Control method, control system and vehicle for vehicle trunk

Abstract

The application provides a method and system for controlling a trunk of a vehicle and a vehicle comprising the system. The method for controlling the trunk of the vehicle comprises: projecting a light pattern to a predetermined projection area in response to determining that a target object enters a predetermined range of the trunk; determining whether a change of the light pattern satisfies a preset condition; and opening the trunk in response to determining that the change of the light pattern satisfies the preset condition. The determining whether the light pattern satisfies the preset condition comprises: determining whether a deformation variable of the light pattern is greater than a first predetermined threshold.

Description

Technical Field

[0001] This application relates to the field of vehicle control, and more specifically to a control system and control method for a vehicle trunk. Background Technology

[0002] With the gradual development of intelligent vehicle control technology, there is an increasing tendency to intelligently manage various components within the vehicle in order to further facilitate user operation in various scenarios.

[0003] For example, the control of the vehicle's trunk has been changed from traditional manual control to sensor control, so that users no longer need to manually open the trunk when their hands are carrying heavy objects.

[0004] Some related technologies propose using car key / mobile terminal positioning to automatically open the trunk when a user holding the car key / mobile terminal is detected approaching. However, this method has a high false trigger rate; for example, the trunk might open even if the user is simply standing by the car chatting with a friend or just passing by.

[0005] Other related technologies propose using sensors in conjunction with a corresponding foot-lifting motion to automatically open the vehicle's trunk. However, due to the sensor's location (e.g., at the bottom of the vehicle's bumper), it usually requires the user to lift their foot to trigger the sensor. But when the object being carried is too heavy, it is difficult to lift the other foot while maintaining balance to trigger the trunk opening. Summary of the Invention

[0006] One objective of this application is to provide a method for controlling the trunk of a vehicle, the advantage of which is that the method can confirm whether the user wants to open the trunk by one or more interactions between the user and a light pattern projected at a predetermined position, thereby reducing the false triggering rate of the trunk.

[0007] Another objective of this application is to provide a system for controlling the trunk of a vehicle, which has the advantages of being able to interact with the user effectively and conveniently, and can effectively reduce the probability of the trunk being opened accidentally.

[0008] Another object of this application is to provide a computer storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements a method for controlling the trunk of a vehicle.

[0009] Other advantages and features of the invention will be fully apparent from the following detailed description and may be achieved by combinations of the means and apparatus specifically pointed out in the appended claims.

[0010] According to a first aspect of this application, a method for controlling a vehicle trunk is provided, comprising: in response to determining that a target object has entered a predetermined range within the trunk, projecting a light pattern onto a predetermined projection area; determining whether a change in the light pattern satisfies the preset conditions; and in response to determining that a change in the light pattern satisfies the preset conditions, opening the trunk. Determining whether the light pattern satisfies the preset conditions includes: determining whether the deformation of the light pattern is greater than a first predetermined threshold.

[0011] According to a second aspect of this application, a system for controlling a vehicle trunk is provided, comprising: a light projector mounted on the vehicle and configured to project a light pattern onto a predetermined projection area; and a processor configured to: project a light pattern onto the predetermined projection area in response to determining that a target object has entered a predetermined range within the trunk; determine whether a change in the light pattern satisfies the preset conditions; and open the trunk in response to the light pattern satisfying the preset conditions. Determining whether a change in the light pattern satisfies the preset conditions includes: whether the deformation of the light pattern is greater than a first predetermined threshold.

[0012] According to a third aspect of this application, this application provides a vehicle that includes the aforementioned system for controlling the vehicle's trunk.

[0013] Compared with related technologies in the field, this application has at least one of the following technical effects:

[0014] 1) By using light pattern projection, the user's need to open the trunk is confirmed through interaction with the light pattern. This can effectively prevent the trunk from opening automatically when the user approaches, thus reducing the false trigger rate of door opening.

[0015] 2) The interactive method of light patterns is simple, convenient, and technologically advanced;

[0016] 3) By using light / sound reminders, the user's need to open the trunk can be further confirmed, which can effectively prevent the user from accidentally stepping on the light pattern and opening the trunk by mistake.

[0017] 4) The entire process of opening and closing the trunk requires no contact with the trunk, ensuring user cleanliness and convenience; and

[0018] 5) The entire process of opening and closing the trunk does not require standing on one leg to complete the specified action, making the interaction process safer. Attached Figure Description

[0019] The above and other embodiments and features of this disclosure will become more apparent from the detailed description of the embodiments with reference to the accompanying drawings, in which:

[0020] Figure 1This is a schematic block diagram illustrating a system for controlling a vehicle trunk according to an embodiment of this application;

[0021] Figure 2 This is a schematic flowchart illustrating a method for controlling a vehicle trunk according to an embodiment of this application;

[0022] Figure 3 This is an exemplary application scenario diagram illustrating a method for controlling a vehicle's trunk;

[0023] Figure 4 This is a schematic flowchart illustrating step S20 according to this application;

[0024] Figure 5 This is a schematic flowchart illustrating step S220 according to another example of this application;

[0025] Figure 6 This is a schematic flowchart illustrating step S2210 for acquiring the region of interest in an image;

[0026] Figure 7 This is a schematic diagram illustrating step S2210 for obtaining the region of interest in an image;

[0027] Figure 8 This is a schematic pixel layout diagram showing the region of interest;

[0028] Figure 9 This is a schematic flowchart illustrating step S220 according to another example of this application;

[0029] Figure 10 This is a schematic flowchart illustrating step S220 according to another example of this application; and

[0030] Figure 11 This is a schematic flowchart illustrating step S20 according to another exemplary embodiment. Detailed Implementation

[0031] The invention will now be described more fully below with reference to the accompanying drawings, in which embodiments of the invention are illustrated. However, the invention may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0032] Those skilled in the art will understand that, unless otherwise stated, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the word “comprising” as used in the specification of this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or combinations thereof.

