initial obstacle corner point information from p_{ultrasonic local coordinate system} to b_{body coordinate system}, which is not limited here.

[0077] The target obstacle corner point information and the door corner point information are located in the same coordinate system, which can be understood as the target obstacle corner point information and the door corner point information obtained after the coordinate transformation of the initial obstacle corner point information are located in the same coordinate system. By way of example, the same coordinate system here can be the vehicle body coordinate system, which is not limited here.

[0078] In the embodiment of the present invention, the target obstacle corner point information is obtained by performing coordinate transformation on the initial obstacle corner point information, and the target obstacle corner point information obtained after the coordinate transformation and the door corner point information are located in the same coordinate system, so that the distance between the target obstacle and the target door can be easily calculated.

[0079] Step S4, determining the target distance based on the target obstacle corner point information and the door corner point information;

[0080] In the embodiment of the present invention, the target distance can be understood as the actual distance between the target obstacle and the target door. For example, the distances between multiple two points can be calculated using the five corner point information of the target obstacle and the nine corner points of the target door, and the smallest distance s is selected as the danger distance, i.e., the target distance, which is not limited here.

[0081] In an embodiment of the present invention, multiple distances are calculated based on information of five corner points of a target obstacle and information of nine door corner points of a target door, and the minimum distance is obtained from the calculated multiple distances as the target distance, which can help the vehicle to more accurately judge whether the distance between the target obstacle and the target door is dangerous, thereby ensuring the driving safety of the vehicle.

[0082] Step S5: Detect the target obstacle based on the target distance and the preset safety distance.

[0083] In the embodiment of the present invention, the preset safety distance can be understood as a threshold range for determining whether the distance between the target obstacle and the target door is safe. For example, the preset safety distance can be set to 20-30 centimeters, which is not limited here.

[0084] Detecting the target obstacle based on the target distance and the preset safety distance can be understood as determining the size relationship between the actual distance between the target obstacle and the target door and the preset safety distance, thereby determining whether the target door is safe.

[0085] In the embodiment of the present invention, the target obstacle is detected based on the target distance and the preset safety distance, which can effectively ensure the safety of opening and closing the door of the target vehicle.

[0086] In the embodiment of the present invention, by obtaining the opening angle or distance of the target door in the target vehicle, and the distance between the target obstacle and the target door within the preset range of the target door, it can be ensured that the door will not hit the surrounding obstacles or other vehicles when opening, thereby reducing the risk of collision. By obtaining the opening angle or distance of the door and then determining the shape of the target door and the information of edge detection or corner point detection, and determining the initial obstacle corner point information and the general outline characteristics of the target obstacle based on the distance information between the detected obstacle and the target door, it can help improve the safety and efficiency of the target vehicle when opening and closing the door. By performing coordinate conversion on the initial obstacle corner point information, the target obstacle corner point information is obtained, and the target obstacle corner point information obtained after the coordinate conversion and the door corner point information are located in the same coordinate system, so that the distance between the target obstacle and the target door can be conveniently calculated. Based on the 5 corner point information of the target obstacle and the 9 door corner point information of the target door, multiple distances are calculated, and the minimum distance is obtained from the calculated multiple distances as the target distance, so that the vehicle can be more accurately judged whether the distance between the target obstacle and the target door is dangerous, thereby ensuring the driving safety of the vehicle. Detecting target obstacles based on the target distance and the preset safety distance can effectively ensure the safety of opening and closing the doors of the target vehicle.

[0087] Through the above steps, the door opening and obstacle distance of the target door in the target vehicle are obtained, wherein the obstacle distance is used to represent the distance between the target obstacle and the target door within the preset range of the target door; the door corner point information of the target door is determined based on the door opening, and the initial obstacle corner point information of the target obstacle is determined based on the obstacle distance, wherein the door corner point information is used to represent the contour features of the target door, and the initial obstacle corner point information is used to predict the contour features of the target obstacle; the initial obstacle corner point information is coordinate-converted to obtain the target obstacle corner point information, wherein the target door corner point information is The target obstacle corner point information and the door corner point information are located in the same coordinate system; the target distance is determined based on the target obstacle corner point information and the door corner point information; the target obstacle is detected based on the target distance and the preset safety distance, so as to achieve the purpose of accurately calculating the specific position of the obstacle and the actual distance between the obstacle and the door, thereby achieving the technical effect that the vehicle can detect whether the environment around the vehicle is safe when the door is automatically opened and closed, thereby reducing the hidden dangers to driving safety, and further solving the technical problem in the related technology that it is difficult to accurately calculate the position of the obstacle, thereby causing hidden dangers to driving safety.

