A vehicle roll-over detection method, device, vehicle and storage medium

Abstract

The application provides a vehicle rollover detection method and device, a vehicle and a storage medium. The method comprises the following steps: identifying a preset mark in a vehicle during driving of the vehicle; detecting a rotation angle of the preset mark; and determining that the vehicle has rolled over when it is determined that the rotation angle is within a preset angle range. The method can achieve vehicle rollover detection while avoiding major hardware modification of the vehicle.

Description

Technical Field

[0001] This application relates to the field of vehicles, and more specifically, to a method, apparatus, vehicle, and storage medium for detecting vehicle rollover in the field of vehicles. Background Technology

[0002] With societal progress, private car use has become more widespread. This has led to some drivers having limited driving experience and poorer handling skills in unexpected situations. For example, in rainy weather, vehicles may overturn on slippery roads, and drivers may not be able to regain control of the vehicle in time, causing danger. Furthermore, excessive speed while turning also increases the risk of rollover, as does the risk of overturning when a truck is carrying cargo.

[0003] Currently, the common method for detecting vehicle rollovers is to add some sophisticated hardware to mechanically determine whether the vehicle has rolled over. However, this method requires significant hardware modifications to the original vehicle. Summary of the Invention

[0004] This application provides a method, apparatus, vehicle, and storage medium for detecting vehicle rollover. The method can detect vehicle rollover while avoiding major hardware modifications to the vehicle.

[0005] In a first aspect, a method for detecting vehicle rollover is provided, the method comprising: identifying a preset sign in the vehicle during vehicle operation; detecting the rotation angle of the preset sign; and determining that the vehicle has rolled over when the rotation angle is determined to be within a preset angle range.

[0006] In the above technical solution, a preset sign in the vehicle is identified during vehicle movement, and the rotation angle of the preset sign is detected. Therefore, when the rotation angle is within a preset range, it is determined that the vehicle has overturned. In other words, the above technical solution determines whether a vehicle has overturned by detecting the rotation angle of a preset sign in the vehicle, without requiring additional sophisticated hardware to mechanically determine whether the vehicle has overturned. Therefore, it avoids significant hardware modifications to the original vehicle, thus helping to avoid increasing hardware costs.

[0007] In conjunction with the first aspect, in some possible implementations, the aforementioned preset sign is set at the target location of the vehicle, and the identification of the preset sign in the vehicle during the vehicle's operation includes: acquiring an image of the target location captured by a camera device during the vehicle's operation; and identifying the preset sign in the vehicle based on the image.

[0008] In the above technical solution, by combining the image of the target location captured by the camera device, the preset mark in the vehicle can be easily and accurately identified.

[0009] In combination with the first aspect and the above implementation, in some possible implementations, the shape of the preset sign is a polygon, and the detection of the rotation angle of the preset sign includes: identifying a first straight line containing the reference side of the preset sign from an image of the target position captured by the camera device; determining a second straight line containing the reference side of the preset sign when the vehicle is in the starting state; and determining the rotation angle based on the angle between the first straight line and the second straight line.

[0010] In the above technical solution, because the preset sign is polygonal in shape, it possesses distinct mathematical properties. From the moment the vehicle starts until it is in motion, the first and second straight lines can relatively accurately measure the change in the position of the reference side of the preset sign. Therefore, the angle between the first and second straight lines can relatively accurately measure the rotation angle. In this technical solution, the rotation angle can be relatively easily and accurately obtained by combining the mathematical properties of the preset sign, thereby improving the accuracy of rollover detection.

[0011] In combination with the first aspect and the above implementation, in some possible implementations, the color of the reference edge of the preset mark is a first color, the color of the non-reference edge of the preset mark is a second color, the first color and the second color are different, and the non-reference edge includes the edges of the preset mark other than the reference edge.

[0012] In the above technical solution, the color of the reference edge of the preset mark is different from the color of the non-reference edge, which makes it relatively easy to identify the reference edge of the preset mark based on the color feature. This can speed up the identification speed of the reference, thereby speeding up the detection speed of the rotation angle and thus speeding up the rollover detection speed.