[0033] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature.

[0034] It will be understood by those skilled in the art that, unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as in the embodiments of this application.

[0035] Figure 1 This is a schematic block diagram illustrating a system for controlling a vehicle trunk according to an embodiment of this application. Figure 2 This is a schematic flowchart illustrating a method for controlling a vehicle trunk according to an embodiment of this application. Figure 3 This is an exemplary application scenario diagram illustrating a method for controlling the trunk of a vehicle.

[0036] First, refer to Figure 1 A brief description of the system used to control the vehicle's trunk.

[0037] like Figure 1 As shown, a system 10 for controlling a vehicle trunk (hereinafter referred to as the "trunk control system") according to an exemplary embodiment may include: a processor 100, a light projector 200, an image acquisition unit 300, and a memory 400.

[0038] Specifically, the processor 100 can be physically and / or communicatively connected to the light projector 200, the image acquisition unit 300, and the memory 400. Exemplarily, the processor 100 can send control signals to the light projector 200 and the image acquisition unit 300 to control them to perform corresponding actions, and can retrieve corresponding preset information from the memory 400. In this application, the method for controlling the vehicle trunk, described below, will be executed by the processor 100 controlling the corresponding components.

[0039] For example, the light projector 200 can be mounted on a vehicle. For instance, the light projector 200 can be mounted near the trunk (e.g., at the bottom of the vehicle bumper) or can be mounted on the trunk itself. Figure 3 In this application, for the convenience of description and illustration only, the light projector 200 is shown exemplarily as mounted on the trunk; however, it should be understood that this application is not limited thereto.

[0040] According to an exemplary embodiment, the light projector 200 can be configured to project a luminous image (also referred to herein as a light pattern) onto a specific location area under the control of the processor 100. As an example, the light projector 200 can project a light pattern toward a predetermined projection area on the ground. Exemplarily, the light projector 200 can be a laser projector, which may include light-emitting elements, such as those with high power, so that the light pattern it projects remains highly visible even in bright light environments.

[0041] According to another embodiment of this application, multiple light projectors 200 can be configured and installed in multiple locations in the trunk of a vehicle, such as the left, right, and / or middle positions of the trunk, to project light patterns to different locations according to the user's movement path. This will be described in detail below.

[0042] For example, the image acquisition device 300 can be mounted on a vehicle. For instance, similar to the light projector 200, the image acquisition device 300 can be mounted near the trunk of the vehicle (e.g., at the bottom of the vehicle bumper) or can be mounted on the trunk. For example, the image acquisition device 300 can be configured to be adjacent to the light projector 200.

[0043] According to an exemplary embodiment, the image acquisition device 300 can be configured to acquire images of a predetermined projection area at predetermined time intervals under the control of the processor 100. For example, the image acquisition device 300 can be a high-definition camera, and can continuously acquire a set of images of the predetermined projection area at a fixed position and a fixed viewing angle.

[0044] Next, we will refer to Figure 2 and Figure 3 A method for controlling the vehicle trunk using a trunk control system is described.

[0045] like Figure 2 As shown, according to an exemplary embodiment, a method 1000 for controlling a vehicle trunk includes:

[0046] Step S10: In response to determining that the target object has entered a predetermined range in the trunk, a light pattern is projected onto the predetermined projection area;

[0047] Step S20: Determine whether the change in the light pattern meets the preset conditions; and

[0048] Step S30: In response to the determination that the change in the emitted light pattern meets the preset conditions, open the trunk.

[0049] In one exemplary embodiment, determining whether a change in the light pattern satisfies a preset condition includes: determining whether the deformation of the light pattern is greater than a first predetermined threshold. If the deformation of the light pattern is greater than the first predetermined threshold, then the change in the light pattern is determined to satisfy the preset condition; otherwise, the change in the light pattern is determined not to satisfy the preset condition.

[0050] Reference Figure 3 This illustrates an exemplary application scenario of method 1000. Specifically, when the trunk control system 10 senses a target object OBJ approaching the trunk (i.e., entering a predetermined range of the trunk), it can use the light projector 200 to project a light pattern PAT onto a predetermined projection area on the ground. If the target object OBJ stands on the light pattern PAT, it indicates that the target object OBJ has a need to open the trunk, thereby the trunk control system 10 can control the vehicle to automatically open the trunk.

[0051] The steps of method 1000 will be described in detail below.

[0052] According to an exemplary embodiment, before step S10, method 1000 may further include step S40: determining whether the target object has entered a predetermined range of the trunk. According to an exemplary embodiment, whether the target object has entered the predetermined range of the trunk can be determined by the car key / mobile terminal positioning function.

[0053] For example, the car key / mobile terminal positioning function can be implemented using a UWB positioning method. The UWB positioning method can be based on, for example, two-way time-of-flight (TOF) methods (including single-sided TDF and double-sided TDF), and the positioning method can be, for example, a combination of one or more of TOA (Time of Arrival), TDOA (Time Difference of Arrival), and AOA (Aspect-of-Area) positioning. In this example, the target object can be a user holding a car key / mobile terminal that has been securely authenticated and successfully paired with the vehicle, thereby ensuring the security of vehicle starting.

