Vehicle back door opening control method and device, medium and electronic equipment

Abstract

The invention discloses a vehicle back door opening control method and device, a medium and electronic equipment, and the method comprises the steps: in a vehicle back door control mode, carrying out the motion detection in a preset range through a millimeter wave radar deployed for a blind area detection system, and obtaining the current description data of the current motion; based on the current description data of the current action and an action template of a kicking action in a self-learning library, determining whether the current action is an action recognition result of the kicking action; and when the action recognition result is that the current action is the kicking action, a back door opening instruction is generated, and a vehicle back door is controlled to be opened based on the back door opening instruction. By executing the technical scheme provided by the invention, the identification accuracy of the kicking action can be improved without increasing the hardware cost, and the success rate of opening the back door of the vehicle is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a vehicle tailgate opening control method, device, medium and electronic equipment. Background Art

[0002] The automatic tailgate opening function has become an important configuration for mid-to-high-end models to enhance user experience, mainly solving the problem of inconvenience in operation when users are holding heavy objects.

[0003] Related technologies include two technical solutions: kick sensor and AR projection. Among them, the kick sensor solution uses the sensor in the rear bumper to detect the waveform characteristics of the user's kicking action to open the back door. The AR projection solution uses a ground projection cursor method. The user only needs to step on the projection area to trigger the back door to open.

[0004] The kick sensor solution requires additional kick sensors and a kick controller, while the AR projection solution requires additional projection equipment. Both solutions increase hardware costs. Furthermore, the kick sensor solution also carries the risk of false triggering, requiring the user to get close to the rear of the vehicle, potentially causing a collision, and unstable recognition rates. Furthermore, the AR projection solution's recognition rate decreases in bright light environments. Summary of the Invention

[0005] The present application provides a vehicle tailgate opening control method, device, medium and electronic device, which can improve the accuracy of kicking action recognition and increase the success rate of vehicle tailgate opening without increasing hardware costs.

[0006] According to a first aspect of the present application, a vehicle back door opening control method is provided, the method comprising:

[0007] In the vehicle back door control mode, the millimeter wave radar deployed for the blind spot detection system detects the action within the preset range to obtain the current description data of the current action;

[0008] determining, based on current description data of the current action and an action template of a kicking action in a self-learning library, whether the current action is an action recognition result of a kicking action;

[0009] When the action recognition result indicates that the current action is a kicking action, a back door opening instruction is generated, and the back door of the vehicle is controlled to open based on the back door opening instruction.

[0010] According to a second aspect of the present application, a vehicle back door opening control device is provided, the device comprising:

[0011] The motion detection module is used to obtain current description data of the current motion by detecting motion within a preset range using the millimeter-wave radar deployed for the blind spot detection system in the vehicle tailgate control mode;

[0012] an action recognition module, configured to determine whether the current action is an action recognition result of a kicking action based on current description data of the current action and an action template of the kicking action in a self-learning library;

[0013] The back door opening module is used to generate a back door opening instruction when the action recognition result shows that the current action is a kicking action, and control the opening of the vehicle back door based on the back door opening instruction.

[0014] According to a third aspect of the present invention, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle tailgate opening control method as described in the embodiment of the present application.

[0015] According to the fourth aspect of the present invention, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein when the processor executes the computer program, the vehicle tailgate opening control method as described in the embodiment of the present application is implemented.

[0016] The technical solution of the present application takes into account the stable detection capability of the millimeter-wave radar in complex environments, reuses the millimeter-wave radar deployed as the blind spot detection system, and adds the function of kicking the back door open for the user, avoiding the problem that traditional sensors are susceptible to environmental interference. The detection mechanism of the millimeter-wave radar for motion detection within a preset range can accurately distinguish between effective actions and random interference. The present application introduces a self-learning library during motion recognition, so that the motion template can be continuously optimized, which can adapt to the differences in behavioral habits of different users, significantly improves the accuracy of kicking action recognition, and can effectively improve the success rate of back door opening, and can avoid abnormal situations such as opening failure or erroneous opening. The vehicle back door opening control method provided by the present application can free the user's hands without increasing the cost of the entire vehicle. When the user carries items, the back door can be opened through natural foot movements without putting down heavy objects, which greatly improves the convenience of use.

