Vehicle trunk opening methods, devices and equipment
By employing dual verification with millimeter-wave radar and ultrasonic radar, and dynamic confidence adjustment, the accuracy and false triggering issues of kick-to-open vehicle trunks in harsh environments have been resolved, enabling efficient and reliable opening in complex environments such as rain, snow, and fog.
Patent Information
- Application Number
- CN202611335883.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-31
- Publication Date
- 2026-11-17
AI Technical Summary
The existing vehicle trunk kick-opening system has low accuracy in harsh environments, is easily affected by environmental interference, and has a high rate of false triggering.
The system employs dual verification using millimeter-wave radar and ultrasonic radar, combined with a master-slave collaborative and event-driven low-power architecture. The millimeter-wave radar is used as the master sensor for low-power scanning, while the ultrasonic radar performs verification. The fusion algorithm verifies whether the kicking information is from the same physical event and dynamically adjusts the confidence threshold.
It maintains stable system operation in harsh environments, reduces power consumption, improves the accuracy and reliability of kicker event recognition, and reduces false triggering.
Smart Images

Figure CN123109512A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of automotive electronics technology, and in particular to a method, device and equipment for opening a vehicle trunk. Background Technology
[0002] With the increasing intelligence of automobiles, intelligent hands-free trunk opening systems have become an important feature in mid-to-high-end models due to their convenience when carrying items with both hands. Currently, the main sensor technologies used in hands-free trunk opening systems include ultrasonic radar, millimeter-wave radar, and capacitive sensor technologies. Each of these technologies has its own significant drawbacks. Ultrasonic radar solution: This solution utilizes the principle of ultrasonic ranging, triggering the system by detecting changes in distance caused by a foot extending underneath. However, its physical characteristics make it susceptible to environmental interference. For example, heavy rain and snow can absorb sound waves, and dirt on the vehicle body can alter the reflective surface, leading to temporary malfunctions or reduced detection range. More importantly, it cannot distinguish between a genuine kicking motion and a person, small animal, or rolling ball passing by, resulting in a high false trigger rate and severely impacting the user experience.
[0003] Millimeter-wave radar solution: Utilizing radio waves, it has good resistance to interference from rain, snow, fog, and dust. However, it has a detection blind spot at very close range and has limited accuracy in recognizing the contours of subtle foot movements, making it difficult to accurately capture the specific action of "extending and retracting the foot".
[0004] Capacitive sensor solution: detects changes in capacitance caused by foot proximity. However, it is extremely sensitive to environmental humidity, temperature, and dirt (such as mud and salt) on the sensor surface, resulting in poor reliability and a sharp decline in performance under harsh weather conditions. Summary of the Invention
[0005] This invention provides a method, apparatus, and device for opening a vehicle trunk, which solves the problem of low accuracy in sensing kicking events in the prior art.
[0006] In a first aspect, embodiments of the present invention provide a method for opening a vehicle trunk, the method comprising: The user's kicking motion is continuously sensed by millimeter-wave radar and ultrasonic radar respectively, so as to obtain the first kicking information by the millimeter-wave radar and the second kicking information by the ultrasonic radar. When it is determined that a primary kicking event has occurred based on the first kicking information, a target kicking event confidence score is generated based on the first kicking information and the second kicking information. When the confidence level of the kicking event is higher than the confidence threshold, the vehicle trunk is opened.
[0007] Optionally, when determining that a primary kicking event has occurred based on the first kicking information, the following steps are included: The feature scores of each first kick feature are obtained through the first kick information. The first kick features include trajectory features and speed features. The trajectory features include motion direction similarity features, motion amplitude features, and trajectory smoothness features. The speed features include speed curve pattern features, dwell features, and total duration features. The feature scores of each of the first kicking features are weighted and summed to obtain the primary kicking event score; When the score of the primary kicking event is higher than the preset primary kicking event score threshold, a primary kicking event is determined to have occurred.