[0054] However, this is merely an example, and this application is not limited thereto. In other examples, various other methods, such as ultrasonic ranging sensors, can be used to measure the distance between the vehicle trunk and the target object in real time.

[0055] For example, "within a predetermined range of the trunk" can mean that the distance from the vehicle's trunk in various directions is less than a preset distance. Specifically, the preset distance can be in the range of 0.5 meters to 1.5 meters, for example, it can be 1 meter. However, this is just an example, and the range of values ​​of this predetermined range can be set by the user according to their preferences. This application does not impose any specific restrictions on it.

[0056] According to an exemplary embodiment, after determining whether a target object has entered a predetermined range in the trunk, the trunk control system 10 can control the light projector 200 to project a light pattern toward a predetermined projection area on the ground.

[0057] According to one embodiment of this application, the predetermined projection area may not be fixed relative to the trunk, but may change according to the movement path of the target object. For example, when the vehicle determines, based on the car key / mobile terminal positioning function, that the target object is approaching the trunk from the left rear of the vehicle, a light pattern can be projected toward a predetermined position at the left rear of the vehicle.

[0058] However, this application is not limited to this. The predetermined projection area can be fixed or set to deviate from the movement path of the target object to avoid direct projection onto the target object (e.g., the target object's feet / shoes), thereby effectively reducing the false trigger rate. For example, when the vehicle determines that the target object is approaching the trunk from the left rear of the vehicle based on the car key / mobile terminal positioning function, a light pattern can be projected towards a predetermined position at the right rear / middle of the vehicle.

[0059] In this application, the light pattern can have various different shapes, sizes, colors, and brightnesses according to user settings. For example, the light pattern can be presented as a car pattern, a key pattern, a car logo, a footprint landmark, and other types, and this application does not specifically limit this. However, for the convenience of illustration and description, this application uses the presentation of a car pattern as an example for illustrative description. Similarly, this application does not specifically limit the size of the light pattern, which can be as follows: Figure 3 The size shown is larger than the target object's feet to facilitate the recognition of the target object standing and subsequent changes in the light pattern, but it can also be relatively small in size to reduce the false trigger rate.

[0060] Figure 4 This is a schematic flowchart illustrating step S20 according to this application.

[0061] In step S20, the trunk control system 10 can use the image acquisition unit 300 and the processor 100 to determine specific changes in the light pattern PAT caused by the standing of the target object OBJ. When the target object OBJ is standing on the light pattern PAT, at least part of the light pattern will fall on the uneven feet (or shoes) of the target object OBJ. Due to the unevenness of the projection surface of the light pattern, the shape of the light pattern may change.

[0062] According to an exemplary embodiment, in step S20, determining whether the change in the light pattern meets a preset condition may include: determining whether the deformation of the light pattern is greater than a specific threshold (e.g., a first predetermined threshold). Specifically, the image acquisition unit 300 can acquire a first image set including multiple images of a predetermined projection area at predetermined time intervals (step S210), and the processor 100 can determine whether the deformation of the light pattern is greater than the first predetermined threshold based on the first image set (step S220). In response to the deformation of the light pattern being greater than the first predetermined threshold, it is determined that the change in the light pattern meets the preset condition (step S230), thereby controlling the vehicle to open the trunk.

[0063] In this document, the first set of images may refer to a series of images of a predetermined projection area acquired over time, starting from a predetermined range where a target object is determined to enter the trunk (e.g., before the projection light pattern is formed).

[0064] As described above, the location of the predetermined projection area can be determined based on the movement path of the target object detected by the vehicle. In this case, in order to ensure that the image acquisition unit 300, which is in a fixed position, can acquire images of the predetermined projection area at different positions, the image acquisition unit 300 can freely rotate under the drive of the processor 100 to track the projection orientation of the light pattern.

[0065] However, after determining the orientation of the light pattern projection (e.g., during the acquisition of the first image set), the shooting angle of the image acquisition unit 300 can remain fixed, and all imaging parameters of the image acquisition unit 300 (such as field of view, focal length, etc.) remain unchanged. Therefore, it can be ensured that the image acquisition unit 300 can capture the first image set of the predetermined projection area from a fixed position and at the same viewing angle, thereby ensuring that the first image set can accurately record changes in the predetermined projection area over time.

[0066] According to an example of this application, in step S220, the deformation of the light pattern can be determined to be greater than a first predetermined threshold based on the changes between each group of adjacent images following the projected light pattern in the first image set. In other words, in this example, after the projected light pattern, each image can be compared with its preceding image to calculate the degree of overlap. The higher the degree of overlap, the smaller the change between adjacent images, which may also mean that the target object is less likely to be standing on the pattern. In response to the degree of overlap in adjacent images being less than a predetermined value, it is determined that the light pattern has deformed, that is, the preset condition for opening the trunk is met.

[0067] In this paper, the term "adjacent images" refers to images taken one after the other in chronological order.

[0068] However, the judgment result of this example is easily affected by changes in other areas of the predetermined projection area besides the light pattern, making it impossible to accurately detect changes in the light pattern itself.

[0069] Figure 5 This is a schematic flowchart illustrating step S220 according to another example of this application.

[0070] like Figure 5 As shown, according to another example of this application, in step S220, firstly, the region of interest including the light pattern of each image in the first image set is determined (step S2210); secondly, based on the region of interest of each group of adjacent images in the first image set, it is determined whether the deformation of the light pattern is greater than a first predetermined threshold.