[0017] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 is a flow chart of a vehicle back door opening control method provided according to the first embodiment;

[0020] Figure 2 is a flow chart of a vehicle back door opening control method provided according to the second embodiment;

[0021] Figure 3 This is a schematic diagram of the structure of the vehicle back door opening control device provided in Example 3 of the present application;

[0022] Figure 4 This is a structural diagram of an electronic device provided in Example 4 of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0024] It should be noted that the terms "first", "second", "target" and "candidate" in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] Example 1

[0026] Figure 1 This is a flowchart of the vehicle tailgate opening control method provided according to Example 1. This embodiment can be applied to scenarios where it is inconvenient for the user to manually open the vehicle tailgate, such as holding a heavy object, and controls the opening of the vehicle tailgate. The method can be executed by a vehicle tailgate opening control device, which is implemented in the form of hardware and / or software and can be integrated into electronic equipment.

[0027] like Figure 1 As shown, the method includes:

[0028] S110, in the vehicle tailgate control mode, obtaining current description data of the current action by performing action detection within a preset range using a millimeter-wave radar deployed for the blind spot detection system;

[0029] S120, determining whether the current action is an action recognition result of a kicking action based on the current description data of the current action and the action template of the kicking action in the self-learning library;

[0030] S130: Generate a back door opening instruction when the action recognition result indicates that the current action is a kicking action, and control the opening of the back door of the vehicle based on the back door opening instruction.

[0031] Among them, the backdoor control command will only take effect in the vehicle backdoor control mode, that is, the backdoor control function will be available. Setting the vehicle backdoor control mode can effectively prevent the vehicle backdoor from opening by mistake. Whether it is in the vehicle backdoor control mode is related to the vehicle's motion state, the vehicle's lock state, and the relative position between the remote control key and the vehicle. Optionally, the millimeter-wave radar is used to determine whether the current environment is relatively closed or whether there is strong electromagnetic interference. If the current environment is relatively closed or there is strong electromagnetic interference, the backdoor control function will be set to unavailable to avoid accidental opening.

[0032] Blind spot detection systems effectively prevent collisions with vehicles behind you when changing lanes, enhancing driving safety. The adoption rate of blind spot detection systems has been increasing year by year, currently approaching 100%. The blind spot detection system utilizes millimeter-wave radar. In tailgate control mode, the millimeter-wave radar detects movement within a preset range and generates current description data.

[0033] The preset range is related to the millimeter-wave radar's installation location and detection capability. For a millimeter-wave radar installed at the rear corner of a vehicle, the preset range refers to the distance from the left or right corner of the vehicle's rear bumper. The preset distance is determined based on actual conditions and is not limited here.

[0034] Current description data is generated by millimeter-wave radar detecting motion within a preset range. Millimeter-wave radar generates raw data by emitting electromagnetic waves and analyzing the return signals. After filtering and signal processing, the resulting structured description information is the current description data. This current description data is used to describe the motion characteristics of the current action.

[0035] The kicking action template in the self-learning library is a standardized set of action features formed through multi-dimensional data modeling. The self-learning library is autonomously evolving, dynamically optimizing the template by continuously collecting millimeter-wave radar signals of kicking actions. It also has the ability to automatically update the feature model based on new samples. Its learning process embodies both initiative and independence. Different users have varying kicking movements, such as height, kicking style, and movement trajectory. Self-learning can record personalized features such as swing amplitude and speed. By recording action features such as kick speed, angle, distance, and dwell time, machine learning is used to classify normal operations from false triggers, such as pets passing by or metal objects blown by wind. Principal component analysis is then used to reduce the dimensionality of the features and extract key features. Action templates are then constructed based on these key features.

[0036] The action template of the kicking action in the self-learning library is used as the judgment basis. By comparing the current description data of the current action with the action template of the kicking action in the self-learning library, it is determined whether the current action is an action recognition result of the kicking action.

