Method, device and system for obtaining vehicle state, storage medium and vehicle
By acquiring images through an onboard camera, analyzing height deviations, calculating loads, and adjusting suspension height, the problem of the vehicle surround view system's inability to dynamically adjust is solved, improving the surround view stitching effect and driving safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- VALEO INTERIOR CONTROLS (SHENZHEN) CO LTD
- Filing Date
- 2024-10-24
- Publication Date
- 2026-04-24
AI Technical Summary
Existing vehicle surround view systems cannot dynamically obtain vehicle load, resulting in poor stitching of the vehicle surround view view and an inability to adjust the position of the vehicle camera according to the vehicle load.
Images are acquired using an onboard camera, and image analysis is performed to determine the current height. The height deviation is calculated, and the vehicle load is determined based on the height deviation. The suspension height is then adjusted to adapt to load changes, and a machine learning model is used for image processing and stitching.
Dynamically obtain vehicle load, improve the stitching effect of surround view, enhance the driver's understanding of the vehicle's surrounding environment, and improve driving safety and experience.
Smart Images
Figure CN121917031A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to vehicles, and more particularly to methods, apparatus, systems, storage media, and vehicles for obtaining vehicle status. Background Technology
[0002] A surround-view view of a vehicle can be obtained by stitching together images captured by multiple onboard cameras. This surround-view view can then provide users such as the driver with a panoramic view of the area around the vehicle. For example, a surround-view view can provide an all-around perspective, assist parking, improve driving safety, and enhance the driving experience.
[0003] When stitching together images captured by multiple vehicle-mounted cameras to obtain a surround-view view, the positions of the vehicle cameras need to be calibrated. For example, the positions of the vehicle cameras can be calibrated during the end-of-line (EOL) inspection after vehicle production. Furthermore, during vehicle operation, motion compensation can be performed on the positions of the vehicle cameras based on motion information.
[0004] However, existing vehicle surround view systems cannot dynamically obtain vehicle load, nor can they adjust the position of the vehicle camera according to the vehicle load, resulting in poor stitching effect of the vehicle surround view view. Summary of the Invention
[0005] This disclosure provides a method for obtaining vehicle status, comprising: acquiring one or more images via one or more vehicle-mounted cameras, and performing image analysis on the one or more images to determine the current height of the one or more vehicle-mounted cameras; obtaining a first height deviation of the one or more vehicle-mounted cameras based on the current height of the one or more vehicle-mounted cameras and the theoretical height of the vehicle-mounted cameras when the vehicle is unloaded; and determining the current load of the vehicle based on the first height deviation of the one or more vehicle-mounted cameras.
[0006] The method according to embodiments of this disclosure further includes: obtaining a second height deviation of the one or more vehicle-mounted cameras based on the current height of the one or more vehicle-mounted cameras and the standard installation height of the one or more vehicle-mounted cameras; and adjusting the suspension height of the vehicle based on the second height deviation of the one or more vehicle-mounted cameras.
[0007] According to an embodiment of the present disclosure, performing image analysis on the one or more images includes processing the one or more images based on a pre-trained machine learning model.
[0008] According to the method of embodiments of the present disclosure, the one or more vehicle-mounted cameras include at least a front vehicle-mounted camera located in front of the vehicle, a rear vehicle-mounted camera located behind the vehicle, a left vehicle-mounted camera located on the left side of the vehicle, and a right vehicle-mounted camera located on the right side of the vehicle, and wherein obtaining the current height of the one or more vehicle-mounted cameras of the vehicle includes obtaining the current height of the front vehicle-mounted camera, the rear vehicle-mounted camera, the left vehicle-mounted camera, and the right vehicle-mounted camera respectively.
[0009] According to an embodiment of the present disclosure, obtaining a first height deviation of the one or more vehicle-mounted cameras of the vehicle includes: obtaining first height deviations of a front vehicle-mounted camera, a rear vehicle-mounted camera, a left vehicle-mounted camera, and a right vehicle-mounted camera, respectively; and performing a weighted summation on the first height deviations of the front vehicle-mounted camera, the rear vehicle-mounted camera, the left vehicle-mounted camera, and the right vehicle-mounted camera to obtain a weighted height deviation as the first height deviation of the one or more vehicle-mounted cameras.