[0071] Figure 6 This is a schematic flowchart illustrating step S2210 for acquiring a region of interest in an image. Figure 7 This is a schematic diagram illustrating step S2210 for acquiring the region of interest in an image. Figure 8 This is a schematic pixel layout diagram showing the region of interest. The following will refer to... Figures 6 to 8 Let me describe in detail the method for obtaining the region of interest.

[0072] like Figure 6 As shown, according to an exemplary embodiment, step S2210 of determining the region of interest including a light pattern for each image in the first image set includes: step S2211, extracting adjacent first and second images from the first image set, wherein the first image does not include a light pattern, and the second image is an image acquired after the first image and includes a light pattern; step S2212, calculating the difference between the first and second images; and step S2213, determining the region of interest based on the calculated difference.

[0073] According to an exemplary embodiment, the first image and the second image may be images captured during the projection of the light pattern.

[0074] Reference Figure 7 For example, the first image corresponds to an image P1 of a predetermined projection area taken moment before the light projector 200 begins to project the light pattern. The first image P1 may include a background portion BG, which may present basic information about the light projection area, such as ground environment information of the projected light pattern.

[0075] For example, the second image may correspond to an image P2 of a predetermined projection area taken momentarily after the projection of the light pattern. In addition to the background portion BG, the second image P2 may also include the light pattern PAT projected onto the ground. Figure 7 In the image, the light pattern PAT is shown as a car pattern, but this is just an example. As mentioned above, the light pattern PAT can have any other arbitrary shape.

[0076] According to an exemplary embodiment, the difference information between a first image P1 and a second image P2 can be obtained by subtracting them. Subtracting two images can represent subtracting the grayscale values ​​or color components of corresponding pixels in the two images. Exemplarily, the image subtraction operation according to this application can be implemented using speckle interferometry, holographic filtering, interference filtering, and grating coding, etc., and this application does not limit the scope of the subtraction operation.

[0077] like Figure 7 As shown, a first difference image P3 can be obtained by subtracting the first image P1 and the second image P2. Through the subtraction operation, the background portion BG in the first image P1 and the second image P2 can be removed, retaining only the light pattern PAT. Therefore, the first difference image P3 can contain only the light pattern PAT, which is presented as a binarized black and white image.

[0078] Subsequently, based on the position of the light pattern PAT in the first difference image P3, a region of interest Q1 including the light pattern PAT is determined in the first difference image P3. The shape of the region of interest Q1 can be determined based on the shape and / or contour of the light pattern PAT. For example, the region of interest Q1 can be as follows: Figure 7 The light pattern PAT is shown to have a rectangular shape, but this application is not limited to this. The region of interest Q1 is determined to be closer to the outer contour edge of the light pattern PAT, so that the changes in the light pattern can be presented more accurately, and thus the deformation of the light pattern can be determined more accurately.

[0079] Next, according to one implementation method, the pixel coordinates of each pixel in the region of interest Q1 in the first difference image P3 can be obtained.

[0080] For example, such as Figure 8As shown, the region of interest Q1 may include multiple pixels PX. 11 To PX mn Pixel PX 11 It can be a pixel located in the first row and first column of the region of interest Q1, and its pixel coordinates in the first difference image P3 can be determined as (x 11 y 11 ). Pixel PX 1n It can be a pixel located in the first row and nth column of the region of interest Q1, and its pixel coordinates in the first difference image P3 can be determined as (x 1n y 1n And so on, pixel PX mn It can be a pixel located in the m-th row and n-th column of the region of interest Q1, and its pixel coordinates in the first difference image P3 can be determined as (x mn y mn ).

[0081] Unlike the previous embodiments where the pixel coordinates of each pixel in the region of interest Q1 are obtained, in another exemplary embodiment, only the pixel coordinates of a portion of the pixels in the region of interest Q1 in the first difference image P3 can be obtained. For example, the pixel coordinates of pixels at the edges of the region of interest Q1 can be obtained, and further, the pixel coordinates of pixels at the four corners of the region of interest Q1 can also be obtained.

[0082] Subsequently, the determined pixel coordinates can be applied to each image in the first image set taken after the second image P2, thereby locking the position of the corresponding region of interest in each image in the first image set.

[0083] Return to reference Figure 5 The method for determining whether the deformation of the light pattern is greater than a first predetermined threshold after locking the region of interest in each image is further described.

[0084] According to exemplary embodiments, such as Figure 5 As shown, determining whether the deformation of the light pattern is greater than a first predetermined threshold based on the region of interest of each group of adjacent images in the first image set includes: step S2220, calculating the overlap degree of the region of interest of each group of adjacent images in the first image set; step S2230, determining whether any of the calculated overlap degrees is less than a predetermined value; and step S2240, in response to determining that any of the calculated overlap degrees is less than the predetermined value, determining that the deformation of the light pattern is greater than the first predetermined threshold, that is, determining that the preset condition for opening the trunk is met.

[0085] For example, in step S2220, for each image in the first image set, when a new image is acquired, the region of interest of the current image can be cropped based on the pixel coordinates of the region of interest; and it is compared with the region of interest of the previous image to calculate the degree of overlap between the two.