[0037] Optionally, the action recognition result includes whether the current action is a kick or not a kick. The kick action is an indicative action for controlling the backdoor opening and is key to identifying whether the user intends to open the backdoor. The accuracy of kick action recognition directly affects the success rate of vehicle backdoor control and the user experience.

[0038] If the action recognition result indicates a kick, indicating the user intends to open the back door, a back door opening command is generated. The back door opening command controls the movement of the back door support mechanism to open the vehicle's back door. Optionally, the back door support mechanism includes a pair of electric struts, which are extended and retracted by the rotation of a motor, thereby opening and closing the vehicle's back door.

[0039] Optionally, based on the back door opening instruction, the back door support mechanism is checked, and when there is no fault in the back door support mechanism, the back door support movement is controlled to open the back door of the vehicle.

[0040] Optionally, before the vehicle's back door opens, a sound device will warn the user to stay away from the vehicle's back door as it is about to open. After the vehicle's back door opens, in order to avoid injury, the hazard lights will light up to warn the user to maintain a certain safe distance from the vehicle's back door.

[0041] The technical solution of the present application takes into account the stable detection capability of the millimeter-wave radar in complex environments, reuses the millimeter-wave radar deployed as the blind spot detection system, and adds the function of kicking the back door open for the user, avoiding the problem that traditional sensors are susceptible to environmental interference. The detection mechanism of the millimeter-wave radar for motion detection within a preset range can accurately distinguish between effective actions and random interference. The present application introduces a self-learning library during motion recognition, so that the motion template can be continuously optimized, which can adapt to the differences in behavioral habits of different users, significantly improves the accuracy of kicking action recognition, and can effectively improve the success rate of back door opening, and can avoid abnormal situations such as opening failure or erroneous opening. The vehicle back door opening control method provided by the present application can free the user's hands without increasing the cost of the entire vehicle. When the user carries items, the back door can be opened through natural foot movements without putting down heavy objects, which greatly improves the convenience of use.

[0042] In an optional embodiment, the determining whether the current action is an action recognition result of a kicking action based on the current description data of the current action and the action template of the kicking action in the self-learning library includes: performing feature extraction on the current description data to obtain the current action feature of the current action, and determining the reference action feature of the action template; determining the feature similarity between the current action and the action template based on the current action feature and the reference action feature; determining whether the current action is an action recognition result of the kicking action based on the feature similarity and a similarity threshold corresponding to the current weather; wherein the current weather is determined based on precipitation data collected by a rain sensor.

[0043] The current motion features are used to determine the motion type of the current motion. Optionally, the current motion features include spatial motion features, time-frequency features, and behavioral semantic features of the current motion. Spatial motion features include 3D trajectory coordinates, velocity gradient changes, and reflection point cloud distribution, which are used to reconstruct the foot motion path; time-frequency features capture the periodicity and burst characteristics of the motion through micro-Doppler spectrum and distance-time energy map; behavioral semantic features such as amplitude threshold, motion duration, and spatial consistency are used to eliminate interference.

[0044] Optionally, the same feature extraction method is used to extract features from the current description data and the action template, and a current action feature corresponding to the current action and a reference action feature corresponding to the action template are obtained, respectively. The feature dimension of the reference action feature is the same as the feature dimension of the current action feature. Optionally, the current action feature and the reference action feature are compared according to the feature dimension to determine the feature similarity between the current action and the action template. The feature similarity is used to quantify the degree of similarity between the current action and the action template. Optionally, the relative size between the two is determined based on the feature similarity and a similarity threshold.

[0045] The similarity threshold is used to measure whether the current action is a kick. The similarity threshold is related to the current weather, which is determined based on precipitation data collected by the rain sensor. If the current weather is determined to be rainy based on precipitation data collected by the rain sensor, the similarity threshold is lowered to the first value to increase the success rate of the back door opening and ensure user experience. If the current weather is not precipitation, the similarity threshold is restored to the second value to reduce the possibility of the back door opening by mistake. The first value is smaller than the second value. The specific values ​​of the first and second values ​​are not limited here and are determined based on actual business needs.