[0088] Optionally, in step S5, detecting the target obstacle based on the target distance and the preset safety distance may include the following execution steps:

[0089] Step S51, in response to the target distance being greater than or equal to the preset safety distance, obtaining a first detection result, wherein the first detection result is used to indicate that there is no target obstacle during the opening and closing process of the target door;

[0090] Step S52, in response to the target distance being less than the preset safety distance, a second detection result is obtained, and a prompt message is reported, wherein the second detection result is used to indicate that there is a target obstacle during the opening and closing process of the target door, and the prompt message is used to indicate that there is a target obstacle outside the target door.

[0091] In the embodiment of the present invention, the first detection result may be understood as a judgment result given by the detection system when the actual distance between the target obstacle and the target door is greater than or equal to a preset safety distance.

[0092] The second detection result can be understood as the judgment result given by the detection system when the actual distance between the target obstacle and the target door is less than the preset safety distance.

[0093] The prompt information can be understood as the warning information given by the detection system when the actual distance between the target obstacle and the target door is less than the preset safety distance.

[0094] In response to the target distance being greater than or equal to the preset safety distance, obtaining the first detection result can be understood as the first detection result given by the detection system when the actual distance between the target obstacle and the target door is greater than or equal to the preset safety distance. For example, the safety distance is set to 25 cm, and when the target distance s ≥ 25 cm, the first detection result given by the detection system is safe, which is not limited here.

[0095] In response to the target distance being less than the preset safety distance, the second detection result can be understood as the second detection result given by the detection system when the actual distance between the target obstacle and the target door is less than the preset safety distance. For example, the safety distance is set to 25 cm. When the target distance s<25 cm, the second detection result given by the detection system is unsafe and an early warning sound is issued, which is not limited here.

[0096] In the embodiment of the present invention, by comparing the size relationship between the target distance and the preset safety distance, it is determined whether the driving of the target vehicle is safe. If the target distance is greater than or equal to the preset safety distance, the target vehicle is safe; if the target distance is less than the preset safety distance, the target vehicle is unsafe and a warning sound needs to be issued, thereby effectively eliminating the potential safety hazard when the vehicle opens and closes the door.

[0097] Optionally, in step S2, the door corner point information includes:

[0098] Step S21, the center point coordinates of the radar on the target door, the preset lower corner point coordinates of the target door, the outermost point coordinates of the target door in the first direction, the preset upper corner point coordinates of the target door, the glass water cut position corner point coordinates of the target door, the top corner point coordinates of the glass, the preset upper corner point coordinates of the front end of the target door, the preset lower corner point coordinates of the front end of the target door and the outermost point coordinates of the rearview mirror corresponding to the target door in the first direction.

[0099] In the embodiment of the present invention, for example, the center point coordinates of the radar on the target door can be understood as Figure 3 The door corner information 1 in the target door, the preset lower corner coordinates can be understood as Figure 3 The door corner point information 2 in the target door, the outermost point coordinates of the target door in the first direction can be understood as Figure 3 The door corner information 3 in the target door, the preset upper corner coordinates can be understood as Figure 3 The door corner information 4 in the target door, the glass water cut position corner coordinates can be understood as Figure 3 The door corner information 5 in the figure, the top corner coordinates of the glass can be understood as Figure 3 The door corner information 6 in the target door, the preset upper corner coordinates of the front end can be understood as Figure 3 The door corner point information 7 in the target door, the preset lower corner point coordinates of the front end can be understood as Figure 3 The door corner point information 8 in the target door, the outermost point coordinates of the rearview mirror corresponding to the target door in the first direction can be understood as Figure 3 The door corner point information 9 in is not restricted here.

[0100] Optionally, in step S21, determining the initial obstacle corner point information of the target obstacle based on the obstacle distance may include the following execution steps:

[0101] Step S211, determining a first field of view angle and a second field of view angle of the radar, wherein the first field of view angle is half of the horizontal field of view angle of the radar, and the second field of view angle is half of the vertical field of view angle of the radar;

[0102] Step S212, determining initial obstacle corner point information according to the obstacle distance, the sine value of the first field of view angle, the cosine value of the first field of view angle, the sine value of the second field of view angle, and the cosine value of the second field of view angle.