[0086] Furthermore, a second difference image can be obtained by performing an image subtraction operation on the regions of interest of the current image and the previous image (which can be the same as the image subtraction operation in step S2210 described earlier). This second difference image can show the changes in the regions of interest between the two images. Subsequently, the degree of overlap between the current image and the previous image can be determined based on the second difference image. The smaller the grayscale value or color component of the pixels in the second difference image, the higher the degree of overlap. The higher the degree of overlap, the smaller the change between adjacent images, which can also mean that the target object is less likely to be standing on the pattern. In response to the degree of overlap in adjacent images being less than a predetermined value, it is determined that the light pattern has undergone a large deformation, that is, the preset condition for opening the trunk is met.

[0087] Figure 9 This is a schematic flowchart illustrating step S220 according to another example of this application.

[0088] like Figure 9 As shown, according to another example of this application, in step S220, firstly, the region of interest including the light pattern of each image in the first image set is determined (step S2210); secondly, based on the region of interest of each group of adjacent images in the first image set, it is determined whether the deformation of the light pattern is greater than a first predetermined threshold.

[0089] Reference Figure 9 The determination of whether the deformation of the light pattern is greater than a first predetermined threshold based on the region of interest of each group of adjacent images in the first image set includes: step S2220, calculating the overlap degree of the region of interest of each group of adjacent images in the first image set; step S2230, determining whether any of the calculated overlap degrees is less than a predetermined value; step S2250, in response to the overlap degree of the region of interest of the adjacent third and fourth images in the first image set being less than the predetermined value, determining whether there is a target object in the fourth image, wherein the fourth image is an image acquired after the third image; and step S2240, in response to the presence of a target object in the fourth image, determining that the deformation of the light pattern is greater than the first predetermined threshold, i.e., determining that the preset condition for opening the trunk is met.

[0090] In short, the above process and reference Figure 5The difference in the described method lies in that, after determining in S2230 that the overlap between adjacent images (corresponding to the third and fourth images) is less than a predetermined value, a step S2250 is added to further determine whether the preset conditions for opening the trunk are met. For ease of description, this application will omit the details regarding... Figure 5 The method described uses the same steps as in the text, and focuses on the same aspects. Figure 5 The methods differ to avoid redundancy.

[0091] Specifically, as previously referred to Figure 5 As described, for each acquired image, its corresponding region of interest is cropped and compared with the previous image to determine the degree of overlap between the regions of interest of the current image and the previous image. In this example, the third image may correspond to the previous image, and the fourth image may correspond to the current image acquired after the previous image.

[0092] After determining that the region of interest in the current image (or the fourth image) has changed compared to the region of interest in the previous image (or the third image) (i.e., the overlap between the two is less than a predetermined value), it can be further determined whether there is a target object (e.g., the target object's feet / shoes) in the current image (or the fourth image).

[0093] For example, an artificial intelligence (AI) model, such as a convolutional neural network, can be used to identify the current image (or a fourth image) to determine whether a target object exists within it. However, this application is not limited to this, and does not specifically limit the implementation of the AI ​​model, as long as it can effectively and intelligently identify the content in the image.

[0094] In step S2240, in response to the determination in step S2250 that a target object exists in the fourth image, it is determined whether the deformation of the light pattern is greater than a first predetermined threshold, that is, it is determined that the preset conditions for opening the trunk are met.

[0095] In another embodiment, further, when it is determined in step S2250 that a target object (e.g., the target object's feet / shoes) exists in the fourth image, the pixel coordinates of the target object (e.g., the target object's feet / shoes) in the current image are determined using an AI model; then, it is compared with the pixel coordinates of the region of interest in the current image; if the overlap between the two is greater than a predetermined value, it indicates that a target object is standing on the light pattern, thereby determining that the preset conditions for opening the trunk are met.

[0096] Figure 10 This is a schematic flowchart illustrating step S220 according to another example of this application.

[0097] like Figure 10As shown, according to another example of this application, in step S220, determining whether the deformation of the light pattern is greater than a first predetermined threshold based on the first image set may include: step S2260, determining the outline of the light pattern in each image of the first image set; step S2270, determining whether the overlap between any one of the light pattern outlines and a preset outline is less than a predetermined value; and step S2280, in response to the overlap between any one of the light pattern outlines and the preset outline being less than a predetermined value, determining that the deformation of the light pattern is greater than the first predetermined threshold.

[0098] In an exemplary embodiment, for each image in the first image set, the processor can identify the outline of the light pattern in the current image as soon as it acquires an image, and compare it with a preset outline to determine in real time whether the deformation of the light pattern in the current image meets the preset conditions for opening the trunk.

[0099] Specifically, in step S2260, the contour of the light pattern in each image of the first image set can be determined based on an artificial intelligence (AI) model such as a convolutional neural network. However, this application is not limited to this, and does not specifically limit the implementation of the artificial intelligence model, as long as it can effectively and intelligently identify the content in the image.

[0100] In step S2270, first processor 100 (refer to...) Figure 1 ) can be retrieved from memory 400 (refer to) Figure 1 The system extracts a preset contour of the light pattern stored in the image. Then, it compares the contour of the light pattern in the current image, which is recognized by the AI ​​model, with the preset contour and determines whether the degree of overlap between the two is less than a predetermined value. The greater the degree of overlap, the smaller the deformation of the light pattern projected onto the ground, which also means that the target object is less likely to be standing on the pattern.

[0101] The following will refer to Figure 11 Further exemplary embodiments according to this application will be described. Figure 11 This is a schematic flowchart illustrating step S20 according to another exemplary embodiment.