[0046] If the feature similarity is greater than the similarity threshold, the action recognition result is determined to be a kicking action. If the feature similarity is less than or equal to the similarity threshold, the action recognition result is determined to be a non-kicking action.

[0047] The above technical solution reuses the rain sensor to determine the current weather based on the precipitation data collected by the rain sensor. When determining the action recognition result, the feature similarity between the current action and the action template is compared with the similarity threshold corresponding to the current weather. This can ensure the success rate of opening the back door while taking into account the user experience.

[0048] In an optional embodiment, the method further includes: if the action recognition result is that the current action is the kicking action, collecting an image of the item to be placed through a surround-view camera; determining the size of the item based on the image of the item, and controlling the opening angle of the vehicle tailgate based on the size of the item.

[0049] If the action recognition result indicates that the current action is a kicking action, it means that the user intends to open the back door. At this time, the surround-view camera is used to collect images of the items to be placed. The surround-view camera is deployed for the driving assistance system. In this application, the surround-view camera is reused to collect images of the items to be placed. The items to be placed refer to items that need to be placed in the trunk of the vehicle. Optionally, the item size can be measured by performing multi-view image stitching and calibration parameter fusion on the item images collected by the surround-view camera, combined with three-dimensional reconstruction or reference object ratio conversion to determine the size of the item. Based on the size of the item, it can be determined whether the item to be placed is a large item or a small item. Optionally, if it is detected that the item to be placed is a large item, the opening angle of the vehicle back door is controlled to be a first angle. If the item to be placed is a small item, the opening angle of the vehicle back door is controlled to be a second angle. The first angle is greater than the second angle. The specific values ​​of the first angle and the second angle are not limited here and are determined according to actual conditions. Exemplarily, the first angle is 100% and the second angle is 60%-80%. It should be noted that the 60%, 80% and 100% here are relative to the maximum physical opening angle of the vehicle tailgate design.

[0050] This technical solution reuses the surround-view cameras deployed for the assisted driving system to capture images of the items to be placed. Based on the size of the items determined in the images, the tailgate's opening angle is controlled. This automatically adapts to the size of the items, reducing manual adjustments and improving the user experience. Furthermore, the angle limit reduces the risk of scratches and enhances ease of placement and retrieval.

[0051] In an optional embodiment, the method further includes: determining the vehicle motion state, the vehicle locking state, and the relative position between the remote control key and the vehicle; wherein, the vehicle motion state is determined based on the current vehicle speed collected by the vehicle speed sensor; if the vehicle motion state is a stationary state, the vehicle locking state is an unlocked state, and the relative position between the remote control key and the vehicle is within a preset range, then the vehicle backdoor control mode is turned on.

[0052] The vehicle's motion state is used to determine whether the vehicle is stationary. This is determined based on the current vehicle speed as measured by the speed sensor. Optionally, if the current vehicle speed is zero, the vehicle's motion state is determined to be stationary. The vehicle's lock state is used to determine whether the vehicle is unlocked. If the vehicle's motion state is stationary and the vehicle's lock state is unlocked, the relative position of the remote control key and the vehicle is further determined.

[0053] Determining whether the relative position is within a preset range is used to determine whether the user is inside the vehicle. The preset range is determined based on actual circumstances and is not limited here. The vehicle's backdoor control mode can only be activated when the remote control key is detected to be absent from the vehicle. The vehicle's backdoor control mode cannot be activated when the remote control key is detected to be present. This prevents the backdoor from being maliciously opened while the user is inside the vehicle.

[0054] The above technical solution determines whether to open the vehicle backdoor control mode based on the vehicle's motion state, vehicle locking state, and the relative position between the remote control key and the vehicle, thereby ensuring the reliability and safety of the backdoor opening method and improving the user experience.