[0013] In combination with the first aspect and the above implementation, in some possible implementations, identifying the first straight line containing the reference edge of the preset mark from the image of the target location captured by the camera device includes: determining the pixel value of each pixel in the region where the preset mark is located in the image; and identifying the first straight line containing the reference edge of the preset mark from the image based on the pixel value of each pixel and the range of pixel values ​​corresponding to the first color.

[0014] In combination with the first aspect and the above implementation, in some possible implementations, the angle between the first straight line and the second straight line includes a first angle and a second angle. Determining the rotation angle based on the angle between the first straight line and the second straight line includes taking the smaller angle between the first angle and the second angle as the rotation angle.

[0015] In combination with the first aspect and the above-described implementation, in some possible implementations, the aforementioned preset mark is set in the dashboard of the vehicle.

[0016] In combination with the first aspect and the above implementation, in some possible implementations, after determining that the vehicle has overturned, the method further includes: controlling the vehicle to return from the overturned state to the normal state by adjusting the vehicle's center of gravity.

[0017] In the above technical solution, after a rollover is detected, the vehicle's center of gravity is adjusted in a timely manner to restore the vehicle to a normal state, thereby improving driving safety.

[0018] Secondly, a vehicle rollover detection device is provided, comprising: an identification module for identifying a preset sign in the vehicle during vehicle operation; a detection module for detecting the rotation angle of the preset sign; and a determination module for determining that the vehicle has rolled over when the rotation angle is determined to be within a preset angle range.

[0019] In conjunction with the second aspect, in some possible implementations, the aforementioned preset sign is set at the target location of the vehicle, and the aforementioned identification module is specifically used to: acquire an image of the target location captured by the camera device during the vehicle's operation; and identify the aforementioned preset sign in the vehicle based on the image.

[0020] In conjunction with the second aspect, in some possible implementations, the shape of the preset sign is a polygon, and the detection module is specifically used to: identify the first straight line where the reference side of the preset sign is located from the image of the target position captured by the camera device; determine the second straight line where the reference side of the preset sign is located when the vehicle is in the starting state; and determine the rotation angle based on the angle between the first straight line and the second straight line.

[0021] In conjunction with the second aspect, in some possible implementations, the color of the reference edge of the aforementioned preset mark is a first color, and the color of the non-reference edge of the aforementioned preset mark is a second color. The first color and the second color are different, and the non-reference edge includes the edges of the aforementioned preset mark other than the reference edge.

[0022] In conjunction with the second aspect, in some possible implementations, the detection module is specifically used to: determine the pixel value of each pixel in the region where the preset mark is located in the image; and identify the first straight line where the reference edge of the preset mark is located in the image based on the pixel value of each pixel and the range of pixel values ​​corresponding to the first color.

[0023] In conjunction with the second aspect, in some possible implementations, the angle between the first straight line and the second straight line includes a first angle and a second angle, and the detection module is specifically used to: take the smaller angle between the first angle and the second angle as the rotation angle.

[0024] In conjunction with the second aspect, in some possible implementations, the aforementioned preset mark is set in the dashboard of the aforementioned vehicle.

[0025] In conjunction with the second aspect, in some possible implementations, the above-mentioned device further includes: an adjustment module, which, after determining that the vehicle has overturned, is used to: control the vehicle to return from the overturned state to a normal state by adjusting the vehicle's center of gravity.

[0026] Thirdly, a vehicle is provided, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, causing the vehicle to perform the methods of the first aspect or any possible implementation thereof.

[0027] Fourthly, a computer program product is provided, comprising: computer program code, which, when run on a computer, causes the computer to perform the methods described in the first aspect or any possible implementation thereof.

