Vehicle height limit detection method, vehicle-mounted image acquisition device and storage medium

Abstract

The application discloses a vehicle height-limiting detection method, a vehicle-mounted image acquisition device and a storage medium. The method comprises the following steps: obtaining a picture reference position of the vehicle-mounted image acquisition device; wherein the picture reference position is obtained by pre-calibration of the vehicle-mounted image acquisition device, and the picture reference position represents the position of a calibration object at a calibration distance in a calibration acquisition picture of the vehicle-mounted image acquisition device; monitoring the position of a road height-limiting facility in a current acquisition picture of the vehicle-mounted image acquisition device during vehicle driving; in response to the road height-limiting facility being located at the picture reference position in the current acquisition picture, performing height-limiting detection on the vehicle based on the image facility height of the road height-limiting facility in the current acquisition picture to obtain a height-limiting detection result; wherein the height-limiting detection result is used to represent whether the vehicle can pass through the road height-limiting facility. In the foregoing manner, the application can improve the accuracy and efficiency of height-limiting detection.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technology, and in particular to a vehicle height limit detection method, an on-board image acquisition device, and a storage medium. Background Technology

[0002] When vehicles (such as buses and trucks) are traveling on the road, if they encounter road height restriction facilities without clearly defined height limits (such as tunnels, bridges, or height restriction barriers), or if the height limit displayed on the road height restriction facility does not match the actual height of the facility, the vehicle may become stuck. This not only results in vehicle damage and delays to the driver, but also requires compensation to the road administration for losses. Therefore, how to detect vehicle height restrictions during driving has become an urgent problem to be solved. Summary of the Invention

[0003] The main technical problem addressed in this application is to provide a vehicle height limit detection method, an on-board image acquisition device, and a storage medium, which can improve the accuracy and efficiency of height limit detection.

[0004] To address the aforementioned technical problems, the first aspect of this application provides a vehicle height restriction detection method. The method includes: acquiring a reference position of an image from an onboard image acquisition device; wherein the reference position is pre-calibrated using the onboard image acquisition device, and the reference position represents the position of a calibration object at a calibration distance within the calibration acquisition image of the onboard image acquisition device; during vehicle operation, monitoring the position of a road height restriction facility in the current acquisition image of the onboard image acquisition device; in response to the road height restriction facility being located at the reference position in the current acquisition image, performing height restriction detection on the vehicle based on the image facility height of the road height restriction facility in the current acquisition image, and obtaining a height restriction detection result; wherein the height restriction detection result is used to characterize whether the vehicle can pass through the road height restriction facility.

[0005] Wherein, the image reference position is the lower baseline, which is a horizontal line passing through the bottom point of the calibration object in the calibration acquisition image, and the position of the road height restriction facility in the current acquisition image is the position of the lower edge of the road height restriction facility in the current acquisition image; the image reference position of the road height restriction facility in the current acquisition image includes: the lower edge of the road height restriction facility coincides with the lower baseline, or the target position point of the lower edge of the road height restriction facility is located on the lower baseline.

[0006] The target location point along the lower edge of the facility includes the midpoint of the lower edge of the facility.

[0007] The step of detecting the vehicle's height restriction based on the image height of the road height restriction facility in the currently captured image, and obtaining the height restriction detection result, includes: acquiring the image height of the road height restriction facility in the currently captured image; determining the height restriction detection result based on the height difference between the facility's representative height and the vehicle's representative height; wherein the facility's representative height is the image facility height, the vehicle's representative height is the image vehicle height, the image vehicle height represents the vehicle height mapped to the calibrated captured image, or the facility's representative height is the actual facility height obtained by mapping the image facility height to actual three-dimensional space, and the vehicle's representative height is the actual vehicle height in actual three-dimensional space.

[0008] Wherein, the facility representative height is the image facility height, the vehicle representative height is the image vehicle height, the image facility height represents the distance between the lower edge and upper edge of the road height restriction facility in the currently captured image, the image reference position is the lower baseline, the lower baseline is the horizontal line passing through the bottom point of the calibration object in the calibration captured image, and the lower edge of the facility is the image reference position; determining the height restriction detection result based on the height difference between the facility representative height and the vehicle representative height includes: extracting the upper edge of the road height restriction facility from the currently captured image; and determining the upper baseline using the lower baseline and the image vehicle height; and determining the height restriction detection result based on the positional relationship between the upper baseline and the upper edge of the facility.

[0009] Wherein, the facility representative height is the actual facility height obtained by mapping the image facility height to the actual three-dimensional space, and the vehicle representative height is the actual vehicle height of the vehicle in the actual three-dimensional space; determining the height limit detection result based on the height difference between the facility representative height and the vehicle representative height includes: mapping the image facility height to the actual three-dimensional space to obtain the actual facility height; and determining the height limit detection result based on the height difference between the actual vehicle height and the actual facility height.

[0010] The determination of the height restriction detection result based on the positional relationship between the upper baseline and the upper edge of the facility, or the determination of the height restriction detection result based on the height difference between the actual vehicle height and the actual facility height, includes: determining that the vehicle can pass through the road height restriction facility in response to the facility's representative height being higher than the vehicle's representative height; and determining that the vehicle cannot pass through the road height restriction facility in response to the facility's representative height being lower than or equal to the vehicle's representative height.