[0055] In an optional embodiment, the determining whether the current action is an action recognition result of a kicking action based on the current description data of the current action and the action template of the kicking action in the self-learning library includes: determining the historical usage frequency of the action template for the kicking action in the self-learning library; determining the usage priority of the action template based on the historical usage frequency; and determining whether the current action is an action recognition result of a kicking action based on the current description data of the current action, the action template and the usage priority of the action template.

[0056] There are at least two kicking action templates in the self-learning library, and each action template has a corresponding user. The historical usage frequency of the action template is used to determine the usage priority of the action template.

[0057] Optionally, the feature matching order of the action templates is first determined based on the usage priority of the action templates. Based on this feature matching order, a target template with the highest feature matching order is selected from the action templates in the self-learning library. Next, a feature match is performed between the current description data of the current action and the target template. If the feature match fails, the target template is updated to the action template with the second highest feature matching order and feature matched again with the current description data of the current action until a match is successful or all action templates in the self-learning library have been matched.

[0058] If the action template in the self-learning library can successfully match the current description data of the current action, the action recognition result can be determined as the current action is a kicking action; otherwise, the action recognition result is determined as the current action is not a kicking action.

[0059] The above technical solution determines the usage priority of the action template based on the historical usage frequency; using the usage priority of the action template to determine the action recognition result can improve the action recognition efficiency and shorten the action recognition time.

[0060] Example 2

[0061] Figure 2 2 is a flow chart of a vehicle back door opening control method provided according to embodiment 2. This embodiment is further optimized based on the above embodiment.

[0062] like Figure 2 As shown, the method includes:

[0063] S210 . In a kicking action self-learning mode, generate a kicking action prompt for a target object so that the target object performs a kicking action.

[0064] The kicking action self-learning mode is used to construct a kicking action template in the self-learning library. The target object is the subject of the action template, typically the user of the vehicle. The kicking action prompt instructs the target object to perform the kicking action.

[0065] S220: Detecting the kicking action of the target object within the preset range by the millimeter-wave radar to obtain initial description data of the kicking action.

[0066] The preset range is related to the millimeter-wave radar's installation location and detection capability. For a millimeter-wave radar installed at the rear corner of a vehicle, the preset range refers to the distance from the left or right corner of the vehicle's rear bumper. The preset distance is determined based on actual conditions and is not limited here.

[0067] The initial description data is used to describe the baseline features obtained by the first detection of the kicking action. The initial description data is the data basis for building the action template.

[0068] S230: Generate an action repetition prompt for the target object to enable the target object to perform the kicking action at least twice again, so that the millimeter wave radar can detect the kicking action of the target object again within the preset range to obtain auxiliary description data of the kicking action.

[0069] The action repetition prompt is used to instruct the target object to perform the kicking action at least twice again.

[0070] The millimeter-wave radar detects the kicking motion of the target object again within the preset range to obtain auxiliary description data of the kicking motion. The auxiliary description data is used to describe the verification features obtained by repeatedly detecting the kicking motion, focusing on capturing the motion stability indicator.

[0071] S240: Generate an action template of a kicking action for the target object based on the initial description data and the auxiliary description data, and write the action template into the self-learning library.

[0072] The initial description data and the auxiliary description data are functionally complementary. Optionally, the initial description data and the auxiliary description data are fused, and an action template of a kicking action is generated for the target object based on the obtained data fusion result.

[0073] Optionally, establish an association between the action template and the target object, and write the action template associated with the target object into the self-learning library

[0074] An embodiment of the present application provides a practical action template construction scheme for constructing an action template for a kicking action in a self-learning library. The initial description data can describe the baseline features obtained by the first detection of the kicking action; the auxiliary description data can describe the verification features obtained by repeated detection of the kicking action, focusing on capturing the action stability index. The present application constructs an action template based on the initial description data and auxiliary description data with functional complementarity, thereby ensuring the accuracy of the action template in the self-learning library and helping to improve the accuracy of action recognition.