[0028] Fifthly, a computer-readable storage medium is provided that stores computer program code, which, when executed on a computer, causes the computer to perform the methods described in the first aspect or any possible implementation thereof. Attached Figure Description

[0029] Figure 1 This is a schematic flowchart of a vehicle rollover detection method provided in an embodiment of this application;

[0030] Figure 2 This is a schematic flowchart illustrating one implementation of step 102 provided in an embodiment of this application;

[0031] Figure 3 This is a schematic diagram of the structure of a vehicle rollover detection device provided in an embodiment of this application;

[0032] Figure 4 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application. Detailed Implementation

[0033] The technical solutions in this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in the text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0034] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0035] With societal progress, private car use has become more widespread. This has led to some drivers having limited driving experience and poorer handling skills in unexpected situations. For example, in rainy weather, vehicles may overturn on slippery roads, and drivers may not be able to regain control of the vehicle in time, causing danger. Furthermore, excessive speed while turning also increases the risk of rollover, as does the risk of overturning when a truck is carrying cargo.

[0036] In related technologies, the common method for detecting vehicle rollovers is to add sophisticated hardware, such as sensors, to mechanically determine whether a vehicle has rolled over. However, this method requires significant modifications to the original vehicle and demands highly sophisticated hardware, which can easily increase hardware costs.

[0037] To address the technical problems existing in related technologies, embodiments of this application provide a method and apparatus for detecting vehicle rollover, as well as a computer-readable storage medium and a vehicle for implementing the above method. The following is a detailed description of an embodiment of the vehicle rollover detection method provided in this application:

[0038] The vehicle rollover detection method provided in this application can be executed by a vehicle, specifically by a controller within the vehicle. Figure 1 This is a schematic flowchart of a vehicle rollover detection method provided in an embodiment of this application.

[0039] For example, such as Figure 1 As shown, the method includes:

[0040] Step 101: Identify preset signs in the vehicle while it is in motion.

[0041] Step 102: Detect the rotation angle of the preset mark.

[0042] Step 103: When it is determined that the above rotation angle is within the preset angle range, it is determined that the above vehicle has overturned.

[0043] In this embodiment, a preset sign in the vehicle is identified and its rotation angle is detected during vehicle movement. When the rotation angle is within a preset range, it is determined that the vehicle has overturned. In other words, the above technical solution determines whether a vehicle has overturned by detecting the rotation angle of a preset sign in the vehicle, without requiring additional sophisticated hardware to mechanically determine whether the vehicle has overturned. Therefore, it avoids significant hardware modifications to the original vehicle, thus helping to prevent increased hardware costs.

[0044] The following is a detailed description of the implementation details of the vehicle rollover detection method in this embodiment. The following content is only for the convenience of understanding and is not necessary for implementing this solution.

[0045] In step 101, the preset sign can be distinguished from existing signs in the vehicle. For example, it can be differentiated by a person skilled in the art based on existing signs in the vehicle, thus making the preset sign different from other existing signs in the vehicle. Optionally, the preset sign can differ from other existing signs in the vehicle in terms of shape, color, and placement. The preset sign can be a sign with distinctive features, making it easily identifiable in its surrounding environment. The vehicle can have a visual recognition function to identify the preset sign in the vehicle. For example, the preset sign in the vehicle can be identified by a dashcam, which can be positioned to capture the preset sign. However, this embodiment does not specifically limit this.

[0046] In an exemplary embodiment, the preset mark can be set at a target location in the vehicle, which can be the center console. The center console can be understood as the dashboard in front of the driver and passenger seats, serving as the mounting surface for the instrument panel, air conditioning and audio panels, storage compartments, airbags, and other devices. Optionally, the target location can be the instrument panel on the center console. In other words, the preset mark can be set within the vehicle's instrument panel. Optionally, the preset mark can be pre-installed in the instrument panel before the vehicle leaves the factory, or it can be affixed to the instrument panel after the vehicle leaves the factory, depending on actual needs. The preset mark is distinct from other marks on the instrument panel, thus facilitating accurate identification of the preset mark within the instrument panel.