[0011] The step of calibrating the vehicle-mounted image acquisition device includes: acquiring an image of a calibration object using the vehicle-mounted image acquisition device to obtain a calibration acquisition image; extracting the bottom edge position and top edge position of the calibration object from the calibration acquisition image; determining the image calibration height of the calibration object based on the bottom edge position and the top edge position, and determining the distance between the vehicle and the calibration object based on the image calibration height and the acquisition parameters of the vehicle-mounted image acquisition device, as the calibration distance; and determining the image reference position based on the bottom edge position.

[0012] Wherein, the image reference position is the lower baseline, which is a horizontal line passing through the bottom point of the calibration object in the calibration acquisition image; before determining the image calibration height of the calibration object based on the bottom edge position and the top edge position, the method further includes: determining the bottom point in the bottom edge and the vertex in the top edge; using the bottom point position as the bottom edge position, and using the vertex position as the top edge position; determining the image calibration height of the calibration object based on the bottom edge position and the top edge position includes: determining the image calibration height of the calibration object based on the bottom point position and the vertex position; determining the image reference position based on the bottom edge position includes: using the horizontal line where the bottom point position is located as the lower baseline.

[0013] Wherein, the height restriction detection result indicates that the vehicle cannot pass through the road height restriction facility; the method further includes: sending alarm information to the user; and / or, the vehicle-mounted image acquisition device includes a driving recorder.

[0014] To address the aforementioned technical problems, a second aspect of this application provides an in-vehicle image acquisition device, which includes a processor and a memory. The memory stores program instructions, and the processor executes the program instructions to implement the aforementioned vehicle height limit detection method.

[0015] To address the aforementioned technical problems, a third aspect of this application provides a computer-readable storage medium for storing program instructions that can be executed to implement the aforementioned vehicle height limit detection method.

[0016] The above technical solution monitors the position of road height restriction facilities by using the reference position of the onboard image acquisition equipment as a benchmark during vehicle movement. When the height restriction facility is located at the reference position in the current captured image, it indicates that the distance between the facility and the vehicle in the actual scenario is approximately equal to the calibrated distance. At this point, the vehicle's height is detected based on the height of the height restriction facility in the current captured image. This height restriction detection method based on the reference position reduces errors caused by changes in the viewing angle and distance of the onboard image acquisition equipment during vehicle movement, improving the accuracy of height restriction detection and providing a reliable basis for whether a vehicle can pass safely.

[0017] In addition, the system monitors the location of road height restriction facilities in the currently captured image in real time while the vehicle is in motion. Once the road height restriction facility is located at the reference position in the currently captured image, height restriction detection is immediately performed. This allows the system to obtain height restriction detection results in a timely manner when the vehicle approaches the road height restriction facility, improving the efficiency of height restriction detection. This helps users (e.g., drivers) make timely decisions and avoid collisions caused by not being aware of height restriction conditions in time. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating an embodiment of the vehicle height restriction detection method provided in this application;

[0019] Figure 2 This is a schematic diagram of an embodiment of the lower baseline and facility lower edge provided in this application; Figure 3 This is a schematic diagram of another embodiment of the lower baseline and facility lower edge provided in this application; Figure 4 yes Figure 1 The flowchart of step S13 shown is a schematic diagram of one embodiment. Figure 5 This is a schematic diagram of the framework of an embodiment of the vehicle height restriction detection device provided in this application; Figure 6 This is a schematic diagram of the framework of an embodiment of the vehicle-mounted image acquisition device provided in this application; Figure 7 This is a schematic diagram of a framework of an embodiment of the computer-readable storage medium provided in this application. Detailed Implementation

[0020] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0021] In the following description, specific details such as particular system architectures, interfaces, and technologies are presented for illustrative purposes rather than for limiting purposes, in order to provide a thorough understanding of this application.

[0022] In this paper, the terms "system" and "network" are often used interchangeably. The term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Additionally, the character " / " generally indicates that the preceding and following related objects have an "or" relationship. Furthermore, "many" in this paper means two or more.

[0023] Please see Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the vehicle height restriction detection method provided in this application. It should be noted that if substantially the same result is obtained, this embodiment does not necessarily reflect that result. Figure 1 The illustrated process sequence is limited. For example... Figure 1 As shown, this embodiment includes: Step S11: Obtain the reference position of the image captured by the vehicle-mounted image acquisition device.

[0024] In this embodiment, the reference position of the image acquisition device is obtained; wherein, the reference position is obtained by pre-calibrating the image acquisition device and the reference position represents the position of the calibration object at the calibration distance in the calibration acquisition image of the image acquisition device.

[0025] The image reference position represents the location of the calibration object at the calibration distance within the calibration capture frame of the vehicle-mounted image acquisition device. Therefore, by pre-calibrating the image reference position of the vehicle-mounted image acquisition device, a correspondence is established between the image reference position in the calibration capture frame and the calibration distance in the actual scene. For example, if, during vehicle operation, the location of a road height restriction facility in the current capture frame of the vehicle-mounted image acquisition device is detected and falls within the image reference position in the current capture frame, it can be inferred that the distance between the road height restriction facility and the vehicle in the actual scene is the calibration distance.