[0008] Optionally, obtaining feature scores for each first kick feature using the first kick information includes: The approach vector and the distance vector of the kicking action are obtained by using the first kicking information, and the feature score of the motion direction similarity feature is obtained according to the directional angle between the approach vector and the distance vector. The vertical and horizontal amplitudes of the kicking motion are obtained from the first kicking information, and the feature scores of the motion amplitude features are obtained according to the preset motion amplitude function, the vertical amplitude, and the horizontal amplitude. The motion acceleration of the kicking action is obtained through the first kicking information, and the feature score of the trajectory smoothness feature is obtained based on the variance of the motion acceleration. The average positive acceleration and the average negative acceleration of the kicking action are obtained through the first kicking information, and the feature score of the velocity curve pattern feature is obtained based on the product of the average positive acceleration and the average negative acceleration. The low-speed movement time when the movement speed is lower than a preset speed threshold is obtained through the first kicking information, and the feature score of the dwell feature is obtained based on the low-speed movement time and the preset low-speed movement reference time. The total movement time of the kicking action is obtained through the first kicking information, and the feature score of the total duration feature is obtained through the total movement time, the preset total movement reference time, and the total movement time reference range.
[0009] Optionally, generating the target kick event confidence score based on the first kick information and the second kick information includes: The feature scores of each second kick feature are obtained through the second kick information. The second kick features include speed matching features and curve completion features. The feature scores of each second kick feature are weighted and summed to obtain the score of the second-level kick event. Based on the environmental information, obtain the first weight corresponding to the score of the primary kicking event and the second weight corresponding to the score of the secondary kicking event. The confidence level of the target kicking event is obtained by weighting and summing the scores of the primary kicking event and the secondary kicking event using the first weight and the second weight.
[0010] Optionally, obtaining feature scores for each second kick feature using the second kick information includes: The actual speed of the kicking action during the kicking and retraction phases is obtained through the second kicking information, and the feature score of the speed matching feature is obtained based on the difference between the actual speed and the preset speed. The effective movement time of the kicking action is obtained through the second kicking information, and the feature score of the curve completion feature is obtained based on the effective movement time and the total movement time.
[0011] Optionally, a first weight corresponding to the score of the primary kicking event and a second weight corresponding to the secondary kicking event are obtained based on environmental information, including: Based on the environmental information, environmental regulation factors are determined from a preset environmental factor database; The first weight is obtained by adjusting the basic weight using the environmental adjustment factor. The second weight is determined based on the first weight; Wherein, the more severe the environment represented by the environmental information, the greater the environmental adjustment factor, and the higher the first weight.
[0012] Optionally, after generating the target kick event confidence score based on the first kick information and the second kick information, the method further includes: Acquire environmental information, historical accuracy information, and false alarm information respectively; The preset base threshold is corrected using the environmental information, the historical accuracy information, and the false alarm information to obtain the confidence threshold. Specifically, the more severe the environment represented by the environmental information, the lower the historical accuracy represented by the historical accuracy information, and the higher the false alarm rate represented by the false alarm information, the higher the confidence threshold will be adjusted.
[0013] Secondly, embodiments of the present invention provide a vehicle trunk opening device, the device comprising: The acquisition module continuously senses the user's kicking action through millimeter-wave radar and ultrasonic radar respectively, so as to acquire the first kicking information through the millimeter-wave radar and the second kicking information through the ultrasonic radar. The generation module, when it is determined that a primary kicking event has occurred based on the first kicking information, generates a target kicking event confidence level based on the first kicking information and the second kicking information; The control module controls the opening of the vehicle's trunk when the confidence level of the kicking event is higher than a confidence threshold.
[0014] Thirdly, embodiments of the present invention provide an electronic device, including: At least one processor; and At least one memory communicatively connected to the processor, wherein: The memory stores program instructions that can be executed by the processor, which can invoke the program instructions to perform the method as described in any of the first aspects.
[0015] Fourthly, embodiments of the present invention provide a storage medium including a stored program, wherein, when the program is executed, it controls the device where the storage medium is located to perform the method as described in any of the first aspects.
[0016] This invention employs dual verification via millimeter-wave radar and ultrasonic radar, combined with a master-slave collaborative and event-driven low-power architecture. By default, the millimeter-wave radar is used as the master sensor to continuously perform low-power scanning. When the millimeter-wave radar detects a kicking event, the ultrasonic radar is used for verification. This avoids unnecessary interference that may be caused by the continuous operation of the ultrasonic radar. It ensures stable operation of the system in complex environments such as rain, snow, fog, and dirt, and is not afraid of severe weather, while also reducing the overall power consumption of the system.