[0102] Figure 11 Step S20 and Figure 4 The difference in step S20 shown is that, after determining in step S220 that the deformation of the light pattern is greater than the first predetermined threshold, steps S240, S250, and S260 are added to further determine whether the preset conditions for opening the trunk are met. For ease of description, this application will omit the details regarding... Figure 4 The method described uses the same steps as in the text, and focuses on the same... Figure 4 The methods differ to avoid redundancy.

[0103] It should be understood that the above references Figures 5 to 10 The method described for determining that the deformation of a light pattern is greater than a first predetermined threshold can also be applied to... Figure 11 Steps S210 and S220 are to form part of this exemplary embodiment.

[0104] Specifically, in step S240, in response to the determination in step S220 that the deformation of the light pattern is greater than a first predetermined threshold, a reminder signal is output to the target object. If the target object continues to stand on the projected pattern after receiving the reminder signal, it further confirms that they indeed have a need to open the trunk. This reminder action avoids scenarios where the trunk is opened directly due to the light pattern being projected onto the target object (or their feet or shoes), or where the target object unintentionally steps on the light pattern, causing the trunk to be accidentally opened. Therefore, the possibility of accidentally opening the trunk can be further eliminated and / or reduced.

[0105] According to an exemplary embodiment, the reminder signal can be a light signal and / or a sound signal. For example, the user can be reminded by changing the color of the light pattern through the light projector 200, such as changing the color of the light pattern from green to a more conspicuous red. At the same time, the vehicle can also send a voice reminder to the user, such as "Please confirm whether the trunk is open", or emit a specific melody as a prompt tone, which is not limited in this application.

[0106] Furthermore, the light pattern can be flashed repeatedly by the light projector 200 to increase the probability that the user will notice the light pattern.

[0107] In other instances, light warning signals can also be output to the target object through other lighting devices of the vehicle (such as taillights), and this application does not limit this.

[0108] In step S250, after outputting the alert signal, a second image set including multiple images of a predetermined projection area is acquired at predetermined time intervals. This step S250 is essentially the same as step S210 for acquiring the first image set, and will not be described in detail here to avoid redundancy.

[0109] Furthermore, the predetermined time interval in step S250 may be the same as or different from the predetermined time interval in step S210, and this application does not specifically limit this.

[0110] In step S260, it is determined whether the deformation of the light pattern is greater than a second predetermined threshold based on the second image set. It should be understood that the second predetermined threshold may be the same as or different from the first predetermined threshold in step S220; this document does not specifically limit this.

[0111] Unlike step S220, which is used to determine whether the deformation of the light pattern is greater than a first predetermined threshold, according to an exemplary embodiment, in step S260, the deformation of the light pattern can be determined to be greater than a second predetermined threshold by: determining whether a target object exists in the region corresponding to the region of interest in one of the plurality of predetermined images in the second image set; and determining that the deformation of the light pattern is greater than the second predetermined threshold in response to determining that a target object exists in the region corresponding to the region of interest in each of the plurality of predetermined images.

[0112] Specifically, for each image in the second image set, the processor, upon acquiring each image, bases its analysis on the reference... Figures 6 to 8 The pixel coordinates of the region of interest obtained in step S2210 are used to crop the region of interest of the current image; then, an AI model such as a convolutional neural network is used to identify whether a target object (e.g., the foot / shoe of the target object) exists in the region of interest.

[0113] It should be noted that in this example, the image acquisition device captures the second image set at a fixed position with the same imaging parameters (such as field of view, focal length, etc.) as the first image set. During the capture of the second image set, the image acquisition device 300 can also capture images of the predetermined projection area at the same angle at a fixed position, thereby ensuring that the second image set can accurately record the changes in the predetermined projection area over time.

[0114] Furthermore, in the example where the light projector 200 flashes a light pattern multiple times consecutively to alert the user, multiple images can be captured during the flashing intervals of the light pattern (i.e., during periods when the light pattern is not being projected), thus forming a second image set. For example, one image can be captured each time the light pattern flashes. This allows for the acquisition of multiple images that do not include the light pattern. Subsequently, an AI model can be used to identify the presence of a target object (e.g., the target object's feet or shoes) in these multiple images that do not include the light pattern. In this embodiment, since the images used for AI recognition do not include the light pattern, interference from the light pattern on the AI ​​model's recognition results can be eliminated, resulting in more accurate recognition results.

[0115] In step S230, in response to the determination in step S260 that the deformation of the light pattern is greater than the second predetermined threshold, and the determination that the change of the light pattern meets the preset conditions, the vehicle can then be controlled to open the trunk.

[0116] According to another exemplary embodiment, in step S260, it can be determined whether the deformation of the light pattern is greater than a second predetermined threshold by: determining the outline of the light pattern in each image of the second image set; and determining that the deformation of the light pattern is greater than the second predetermined threshold in response to any one of the light pattern outlines having an overlap with a preset outline that is less than a predetermined value. This process can be compared with a reference... Figure 10 The steps S220 for determining that the deformation of the light pattern is greater than a first predetermined threshold are essentially the same, and therefore will not be repeated here to avoid redundancy.

[0117] Reference above Figure 11 In the described implementation, after the alert signal is output to the target object, the projection position of the light pattern remains unchanged, and the imaging parameters of the image acquisition device remain the same during the two determinations of the light pattern deformation.