[0026] As vehicles move, factors such as the viewing angle and distance of the onboard image acquisition equipment constantly change, causing the position and size of road height restriction facilities in the current captured image to also change. The image reference position provides a unified benchmark for height restriction detection, allowing the position of road height restriction facilities to be measured with a relatively fixed standard at different times and under different driving conditions. Regardless of whether the vehicle is accelerating, decelerating, turning, or in different road conditions, as long as the road height restriction facility appears at the image reference position, it means that its distance from the vehicle in the actual scenario has reached the calibrated distance. Therefore, subsequent height restriction detection can be based on this relatively stable benchmark.

[0027] Furthermore, with a reference location in the image, the detection algorithm can focus more on image information at a specific location, without needing to perform complex searches and analyses of the entire image. When a road height restriction facility is located at the reference location, the algorithm can directly perform height restriction detection on the image data at that location, greatly simplifying the calculation process and improving the efficiency and real-time performance of height restriction detection.

[0028] In one embodiment, the vehicle-mounted image acquisition device can be a dashcam. Of course, in other embodiments, the vehicle-mounted image acquisition device can also be other image acquisition devices on the vehicle, and this is not limited thereto.

[0029] In one implementation, such as Figure 2 As shown, Figure 2 This is a schematic diagram of an embodiment of the lower baseline and facility lower edge provided in this application. The reference position of the screen is the lower baseline, which is the horizontal line passing through the bottom point of the calibration object in the calibration acquisition screen.

[0030] Step S12: During vehicle operation, monitor the location of road height restriction facilities in the current captured image of the vehicle-mounted image acquisition device.

[0031] In this embodiment, the location of road height restriction facilities in the current captured image of the vehicle-mounted image acquisition device is monitored during vehicle operation.

[0032] In one implementation, such as Figure 2 As shown, the location of the road height restriction facility in the currently captured image is the position of its lower edge. Specifically, a deep learning model is used to identify the road height restriction facility in the current captured image of the vehicle-mounted image acquisition device, thereby determining the position of its lower edge.

[0033] In one embodiment, the road height restriction facility can be a tunnel, bridge, height restriction bar, etc., and is not limited thereto.

[0034] Step S13: In response to the road height restriction facility being located at the image reference position in the current captured image, perform height restriction detection on the vehicle based on the image facility height of the road height restriction facility in the current captured image, and obtain the height restriction detection result.

[0035] In this embodiment, in response to the road height restriction facility being located at the image reference position in the currently captured frame, height restriction detection is performed on the vehicle based on the image facility height of the road height restriction facility in the currently captured frame, resulting in a height restriction detection result. This result indicates whether the vehicle can pass the road height restriction facility. During vehicle movement, the position of the road height restriction facility is monitored using the image reference position of the onboard image acquisition device as a benchmark. When the road height restriction facility is located at the image reference position in the currently captured frame, it indicates that the distance between the road height restriction facility and the vehicle in the actual scenario is approximately equal to the calibrated distance. At this point, height restriction detection is performed on the vehicle based on the image facility height of the road height restriction facility in the currently captured frame. This method, based on the image reference position and image information at a specific moment, reduces errors caused by changes in the viewing angle and distance of the onboard image acquisition device during vehicle movement, improves the accuracy of height restriction detection, and provides a reliable basis for whether the vehicle can safely pass.

[0036] In addition, the system monitors the location of road height restriction facilities in the currently captured image in real time while the vehicle is in motion. Once the road height restriction facility is located at the reference position in the currently captured image, height restriction detection is immediately performed. This allows the system to obtain height restriction detection results in a timely manner when the vehicle approaches the road height restriction facility, improving the efficiency of height restriction detection. This helps users (e.g., drivers) make timely decisions and avoid collisions caused by not being aware of height restriction conditions in time.

[0037] In one embodiment, the reference position of the image is the lower baseline, which is the horizontal line passing through the bottom point of the calibration object in the calibration acquisition image. The position of the road height restriction facility in the current acquisition image is the position of the lower edge of the road height restriction facility in the current acquisition image. The reference position of the road height restriction facility in the current acquisition image is: the lower edge of the road height restriction facility coincides with the lower baseline.

[0038] Specifically, such as Figure 2 As shown, the reference position of the image is the lower baseline, and the position of the road height restriction facility in the currently captured image is the position of the lower edge of the road height restriction facility in the currently captured image. When the vehicle's driving direction is perpendicular to the lower edge of the road height restriction facility, and the lower edge of the road height restriction facility coincides with the lower baseline in the currently captured image, the vehicle's height is detected based on the image height of the road height restriction facility in the currently captured image. That is, height restriction detection is triggered when the lower edge of the road height restriction facility coincides with the lower baseline in the currently captured image.

[0039] In other embodiments, the reference position of the image is the lower baseline, which is the horizontal line passing through the bottom point of the calibration object in the calibration acquisition image. The position of the road height restriction facility in the current acquisition image is the position of the lower edge of the road height restriction facility in the current acquisition image. The reference position of the road height restriction facility in the current acquisition image is: the target position point of the lower edge of the road height restriction facility is located on the lower baseline.