[0017] This invention combines the all-weather advantages of millimeter-wave radar with a dynamic weighting mechanism. The fusion algorithm verifies whether the two types of kicker information describe the same physical event through time alignment, and only when they highly match is it determined to be a valid action. Simultaneously, this invention dynamically and adaptively adjusts the time trigger threshold based on the user's historical behavior and environmental sensors, ensuring the reliability and efficiency of the system. Attached Figure Description
[0018] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0019] Figure 1 The diagram shown is a flowchart of a method for opening a vehicle trunk according to an embodiment of this application; Figure 2The diagram shown is a structural schematic of a vehicle trunk opening device provided in an embodiment of this application. Figure 3 The diagram shown is a structural schematic of an electronic device provided in an embodiment of this application. Detailed Implementation
[0020] To better understand the technical solution of this application, the embodiments of this application will be described in detail below with reference to the accompanying drawings.
[0021] It should be understood that the described embodiments are merely some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.
[0022] like Figure 1 The diagram shown is a flowchart of a method for opening a vehicle trunk according to an embodiment of the present invention. See also... Figure 1 The specific steps of this method include: S101 continuously senses the user's kicking motion using millimeter-wave radar and ultrasonic radar respectively, so as to obtain the first kicking information through millimeter-wave radar and the second kicking information through ultrasonic radar.
[0023] Specifically, the vehicle is equipped with both millimeter-wave radar and ultrasonic radar, which are used simultaneously to continuously sense the user's kicking motion. The kicking information collected by the millimeter-wave radar is the first kicking information, and the biological kicking information collected by the ultrasonic radar is the second kicking information.
[0024] The first and second kick information collected are both in the form of three-dimensional trajectory points, such as p(t)={x(t),y(t),z(t)}.
[0025] In this embodiment of the invention, a low-power architecture with master-slave collaboration is adopted. The millimeter-wave radar serves as the master sensor, continuously analyzing the collected first kick-off information to determine whether a primary kick-off event has occurred. When a primary kick-off event is determined to have occurred, S102 is executed to trigger the ultrasonic radar to re-evaluate the second kick-off information.
[0026] S102, when it is determined that a primary kicking event has occurred through the first kicking information, the confidence level of the target kicking event is generated based on the first kicking information and the second kicking information.
[0027] Specifically, the user's kicking action features are extracted from the obtained first kicking information, and feature scores are obtained for each first kicking feature.
[0028] The first kick feature is divided into trajectory features and velocity features. The trajectory features specifically include similarity features of movement direction, amplitude features, and trajectory smoothness features, while the velocity features specifically include velocity curve pattern features, dwell features, and total duration features.
[0029] The feature scores of each specific first kick feature are weighted and summed to obtain the primary kick event score.
[0030] Typically, vehicles are linked to user identity information and acquire basic user data, such as height, weight, range of motion, and exercise habits. The weights assigned to each feature score are then determined based on this basic user information.
[0031] When the score of the primary kicking event is higher than the preset primary kicking event score threshold, a primary kicking event is determined to have occurred. This triggers feature extraction of the secondary kicking information acquired by the ultrasonic radar.
[0032] The user's kicking action features are extracted from the second kicking information, and feature scores are obtained for each second kicking feature. The second kicking features include speed matching features and curve completion features.
[0033] The feature scores of the second kick-off feature are weighted and summed to obtain the second-level kick-off event score. Similarly, the weights assigned to the feature scores of each second kick-off feature are determined based on the user's basic information.
[0034] In this embodiment of the invention, a fusion algorithm is also needed to perform temporal alignment and feature association on the first kicking information and the second kicking information in order to verify whether the two pieces of information describe the same kicking event.
[0035] When identified as the same event, environmental information acquired by environmental sensors is used to obtain a first weight corresponding to the score of the primary kicking event and a second weight corresponding to the score of the secondary kicking event. The scores of the primary kicking event and the secondary kicking event are then weighted and summed using the first and second weights to obtain the confidence level of the target kicking event.
[0036] In determining the first and second weights, since environmental factors such as rain, snow, and dirt have a significant impact on the performance of ultrasonic radar, the first and second weights are dynamically adjusted based on the environmental information collected by the sensor.
[0037] In this embodiment of the invention, an environmental factor library is pre-set, storing environmental adjustment factors corresponding to different environmental conditions. Environmental adjustment factors are determined from the pre-set environmental factor library based on collected environmental information. The basic weights are adjusted using these environmental adjustment factors to obtain a first weight. Then, a second weight is obtained based on the first weight.