[0047] In this embodiment, because the preset marker is set in the dashboard, it is controllable. For example, the display of the dashboard can be controlled to control the display of the preset marker, so that the preset marker is displayed in the dashboard in a desired position, shape, and color. Furthermore, the desired position, shape, and color can be adjusted according to actual needs, making the preset marker not static. Optionally, when the vehicle's infotainment system is updated, the preset marker in the dashboard can also be updated accordingly; for example, the position, shape, and color of the preset marker can all be updated. This embodiment, by setting the preset marker in the dashboard, makes the preset marker controllable and, to a certain extent, can also improve the accuracy of the detected preset marker.

[0048] It should be noted that in this embodiment, the preset sign is set in the vehicle's dashboard as an example. In actual implementation, it can also be set in other locations in the vehicle, but this embodiment does not make any specific limitation on this.

[0049] In an exemplary embodiment, the shape of the preset marker can be a polygon, such as a triangle, rectangle, square, trapezoid, etc. Optionally, the shape of the preset marker can be an equilateral triangle, or in other words, the preset marker itself can be an equilateral triangle (“△”). In this embodiment, the equilateral triangle preset marker can be used to determine whether a vehicle has overturned. It is understood that an equilateral triangle will only coincide with the original triangle after rotating 120 degrees, and a vehicle is generally in great danger when it has rotated 90 degrees. Therefore, in this embodiment, using an equilateral triangle as the basis for vehicle overturning can detect whether a vehicle has overturned in a timely and accurate manner. Furthermore, using an equilateral triangle as a preset marker is relatively simple, which helps to avoid increasing the complexity of overturning detection.

[0050] In an exemplary embodiment, step 101 may include: acquiring an image of the target location captured by the camera device; and identifying the preset sign in the vehicle based on the image. The camera device can be an in-vehicle camera, installed at a location capable of capturing the target location to obtain an image of it. For example, if the target location is the vehicle's dashboard, the camera device can be installed on the roof above the driver's seat, i.e., above the driver's head, thus clearly capturing the dashboard and avoiding the impact of different driver heights. In a specific implementation, the camera device can start capturing images after the vehicle starts. The camera device can capture images of the target location in real time while the vehicle is in motion and send the captured images to the vehicle's controller in real time. The vehicle's controller can then identify the preset sign in the received image.

[0051] In an exemplary embodiment, the aforementioned camera device can be a pan-tilt camera, so the horizontal position of the captured image is only affected by gravity and not by the vehicle, exhibiting high stability. Therefore, the image captured by this pan-tilt camera can accurately reflect the location of the preset sign, thereby improving the accuracy of the determined rotation angle of the preset sign, and further improving the accuracy of rollover detection based on this rotation angle. Furthermore, adding a pan-tilt camera does not require significant hardware modifications to the vehicle itself. Optionally, the aforementioned camera device can also be a dashcam.

[0052] In an exemplary embodiment, the method for identifying the preset sign in the vehicle based on the image may include: extracting an image of the target location from the image using a target detection network; then detecting the preset sign from the extracted image of the target location using the target detection network. The target detection network can be selected from existing target detection networks in the relevant art as needed; this embodiment does not specifically limit which target detection network to use. For example, if the target location is the dashboard in the vehicle, an image of the dashboard can be extracted from the image using a target detection network. Then, the preset sign can be detected from the extracted image of the dashboard using the target detection network. In this embodiment, interference from objects similar to the preset sign in the real-world scene can be removed, and because the preset sign is located in the dashboard, it is controllable, resulting in a higher accuracy rate for detecting the preset sign.

[0053] In step 102, during the vehicle's movement, the rotation angle of the preset sign is detected. This rotation angle can be the rotation angle of the preset sign detected at the current moment compared to the rotation angle of the preset sign detected when the vehicle is stationary. Here, "stationary" can also be understood as the vehicle being in its initial state or the vehicle being in a starting state.