[0040] Specifically, such as Figure 3 As shown, Figure 3 This is a schematic diagram of another embodiment of the lower baseline and lower edge of the facility provided in this application. The reference position of the image is the lower baseline, and the position of the road height restriction facility in the currently captured image is the position of the lower edge of the road height restriction facility in the currently captured image. When the vehicle's driving direction is not perpendicular to the lower edge of the road height restriction facility, such as when the vehicle is turning and encounters the road height restriction facility in front, from the perspective of the vehicle's interior, the lower edge of the road height restriction facility is not horizontal and cannot coincide with the lower baseline in the currently captured image. Therefore, when the target position point of the lower edge of the road height restriction facility is located on the lower baseline, height restriction detection is performed on the vehicle based on the image facility height of the road height restriction facility in the currently captured image. That is, height restriction detection is triggered when the lower baseline in the currently captured image passes through the target position point of the lower edge of the road height restriction facility.

[0041] In one specific implementation, the target location point of the lower edge of the facility includes the midpoint of the lower edge of the facility. When the midpoint of the lower edge of the road height restriction facility is located on the lower baseline, the vehicle height is detected based on the image facility height of the road height restriction facility in the current captured image. That is, the height restriction detection is triggered when the lower baseline in the current captured image passes through the midpoint of the lower edge of the road height restriction facility.

[0042] In one implementation, the height restriction detection result indicates that the vehicle cannot pass through the road height restriction facility, and an alarm message is also sent to the user. When it is determined that the vehicle cannot pass through the road height restriction facility, sending an alarm message to the user (e.g., the driver) in a timely manner allows the user to be aware of the danger at the first moment, giving them enough time to take measures such as braking and steering to avoid collisions and ensure the safety of the vehicle, the user, and the road height restriction facility.

[0043] Please see Figure 4 , Figure 4 yes Figure 1 The diagram shows a flowchart of one embodiment of step S13. It should be noted that if substantially the same result is achieved, this embodiment does not necessarily follow that approach. Figure 4 The illustrated process sequence is limited. For example... Figure 4 As shown, this embodiment includes: Step S41: Obtain the image height of the road height restriction facility in the current captured image.

[0044] In this embodiment, the height of the road height restriction facility in the image of the currently captured frame is obtained.

[0045] Step S42: Determine the height restriction detection result based on the height difference between the facility representative height and the vehicle representative height.

[0046] In this embodiment, the height limit detection result is determined based on the height difference between the facility representative height and the vehicle representative height; wherein, the facility representative height is the image facility height, the vehicle representative height is the image vehicle height, the image vehicle height represents the vehicle height mapped to the calibration acquisition screen, or, the facility representative height is the actual facility height obtained by mapping the image facility height to the actual three-dimensional space, and the vehicle representative height is the actual vehicle height in the actual three-dimensional space.

[0047] It should be noted that the image facility height represents the distance between the bottom and top edges of the road height restriction facility in the current captured image, which is the facility pixel height. The facility pixel height of the road height restriction facility is the number of pixels it occupies vertically in the current captured image. The image vehicle height is the vehicle pixel height, which is the number of pixels the vehicle occupies vertically in the current captured image. For example, if the bottom point coordinates p1 of the road height restriction facility's bottom edge are [960, 500] and the top point coordinates p2 of the road height restriction facility's top edge are [960, 580], then the facility pixel height hpixel of the road height restriction facility is 80 pixels. That is, the image facility height of the road height restriction facility is 80 pixels.

[0048] In one embodiment, the facility representative height is the actual facility height obtained by mapping the image facility height to actual three-dimensional space, and the vehicle representative height is the actual vehicle height in actual three-dimensional space. The height restriction detection result is determined based on the height difference between the facility representative height and the vehicle representative height. Specifically, the image facility height is mapped to actual three-dimensional space to obtain the actual facility height; the height restriction detection result is determined based on the height difference between the actual vehicle height and the actual facility height. In other words, by comparing the actual vehicle height with the actual facility height of the road height restriction facility, it is determined whether the vehicle can pass through the road height restriction facility.

[0049] In one specific implementation, the height restriction detection result is determined based on the height difference between the actual vehicle height and the actual facility height. Specifically: if the representative height of the facility is higher than the representative height of the vehicle, it is determined that the vehicle can pass through the road height restriction facility; if the representative height of the facility is lower than or equal to the representative height of the vehicle, it is determined that the vehicle cannot pass through the road height restriction facility. In other words, if the actual facility height is higher than the actual vehicle height, the vehicle can pass through the road height restriction facility; if the actual facility height is lower than or equal to the actual vehicle height, the vehicle cannot pass through the road height restriction facility.

[0050] In one specific implementation, the actual vehicle height is input by the user into the in-vehicle image acquisition device. For example, the in-vehicle image acquisition device is a dashcam, and the user inputs the actual vehicle height on the dashcam's operation page.

[0051] In one specific implementation, a deep learning model is used to identify road height restriction facilities in the current captured image of the vehicle-mounted image acquisition device, so as to identify the road height restriction facilities from the current captured image of the vehicle-mounted image acquisition device, thereby determining the lower edge and upper edge of the road height restriction facilities in the current captured image; the distance between the lower edge and upper edge of the road height restriction facilities in the current captured image is the image height of the road height restriction facilities.

[0052] In one specific implementation, the image facility height is mapped to the actual three-dimensional space to obtain the actual facility height. Specifically, the actual facility height is obtained based on the image facility height using the thin lens formula and the magnification formula.