[0075] In an optional implementation, the method further includes: if the action recognition results are that the current action is not the kicking action for a set number of consecutive times, then entering a kicking action re-learning mode; in the kicking action re-learning mode, based on the selection operation for the action template, determining the action template to be updated in the self-learning library; based on the historical actions obtained by the millimeter-wave radar through action detection within the set number of consecutive times, updating the action template to be updated.

[0076] If the action recognition results are consistently incorrect for the current action, indicating that the kicking action is not the kicking action, the action template may have expired and the kicking action template in the self-learning library needs to be updated. The number of consecutive times set depends on actual business needs and is not limited here.

[0077] In the kicking action re-learning mode, the kicking action template in the self-learning library will be updated. Since the self-learning library includes at least two action templates associated with different objects, the action template selection operation is used to determine which action template in the self-learning library to update.

[0078] The template to be updated refers to the action template that needs to be updated in the self-learning library. The action template to be updated is updated based on the historical actions detected by the millimeter wave radar within a set number of consecutive motion detections.

[0079] The above technical solution enters the kicking action re-learning mode when the action recognition results show that the current action is not a kicking action for a set number of consecutive times, which can avoid invalid updates caused by occasional misjudgments. In the kicking action re-learning mode, based on the selection operation for the action template, the action template to be updated is determined in the self-learning library, which can ensure the accuracy of the template update. The action template to be updated is updated based on the historical actions obtained by the millimeter wave radar for a set number of consecutive action detections, rather than the user re-performing the kicking action. This realizes the reuse of historical action data, avoids user fatigue caused by repeated collection, improves the update efficiency of the action template, and ensures user experience.

[0080] Example 3

[0081] Figure 3 This is a structural diagram of the vehicle tailgate opening control device provided in Example 3 of the present application. This embodiment can be used in scenarios where it is inconvenient for the user to manually open the vehicle tailgate, such as holding heavy objects, to control the opening of the vehicle tailgate. The device can be implemented by software and / or hardware and can be integrated into electronic devices such as smart terminals.

[0082] like Figure 3 As shown, the device may include:

[0083] The motion detection module 310 is used to obtain current description data of the current motion by performing motion detection within a preset range using the millimeter-wave radar deployed for the blind spot detection system in the vehicle tailgate control mode;

[0084] An action recognition module 320 is configured to determine whether the current action is an action recognition result of a kicking action based on current description data of the current action and an action template of a kicking action in a self-learning library;

[0085] The back door opening module 330 is configured to generate a back door opening instruction when the action recognition result indicates that the current action is a kicking action, and control the opening of the vehicle back door based on the back door opening instruction.

[0086] The technical solution of the present application takes into account the stable detection capability of the millimeter-wave radar in complex environments, reuses the millimeter-wave radar deployed as the blind spot detection system, and adds the function of kicking the back door open for the user, avoiding the problem that traditional sensors are susceptible to environmental interference. The detection mechanism of the millimeter-wave radar for motion detection within a preset range can accurately distinguish between effective actions and random interference. The present application introduces a self-learning library during motion recognition, so that the motion template can be continuously optimized, which can adapt to the differences in behavioral habits of different users, significantly improves the accuracy of kicking action recognition, and can effectively improve the success rate of back door opening, and can avoid abnormal situations such as opening failure or erroneous opening. The vehicle back door opening control method provided by the present application can free the user's hands without increasing the cost of the entire vehicle. When the user carries items, the back door can be opened through natural foot movements without putting down heavy objects, which greatly improves the convenience of use.

[0087] Optionally, the action recognition module includes: a feature extraction submodule, used to extract features from the current description data to obtain the current action features of the current action, and determine the reference action features of the action template; a feature comparison submodule, used to determine the feature similarity between the current action and the action template based on the current action features and the reference action features; an action recognition submodule, used to determine whether the current action is the action recognition result of the kicking action based on the feature similarity and a similarity threshold corresponding to the current weather; wherein, the current weather is determined based on precipitation data collected by a rain sensor.

[0088] Optionally, the method further includes: an object image acquisition module, which is used to acquire an image of the object to be placed through a surround-view camera if the action recognition result is that the current action is the kicking action; an opening angle control module, which is used to determine the size of the object based on the object image, and control the opening angle of the vehicle tailgate based on the object size.