[0010] According to the method of an embodiment of the present disclosure, in the weighted summation process, the weight of the first height deviation of the rear vehicle camera is higher than the weight of the first height deviations of the front vehicle camera, the left vehicle camera, and the right vehicle camera.
[0011] According to an embodiment of the present disclosure, determining the current load of a vehicle includes: obtaining, based on the correspondence between the theoretical height values of one or more on-board cameras under different load states of the vehicle and the load of the vehicle, the theoretical load difference between the vehicle under full load and the vehicle under no-load conditions, and the theoretical height difference of one or more on-board cameras of the vehicle under full load and the vehicle under no-load conditions; dividing the product of the theoretical load difference between the vehicle under full load and the vehicle under no-load conditions and a first height deviation of the one or more on-board cameras by the theoretical height difference of the one or more on-board cameras of the vehicle under full load and the vehicle under no-load conditions, to obtain the current load of the vehicle.
[0012] The method according to an embodiment of the present disclosure further includes: issuing an overload warning when the current load of the vehicle exceeds the theoretical full load of the vehicle.
[0013] The method according to embodiments of the present disclosure further includes, after adjusting the suspension height of the vehicle, acquiring multiple images using each of the one or more on-board cameras, and stitching the multiple images together to form a surround view image.
[0014] This disclosure provides a non-transitory computer storage medium having instructions stored thereon that, when executed by a processor, cause the processor to perform the method described above.
[0015] This disclosure provides a vehicle status acquisition device, comprising: a height acquisition module configured to acquire one or more images via one or more vehicle-mounted cameras, and perform image analysis on the one or more images to determine the current height of the one or more vehicle-mounted cameras; a height deviation acquisition module configured to obtain a first height deviation of the one or more vehicle-mounted cameras based on the current height of the one or more vehicle-mounted cameras and the theoretical height of the vehicle-mounted cameras in a vehicle-unloaded state; and a load acquisition module configured to determine the current load of the vehicle based on the first height deviation of the one or more vehicle-mounted cameras.
[0016] This disclosure provides a vehicle status acquisition system, comprising: one or more vehicle-mounted cameras configured to acquire one or more images; and a processor coupled to the one or more vehicle-mounted cameras and configured to: perform image analysis on the one or more images to determine the current height of the one or more vehicle-mounted cameras; obtain a first height deviation of the one or more vehicle-mounted cameras based on the current height of the one or more vehicle-mounted cameras and a theoretical height of the vehicle-mounted cameras in a vehicle-unloaded state; and determine the current load of the vehicle based on the first height deviation of the one or more vehicle-mounted cameras.
[0017] This disclosure provides a vehicle including at least one of the non-transitory computer storage medium, the device, and the system described above.
[0018] The method, apparatus, system, and storage medium disclosed herein for obtaining vehicle status allow for dynamic acquisition of vehicle loads and adaptive adjustment of vehicle status in response to different vehicle loads, thereby improving the surround-view view obtained by stitching together images acquired by the vehicle's onboard cameras. Therefore, this can help drivers better understand the environment surrounding the vehicle, improving driving safety and driving experience. Attached Figure Description
[0019] The above and other aspects, features, and advantages of specific embodiments of the present disclosure will become clearer from the following description taken in conjunction with the accompanying drawings, in which:
[0020] Figure 1 This is a flowchart of a method for obtaining vehicle status according to an embodiment of the present disclosure.
[0021] Figure 2 This is a flowchart of another method for obtaining vehicle status according to embodiments of the present disclosure.
[0022] Figure 3 This is a schematic diagram illustrating the determination of the current load of a vehicle according to embodiments of the present disclosure.
[0023] Figure 4It is a non-transitory computer-readable storage medium according to embodiments of the present disclosure.
[0024] Figure 5 This is a schematic diagram of a vehicle status acquisition device according to an embodiment of the present disclosure.
[0025] Figure 6 This is a schematic diagram of a vehicle status acquisition system according to an embodiment of the present disclosure.