[0118] However, according to another embodiment of this application, unlike Figure 11 In this implementation, after outputting a reminder signal to the target object, the light pattern can be projected to other locations deviating from the initial projection position. If the target object does need to open the trunk, it can move to the new light pattern projection position. Accordingly, if the processor 100 detects a target object standing on the light pattern after changing the light pattern projection position (e.g., the deformation of the light pattern is greater than a certain threshold), it can open the trunk.

[0119] In this exemplary embodiment, the changes in the newly projected light pattern can be observed by referring to... Figures 5 to 10 The method described for determining that the deformation of the light pattern is greater than a first predetermined threshold (step S220) is used to achieve this.

[0120] Furthermore, the method for controlling a vehicle trunk according to an exemplary embodiment may further include: closing the trunk in response to determining that a target object has left a predetermined area of ​​the trunk. Similar to... Figure 2 Step S40, which determines that a target object has entered its predetermined range, can also be implemented using the car key / mobile terminal positioning function.

[0121] Furthermore, the light projector according to the exemplary embodiment can emit infrared light, i.e., it can project an infrared light pattern. The image acquisition device may include an infrared filter that only allows infrared light to pass through. Since the target object (i.e., the vehicle user) can emit infrared radiation, in this example, it is determined by an AI model or the like whether other infrared patterns overlap at the infrared light pattern / whether the outline of the infrared light pattern has a low degree of overlap with a preset outline. If so, it can be determined that the trunk opening condition is met; otherwise, the trunk opening condition is not met.

[0122] According to another aspect of this application, a vehicle is also provided that may include the trunk control system 10 described above, which can perform the aforementioned... Figures 2 to 11 The method described is for controlling the trunk of a vehicle.

[0123] Another aspect of this application provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the method for controlling the vehicle trunk mentioned in the above embodiments.

[0124] The embodiments of this application have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this application. The scope of this application is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this application, and all such substitutions and modifications should fall within the scope of this application.

[0125] Those skilled in the art should understand that the scope of the invention involved in this application is not limited to the technical solutions formed by specific combinations of the above-mentioned technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-mentioned technical features or their equivalent features without departing from the concept of this application. For example, technical solutions formed by substituting the above-mentioned features with technical features disclosed in this application (but not limited to) that have similar functions.

Claims

1. A method for controlling the trunk of a vehicle, comprising: In response to determining that a target object has entered a predetermined range of the trunk, a light pattern is projected onto a predetermined projection area; Determine whether the change in the light pattern meets the preset conditions; as well as In response to determining that the change in the light pattern satisfies the preset condition, the trunk is opened. Determining whether the light pattern meets the preset conditions includes: determining whether the deformation of the light pattern is greater than a first predetermined threshold. The step of projecting a light pattern onto a predetermined projection area in response to determining that a target object has entered a predetermined range of the trunk includes: The position of the predetermined projection area is determined based on the movement path of the target object detected by the vehicle, wherein the position is offset from the movement path of the target object.

2. The method according to claim 1, wherein, The method further includes: In response to determining that the target object has left a predetermined range of the trunk, the trunk is closed.

3. The method according to claim 1, wherein, Determining whether the deformation of the light pattern is greater than the first predetermined threshold includes: Acquire a first image set including multiple images of the predetermined projection area at predetermined time intervals; and Based on the first image set, it is determined whether the deformation of the light pattern is greater than the first predetermined threshold.

4. The method according to claim 3, wherein, Determining whether the deformation of the light pattern is greater than the first predetermined threshold based on the first image set includes: Determine the region of interest, including the light pattern, for each image in the first image set; and Based on the region of interest of each pair of adjacent images in the first image set, determine whether the deformation of the light pattern is greater than the first predetermined threshold.

5. The method according to claim 4, wherein, Determining the region of interest, including the light pattern, for each image in the first image set includes: Extract adjacent first and second images from the first image set, wherein the first image does not include the light pattern, and the second image is an image acquired after the first image and includes the light pattern; and The region of interest is determined based on the difference between the first image and the second image.

6. The method according to claim 4 or 5, wherein, Determining whether the deformation of the light pattern is greater than the first predetermined threshold based on the region of interest of each pair of adjacent images in the first image set includes: Calculate the overlap of the regions of interest in each pair of adjacent images in the first image set; and In response to any of the overlap degrees being less than a predetermined value, it is determined that the deformation of the light pattern is greater than the first predetermined threshold.

7. The method according to claim 4 or 5, wherein, Determining whether the deformation of the light pattern is greater than a first predetermined threshold based on the region of interest of each pair of adjacent images in the first image set includes: Calculate the overlap of the regions of interest in each pair of adjacent images in the first image set; In response to the fact that the overlap of the regions of interest of adjacent third and fourth images in the first image set is less than a predetermined value, it is determined whether a target object exists in the fourth image, wherein the fourth image is an image acquired after the third image; and In response to the presence of the target object in the fourth image, it is determined that the deformation of the light pattern is greater than the first predetermined threshold.

8. The method according to claim 3, wherein, Determining whether the deformation of the light pattern is greater than the first predetermined threshold based on the first image set includes: Determine the outline of the light pattern in each image of the first image set; and In response to any one of the contours of the light pattern having an overlap with a preset contour that is less than a predetermined value, it is determined that the deformation of the light pattern is greater than a first predetermined threshold.

9. The method according to claim 4 or 5, wherein, Determining whether the light pattern meets the preset conditions also includes: In response to determining that the deformation of the light pattern is greater than the first predetermined threshold, an alert signal is output to the target object; and Determine whether the deformation of the light pattern is greater than a second predetermined threshold.