[0089] Optionally, the device also includes: a mode determination module, which is used to enter a kicking action re-learning mode if the action recognition results are that the current action is not the kicking action for a set number of consecutive times; a template determination module, which is used to determine the action template to be updated in the self-learning library based on the selection operation for the action template in the kicking action re-learning mode; and a template update module, which is used to update the action template to be updated based on the historical actions obtained by the millimeter-wave radar performing action detection within the set number of consecutive times.

[0090] Optionally, the action recognition module 320 includes: a usage frequency determination submodule, used to determine the historical usage frequency of the action template for the kicking action in the self-learning library; a priority determination submodule, used to determine the usage priority of the action template based on the historical usage frequency; and an action recognition submodule, used to determine whether the current action is an action recognition result of a kicking action based on the current description data of the current action, the action template and the usage priority of the action template.

[0091] Optionally, the device also includes: a first prompt generation module, which is used to generate a kicking action prompt for the target object in a kicking action self-learning mode to enable the target object to perform a kicking action before determining whether the current action is an action recognition result of a kicking action based on the current description data of the current action and the action template of the kicking action in the self-learning library; an initial data determination module, which is used to detect the kicking action of the target object within the preset range by the millimeter-wave radar to obtain initial description data of the kicking action; an auxiliary data determination module, which is used to generate an action repetition prompt for the target object to enable the target object to perform the kicking action at least twice again, so that the millimeter-wave radar can detect the kicking action of the target object again within the preset range to obtain auxiliary description data of the kicking action; an action template generation module, which is used to generate an action template of the kicking action for the target object based on the initial description data and the auxiliary description data, and write the action template into the self-learning library.

[0092] Optionally, the device also includes: a relative position determination module, used to determine the vehicle motion state, the vehicle locking state, and the relative position between the remote control key and the vehicle; wherein the vehicle motion state is determined based on the current vehicle speed collected by the vehicle speed sensor; a control mode activation module, used to activate the vehicle backdoor control mode if the vehicle motion state is a stationary state, the vehicle locking state is an unlocked state, and the relative position between the remote control key and the vehicle is within a preset range.

[0093] The vehicle tailgate opening control device provided in the embodiment of the invention can execute the vehicle tailgate opening control method provided in any embodiment of the present application, and has the corresponding performance modules and beneficial effects for executing the vehicle tailgate opening control method.

[0094] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user data involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0095] Example 4

[0096] Figure 4The structure diagram of the electronic device 410 that can be used to implement the embodiment is shown. The electronic device 410 includes at least one processor 411, and a memory connected to the at least one processor 411 in communication, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc., wherein the memory stores a computer program that can be executed by the at least one processor, and the processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or the computer program loaded from the storage unit 418 into the random access memory (RAM) 413. Various programs and data required for the operation of the electronic device 410 can also be stored in the RAM 413. The processor 411, ROM 412 and RAM 413 are connected to each other via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0097] Multiple components in electronic device 410 are connected to I / O interface 415, including an input unit 416, such as a keyboard, mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a magnetic disk, optical disk, etc.; and a communication unit 419, such as a network card, modem, wireless communication transceiver, etc. The communication unit 419 allows electronic device 410 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0098] Processor 411 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 411 executes the various methods and processes described above, such as the vehicle backdoor opening control method.

[0099] In some embodiments, the vehicle backdoor opening control method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the vehicle backdoor opening control method described above can be performed. Alternatively, in other embodiments, processor 411 can be configured to execute the vehicle backdoor opening control method in any other suitable manner (e.g., via firmware).

[0100] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0101] Computer programs for implementing the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable vehicle tailgate opening control device, such that, when executed by the processor, the computer programs implement the functions / operations specified in the flowcharts and / or block diagrams. The computer programs can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0102] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0103] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0104] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a vehicle tailgate opening control server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0105] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0106] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of this application can be achieved. This is not limited herein.