[0026] Figure 7 This is a schematic diagram of a vehicle according to an embodiment of the present disclosure. Detailed Implementation
[0027] Before proceeding with the detailed description below, it may be advantageous to define certain words and phrases used throughout this disclosure. The terms “comprising” and “including” and their derivatives mean, but are not limited to, “including”. The phrase “at least one”, when used with a list of items, means that different combinations of one or more of the listed items may be used, and that only one item in the list may be required. For example, “at least one of A, B, and C” includes any one of the following combinations: A, B, C, A and B, A and C, B and C, A and B and C.
[0028] Definitions of other specific words and phrases are provided throughout this disclosure. Those skilled in the art will understand that, in many, if not most, cases, such definitions apply to the prior and future use of the words and phrases thus defined.
[0029] The various embodiments of the principles of this disclosure described below in conjunction with the accompanying drawings are for illustrative purposes only and should not be construed as limiting the scope of this disclosure in any way. Those skilled in the art will understand that the principles of this disclosure can be implemented in any suitably arranged system or device. In some cases, the actions described in this disclosure may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific order or sequential sequence to achieve the desired result. In certain embodiments, multitasking and parallel processing may be advantageous.
[0030] The text and accompanying drawings are provided by way of example only to aid in understanding this disclosure. They should not be construed as limiting the scope of the claims appended to this disclosure in any way. Throughout the drawings, the same reference numerals generally indicate the same elements. Although certain embodiments and examples have been provided, it will be apparent to those skilled in the art, based on the content of this disclosure, that changes may be made to the illustrated embodiments and examples without departing from the scope of this disclosure.
[0031] In existing vehicle surround view systems, to achieve better stitching results when combining images captured by multiple onboard cameras to obtain a surround view, the positions of the vehicle cameras can be calibrated during the end-of-life (EOL) process after vehicle production. Furthermore, during vehicle operation, motion compensation can be performed on the vehicle camera positions based on motion information. Camera position calibration and motion compensation can be based on factors such as vehicle turning signals, door status, and vehicle speed. However, existing vehicle surround view systems cannot adjust the vehicle camera positions according to the vehicle's load, resulting in poor stitching quality of the surround view.
[0032] Therefore, there is a need for a system that can dynamically acquire vehicle load and adjust the vehicle's state based on that load, thereby improving the surround-view view obtained by stitching together images acquired by the vehicle's onboard cameras. This would help drivers better understand the environment around the vehicle, improving driving safety and the driving experience.
[0033] Figure 1 This is a flowchart of a method for obtaining vehicle status according to embodiments of the present disclosure. Figure 1 As shown, the method for obtaining the vehicle status includes steps S110-S130.
[0034] In S110, one or more images can be acquired through one or more vehicle-mounted cameras, and image analysis can be performed on the one or more images to determine the current height of the one or more vehicle-mounted cameras. Furthermore, corresponding distance sensors can be configured for the one or more vehicle-mounted cameras to obtain their current height. However, this disclosure is not limited to this; other methods of obtaining the current height of one or more vehicle-mounted cameras are also possible.
[0035] In S120, a first height deviation of one or more vehicle-mounted cameras can be obtained based on the current height of one or more vehicle-mounted cameras and the theoretical height of the vehicle-mounted cameras when the vehicle is unloaded. The theoretical height when the vehicle is unloaded can be pre-written into the vehicle's internal memory.
[0036] In S130, the current load of the vehicle can be determined based on a first height deviation of one or more vehicle-mounted cameras. For example, in response to the first height deviation indicating that the current height of one or more vehicle-mounted cameras is lower than the theoretical height of one or more vehicle-mounted cameras when the vehicle is unloaded, a first load of the vehicle can be determined. For example, in response to the first height deviation indicating that the current height of one or more vehicle-mounted cameras is lower than the theoretical height of one or more vehicle-mounted cameras when the vehicle is unloaded, a second load of the vehicle can be determined.
[0037] Figure 2This is a flowchart of another method for obtaining vehicle status according to embodiments of this disclosure. Figure 2 As shown, the method for adjusting the vehicle status also includes steps S210-S220. Figure 2 Zhongyu Figure 1 Similar steps will not be described in detail to avoid redundancy.