10. The method of claim 9, wherein, Determining whether the deformation of the light pattern is greater than the second predetermined threshold includes: After outputting the alert signal, a second image set including multiple images of the predetermined projection area is acquired at predetermined time intervals; and Based on the second image set, determine whether the deformation of the light pattern is greater than the second predetermined threshold.

11. The method of claim 10, wherein, Determining whether the deformation of the light pattern is greater than the second predetermined threshold based on the second image set includes: Determine whether the target object exists in the region corresponding to the region of interest among a plurality of predetermined images in the second image set; and In response to determining that the target object exists in the region corresponding to the region of interest in each of the plurality of predetermined images, the deformation of the light pattern is determined to be greater than the second predetermined threshold.

12. The method according to claim 9, wherein, Determining whether the deformation of the light pattern is greater than the second predetermined threshold includes: After the reminder signal is output, a second set of images, including multiple images of the predetermined projection area, is acquired at predetermined time intervals; Determine the outline of the light pattern in each image of the second image set; and In response to any one of the contours of the light pattern having an overlap with a preset contour that is less than a predetermined value, it is determined that the deformation of the light pattern is greater than the second predetermined threshold.

13. A system for controlling the trunk of a vehicle, including: A light projector is mounted on the vehicle and configured to project a light pattern onto a predetermined projection area, the position of which is determined based on the movement path of a target object detected by the vehicle, wherein the position is offset from the movement path of the target object; as well as The processor is configured as follows: In response to determining that the target object has entered a predetermined range of the trunk, a light pattern is projected onto the predetermined projection area; Determine whether the change in the light pattern meets the preset conditions; as well as In response to the light pattern satisfying the preset condition, the trunk is opened. Determining whether the change in the light pattern meets the preset conditions includes: whether the deformation of the light pattern is greater than a first predetermined threshold.

14. The system according to claim 13, wherein, The system further includes: an image acquisition unit, mounted on the vehicle and configured to acquire an image of the predetermined projection area at a fixed position and a fixed viewing angle; and The processor is further configured to: Control the image acquisition device to acquire a first image set including multiple images of the predetermined projection area at predetermined time intervals; and Based on the first image set, it is determined whether the deformation of the light pattern is greater than the first predetermined threshold.

15. The system according to claim 14, wherein, The processor is also configured to: Determine the region of interest, including the light pattern, for each image in the first image set; and Based on the region of interest of each pair of adjacent images in the first image set, determine whether the deformation of the light pattern is greater than the first predetermined threshold.

16. The system according to claim 15, wherein, The processor is further configured to: extract adjacent first and second images from the first image set, wherein the first image does not include the light pattern, and the second image is an image acquired after the first image and includes the light pattern; as well as The region of interest is determined based on the difference between the first image and the second image.

17. The system according to claim 15 or 16, wherein, The processor is further configured to: calculate the overlap of regions of interest in each pair of adjacent images in the first image set; and In response to any of the overlap degrees being less than a predetermined value, it is determined that the deformation of the light pattern is greater than the first predetermined threshold.

18. The system according to claim 15 or 16, wherein, The processor is further configured to: calculate the overlap of regions of interest in each pair of adjacent images in the first image set; In response to the fact that the overlap of the regions of interest of adjacent third and fourth images in the first image set is less than a predetermined value, it is determined whether there is a target object in the fourth image, which is an image acquired after the third image; as well as In response to the presence of the target object in the fourth image, it is determined that the deformation of the light pattern is greater than the first predetermined threshold.

19. The system according to claim 14, wherein, The processor is also configured to: Determine the outline of the light pattern in each image of the first image set; and In response to any one of the contours of the light pattern having an overlap with a preset contour that is less than a predetermined value, it is determined that the deformation of the light pattern is greater than a first predetermined threshold.

20. The system according to claim 15 or 16, wherein, The processor is further configured to: in response to determining that the deformation of the light pattern is greater than the first predetermined threshold, output a reminder signal to the target object; as well as Determine whether the deformation of the light pattern is greater than a second predetermined threshold.

21. The system according to claim 20, wherein, The processor is further configured to: after outputting the alert signal, control the image acquisition device to acquire a second set of images including multiple images of the predetermined projection area at predetermined time intervals; and Based on the second image set, determine whether the deformation of the light pattern is greater than the second predetermined threshold.

22. The system according to claim 21, wherein, The processor is also configured to: Determine whether the target object exists in the region corresponding to the region of interest among a plurality of predetermined images in the second image set; as well as In response to determining that the target object exists in the region corresponding to the region of interest in each of the plurality of predetermined images, the deformation of the light pattern is determined to be greater than the second predetermined threshold.

23. The system according to claim 20, wherein, The processor is further configured to: after outputting the reminder signal, control the image acquisition device to acquire a second set of images including multiple images of the predetermined projection area at predetermined time intervals; Determine the outline of the light pattern in each image of the second image set; as well as In response to any one of the contours of the light pattern having an overlap with a preset contour that is less than a predetermined value, it is determined that the deformation of the light pattern is greater than the second predetermined threshold.

24. The system according to claim 13, wherein, The processor is further configured to close the trunk in response to determining that the target object has left a predetermined range of the trunk.

25. A vehicle, including the system for controlling the trunk of a vehicle as claimed in any one of claims 13 to 24.

26. A computer storage medium storing a computer program, wherein, When the computer program is executed by the processor, it implements the method for controlling the vehicle trunk as described in any one of claims 1 to 12.

Images