[0054] In an exemplary embodiment, during vehicle operation, the current position of a preset sign can be determined in real time. The rotation angle is determined based on the angle between the line containing the current position of the preset sign and the line containing its initial position. It is understood that the angle between the two lines typically has a larger angle and a smaller angle; in this embodiment, the smaller angle can be used as the rotation angle. The current position of the preset sign can be determined in real time by capturing an image of the preset sign in real time using a camera device.

[0055] In step 103, when the rotation angle is determined to be within a preset angle range, it can be determined that the vehicle has overturned. The preset angle range can be set according to actual safety needs. For example, the preset angle range can be greater than or equal to 30 degrees, such as between 30 and 90 degrees. Therefore, when the rotation angle is determined to be between 30 and 90 degrees, it can be determined that the vehicle has overturned. However, in this embodiment, the preset angle range is only an example of 30 to 90 degrees, and is not limited to this in specific implementations. Correspondingly, when the rotation angle is determined to be outside the preset angle range, it can be determined that the vehicle has not overturned, i.e., the vehicle is in a normal state.

[0056] In an exemplary embodiment, the shape of the preset mark is a polygon, and the implementation of step 102 can be found in [reference needed]. Figure 2 ,include:

[0057] Step 1021: Identify the first straight line containing the reference edge of the preset mark from the image of the target location captured by the camera device;

[0058] Step 1022: Determine the second straight line where the reference edge of the preset mark is located when the vehicle is in the starting state;

[0059] Step 1023: Determine the rotation angle based on the angle between the first straight line and the second straight line.

[0060] In this embodiment, because the preset sign is polygonal in shape, it possesses distinct mathematical properties. From the moment the vehicle starts until it is in motion, the first and second straight lines can relatively accurately measure the change in the position of the reference edge of the preset sign. Therefore, the angle between the first and second straight lines can relatively accurately measure the rotation angle. In the above technical solution, the rotation angle can be accurately obtained relatively easily by combining the mathematical properties of the preset sign, thereby improving the accuracy of rollover detection.

[0061] The following is about Figure 2 The steps in the embodiments shown are explained in detail below:

[0062] In step 1021, the reference edge of the preset mark can be any one of the multiple edges of the preset mark. The reference edge can be preset according to actual needs, and the other edges of the preset mark besides the reference edge are non-reference edges. For example, if the preset mark is an equilateral triangle, the base of the equilateral triangle can be used as the reference edge, and the two lateral sides of the equilateral triangle can be used as non-reference edges. After receiving the image of the target position captured by the camera device, the controller in the vehicle can identify the first straight line where the reference edge of the preset mark is located from the image.

[0063] In an exemplary embodiment, the reference edge of the preset mark is a first color, and the non-reference edge of the preset mark is a second color. The first color and the second color are different, and the non-reference edges include all edges of the preset mark other than the reference edge. That is, the colors of the reference edge and the non-reference edge of the preset mark are different.

[0064] For example, the preset marker is an equilateral triangle, with the base of the equilateral triangle as the reference side and the lateral sides as the non-reference sides. The base of the equilateral triangle is red, and the other two lateral sides are white. Thus, based on the color difference, the first straight line containing the base of the triangle, i.e., the reference side, can be easily identified. Optionally, the preset marker can be placed in the vehicle's dashboard, making it easier to identify the red base against a black background, thus obtaining the first straight line containing that red base. It should be noted that this embodiment only uses red as the reference side and white as the non-reference side as an example; in specific implementations, it is not limited to this.

[0065] In this embodiment, the color of the reference edge of the preset mark is different from the color of the non-reference edge, which makes it relatively easy to identify the reference edge of the preset mark based on the color feature. This can speed up the identification speed of the reference, thereby speeding up the detection speed of the rotation angle and thus speeding up the rollover detection speed.