[0038] Generally, the more severe the environment represented by environmental information, the greater the corresponding environmental adjustment factor will be, and the higher the corrected first weight will be.
[0039] For example, the range of environmental regulation factors in the environmental factor library is [0,1]. The better the environment, the closer the environmental regulation factor is to 0, and the worse the environment, the closer the environmental regulation factor is to 1.
[0040] When adjusting the basic weights of millimeter-wave radar using the environmental adjustment factor E, it can be specifically done through the formula R. _urc =R_ urc_base (1-γ E), and α=R _crs / (R _crs +R _urc The first weight is calculated. The second weight is β = 1 - α.
[0041] Where γ is an environmental parameter, usually a constant set empirically, E is an environmental adjustment factor, and R_ urc_base The baseline threshold, typically derived from laboratory calibration and performance testing, is R. _urc R represents the confidence level of the ultrasonic radar. _crs Let α represent the confidence level of the millimeter-wave radar, and α be the first weight.
[0042] In the above formula, the harsher the environment, the larger the environmental regulation factor E, and the greater the relationship with the basic threshold R_ urc_base The lower the confidence level of the ultrasonic radar used to represent the signal after multiplication, the higher the weight of the millimeter-wave radar in calculating the first weight, and thus the higher the first weight. A higher first weight corresponds to a lower second weight. In other words, in adverse weather conditions, the first signal obtained from the millimeter-wave radar is given more weight.
[0043] S103, when the confidence level of the kicking event is higher than the confidence level threshold, control the opening of the vehicle's trunk.
[0044] Specifically, before comparing the confidence level of the target kicking event with the confidence threshold, the confidence threshold needs to be adjusted to find a confidence threshold that better matches the current environment and the accuracy of the system's judgment.
[0045] Generally, the confidence threshold is dynamically adjusted using basic thresholds, environmental information, historical accuracy information, and false alarm information to seek the optimal balance between false triggers and missed triggers.
[0046] For example, the baseline threshold can be adjusted based on historical accuracy. When historical accuracy is low, the environment is harsher, and the recent false alarm rate is higher, the baseline threshold will be adjusted higher, making it less likely to cause false triggers.
[0047] The following is a formula for calculating a confidence threshold: T_ adaptive =[ T0+λ (1-T) Historical )]+η E+ξ FP_ recent .
[0048] Among them, T_ adaptive The final calculated confidence threshold is defined by T0 as the base threshold, and T... Historical FP_ represents historical accuracy, E represents the environmental adjustment factor obtained from environmental information, and FP_ represents the historical accuracy. recent λ, η, and ξ represent the recent false alarm rate, which is a constant set based on experimental parameters. The recent false alarm rate is the false alarm rate within the most recent time frame, reported by the user after an accidental touch.
[0049] The confidence level of the target kicking event calculated by S102 is compared with the dynamically adjusted confidence threshold. When the confidence level is higher than the confidence threshold, the trunk is opened; when the confidence level is lower than the confidence threshold, the trunk is kept closed.
[0050] This invention employs dual verification via millimeter-wave radar and ultrasonic radar, combined with a master-slave collaborative and event-driven low-power architecture. By default, the millimeter-wave radar is used as the master sensor to continuously perform low-power scanning. When the millimeter-wave radar detects a kicking event, the ultrasonic radar is used for verification. This avoids unnecessary interference that may be caused by the continuous operation of the ultrasonic radar. It ensures stable operation of the system in complex environments such as rain, snow, fog, and dirt, and is not afraid of severe weather, while also reducing the overall power consumption of the system.
[0051] This invention combines the all-weather advantages of millimeter-wave radar with a dynamic weighting mechanism. The fusion algorithm verifies whether the two types of kicker information describe the same physical event through time alignment, and only when they highly match is it determined to be a valid action. Simultaneously, this invention dynamically and adaptively adjusts the time trigger threshold based on the user's historical behavior and environmental sensors, ensuring the reliability and efficiency of the system.
[0052] Optionally, in this embodiment of the invention, when executing S102, it is necessary to calculate the feature score of each first kicker feature and the feature score of each second kicker feature respectively.