[0038] In S110, one or more images can be acquired through one or more vehicle-mounted cameras, and image analysis can be performed on these images to determine the current height of the one or more vehicle-mounted cameras. For example, performing image analysis on the one or more images can include processing the one or more images based on a pre-trained machine learning model. The machine learning model can include optical flow algorithms. Optical flow methods can include pixel-level and region-level optical flow analysis algorithms, such as the Lucas-Kanade algorithm, the Farneback algorithm, etc. Furthermore, the machine learning model can include image segmentation algorithms, such as threshold-based segmentation, edge segmentation, region segmentation, etc. The above machine learning models are provided merely as examples; other machine learning models or image analysis algorithms can also be used.
[0039] One or more vehicle-mounted cameras may include at least four vehicle-mounted cameras. For example, a front vehicle-mounted camera located at the front of the vehicle, a rear vehicle-mounted camera located at the rear of the vehicle, a left vehicle-mounted camera located on the left side of the vehicle, and a right vehicle-mounted camera located on the right side of the vehicle. Obtaining the current height of one or more vehicle-mounted cameras includes obtaining the heights of the front, rear, left, and right vehicle-mounted cameras, respectively. Those skilled in the art will understand that the number of vehicle-mounted cameras is provided only as an example, and the number of vehicle-mounted cameras according to embodiments of this disclosure may be more or less.
[0040] In S120, a first height deviation of one or more vehicle-mounted cameras can be obtained based on the current height of one or more vehicle-mounted cameras and their theoretical height when the vehicle is unloaded. Obtaining the first height deviation of one or more vehicle-mounted cameras can include obtaining the first height deviation of the front vehicle-mounted camera, rear vehicle-mounted camera, left vehicle-mounted camera, and right vehicle-mounted camera separately. For example, the current height of the front vehicle-mounted camera, rear vehicle-mounted camera, left vehicle-mounted camera, and right vehicle-mounted camera can be obtained through methods such as image analysis or others. The corresponding first height deviation is obtained based on the current height of the front vehicle-mounted camera, rear vehicle-mounted camera, left vehicle-mounted camera, and right vehicle-mounted camera and their theoretical height when the vehicle is unloaded. After obtaining the corresponding first height deviation, a weighted summation can be performed on the first height deviations of the front vehicle-mounted camera, rear vehicle-mounted camera, left vehicle-mounted camera, and right vehicle-mounted camera to obtain a weighted height deviation as the first height deviation of one or more vehicle-mounted cameras. The first height deviation of some of the one or more vehicle-mounted cameras may be more sensitive to load changes. Therefore, in the above weighted summation process, the first height deviation of some of the vehicle-mounted cameras can be assigned a higher weight than the first height deviation of the remaining vehicle-mounted cameras. For example, the weight of the first height deviation of the rear vehicle-mounted camera can be set higher than the weight of the first height deviation of the front, left, and right vehicle-mounted cameras. As an example, see equation (1):
[0041] ΔH1=(ΔH RV1 *40%+ΔH FV1 *20%+ΔH MVL1 *20%+ΔH MVR1 *20%) (1)
[0042] In Equation 1, ΔH1 can represent the first height deviation of one or more vehicle-mounted cameras, ΔH RV1 This can represent the first height deviation of the rear-mounted camera, ΔH. FV1 This can represent the first height deviation of the front vehicle-mounted camera, ΔH. MVL1 This can represent the first height deviation of the left-side vehicle-mounted camera, ΔH. MVR1 This can represent the first height deviation of the right-side vehicle-mounted camera. As shown in Equation 1, ΔH RV1 It can be set with a weight of 40%, ΔH FV1 A weight of 20% can be set, ΔH MVL1 A weight of 20% can be set, ΔH MVR1A weight of 20% can be set. In this way, a more accurate first height deviation of one or more vehicle-mounted cameras can be obtained. Those skilled in the art will understand that the specific weight values described above are provided as examples only, and other appropriate weights can be set according to specific configurations.