[0107] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. A vehicle back door opening control method, characterized in that: The method comprises: In the vehicle back door control mode, the millimeter wave radar deployed for the blind spot detection system detects the action within the preset range to obtain the current description data of the current action; Determining, based on current description data of the current action and an action template of a kicking action in a self-learning library, whether the current action is an action recognition result of a kicking action; When the action recognition result indicates that the current action is a kicking action, a back door opening instruction is generated, and the back door of the vehicle is controlled to open based on the back door opening instruction.

2. The method according to claim 1, characterized in that The step of determining whether the current action is an action recognition result of a kicking action based on the current description data of the current action and an action template of the kicking action in the self-learning library includes: Performing feature extraction on the current description data to obtain a current action feature of the current action, and determining a reference action feature of the action template; Determining a feature similarity between the current action and the action template based on the current action feature and the reference action feature; Based on the feature similarity and a similarity threshold corresponding to the current weather, it is determined whether the current action is an action recognition result of the kicking action; wherein the current weather is determined based on precipitation data collected by a rain sensor.

3. The method according to claim 1, characterized in that The method further comprises: If the action recognition result is that the current action is the kicking action, collecting an image of the object to be placed by using a surround-view camera; The size of the object is determined based on the image of the object, and the opening angle of the vehicle tailgate is controlled based on the size of the object.

4. The method according to claim 1, wherein The method further comprises: If the action recognition results are that the current action is not the kicking action for a set number of consecutive times, the kicking action re-learning mode is entered; In the kicking action re-learning mode, based on the selection operation for the action template, determining the action template to be updated in the self-learning library; The action template to be updated is updated based on the historical actions obtained by the millimeter wave radar performing action detection within the consecutive set number of times.

5. The method according to claim 1, wherein The step of determining whether the current action is an action recognition result of a kicking action based on the current description data of the current action and an action template of the kicking action in the self-learning library includes: For the kicking action template in the self-learning library, determining the historical usage frequency of the action template; Determining a usage priority of the action template based on the historical usage frequency; Based on the current description data of the current action, the action template and the use priority of the action template, it is determined whether the current action is an action recognition result of a kicking action.

6. The method according to claim 1, characterized in that Before determining whether the current action is an action recognition result of a kicking action based on the current description data of the current action and the action template of the kicking action in the self-learning library, the method further includes: In a kicking action self-learning mode, generating a kicking action prompt for a target object so that the target object performs a kicking action; detecting the kicking action of the target object within the preset range by the millimeter-wave radar to obtain initial description data of the kicking action; generating an action repetition prompt for the target object to cause the target object to perform the kicking action again at least twice, so that the millimeter-wave radar can detect the kicking action of the target object again within the preset range to obtain auxiliary description data of the kicking action; Based on the initial description data and the auxiliary description data, an action template of a kicking action is generated for the target object, and the action template is written into the self-learning library.

7. The method according to claim 1, characterized in that The method further comprises: Determining a vehicle motion state, a vehicle lock state, and a relative position between the remote control key and the vehicle; wherein the vehicle motion state is determined based on a current vehicle speed acquired by a vehicle speed sensor; If the vehicle's motion state is a stationary state, the vehicle's locked state is an unlocked state, and the relative position between the remote control key and the vehicle is within a preset range, the vehicle backdoor control mode is activated.

8. A vehicle back door opening control device, characterized in that: The device comprises: The motion detection module is used to obtain current description data of the current motion by detecting motion within a preset range using the millimeter-wave radar deployed for the blind spot detection system in the vehicle tailgate control mode; an action recognition module, configured to determine whether the current action is an action recognition result of a kicking action based on current description data of the current action and an action template of the kicking action in a self-learning library; The back door opening module is used to generate a back door opening instruction when the action recognition result shows that the current action is a kicking action, and control the opening of the vehicle back door based on the back door opening instruction.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the vehicle tailgate opening control method according to any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein: When the processor executes the computer program, the vehicle tailgate opening control method according to any one of claims 1 to 7 is implemented.

Images