[0103] In the embodiment of the present invention, the first field of view angle of the radar can be understood as half of the horizontal field of view angle of the radar. Exemplarily, the first field of view angle of the radar can be θ, which is not limited here.

[0104] The second field of view angle of the radar can be understood as half of the vertical field of view angle of the radar. Exemplarily, the first field of view angle of the radar can be β, which is not limited here.

[0105] The initial obstacle corner point information is determined according to the obstacle distance, the sine value of the first field of view angle, the cosine value of the first field of view angle, the sine value of the second field of view angle and the cosine value of the second field of view angle. For example, it can be understood that assuming that the distance between the obstacle and the ultrasonic radar is L, the initial obstacle corner point information can be obtained as follows: point 1: (0, L, 0), point 2: (L*sin(θ), L*cos(θ), 0), point 3: (-L*sin(θ), L*cos(θ), 0), point 4: (0, L*cos(β), L*sin(β)), point 5: (0, L*cos(β), -L*sin(β)), which is not limited here.

[0106] In an embodiment of the present invention, by determining the first field of view angle and the second field of view angle of the radar, and then determining the initial obstacle corner point information according to the obstacle distance, the sine value of the first field of view angle, the cosine value of the first field of view angle, the sine value of the second field of view angle, and the cosine value of the second field of view angle, a basis can be provided for the subsequent calculation of the actual distance between the target obstacle and the target door.

[0107] Optionally, in step S212, performing coordinate transformation on the initial obstacle corner point information to obtain the target obstacle corner point information may include the following execution steps:

[0108] Step S2121, when the target door is closed, determining the normal point and the horizontal point of the radar based on a preset distance;

[0109] Step S2122, determining a conversion relationship between a first coordinate system and a second coordinate system based on the normal point and the horizontal point of the radar, wherein the first coordinate system is the coordinate system where the initial obstacle corner point information is located, and the second coordinate system is the coordinate system where the target obstacle corner point information is located;

[0110] Step S2123: performing coordinate transformation on the initial obstacle corner point information based on the transformation relationship to obtain target obstacle corner point information.

[0111] In the embodiment of the present invention, the normal point and the horizontal point of the radar can be understood as two points established to determine the conversion relationship between the first coordinate system and the second coordinate system. Figure 4 As shown, the local coordinate system 1MP of the ultrasonic radar is established. Assuming that the car door is closed, a new radar normal point P: |1P|=100mm and a new radar horizontal point M: |1M|=100mm are added, and there is no restriction here.

[0112] The first coordinate system may be understood as the coordinate system where the initial obstacle corner point information is located. Exemplarily, the first coordinate system may be p_{ultrasonic local coordinate system}, which is not limited here.

[0113] The second coordinate system may be understood as a coordinate system where the target obstacle corner point information is located. Exemplarily, the second coordinate system may be b_{body coordinate system}, which is not limited here.

[0114] The coordinate transformation of the initial obstacle corner point information based on the transformation relationship can be understood as transforming the initial obstacle corner point information from the first coordinate system to the second coordinate system. Exemplarily, the transformation relationship between the first coordinate system p_{ultrasonic local coordinate system} and the second coordinate system b_{body coordinate system} can be p_{ultrasonic local coordinate system point}*SR+T= b_{body coordinate system point}, where R is a rotation matrix, S is a scaling matrix, and T is a translation matrix, which is not limited here.

[0115] In an embodiment of the present invention, when the target door is closed, the normal point P and the horizontal point M of the radar are determined based on a preset safety distance, and the conversion relationship between the coordinate system where the initial obstacle corner point information is located and the coordinate system where the target obstacle corner point information is located is determined based on the normal point and the horizontal point of the radar. The initial obstacle corner point information is transformed based on the conversion relationship to obtain the target obstacle corner point information, thereby facilitating the subsequent calculation of the distance between the target obstacle and the target door.

[0116] Optionally, in step S4, determining the target distance based on the target obstacle corner point information and the door corner point information may include the following execution steps:

[0117] Step S41, determining the distance between any target obstacle corner point in the target obstacle corner point information and any door corner point in the door corner point information to obtain distance information;

[0118] Step S42: determining the target distance based on the minimum distance in the distance information.

[0119] In an embodiment of the present invention, the distance between any target obstacle corner point in the target obstacle corner point information and any door corner point in the door corner point information is determined to obtain distance information. This can be understood as calculating the distance between all target obstacle corner points and door corner points respectively, thereby obtaining multiple distance information.