[0043] In S130, the current load of the vehicle can be determined based on a first height deviation of one or more vehicle-mounted cameras. For example, the current load of the vehicle can be determined based on the correspondence between the theoretical height values of one or more vehicle-mounted cameras under different load conditions of the vehicle and the vehicle's load, as well as the first height deviation of one or more vehicle-mounted cameras.
[0044] In S210, a second height deviation of one or more vehicle-mounted cameras can be obtained based on the current height of one or more vehicle-mounted cameras and their standard mounting height. The standard mounting height of the one or more vehicle-mounted cameras can be the standard mounting height calibrated during the EOL (End-of-Life) process. The standard mounting height of the one or more vehicle-mounted cameras can correspond to the standard mounting height calibrated under one of the following conditions: fully loaded, unloaded, partially loaded, or other load conditions. Obtaining the second height deviation of the vehicle's one or more vehicle-mounted cameras can include obtaining the second height deviations of the front, rear, left, and right vehicle-mounted cameras respectively. For example, the current heights of the front, rear, left, and right vehicle-mounted cameras can be obtained through methods such as image analysis or others. The corresponding second height deviations are obtained based on the current heights of the front, rear, left, and right vehicle-mounted cameras and their standard mounting heights, respectively. After obtaining the corresponding second height deviation, a weighted summation can be performed on the second height deviations of the front, rear, left, and right vehicle-mounted cameras to obtain a weighted height deviation as the second height deviation of one or more vehicle-mounted cameras. The second height deviation of some of the vehicle-mounted cameras may be more sensitive to load changes. Therefore, in the above weighted summation process, the second height deviation of some of the vehicle-mounted cameras can be given a higher weight than the second height deviation of the remaining vehicle-mounted cameras. For example, the weight of the second height deviation of the rear vehicle-mounted camera can be set higher than the weight of the second height deviations of the front, left, and right vehicle-mounted cameras. As an example, see equation (2):
[0045] ΔH2=(ΔH RV2 *40%+ΔH FV *20%+ΔH MVL2 *20%+ΔH MVR2 *20%) (2)
[0046] In Equation 2, ΔH2 can represent the second height deviation of one or more vehicle-mounted cameras, ΔH RV2 This can represent the second height deviation of the rear-mounted camera, ΔH. FV2 This can represent the second height deviation of the front vehicle-mounted camera, ΔH. MVL2 This can represent the second height deviation of the left-side vehicle-mounted camera, ΔH. MVR2 This can represent the second height deviation of the right-side vehicle-mounted camera. As shown in Equation 2, ΔH RV2 It can be set with a weight of 40%, ΔH FV2 A weight of 20% can be set, ΔH MVL2 A weight of 20% can be set, ΔH MVR2 A weight of 20% can be set. In this way, a more accurate second height deviation of one or more vehicle-mounted cameras can be obtained. Those skilled in the art will understand that the specific weight values described above are provided as examples only, and other appropriate weights can be set according to specific configurations.
[0047] In S220, the vehicle's suspension height can be adjusted based on a second height deviation of one or more vehicle-mounted cameras. For example, in response to the second height deviation indicating that the current height of one or more vehicle-mounted cameras is lower than the standard mounting height of one or more vehicle-mounted cameras by a first height value, the vehicle's suspension height can be adjusted to increase the suspension height by the first height value, thereby compensating for changes in the height of one or more vehicle-mounted cameras due to the current load. For example, in response to the second height deviation indicating that the current height of one or more vehicle-mounted cameras is higher than the standard mounting height of one or more vehicle-mounted cameras by a second height value, the vehicle's suspension height can be adjusted to decrease the suspension height by the second height value, thereby compensating for changes in the height of one or more vehicle-mounted cameras due to the current load. For example, after adjusting the vehicle's suspension height, one or more images can be obtained from the front vehicle-mounted camera, rear vehicle-mounted camera, left vehicle-mounted camera, and right vehicle-mounted camera to stitch the one or more images into a surround-view image after adjusting the vehicle's state. Since the height of one or more vehicle-mounted cameras is adjusted to the standard mounting height, the stitching effect of the surround-view image after adjusting the vehicle's state will be improved, thereby helping the driver better understand the environment around the vehicle, improving driving safety and driving experience.