[0053] When calculating the feature scores of each first kick feature, it is necessary to obtain the feature scores of motion direction similarity feature, motion amplitude feature, trajectory smoothness feature, as well as velocity curve pattern feature, dwell feature, and total duration feature.
[0054] The approach and distance vectors of the kicking action are obtained from the first kicking information, and the feature score of the motion direction similarity feature is obtained based on the directional angle between the approach and distance vectors.
[0055] Among them, motion direction similarity is used to characterize whether the direction of leg movement remains consistent during a single kicking action by a user. Since a purposeful kicking action typically has a unidirectional and coherent trajectory, rather than a chaotic movement, directional consistency is obtained by calculating the angle θ between the approaching and distant vectors, thus characterizing its feature score.
[0056] For example, the formula for the feature score of motion amplitude features is: cosθ=(V_ approach ·V_ retreat ) / (‖V_ approach || ||V_ retreat ||); S_ direction =max(0,(1-cosθ) / 2) Among them, V_ approach To be closer to the vector, V_ retreat Let θ be the moving vector, and θ be the angle between the approaching and moving vectors. Ideally, the closer the directions of the approaching and moving vectors are to 180°, the closer cosine is to -1. In this case, the feature score S_ of the similarity of motion directions... direction The closer it is to 1, the closer it is to 0.
[0057] The vertical and horizontal amplitudes of the kicking motion are obtained from the first kicking information, and feature scores of the motion amplitude features are obtained based on the preset motion amplitude function, vertical amplitude, and horizontal amplitude.
[0058] Among them, the motion amplitude feature is used to characterize the distance or spatial span of the leg millimeter-wave radar movement within the effective detection area during the user's kicking action, thereby ensuring that the kicking action is purposefully occurring in a specific area under the trunk.
[0059] For example, the formula for the feature score of motion amplitude features is: S_ amplitude =f_amp(A_ vertiacl A_ horizontal ) Among them, A_ vertiacl A_ represents the vertical motion amplitude, and A_ represents the difference between the maximum and minimum points of motion in the vertical direction. horizontal is the horizontal motion amplitude, and is the difference between the maximum and minimum points of motion in the horizontal direction. The f_amp function is a preset function based on experimental data, used to map the feature scores of motion amplitude characteristics under corresponding vertical and horizontal motion amplitudes.
[0060] The motion acceleration of the kicking action is obtained by using the first kicking information, and the feature score of the trajectory smoothness feature is obtained based on the variance of the motion acceleration.
[0061] Among them, trajectory smoothness is used to characterize the continuity and naturalness of the leg movement trajectory in a kicking motion. A natural biological movement trajectory is usually a smooth, continuous curve, rather than a mechanical abrupt change, thus filtering out interference from non-biological organisms.
[0062] For example, the formula for the feature score of trajectory smoothness feature is: S_ smoothness =1 / (1+Var(‖a(t)‖)) Where a(t) = d²p / dt² is the motion acceleration extracted based on the trajectory point sequence. First, the acceleration vector is estimated from the discrete trajectory points of the first kick information, and its variance is obtained by taking the modulus to represent the fluctuation. When the variance is small, it indicates uniform motion, and the feature score S_ of the trajectory smoothness feature is [value missing]. smoothness It will be closer to 1, otherwise it will be closer to 0.
[0063] The average positive and negative acceleration values of the kicking action are obtained from the first kicking information, and the feature score of the velocity curve pattern feature is obtained based on the product of the average positive and negative acceleration values.
[0064] The velocity curve pattern feature is used to characterize the change in leg velocity over time throughout the entire duration of the kicking event. During this process, due to the clear intent, the kicking action should exhibit distinct acceleration and deceleration phases.
[0065] For example, the formula for the feature score of the velocity curve pattern feature is: S_ speed =1 / (1+exp(-k (|a_ positive a_ negative )|-φ))) Among them, a_positive a_ is the mean of positive acceleration. negative The sigmoid function represents the mean of negative acceleration, and k is a constant set empirically to control the steepness of the curve. A larger k value results in a steeper curve, making the function more sensitive to the product of the mean positive and negative accelerations and providing stronger differentiation. A decisive kick will have a clear acceleration and deceleration process. The larger the absolute value of the product of the mean positive and negative accelerations, the more sufficient the acceleration and deceleration are, conforming to the motion law of a kick. Furthermore, the sigmoid function maps the product value to the range (0, 1), with a larger product approaching 1. Optionally, a threshold φ can be set to determine if the intention is clear enough. When the product is greater than φ, the function output will be greater than 0.5 and quickly approach 1; conversely, the output will approach 0.