[0120] Determining the target distance based on the minimum distance in the distance information can be understood as taking the minimum value among the calculated distances between the multiple target obstacles and the target door as the final distance between the target obstacle and the target door, that is, the target distance.

[0121] In an embodiment of the present invention, by determining the distance between any target obstacle corner point in the target obstacle corner point information and any door corner point in the door corner point information, distance information between multiple target obstacles and the target door is obtained, and the minimum value in the distance information is used as the target distance, so as to accurately judge whether there is a safety problem in the opening and closing process of the target door.

[0122] Optionally, the method further comprises updating the second coordinate system based on an inertial measurement unit of the target vehicle.

[0123] In the embodiment of the present invention, the second coordinate system may be understood as a coordinate system where the target obstacle corner point information and the door corner point information are located.

[0124] The second coordinate system is updated based on the inertial measurement unit of the target vehicle, so that the distance between the target obstacle and the target door can be calculated more accurately.

[0125] Optionally, obtaining the door opening of a target door in the target vehicle includes: obtaining a Hall count of the target door based on a Hall sensor; and determining the door opening of the target door based on the Hall count.

[0126] In the embodiment of the present invention, by using a Hall sensor to obtain the Hall count of the target door and determining the door opening of the target door based on the Hall count, the door opening can be conveniently determined without complicated measurement and calculation.

[0127] The invention provides an accurate and reliable ultrasonic modeling method, which has wide adaptability and is suitable for different automatic vehicle doors and different sensors.

[0128] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0129] In this embodiment, an obstacle detection device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0130] Fig. 9 is a structural block diagram of an obstacle detection device according to one embodiment of the present invention. Fig. 9As shown, an obstacle detection device 900 is used as an example, and the device includes: an acquisition module 901, which is used to acquire the door opening and obstacle distance of a target door in a target vehicle, wherein the obstacle distance is used to represent the distance between the target obstacle and the target door within a preset range of the target door; a first determination module 902, which is used to determine the door corner point information of the target door based on the door opening, and to determine the initial obstacle corner point information of the target obstacle based on the obstacle distance, wherein the door corner point information is used to represent the contour features of the target door, and the initial obstacle corner point information is used to predict the contour features of the target obstacle; a conversion module 903, which is used to perform coordinate conversion on the initial obstacle corner point information to obtain the target obstacle corner point information, wherein the target obstacle corner point information and the door corner point information are located in the same coordinate system; a second determination module 904, which is used to determine the target distance based on the target obstacle corner point information and the door corner point information; and a detection module 905, which is used to detect the target obstacle based on the target distance and the preset safety distance.

[0131] Optionally, the detection module 905 is also used to obtain a first detection result in response to the target distance being greater than or equal to a preset safety distance, wherein the first detection result is used to indicate that there is no target obstacle during the opening and closing process of the target door; in response to the target distance being less than a preset safety distance, obtain a second detection result and report a prompt message, wherein the second detection result is used to indicate that there is a target obstacle during the opening and closing process of the target door, and the prompt message is used to indicate that there is a target obstacle outside the target door.

[0132] Optionally, the first determination module 902 is also used to determine the center point coordinates of the radar on the target door, the preset lower corner point coordinates of the target door, the outermost point coordinates of the target door in the first direction, the preset upper corner point coordinates of the target door, the glass water cut position corner point coordinates of the target door, the top corner point coordinates of the glass, the preset upper corner point coordinates of the front end of the target door, the preset lower corner point coordinates of the front end of the target door and the outermost point coordinates of the rearview mirror corresponding to the target door in the first direction.

[0133] Optionally, the first determination module 902 is also used to determine the first field of view angle and the second field of view angle of the radar, wherein the first field of view angle is half of the horizontal field of view angle of the radar, and the second field of view angle is half of the vertical field of view angle of the radar; and determine the initial obstacle corner point information according to the obstacle distance, the sine value of the first field of view angle, the cosine value of the first field of view angle, the sine value of the second field of view angle, and the cosine value of the second field of view angle.

[0134] Optionally, the conversion module 903 is also used to determine the normal point and horizontal point of the radar based on a preset distance when the target door is closed; determine the conversion relationship between the first coordinate system and the second coordinate system based on the normal point and horizontal point of the radar, wherein the first coordinate system is the coordinate system where the initial obstacle corner point information is located, and the second coordinate system is the coordinate system where the target obstacle corner point information is located; perform coordinate conversion on the initial obstacle corner point information based on the conversion relationship to obtain the target obstacle corner point information.