[0048] Reference Figure 3 S130 is described in detail. Figure 3 This is a schematic diagram illustrating the determination of the current load of a vehicle according to embodiments of the present disclosure.
[0049] For example, based on the correspondence between the theoretical height values of one or more on-board cameras under different vehicle load conditions and the vehicle load, the theoretical load difference between a fully loaded and unloaded vehicle, as well as the theoretical height difference of one or more on-board cameras under the same conditions, can be obtained. For instance, the theoretical height difference ΔH between one or more on-board cameras under fully loaded and unloaded vehicle conditions can be obtained. max Furthermore, it can obtain the theoretical load difference ΔW between a fully loaded and unloaded vehicle. For example, ΔH max ΔW can be pre-written into the vehicle's internal memory. The theoretical load difference ΔW between the vehicle being fully loaded and unloaded can be divided by the theoretical height difference ΔH between one or more onboard cameras of the vehicle being fully loaded and unloaded. max This is used to obtain the scaling factor. The scaling factor represents the difference ΔW between the theoretical load of the vehicle when it is fully loaded and when it is unloaded, and the difference ΔH between the theoretical height of one or more onboard cameras of the vehicle when it is fully loaded and when it is unloaded. max The correlation between them. That is, the initial height deviation of one or more cameras under different loads is linearly related to the load. For example, this can be achieved by considering the theoretical height difference ΔH between one or more onboard cameras of a vehicle under half-load and unloaded conditions. maxh And the theoretical load difference ΔW between a fully loaded and unloaded vehicle. h Obtain the scaling factor. Those skilled in the art will understand that other methods of obtaining the scaling factor are also possible. As shown in equation (3), the current load k of the vehicle can be obtained by multiplying the scaling factor by the first height deviation ΔH1 of one or more vehicle-mounted cameras.
[0050] k=ΔW*ΔH1 / ΔH max (3)
[0051] As shown in equation (3), the product ΔW of the theoretical load difference between the vehicle under full load and the vehicle under no load and the first height deviation of one or more vehicle-mounted cameras can be divided by the theoretical height difference ΔH of the vehicle under full load and the vehicle under no load. max To obtain the current load of the vehicle. Equation (3) is provided only as an example; other equations for calculating the current load k can be obtained by obtaining the scaling factor in other ways.
[0052] In addition, a load status percentage can be provided to users such as drivers based on the current load k, so that an overload warning can be issued when necessary.
[0053] In one embodiment, the load state percentage can be calculated using equation (4):
[0054] Q=(k / ΔW) *100% (4)
[0055] In equation (4), Q is the load percentage, k is the current load, and ΔW is the theoretical load difference between the vehicle under full load and unloaded conditions. Substituting equation (3) into equation (4) yields equation (5):
[0056] Q=(ΔH1 / ΔH max ) *100% (5)
[0057] As shown in equation (5), when Q exceeds 100%, it means that the current load of the vehicle exceeds the theoretical full load of the vehicle, and an overload warning can be issued to the user.
[0058] In another embodiment, the load state percentage can be calculated using equation (6):
[0059] Q = (k / Wf) * 100% (6)
[0060] In equation (6), Q is the load percentage, k is the current load, and Wf is the total weight of the vehicle and load when the vehicle is fully loaded. Substituting equation (3) into equation (6) yields equation (7):
[0061] Q=(ΔW*ΔH1 / Wf *ΔH max )*100% (7)
[0062] In another embodiment, the load state percentage can be calculated using equation (8):
[0063] Q=(k / ΔW max )*100% (8)
[0064] In equation (8), Q is the load state percentage, k is the current load, and ΔW max W is the maximum load that the vehicle can withstand. max It can be greater than the theoretical load difference ΔW between the vehicle under full load and the vehicle under no load. Substituting equation (3) into equation (8) yields equation (9):
[0065] Q=(ΔW*ΔH1 / ΔW max *ΔH max )*100% (9)
[0066] Those skilled in the art will understand that other methods are also possible to obtain the load state percentage Q.
[0067] Figure 4 It is a non-transitory computer-readable storage medium according to embodiments of the present disclosure.