[0053] The formula for a thin lens is shown below: 1 / u1 + 1 / v1 = 1 / f1 In the formula: u1 represents the object distance (the actual distance from the road height restriction facility to the lens of the vehicle-mounted image acquisition device, which is basically equal to the calibration distance); v1 represents the image distance (the distance from the image road height restriction facility to the lens of the vehicle-mounted image acquisition device); f1 represents the focal length of the lens of the vehicle-mounted image acquisition device.

[0054] The magnification formula is shown below: m1=hi1 / ho1=v1 / u1 In the formula: m1 represents the magnification; hi1 represents the physical facility height, which is the actual physical height of the road height restriction facility as imaged on the plane of the image sensor, in mm; ho1 represents the actual facility height.

[0055] Combining the thin lens formula and the magnification formula, we can obtain: hi1=f1 ho1 / (u1-f1) When u1 is much larger than f1, we can approximate the result as follows: hi1=f1 ho1 / u1 Furthermore, combining the formula hi1=f1 ho1 / u1 and image facility height are used to map the image facility height to actual three-dimensional space, obtaining the actual facility height of the road height restriction facility. Specifically, the physical facility height of the road height restriction facility can be determined by the image facility height, image sensor size, image sensor aspect ratio, and image resolution.

[0056] In one embodiment, the facility representative height is the image facility height, and the vehicle representative height is the image vehicle height. The image facility height represents the distance between the lower edge and the upper edge of the road height restriction facility in the current captured image. The image reference position is the lower baseline, which is a horizontal line passing through the bottom point of the calibration object in the calibration captured image. The lower edge of the facility is the image reference position. Based on the height difference between the facility representative height and the vehicle representative height, the height restriction detection result is determined, specifically: the upper edge of the road height restriction facility is extracted from the current captured image; and the upper baseline is determined using the lower baseline and the image vehicle height; the height restriction detection result is determined based on the positional relationship between the upper baseline and the upper edge of the facility.

[0057] In one specific implementation, the height restriction detection result is determined based on the positional relationship between the upper baseline and the upper edge of the facility. Specifically: in response to the facility's representative height being higher than the vehicle's representative height, it is determined that the vehicle can pass through the road height restriction facility; in response to the facility's representative height being lower than or equal to the vehicle's representative height, it is determined that the vehicle cannot pass through the road height restriction facility. That is, if the upper edge of the facility is higher than or exceeds the upper baseline, the vehicle can pass through the road height restriction facility; if the upper edge of the facility is lower than or equal to the upper baseline, or if the upper edge of the facility does not exceed the upper baseline, the vehicle cannot pass through the road height restriction facility.

[0058] In one specific implementation, a deep learning model is used to identify road height restriction facilities in the current captured image of the vehicle-mounted image acquisition device, so as to identify the road height restriction facilities from the current captured image of the vehicle-mounted image acquisition device, thereby determining the upper edge of the road height restriction facilities in the current captured image.

[0059] In one specific implementation, the actual vehicle height is input by the user into the in-vehicle image acquisition device. For example, the in-vehicle image acquisition device is a dashcam, and the user inputs the actual vehicle height on the dashcam's operation page.

[0060] In one specific implementation, the actual vehicle height is mapped to the image space to obtain the image vehicle height.

[0061] In one specific implementation, the actual vehicle height is mapped to the image space to obtain the image vehicle height. Specifically, the image vehicle height is obtained based on the actual vehicle height using the calibration distance, thin lens formula, and magnification formula.

[0062] The formula for a thin lens is shown below: 1 / u² + 1 / v² = 1 / f² In the formula: u2 represents the calibration distance; v2 represents the image distance (the distance from the vehicle to the lens of the vehicle-mounted image acquisition device); f2 represents the focal length of the lens of the vehicle-mounted image acquisition device.

[0063] The magnification formula is shown below: m2=hi2 / ho2=v2 / u2 In the formula: m2 represents the magnification; hi2 represents the physical vehicle height, which is the actual physical height of the vehicle as imaged on the image sensor plane, in mm; ho2 represents the actual vehicle height.

[0064] Combining the thin lens formula and the magnification formula, we can obtain: hi2=f2 ho2 / (u2-f2) When u2 is much larger than f2, we can approximate the result as follows: hi2=f2 ho2 / u2 Furthermore, combining the formula hi2=f2 Using ho2 / u2, actual vehicle height, calibration distance, image sensor size, image sensor aspect ratio, and image resolution, the vehicle's image height is determined, and the actual vehicle height is mapped to the image space to obtain the vehicle's image height.

[0065] For example, consider a vehicle-mounted image acquisition device with a lens focal length f2=8mm, actual vehicle height ho2=1m=1000mm, calibration distance u2=10m=10000mm, image sensor size S=1 / 2.8 inch ≈6.4 mm (diagonal), image sensor aspect ratio of 16:9, and image resolution of 1920×1080. First, calculate the physical height Hsensor of the image sensor, as shown below:

[0066] Then, the pixel density ρ of the image sensor and the physical vehicle height are calculated, as shown below: ρ = 1080 / 3.2 = 337.5 pixels / mm hi2=1000 8 / 10000 = 0.8 mm Then, the vehicle pixel height hpixel2 (i.e., the image vehicle height) is calculated, as shown above: hpixel2 = 0.8 × 337.5 ≈ 270 pixels In one specific implementation, the upper baseline is obtained by adding the number of pixels occupied vertically by the actual vehicle height in the current captured image to the lower baseline in the current captured image.