[0066] The low-speed movement time when the speed of the kick is lower than the preset speed threshold is obtained by using the first kick information, and the feature score of the dwell feature is obtained based on the low-speed movement time and the preset low-speed movement reference time. The dwell feature is used to characterize whether the user's leg pauses briefly and intentionally under the sensor during a kicking motion. Since a kicking motion is a process of kicking out, dwelling, and retracting, this dwelling process is used to obtain the user's intention, indicating that the user is not swinging their leg randomly, but consciously extending their foot to the sensing area and waiting for feedback. This can effectively eliminate interference from continuous movements.
[0067] For example, the formula for the feature score of the stay feature is: S_ dwell =min(1,t_ dwell / T_ max_dwell ) Among them, t_ dwell T_ represents the duration of low-speed motion when the motion speed is below a preset speed threshold. max_dwell The preset low-speed motion reference time is t_. dwell The dwell time must be greater than the minimum dwell time; otherwise, it is 0. The closer the low-speed movement time is to the reference time, the closer the dwell feature score is to 1.
[0068] The total motion time of the kicking action is obtained by using the first kicking information, and the feature score of the total duration feature is obtained by using the total motion time, the preset total motion reference time, and the total motion time reference range.
[0069] The total duration feature is used to characterize the total length of time from the start to the end of a kicking motion. Since a complete kicking motion usually has a fixed duration, a duration that is too short or too long may be due to other interferences.
[0070] For example, the formula for the feature score of the total duration feature is: S_ duration =1-min(1, |T_ total -T_ ideal | / T_ range ) Among them, T_ total Let T_ be the total motion time. ideal T_ is the total reference time for the motion. range The total motion time reference range is usually a set ideal range [T_ min T_ max The closer the total exercise time is to the total exercise reference time, the closer the score is to 1; otherwise, the closer it is to 0.
[0071] When calculating the feature scores of each second kick feature, it is necessary to obtain the feature scores of the speed matching feature and the curve completion feature respectively.
[0072] The actual speed of the kicking action during the kicking and retraction phases is obtained by using the second kicking information, and the feature score of the speed matching feature is obtained based on the difference between the actual speed and the preset speed.
[0073] Among them, the velocity matching feature is used to characterize the degree of matching between the distance and time variation detected by ultrasonic radar and the ideal curve. In a standard kicking motion detected by ultrasonic radar, the change in distance and time between the user's legs follows a V-shaped curve. An ideal V-shaped curve has a distance that first decreases and then increases, with a symmetrical rate of change.
[0074] For example, the formula for the feature score of the velocity matching feature is: S_ v =exp{-((k_ down -k_ down_ideal )^²+(k_ up -k_ up_ideal )^²) / (2 σ_k^²)} Among them, k_ down k_ represents the actual speed during the kick-out phase. down_ideal The preset speed for the kick-out phase, k_ up k_ represents the actual velocity during the recovery phase. up_ideal The preset speed is the speed for the recovery phase, and σ_k is the tolerance parameter. The smaller the difference between the actual speed and the preset speed, the closer the actual action is to the ideal state, and the closer the feature score of the speed matching feature is to 1; otherwise, it is closer to 0.
[0075] The effective movement time of the kicking action is obtained by using the second kicking information, and the feature score of the curve completion feature is obtained based on the effective movement time and the total movement time.
[0076] Among them, the curve completion feature is used to characterize whether the detected signal is a complete and coherent action, rather than interference.
[0077] For example, the formula for the feature score of the curve completion feature is: S_ completeness =t_ valid / T_ total Among them, t_ valid For effective exercise time, T_ total The total motion time is denoted as . The closer the detected effective motion time is to the total motion time, the more clear and continuous leg movement signals are detected throughout the entire time period. In this case, the feature score of the curve completion feature is closer to 1; otherwise, it is closer to 0.
[0078] Corresponding to the above-described method for opening a vehicle trunk, this application also provides a vehicle trunk opening device. See [link to related documentation]. Figure 2 This is a schematic diagram of a vehicle trunk opening device provided in an embodiment of this application. The vehicle trunk opening device may include: an acquisition module 201, a generation module 202, and a control module 203.