[0135] Optionally, the second determination module 904 is further used to determine the distance between any target obstacle corner point in the target obstacle corner point information and any door corner point in the door corner point information to obtain distance information; and determine the target distance based on the minimum distance in the distance information.

[0136] Optionally, the first determination module 902 is further configured to update the second coordinate system based on an inertial measurement unit of the target vehicle.

[0137] Optionally, the acquisition module 901 is further configured to acquire a Hall count of the target door based on the Hall sensor; and determine the door opening of the target door based on the Hall count.

[0138] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0139] An embodiment of the present invention further provides a vehicle, which is used to execute the steps in any of the above method embodiments.

[0140] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any of the above method embodiments when running on a computer or a processor.

[0141] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0142] Step S1, obtaining a door opening and an obstacle distance of a target door in a target vehicle, wherein the obstacle distance is used to represent a distance between a target obstacle and the target door within a preset range of the target door;

[0143] Step S2, determining the door corner point information of the target door based on the door opening, and determining the initial obstacle corner point information of the target obstacle based on the obstacle distance, wherein the door corner point information is used to represent the contour features of the target door, and the initial obstacle corner point information is used to predict the contour features of the target obstacle;

[0144] Step S3, performing coordinate conversion on the initial obstacle corner point information to obtain target obstacle corner point information, wherein the target obstacle corner point information and the door corner point information are located in the same coordinate system;

[0145] Step S4, determining the target distance based on the target obstacle corner point information and the door corner point information;

[0146] Step S5: Detect the target obstacle based on the target distance and the preset safety distance.

[0147] Optionally, in this embodiment, the above-mentioned computer-readable storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0148] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0149] Optionally, in this embodiment, the processor in the electronic device may be configured to run a computer program to perform the following steps:

[0150] Step S1, obtaining a door opening and an obstacle distance of a target door in a target vehicle, wherein the obstacle distance is used to represent a distance between a target obstacle and the target door within a preset range of the target door;

[0151] Step S2, determining the door corner point information of the target door based on the door opening, and determining the initial obstacle corner point information of the target obstacle based on the obstacle distance, wherein the door corner point information is used to represent the contour features of the target door, and the initial obstacle corner point information is used to predict the contour features of the target obstacle;

[0152] Step S3, performing coordinate conversion on the initial obstacle corner point information to obtain target obstacle corner point information, wherein the target obstacle corner point information and the door corner point information are located in the same coordinate system;

[0153] Step S4, determining the target distance based on the target obstacle corner point information and the door corner point information;

[0154] Step S5: Detect the target obstacle based on the target distance and the preset safety distance.

[0155] An embodiment of the present invention further provides a computer program product, including a computer program, which implements the steps in any of the above method embodiments when executed by a processor.

[0156] Optionally, in this embodiment, the computer program in the above computer program product may be configured to perform the following steps when executed by a processor:

[0157] Step S1, obtaining a door opening and an obstacle distance of a target door in a target vehicle, wherein the obstacle distance is used to represent a distance between a target obstacle and the target door within a preset range of the target door;

[0158] Step S2, determining the door corner point information of the target door based on the door opening, and determining the initial obstacle corner point information of the target obstacle based on the obstacle distance, wherein the door corner point information is used to represent the contour features of the target door, and the initial obstacle corner point information is used to predict the contour features of the target obstacle;

[0159] Step S3, performing coordinate conversion on the initial obstacle corner point information to obtain target obstacle corner point information, wherein the target obstacle corner point information and the door corner point information are located in the same coordinate system;

[0160] Step S4, determining the target distance based on the target obstacle corner point information and the door corner point information;

[0161] Step S5: Detect the target obstacle based on the target distance and the preset safety distance.

[0162] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0163] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0164] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0165] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0166] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0167] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0168] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk, etc., various media that can store program codes.

[0169] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An obstacle detection method, characterized in that: include: Obtaining a door opening and an obstacle distance of a target door in a target vehicle, wherein the obstacle distance is used to represent a distance between a target obstacle and the target door within a preset range of the target door; Determining door corner information of the target door based on the door opening, and determining initial obstacle corner information of the target obstacle based on the obstacle distance, wherein the door corner information is used to represent contour features of the target door, and the initial obstacle corner information is used to predict contour features of the target obstacle; Performing coordinate transformation on the initial obstacle corner point information to obtain target obstacle corner point information, wherein the target obstacle corner point information and the door corner point information are located in the same coordinate system; Determining a target distance based on the target obstacle corner point information and the door corner point information; The target obstacle is detected based on the target distance and a preset safety distance.