[0067] In one embodiment, the step of calibrating the vehicle-mounted image acquisition device specifically includes: acquiring an image of the calibration object using the vehicle-mounted image acquisition device to obtain a calibration acquisition image; extracting the bottom edge position and top edge position of the calibration object from the calibration acquisition image; determining the image calibration height of the calibration object based on the bottom edge position and top edge position, and determining the distance between the vehicle and the calibration object based on the image calibration height and the acquisition parameters of the vehicle-mounted image acquisition device, as the calibration distance; and determining the image reference position based on the bottom edge position.

[0068] In one specific embodiment, the calibration object can be a plastic rod, or a graduated paper strip affixed to a wall as a calibration object.

[0069] In one specific implementation, a deep learning model is used to identify calibration objects in the calibration acquisition image, thereby determining the bottom and top positions of the calibration objects in the calibration acquisition image.

[0070] In one specific implementation, before determining the image calibration height of the calibrator based on the bottom edge position and the top edge position, the bottom point in the bottom edge and the vertex in the top edge are also determined; the bottom point position is taken as the bottom edge position, and the vertex position is taken as the top edge position.

[0071] Here, the bottom point position can be the coordinates of the bottom point, and the vertex position can be the coordinates of the vertex.

[0072] In one specific implementation, to ensure calibration accuracy, it is necessary to ensure that the calibration object is vertical in the calibration acquisition image, and that the bottom point position and the vertex position are located in the same vertical direction in the calibration acquisition image. For example, the coordinates of the vertex p2 are [960, 580], and the coordinates of the bottom point p1 are [960, 500].

[0073] In one specific implementation, the image reference position is the lower baseline, which is the horizontal line passing through the bottom point of the calibration object in the calibration acquisition image. Before determining the image calibration height of the calibration object based on the bottom edge position and the top edge position, the bottom point in the bottom edge and the vertex in the top edge are also determined. The bottom point position is taken as the bottom edge position, and the vertex position is taken as the top edge position. At this time, the image calibration height of the calibration object is determined based on the bottom edge position and the top edge position, specifically: the image calibration height of the calibration object is determined based on the bottom point position and the vertex position; the image reference position is determined based on the bottom edge position, specifically: the horizontal line where the bottom point position is located is taken as the lower baseline.

[0074] The image calibration height of the calibration object can be determined by counting the number of vertical pixels between the base point and the vertex point. For example, if the coordinates of the vertex p2 are [960, 580] and the coordinates of the base point p1 are [960, 500], then the image calibration height of the calibration object (i.e., the calibration pixel height of the calibration object) can be determined to be 80 pixels.

[0075] In one specific implementation, the distance between the vehicle and the calibration object is determined based on the image calibration height and the acquisition parameters of the vehicle-mounted image acquisition device, and is used as the calibration distance. Specifically, the calibration distance from the vehicle to the calibration object is calculated by combining the acquisition parameters of the vehicle-mounted image acquisition device (including the focal length of the lens of the vehicle-mounted image acquisition device, the image sensor size, the image resolution, etc.) and the image calibration height of the calibration object, using the thin lens formula and the magnification formula.

[0076] Please see Figure 5 , Figure 5 This is a schematic diagram of a framework of an embodiment of the vehicle height restriction detection device provided in this application. The vehicle height restriction detection device 50 includes an acquisition module 51, a monitoring module 52, and a detection module 53. The acquisition module 51 is used to acquire the screen reference position of the vehicle-mounted image acquisition device; wherein, the screen reference position is obtained by pre-calibration of the vehicle-mounted image acquisition device, and the screen reference position represents the position of the calibration object at the calibration distance in the calibration acquisition screen of the vehicle-mounted image acquisition device; the monitoring module 52 is used to monitor the position of the road height restriction facility in the current acquisition screen of the vehicle-mounted image acquisition device during vehicle travel; the detection module 53 is used to perform height restriction detection on the vehicle based on the image facility height of the road height restriction facility in the current acquisition screen in response to the screen reference position of the road height restriction facility in the current acquisition screen, and obtain the height restriction detection result; wherein, the height restriction detection result is used to characterize whether the vehicle can pass through the road height restriction facility.

[0077] The reference position of the above-mentioned image is the lower baseline, which is the horizontal line passing through the bottom point of the calibration object in the calibration acquisition image. The position of the road height restriction facility in the current acquisition image is the position of the lower edge of the road height restriction facility in the current acquisition image. The reference position of the road height restriction facility in the current acquisition image includes: the lower edge of the road height restriction facility coincides with the lower baseline, or the target position point of the lower edge of the road height restriction facility is located on the lower baseline.

[0078] The target location point along the lower edge of the aforementioned facility includes the midpoint of the lower edge of the facility.