[0066] In an exemplary embodiment, step 1021 may be implemented by: determining the pixel value of each pixel in the region where the preset mark is located in the image; and identifying the first straight line containing the reference edge of the preset mark from the image based on the pixel values ​​of each pixel and the pixel value range corresponding to the first color. It is understood that different colors correspond to different pixel value ranges, which can be set according to actual needs. Specifically, pixels within the pixel value range corresponding to the first color can be determined based on the pixel values ​​of each pixel in the region where the preset mark is located, and the edge containing the pixel within the pixel value range corresponding to the first color can be used as a reference edge, thereby using the straight line containing the reference edge as the first straight line.

[0067] For example, the first color is red, and the pixel value range corresponding to red can be an R channel value between 200 and 255. Therefore, based on the pixel values ​​of each pixel in the area where the preset mark is located, the pixels with R channel values ​​between 200 and 255 can be determined, and the edge containing the pixels with R channel values ​​between 200 and 255 can be used as a reference edge, thereby using the straight line containing the reference edge as the first straight line.

[0068] For example, the area where the preset mark is located in the above image can be the area after expanding the outer rectangle of the preset mark by a preset number of pixels. This preset number can be set according to actual needs, such as 10, but this embodiment does not specifically limit it. Expanding the outer rectangle of the preset mark by a preset number of pixels can expand the recognition range of the first straight line to a certain extent, thereby facilitating the accurate recognition of the first straight line and further improving the accuracy of the detected rotation angle.

[0069] In step 1022, the second straight line containing the reference edge of the preset mark when the vehicle is in the starting state can be determined. Here, "vehicle in the starting state" can also be understood as the vehicle being in a stationary state or an initial state. Specifically, the second straight line containing the reference edge of the preset mark can be identified from the initial image captured by the camera. This initial image can be an image of the target location captured by the camera device when the vehicle is in the initial state.

[0070] In step 1023, the first slope of the first straight line and the second slope of the second straight line can be calculated first, and the angle between the first and second straight lines can be obtained based on the first and second slopes. Then, the rotation angle of the preset sign is determined based on this angle. It is understood that the angle between two straight lines usually has two angles, and the angle to be selected as the rotation angle can be determined according to the actual situation. Usually, the rotation angle of the vehicle is detected in real time, so the vehicle generally does not suddenly rotate a large angle. Therefore, at the beginning, a smaller angle can be selected as the rotation angle for storage. If the vehicle is constantly overturned or in the process of recovering from an overturn, the rotation angle corresponding to the current moment is similar to the rotation angle corresponding to the previous moment and will not change much. Therefore, since the angle between the first and second straight lines detected at the current moment has two angles, these two angles can be compared with the rotation angle detected at the previous moment, and the angle that is closer to the rotation angle detected at the previous moment can be used as the rotation angle of the preset sign detected at the current moment.

[0071] In an exemplary embodiment, the angle between the first straight line and the second straight line includes a first angle and a second angle. Step 1023 can be implemented by using the smaller of the first and second angles as the rotation angle. It is understood that the angle between two straight lines typically has two angles: a relatively large angle, such as an obtuse angle, and a relatively small angle, such as an acute angle. In this embodiment, the smaller of the two angles, namely the first and second angles, can be used as the rotation angle.

[0072] In an exemplary embodiment, after step 103, the method may further include: controlling the vehicle to return from a rollover state to a normal state by adjusting the vehicle's center of gravity. Specifically, a physical device can be installed in the vehicle to adjust its center of gravity. This physical device can be a cuboid container located at the bottom center of the vehicle. Inside the container, a control object capable of controlling the vehicle's overall center of gravity can be placed. By controlling the position of this control object within the container, the vehicle's overall center of gravity can be controlled, thereby allowing the vehicle to return from a rollover state to a normal state.

[0073] In this embodiment, after a rollover is detected, the vehicle's center of gravity is adjusted in a timely manner to restore the vehicle to a normal state, thereby improving driving safety.