2. The method according to claim 1, characterized in that The detecting the target obstacle based on the target distance and the preset safety distance includes: In response to the target distance being greater than or equal to the preset safety distance, obtaining a first detection result, wherein the first detection result is used to indicate that the target obstacle does not exist during the opening and closing process of the target door; In response to the target distance being less than the preset safety distance, a second detection result is obtained and a prompt message is reported, wherein the second detection result is used to indicate that the target obstacle exists during the opening and closing process of the target door, and the prompt message is used to prompt that the target obstacle exists outside the target door.

3. The method according to claim 1, characterized in that The door corner point information includes: the center point coordinates of the radar on the target door, the preset lower corner point coordinates of the target door, the outermost point coordinates of the target door in the first direction, the preset upper corner point coordinates of the target door, the glass water cut position corner point coordinates of the target door, the top corner point coordinates of the glass, the preset upper corner point coordinates of the front end of the target door, the preset lower corner point coordinates of the front end of the target door and the outermost point coordinates of the rearview mirror corresponding to the target door in the first direction.

4. The method according to claim 3, characterized in that The determining of the initial obstacle corner point information of the target obstacle based on the obstacle distance includes: Determine a first field of view angle and a second field of view angle of the radar, wherein the first field of view angle is half of a horizontal field of view angle of the radar, and the second field of view angle is half of a vertical field of view angle of the radar; The initial obstacle corner point information is determined according to the obstacle distance, the sine value of the first field of view angle, the cosine value of the first field of view angle, the sine value of the second field of view angle, and the cosine value of the second field of view angle.

5. The method according to claim 4, characterized in that The performing coordinate transformation on the initial obstacle corner point information to obtain the target obstacle corner point information comprises: When the target door is closed, determining the normal point and the horizontal point of the radar based on a preset distance; Determine a conversion relationship between a first coordinate system and a second coordinate system based on the normal point and the horizontal point of the radar, wherein the first coordinate system is the coordinate system where the initial obstacle corner point information is located, and the second coordinate system is the coordinate system where the target obstacle corner point information is located; The initial obstacle corner point information is subjected to coordinate transformation based on the transformation relationship to obtain the target obstacle corner point information.

6. The method according to claim 1, characterized in that The determining the target distance based on the target obstacle corner point information and the door corner point information comprises: Determine the distance between any of the target obstacle corner points in the target obstacle corner point information and any of the door corner points in the door corner point information to obtain distance information; The target distance is determined based on a minimum distance in the distance information.

7. The method according to claim 5, characterized in that The method further comprises: The second coordinate system is updated based on an inertial measurement unit of the target vehicle.

8. The method according to any one of claims 1 to 7, characterized in that The step of obtaining the door opening of a target door in the target vehicle comprises: Acquiring a Hall count of the target door based on a Hall sensor; The door opening degree of the target door is determined based on the Hall count.

9. An obstacle detection device, characterized in that: include: An acquisition module, used for acquiring a door opening and an obstacle distance of a target door in a target vehicle, wherein the obstacle distance is used to represent a distance between a target obstacle and the target door within a preset range of the target door; a first determination module, configured to determine door corner point information of the target door based on the door opening, and to determine initial obstacle corner point information of the target obstacle based on the obstacle distance, wherein the door corner point information is used to represent contour features of the target door, and the initial obstacle corner point information is used to predict contour features of the target obstacle; A conversion module, used for performing coordinate conversion on the initial obstacle corner point information to obtain target obstacle corner point information, wherein the target obstacle corner point information and the door corner point information are located in the same coordinate system; A second determination module, configured to determine a target distance based on the target obstacle corner point information and the door corner point information; A detection module is used to detect the target obstacle based on the target distance and a preset safety distance.

10. A vehicle, characterized in that: The vehicle is used to execute the obstacle detection method described in any one of claims 1 to 8 above.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the obstacle detection method described in any one of claims 1 to 8 when running on a computer or a processor.

12. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the obstacle detection method described in any one of claims 1 to 8.

13. A computer program product, characterized in that The invention comprises a computer program, which implements the obstacle detection method described in any one of claims 1 to 8 when being executed by a processor.

Images