[0079] The detection module 53 is used to detect vehicle height restrictions based on the image height of the road height restriction facility in the current acquisition screen, and obtain the height restriction detection result. This includes: acquiring the image height of the road height restriction facility in the current acquisition screen; determining the height restriction detection result based on the height difference between the facility's representative height and the vehicle's representative height; wherein the facility's representative height is the image facility height, the vehicle's representative height is the image vehicle height, the image vehicle height represents the vehicle height mapped to the calibrated acquisition screen, or the facility's representative height is the actual facility height obtained by mapping the image facility height to the actual three-dimensional space, and the vehicle's representative height is the actual vehicle height in the actual three-dimensional space.

[0080] Wherein, the above-mentioned facility representative height is the image facility height, the vehicle representative height is the image vehicle height, the image facility height represents the distance between the lower edge and the upper edge of the road height restriction facility in the current captured image, the image reference position is the lower baseline, the lower baseline is the horizontal line passing through the bottom point of the calibration object in the calibration captured image, and the lower edge of the facility is the image reference position; the detection module 53 is used to determine the height restriction detection result based on the height difference between the facility representative height and the vehicle representative height, including: extracting the upper edge of the road height restriction facility from the current captured image; and determining the upper baseline using the lower baseline and the image vehicle height; and determining the height restriction detection result based on the positional relationship between the upper baseline and the upper edge of the facility.

[0081] Wherein, the above-mentioned facility representative height is the actual facility height obtained by mapping the image facility height to the actual three-dimensional space, and the vehicle representative height is the actual vehicle height in the actual three-dimensional space; the detection module 53 is used to determine the height limit detection result based on the height difference between the facility representative height and the vehicle representative height, including: mapping the image facility height to the actual three-dimensional space to obtain the actual facility height; and determining the height limit detection result based on the height difference between the actual vehicle height and the actual facility height.

[0082] The detection module 53 is used to determine the height restriction detection result based on the positional relationship between the upper baseline and the upper edge of the facility, or based on the height difference between the actual vehicle height and the actual facility height, including: determining that the vehicle can pass through the road height restriction facility in response to the facility's representative height being higher than the vehicle's representative height; and determining that the vehicle cannot pass through the road height restriction facility in response to the facility's representative height being lower than or equal to the vehicle's representative height.

[0083] The vehicle height restriction detection device includes a calibration module 54, which is used to calibrate the vehicle-mounted image acquisition device. The calibration module 54 includes: acquiring an image of the calibration object using the vehicle-mounted image acquisition device to obtain a calibration acquisition image; extracting the bottom edge position and top edge position of the calibration object from the calibration acquisition image; determining the image calibration height of the calibration object based on the bottom edge position and top edge position, and determining the distance between the vehicle and the calibration object based on the image calibration height and the acquisition parameters of the vehicle-mounted image acquisition device, as the calibration distance; and determining the image reference position based on the bottom edge position.

[0084] Wherein, the aforementioned image reference position is the lower baseline, which is the horizontal line passing through the bottom point of the calibration object in the calibration acquisition image; the calibration module 54 is used to determine the image calibration height of the calibration object based on the bottom edge position and the top edge position, including: determining the bottom point in the bottom edge and the vertex in the top edge; taking the bottom point position as the bottom edge position, and taking the vertex position as the top edge position; the calibration module 54 is used to determine the image calibration height of the calibration object based on the bottom edge position and the top edge position, including: determining the image calibration height of the calibration object based on the bottom point position and the vertex position; the calibration module 54 is used to determine the image reference position based on the bottom edge position, including: taking the horizontal line where the bottom point position is located as the lower baseline.

[0085] The height restriction detection result indicates that the vehicle cannot pass through the road height restriction facility; the detection module 53 is used to send alarm information to the user; and / or, the vehicle image acquisition device includes a driving recorder.

[0086] Please see Figure 6 , Figure 6 This is a schematic diagram of the framework of an embodiment of the vehicle-mounted image acquisition device provided in this application. The vehicle-mounted image acquisition device 60 includes a memory 61 and a processor 62 coupled to each other. The memory 61 stores program instructions, and the processor 62 is used to execute the program instructions to implement the steps in any of the vehicle height limit detection method embodiments described above. Specifically, the vehicle-mounted image acquisition device 60 may include, but is not limited to, desktop computers, laptops, servers, mobile phones, tablets, etc., and is not limited thereto.

[0087] Specifically, processor 62 controls itself and memory 61 to implement the steps in any of the vehicle height restriction detection method embodiments described above. Processor 62 can also be referred to as a CPU (Central Processing Unit). Processor 62 may be an integrated circuit chip with signal processing capabilities. Processor 62 can also be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor. Furthermore, processor 62 can be implemented using integrated circuit chips.

[0088] Please see Figure 7 , Figure 7 This is a schematic diagram of a framework of an embodiment of the computer-readable storage medium provided in this application. The computer-readable storage medium 70 stores program instructions 71 that can be executed by a processor. The program instructions 71 are used to implement the steps in any of the vehicle height restriction detection method embodiments described above.

[0089] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0090] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.

[0091] In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the apparatus implementations 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 system, 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.