[0079] The acquisition module 201 continuously senses the user's kicking action through millimeter-wave radar and ultrasonic radar respectively, so as to acquire first kicking information through the millimeter-wave radar and second kicking information through the ultrasonic radar.
[0080] The generation module 202, when it is determined that a primary kicking event has occurred through the first kicking information, generates a target kicking event confidence level based on the first kicking information and the second kicking information.
[0081] The control module 203 controls the opening of the vehicle trunk when the confidence level of the kicking event is higher than the confidence level threshold.
[0082] Figure 3 This is a schematic diagram illustrating the structure of one embodiment of the electronic device described in this specification. Specifically, the electronic device can be implemented as a vehicle executing the trunk opening method provided in this embodiment. Figure 3 As shown, the electronic device may include at least one processor; and at least one memory communicatively connected to the processing unit, wherein the memory stores program instructions executable by the processing unit, and the processor can execute the vehicle trunk opening method provided in this embodiment by calling the program instructions.
[0083] The aforementioned electronic device can be a device capable of intelligent dialogue with the user, such as a cloud server. This specification does not limit the specific form of the electronic device in the embodiments. It is understood that the electronic device here refers to the machine mentioned in the method embodiments.
[0084] Figure 3 A block diagram of an exemplary electronic device suitable for implementing embodiments of this specification is shown. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments described in this specification.
[0085] like Figure 3 As shown, the electronic device is represented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: one or more processors 310, communication interface 320, memory 330, and communication bus 340 connecting different system components (including memory 330, communication interface 320 and processor 310).
[0086] Communication bus 340 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) buses, Micro Channel Architecture (MAC) buses, Enhanced ISA buses, Video Electronics Standards Association (VESA) local buses, and Peripheral Component Interconnect (PCI) buses.
[0087] Electronic devices typically include a variety of computer-readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, and removable and non-removable media.
[0088] Memory 330 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. Memory 330 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments described herein.
[0089] A program / utility having a set (at least one) of program modules may be stored in memory 330. Such program modules include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. The program modules typically perform the functions and / or methods described in the embodiments of this specification.
[0090] The processor 310 executes various functional applications and data processing by running programs stored in the memory 330, such as implementing the vehicle trunk opening method provided in the embodiments shown in this specification.
[0091] This specification provides a non-transitory computer-readable storage medium that stores computer instructions that cause the computer to execute the vehicle trunk opening method provided in the embodiments shown in this specification.
[0092] The aforementioned non-transitory computer-readable storage medium may be any combination of one or more computer-readable media. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory, optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in connection with an instruction execution system, apparatus, or device.
[0093] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.
[0094] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.
[0095] Computer program code for performing the operations described herein can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, as well as conventional procedural programming languages such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0096] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0097] 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 as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this specification, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0098] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this specification includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which the embodiments of this specification pertain.
[0099] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."
[0100] It should be noted that the terminals involved in the embodiments of this specification may include, but are not limited to, personal computers (PCs), personal digital assistants (PDAs), wireless handheld devices, tablet computers, mobile phones, MP3 players, MP4 players, etc.
[0101] In the embodiments provided in this specification, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.
[0102] Furthermore, the functional units in the various embodiments of this specification can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in a combination of hardware and software functional units.
[0103] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of this specification.
[0104] The above description is merely a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of protection of this specification.
Claims
1. A method for opening a vehicle trunk, characterized in that, The method includes: The user's kicking motion is continuously sensed by millimeter-wave radar and ultrasonic radar respectively, so as to obtain the first kicking information by the millimeter-wave radar and the second kicking information by the ultrasonic radar. When it is determined that a primary kicking event has occurred based on the first kicking information, a target kicking event confidence score is generated based on the first kicking information and the second kicking information. When the confidence level of the kicking event is higher than the confidence threshold, the vehicle trunk is opened.
2. The method according to claim 1, characterized in that, When it is determined through the first kicking information that a primary kicking event has occurred, the following steps are included: The feature scores of each first kick feature are obtained through the first kick information. The first kick features include trajectory features and speed features. The trajectory features include motion direction similarity features, motion amplitude features, and trajectory smoothness features. The speed features include speed curve pattern features, dwell features, and total duration features. The feature scores of each of the first kicking features are weighted and summed to obtain the primary kicking event score; When the score of the primary kicking event is higher than the preset primary kicking event score threshold, a primary kicking event is determined to have occurred.