[0068] like Figure 4As shown, a non-transitory readable storage medium 400 stores computer instructions 410, which, when executed by a processor, perform one or more steps of the various methods and their additional aspects as described above.
[0069] For example, the non-temporarily readable storage medium 400 may be any combination of one or more computer-readable storage media, such as a computer-readable storage medium containing program code for performing the various methods described above.
[0070] For example, when the program code is read by a computer, the computer can execute the program code stored in the computer storage medium to perform one or more steps of the various methods and additional aspects described above, such as those according to at least one embodiment of the present disclosure.
[0071] For example, the non-transitory readable storage medium may include a memory card of a smartphone, a storage component of a tablet computer, a hard disk of a personal computer, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), portable compact disc read-only memory (CD-ROM), flash memory, and other non-transitory readable storage media or any combination thereof.
[0072] Figure 5 This is a schematic diagram of a vehicle state adjustment device according to an embodiment of the present disclosure.
[0073] like Figure 5 As shown, the vehicle status acquisition device 500 may include a height acquisition module 510, a height deviation acquisition module 520, and a load acquisition module 530.
[0074] The altitude acquisition module 510 can be configured to acquire one or more images via one or more vehicle-mounted cameras, and perform image analysis on the one or more images to determine the current altitude of the one or more vehicle-mounted cameras.
[0075] The height deviation acquisition module 520 can be configured to obtain a first height deviation of one or more vehicle-mounted cameras based on the current height of one or more vehicle-mounted cameras and the theoretical height of the vehicle-mounted cameras when the vehicle is unloaded.
[0076] The load acquisition module 530 can be configured to determine the current load of the vehicle based on a first height deviation from one or more onboard cameras.
[0077] Figure 6 This is a schematic diagram of a vehicle status acquisition system according to an embodiment of the present disclosure.
[0078] like Figure 6 As shown, the vehicle status adjustment system 600 may include one or more on-board cameras 610 and a processor 620.
[0079] One or more vehicle-mounted cameras 610 can capture one or more images of the environment around the vehicle.
[0080] The processor 620 may be coupled to one or more vehicle-mounted cameras and configured to acquire one or more images through the one or more vehicle-mounted cameras, and perform image analysis on the one or more images to determine the current height of the one or more vehicle-mounted cameras; obtain a first height deviation of the one or more vehicle-mounted cameras based on the current height of the one or more vehicle-mounted cameras and the theoretical height of the vehicle-mounted cameras when the vehicle is unloaded; and determine the current load of the vehicle based on the first height deviation of the one or more vehicle-mounted cameras.
[0081] Figure 7 This is a schematic diagram of a vehicle according to an embodiment of the present disclosure.
[0082] like Figure 7 As shown, vehicle 700 may include component 710. Component 710 may be as follows: Figure 4 The non-transitory computer storage medium 400, such as Figure 5 The vehicle status acquisition device 500, and as described above Figure 6 At least one of the vehicle status acquisition systems 600.
[0083] The method, apparatus, system, storage medium, and vehicle state acquisition method disclosed herein can dynamically acquire vehicle load and adaptively adjust the vehicle state in response to different vehicle loads, thereby improving the surround view obtained by stitching together images acquired by the vehicle's onboard cameras. Therefore, it can help the driver better understand the environment around the vehicle, improving driving safety and driving experience. Furthermore, the method, apparatus, system, storage medium, and vehicle state acquisition method disclosed herein can acquire vehicle load in real time, thereby providing alerts or prompts to users such as the driver when necessary.
[0084] Although this disclosure has been described with reference to exemplary embodiments, various changes and modifications may be suggested to those skilled in the art. This disclosure is intended to cover such changes and modifications that fall within the scope of the appended claims.
[0085] Any description in this invention should not be construed as implying that any particular element, step, or function is an essential element that must be included within the scope of the claims. The scope of the patent application subject matter is defined only by the claims.
Claims
1. A method for obtaining vehicle status, comprising: One or more images are acquired using one or more vehicle-mounted cameras, and image analysis is performed on the one or more images to determine the current height of the one or more vehicle-mounted cameras; Based on the current height of the one or more vehicle-mounted cameras and their theoretical height when the vehicle is unloaded, a first height deviation of the one or more vehicle-mounted cameras is obtained; and The current load of the vehicle is determined based on a first height deviation of the one or more vehicle-mounted cameras.