[0074] For example, if the current rotation angle is 90 degrees, and assuming that at the next moment the angle between the first and second straight lines is one around 90 degrees and the other around 80 degrees, it may be difficult to determine whether the rotation angle at the next moment is around 90 degrees or around 80 degrees. This is because the vehicle may be continuing to roll over or it may be returning to a level position. However, when the vehicle rolls over to a less than 90-degree angle, such as around 60 degrees or less, the vehicle is already in a very dangerous situation. In this embodiment, a physical device will be used promptly to restore the vehicle to a level position, i.e., a normal state. Therefore, before reaching this point where it is difficult to determine, this embodiment has already used a physical device to restore the vehicle to a safe state.

[0075] In this embodiment, a gimbal camera can be used to capture images of the target location. The horizontal orientation of the captured image is only affected by gravity, not by the vehicle's state, resulting in high stability and improved accuracy of the determined rotation angle, thus further enhancing rollover detection accuracy. Furthermore, the preset marker features to be detected in this embodiment are obvious and easily extracted from the background environment, ensuring high accuracy. The preset markers are simple and clear, facilitating their inclusion in the dashboard display. The simple design also makes processing convenient and the occurrence of rollovers controllable, thereby achieving accurate rollover detection.

[0076] It should be noted that the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may, for example, be executed synchronously or asynchronously in multiple modules.

[0077] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein. For details not disclosed in the apparatus embodiments of this disclosure, please refer to the embodiments of the method disclosed herein.

[0078] Figure 3 This is a schematic diagram of the structure of a vehicle rollover detection device provided in an embodiment of this application.

[0079] For example, such as Figure 3 As shown, the device 300 includes:

[0080] Identification module 301: used to identify preset marks in the vehicle during vehicle operation;

[0081] Detection module 302: used to detect the rotation angle of the preset mark mentioned above;

[0082] Determining module 303: used to determine that the vehicle has overturned when the rotation angle is within a preset angle range.

[0083] In one possible implementation, the preset sign is set at the target location of the vehicle, and the identification module 301 is specifically used to: acquire an image of the target location captured by the camera device during the vehicle's operation; and identify the preset sign in the vehicle based on the image.

[0084] In one possible implementation, the shape of the preset sign is a polygon, and the detection module 302 is specifically used to: identify the first straight line where the reference side of the preset sign is located from the image of the target position captured by the camera device; determine the second straight line where the reference side of the preset sign is located when the vehicle is in the starting state; and determine the rotation angle based on the angle between the first straight line and the second straight line.

[0085] In one possible implementation, the color of the reference edge of the preset mark is a first color, and the color of the non-reference edge of the preset mark is a second color. The first color and the second color are different, and the non-reference edge includes the edges of the preset mark other than the reference edge.

[0086] In one possible implementation, the detection module 302 is specifically used to: determine the pixel value of each pixel in the region where the preset mark is located in the image; and identify the first straight line where the reference edge of the preset mark is located in the image based on the pixel value of each pixel and the range of pixel values ​​corresponding to the first color.

[0087] In one possible implementation, the angle between the first straight line and the second straight line includes a first angle and a second angle, and the detection module 302 is specifically used to: take the smaller angle between the first angle and the second angle as the rotation angle.

[0088] In one possible implementation, the aforementioned preset mark is set in the dashboard of the vehicle.

[0089] In one possible implementation, the device further includes an adjustment module, which, after determining that the vehicle has overturned, is used to control the vehicle to return from the overturned state to a normal state by adjusting the vehicle's center of gravity.

[0090] Figure 4 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application.

[0091] For example, such as Figure 4 As shown, the vehicle includes a memory 401 and a processor 402. The memory 401 stores executable program code, and the processor 402 is used to call and execute the executable program code to perform a vehicle rollover detection method.

[0092] This embodiment can divide the vehicle into functional modules according to the above method example. For example, each function can be assigned to a separate module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0093] When each functional module is divided according to its corresponding function, the vehicle may include: an identification module, a detection module, and a determination module, etc. It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional descriptions of the corresponding functional modules, and will not be repeated here.

[0094] The vehicle provided in this embodiment is used to perform the vehicle rollover detection method described above, and therefore can achieve the same effect as the above implementation method.