[0092] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0093] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0094] If the integrated unit is implemented as 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 this application, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0095] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the individual through pop-up information or by asking the individual to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0096] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for detecting vehicle height restrictions, characterized in that, The method includes: Obtain the reference position of the image acquisition device; wherein, the reference position is obtained by pre-calibrating the image acquisition device, and the reference position indicates the position of the calibration object at the calibration distance in the calibration acquisition image of the image acquisition device. During vehicle operation, the location of road height restriction facilities in the current captured image of the vehicle-mounted image acquisition device is monitored; In response to the road height restriction facility being located at a reference position in the currently captured image, the vehicle is subjected to height restriction detection based on the image facility height of the road height restriction facility in the currently captured image, and a height restriction detection result is obtained; wherein, the height restriction detection result is used to characterize whether the vehicle can pass through the road height restriction facility.

2. The method according to claim 1, characterized in that, The reference position of the image is the lower baseline, which is the horizontal line passing through the bottom point of the calibration object in the calibration acquisition image. The position of the road height restriction facility in the current acquisition image is the position of the lower edge of the road height restriction facility in the current acquisition image. The reference position of the road height restriction facility in the currently captured image includes: the lower edge of the road height restriction facility coincides with the lower baseline, or the target position point of the lower edge of the road height restriction facility is located on the lower baseline.

3. The method according to claim 2, characterized in that, The target location point along the lower edge of the facility includes the midpoint of the lower edge of the facility.

4. The method according to claim 1, characterized in that, The method of detecting the height of the vehicle based on the image height of the road height restriction facility in the currently captured frame, and obtaining the height restriction detection result, includes: Obtain the height of the road height restriction facility in the currently captured image; The height restriction detection result is determined based on the height difference between the facility representative height and the vehicle representative height; wherein, the facility representative height is the image facility height, the vehicle representative height is the image vehicle height, and the image vehicle height represents the vehicle height mapped to the calibration acquisition screen; or, the facility representative height is the actual facility height obtained by mapping the image facility height to the actual three-dimensional space, and the vehicle representative height is the actual vehicle height in the actual three-dimensional space.

5. The method according to claim 4, characterized in that, The facility represents the height of the image facility, the vehicle represents the height of the image vehicle, the image facility height represents the distance between the lower edge and the upper edge of the road height restriction facility in the current captured image, the image reference position is the lower baseline, the lower baseline is the horizontal line passing through the bottom point of the calibration object in the calibration captured image, and the lower edge of the facility is the image reference position; The determination of the height restriction detection result based on the height difference between the representative height of the facility and the representative height of the vehicle includes: Extract the upper edge of the road height restriction facility from the currently captured image; And, using the lower baseline and the image vehicle height, the upper baseline is determined; The height restriction detection result is determined based on the positional relationship between the upper baseline and the upper edge of the facility.

6. The method according to claim 4, characterized in that, The facility representative height is the actual facility height obtained by mapping the image facility height to actual three-dimensional space, and the vehicle representative height is the actual vehicle height in the actual three-dimensional space; determining the height limit detection result based on the height difference between the facility representative height and the vehicle representative height includes: The actual facility height is obtained by mapping the image facility height to the actual three-dimensional space; The height restriction detection result is determined based on the height difference between the actual vehicle height and the actual facility height.

7. The method according to claim 5 or 6, characterized in that, Determining the height restriction detection result based on the positional relationship between the upper baseline and the upper edge of the facility, or determining the height restriction detection result based on the height difference between the actual vehicle height and the actual facility height, includes: In response to the fact that the height represented by the facility is higher than the height represented by the vehicle, it is determined that the vehicle can pass through the road height restriction facility; In response to the fact that the height represented by the facility is less than or equal to the height represented by the vehicle, it is determined that the vehicle cannot pass through the road height restriction facility.

8. The method according to claim 1, characterized in that, The steps for calibrating vehicle-mounted image acquisition equipment include: The vehicle-mounted image acquisition device is used to acquire images of the calibration object, resulting in a calibration acquisition image. Extract the bottom edge position and top edge position of the calibration object from the calibration acquisition image; Based on the bottom edge position and the top edge position, the image calibration height of the calibration object is determined, and based on the image calibration height and the acquisition parameters of the vehicle-mounted image acquisition device, the distance between the vehicle and the calibration object is determined as the calibration distance; And, based on the bottom edge position, the image reference position is determined.

9. The method according to claim 8, characterized in that, The reference position of the image is the lower baseline, which is a horizontal line passing through the bottom point of the calibration object in the calibration acquisition image; Before determining the image calibration height of the calibrator based on the bottom edge position and the top edge position, the method further includes: Determine the bottom point of the bottom edge and the vertex of the top edge; The bottom point position is taken as the bottom edge position, and the vertex position is taken as the top edge position; Determining the image calibration height of the calibration object based on the bottom edge position and the top edge position includes: Based on the base point position and the vertex position, determine the image calibration height of the calibration object; Determining the image reference position based on the bottom edge position includes: The horizontal line where the bottom point is located is taken as the lower baseline.

10. The method according to claim 1, characterized in that, The height restriction detection result indicates that the vehicle cannot pass through the road height restriction facility; the method further includes: Send alarm information to users; And / or, The vehicle-mounted image acquisition device includes a dashcam.

11. A vehicle-mounted image acquisition device, characterized in that, The vehicle-mounted image acquisition device includes a processor and a memory, the memory being used to store program instructions, and the processor being used to execute the program instructions to implement the vehicle height limit detection method as described in any one of claims 1-10.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program instructions that can be executed to implement the vehicle height restriction detection method as described in any one of claims 1-10.

Images