3. The method according to claim 2, characterized in that, The step of obtaining feature scores for each first kick feature based on the first kick information includes: The approach vector and the distance vector of the kicking action are obtained by using the first kicking information, and the feature score of the motion direction similarity feature is obtained according to the directional angle between the approach vector and the distance vector. The vertical and horizontal amplitudes of the kicking motion are obtained from the first kicking information, and the feature scores of the motion amplitude features are obtained according to the preset motion amplitude function, the vertical amplitude, and the horizontal amplitude. The motion acceleration of the kicking action is obtained through the first kicking information, and the feature score of the trajectory smoothness feature is obtained based on the variance of the motion acceleration. The average positive acceleration and average negative acceleration of the kicking action are obtained through the first kicking information, and the feature score of the velocity curve pattern feature is obtained based on the product of the average positive acceleration and the average negative acceleration. The low-speed movement time when the movement speed is lower than a preset speed threshold is obtained through the first kicking information, and the feature score of the dwell feature is obtained based on the low-speed movement time and the preset low-speed movement reference time. The total movement time of the kicking action is obtained through the first kicking information, and the feature score of the total duration feature is obtained through the total movement time, the preset total movement reference time, and the total movement time reference range.
4. The method according to claim 1, characterized in that, The step of generating the target kick event confidence score based on the first kick information and the second kick information includes: The feature scores of each second kick feature are obtained through the second kick information. The second kick features include speed matching features and curve completion features. The feature scores of each second kick feature are weighted and summed to obtain the score of the second-level kick event. Based on the environmental information, obtain the first weight corresponding to the score of the primary kicking event and the second weight corresponding to the score of the secondary kicking event. The confidence level of the target kicking event is obtained by weighting and summing the scores of the primary kicking event and the secondary kicking event using the first weight and the second weight.
5. The method according to claim 4, characterized in that, The step of obtaining feature scores for each second kick feature using the second kick information includes: The actual speed of the kicking action during the kicking and retraction phases is obtained through the second kicking information, and the feature score of the speed matching feature is obtained based on the difference between the actual speed and the preset speed. The effective movement time of the kicking action is obtained through the second kicking information, and the feature score of the curve completion feature is obtained based on the effective movement time and the total movement time.
6. The method according to claim 4, characterized in that, Based on environmental information, a first weight corresponding to the score of the primary kicking event and a second weight corresponding to the secondary kicking event are obtained, including: Based on the environmental information, environmental regulation factors are determined from a preset environmental factor database; The first weight is obtained by adjusting the basic weight using the environmental adjustment factor. The second weight is determined based on the first weight; Wherein, the more severe the environment represented by the environmental information, the greater the environmental adjustment factor, and the higher the first weight.
7. The method according to claim 1, characterized in that, After generating the target kick event confidence score based on the first kick information and the second kick information, the method further includes: Acquire environmental information, historical accuracy information, and false alarm information respectively; The preset base threshold is corrected using the environmental information, the historical accuracy information, and the false alarm information to obtain the confidence threshold. Specifically, the more severe the environment represented by the environmental information, the lower the historical accuracy represented by the historical accuracy information, and the higher the false alarm rate represented by the false alarm information, the higher the confidence threshold will be adjusted.
8. A vehicle trunk opening device, characterized in that, The device includes: The acquisition module continuously senses the user's kicking action through millimeter-wave radar and ultrasonic radar respectively, so as to acquire the first kicking information through the millimeter-wave radar and the second kicking information through the ultrasonic radar. The generation module, when it is determined that a primary kicking event has occurred based on the first kicking information, generates a target kicking event confidence level based on the first kicking information and the second kicking information; The control module controls the opening of the vehicle's trunk when the confidence level of the kicking event is higher than a confidence threshold.
9. An electronic device, characterized in that, include: At least one processor; as well as At least one memory communicatively connected to the processor, wherein: The memory stores program instructions that can be executed by the processor, and the processor can invoke the program instructions to perform the method as described in any one of claims 1 to 7.
10. A storage medium, characterized in that, The storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the storage medium is located to perform the method according to any one of claims 1 to 7.