2. The method according to claim 1, further comprising: Based on the current height of the one or more vehicle-mounted cameras and their standard installation height, a second height deviation of the one or more vehicle-mounted cameras is obtained; and Adjust the vehicle's suspension height based on the second height deviation from the one or more on-board cameras.
3. The method according to claim 1, wherein, Performing image analysis on the one or more images includes processing the one or more images based on a pre-trained machine learning model.
4. The method according to claim 1, wherein, The one or more vehicle-mounted cameras include at least a front vehicle-mounted camera located at the front of the vehicle, a rear vehicle-mounted camera located at the rear of the vehicle, a left vehicle-mounted camera located on the left side of the vehicle, and a right vehicle-mounted camera located on the right side of the vehicle. Obtaining the current height of one or more vehicle-mounted cameras includes obtaining the current height of the front vehicle-mounted camera, rear vehicle-mounted camera, left vehicle-mounted camera, and right vehicle-mounted camera, respectively.
5. The method according to claim 1, wherein, Obtaining the first height deviation of the one or more onboard cameras of the vehicle includes: The first height deviations of the front, rear, left, and right vehicle-mounted cameras were obtained respectively, and A weighted summation is performed on the first height deviations of the front vehicle camera, rear vehicle camera, left vehicle camera, and right vehicle camera to obtain a weighted height deviation as the first height deviation of the one or more vehicle cameras.
6. The method according to claim 5, in, In the weighted summation process, the weight of the first height deviation of the rear vehicle camera is higher than the weight of the first height deviation of the front vehicle camera, the left vehicle camera, and the right vehicle camera.
7. The method according to claim 1, wherein, Determining the vehicle's current load includes: Based on the correspondence between the theoretical height values of one or more vehicle-mounted cameras and the vehicle's load under different load conditions, the theoretical load difference between the vehicle under full load and unloaded conditions, as well as the theoretical height difference of one or more vehicle-mounted cameras under full load and unloaded conditions, are obtained. The current load of the vehicle is obtained by dividing the product of the theoretical load difference between the vehicle when fully loaded and when the vehicle is unloaded and the first height deviation of the one or more vehicle-mounted cameras by the theoretical height difference of the one or more vehicle-mounted cameras when the vehicle is fully loaded and when the vehicle is unloaded.
8. The method according to claim 2, further comprising: An overload warning is issued when the current load of the vehicle exceeds its theoretical full load capacity.
9. The method according to claim 2, further comprising, after adjusting the suspension height of the vehicle, acquiring multiple images using each of the one or more vehicle-mounted cameras, and stitching the multiple images into a surround view image.
10. A non-transitory computer storage medium having instructions stored thereon that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1-9.
11. A vehicle status acquisition device, comprising: An altitude acquisition module is configured to acquire one or more images via one or more vehicle-mounted cameras, and to perform image analysis on the one or more images to determine the current altitude of the one or more vehicle-mounted cameras; The height deviation acquisition module is configured to obtain a first height deviation of the one or more vehicle-mounted cameras based on the current height of the one or more vehicle-mounted cameras and the theoretical height of the vehicle-mounted cameras when the vehicle is unloaded. as well as The load acquisition module is configured to determine the current load of the vehicle based on a first height deviation of the one or more vehicle-mounted cameras.
12. A vehicle status acquisition system, comprising: One or more vehicle-mounted cameras are configured to acquire one or more images; as well as The processor, coupled to the one or more vehicle-mounted cameras, is configured to: Perform image analysis on the one or more images to determine the current height of the one or more vehicle-mounted cameras; Based on the current height of the one or more vehicle-mounted cameras and their theoretical height when the vehicle is unloaded, a first height deviation of the one or more vehicle-mounted cameras is obtained; and The current load of the vehicle is determined based on a first height deviation of the one or more vehicle-mounted cameras.
13. A vehicle comprising at least one of the non-transitory computer storage medium of claim 10, the apparatus of claim 11, and the system of claim 12.