[0095] When using integrated units, the vehicle may include a processing module and a storage module. The processing module is used to control and manage the vehicle's actions. The storage module supports the vehicle in executing program code and data.

[0096] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as disclosed in this application. The processor may also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and microprocessors, etc., and the storage module may be a memory.

[0097] This embodiment also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the above-described related method steps to implement a vehicle rollover detection method in the above embodiment.

[0098] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to implement a vehicle rollover detection method as described in the above embodiment.

[0099] In addition, the vehicle provided in the embodiments of this application may specifically be a chip, component or module. The vehicle may include a connected processor and a memory. The memory is used to store instructions. When the vehicle is running, the processor may call and execute the instructions to make the chip execute a vehicle rollover detection method in the above embodiments.

[0100] In this embodiment, the vehicle, computer-readable storage medium, computer program product, or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.

[0101] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0102] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0103] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for detecting vehicle rollover, characterized in that, The method includes: During vehicle operation, images of the target location captured by a camera device are acquired; wherein the target location is the vehicle's dashboard, the camera device is a pan-tilt camera, and the camera device is mounted on the roof above the driver's seat. Based on the image, a preset sign in the vehicle is identified; wherein the preset sign is set at the target location, and the attribute information of the preset sign is updated along with the vehicle's infotainment system, the attribute information including one or any combination of the following: the shape, color, and position of the preset sign in the dashboard; Identify the first straight line containing the reference edge of the preset mark from the image of the target location captured by the camera device; When the vehicle is in the starting state, the second straight line where the reference edge of the preset mark is located; For the two angles between the first straight line and the second straight line detected at the current moment, the two angles are compared with the rotation angle detected at the previous moment, and the angle that is closer to the rotation angle detected at the previous moment is taken as the rotation angle of the preset flag detected at the current moment. When it is determined that the rotation angle detected at the current moment is within a preset angle range, it is determined that the vehicle has overturned.

2. The method according to claim 1, characterized in that, The color of the reference edge of the preset mark is a first color, and the color of the non-reference edge of the preset mark is a second color. The first color and the second color are different, and the non-reference edge includes the edges of the preset mark other than the reference edge.

3. The method according to claim 2, characterized in that, The step of identifying the first straight line containing the reference edge of the preset mark from the image of the target location captured by the camera device includes: Determine the pixel value of each pixel in the region where the preset mark is located in the image; Based on the pixel values ​​of each pixel and the range of pixel values ​​corresponding to the first color, the first straight line containing the reference edge of the preset mark is identified from the image.

4. The method according to any one of claims 1 to 3, characterized in that, After determining that the vehicle has overturned, the method further includes: The vehicle's center of gravity is adjusted to control its recovery from a rollover state to a normal state.

5. A vehicle rollover detection device, characterized in that, The device includes: The recognition module is used to acquire an image of a target location captured by a camera device while the vehicle is in motion; and to recognize a preset sign in the vehicle based on the image; wherein the target location is the dashboard of the vehicle, the preset sign is set at the target location, and the attribute information of the preset sign is updated with the vehicle's infotainment system. The attribute information includes one or any combination of the following: the shape, color, and position of the preset sign in the dashboard. The camera device is a pan-tilt camera, and the camera device is mounted on the roof above the driver's seat. The detection module is used to identify a first straight line containing the reference edge of the preset sign from an image of the target location captured by the camera device; determine a second straight line containing the reference edge of the preset sign when the vehicle is in the starting state; and for the two angles between the first straight line and the second straight line detected at the current moment, compare the two angles with the rotation angle detected at the previous moment, and take the angle that is closer to the rotation angle detected at the previous moment as the rotation angle of the preset sign detected at the current moment. The determination module is used to determine that the vehicle has overturned when the rotation angle detected at the current moment is within a preset angle range.

6. A vehicle, characterized in that, The vehicles include: Memory, used to store executable program code; A processor for calling and running the executable program code from the memory, causing the vehicle to perform the method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the method as described in any one of claims 1 to 4.

Images