Trunk self-adaptive adjustment control method and system and computer equipment
By detecting user posture and behavioral characteristics, identifying the shape and size of items, and adjusting the posture of the rear seats and shelves, the problem of insufficient intelligent design of the trunk is solved, realizing adaptive storage space adjustment and improving user experience and safety.
Patent Information
- Application Number
- CN202411196544.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-11-19
AI Technical Summary
In existing technologies, the intelligent design of vehicle trunks is limited to contactless opening functions, lacking intelligent adjustment and adaptive design of internal storage space. This leads to problems such as users needing to manually adjust the storage space or items shifting or colliding while driving.
By detecting and recognizing the user's posture and behavioral characteristics, the system can predict the user's intention to use the trunk and identify the shape and size of the items being carried. It can then adjust the posture of the rear seats and storage shelves to adapt to the user's storage needs, thus achieving intelligent adjustment of the trunk space.
It improves the intelligence of the trunk storage function and user comfort, avoids problems such as manual adjustment by users and displacement or collision of items due to oversized items or mismatched storage space, and improves response efficiency and accuracy.
Smart Images

Figure CN118977665A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the field of automatic control, and in particular to a method, system and computer equipment for adaptively adjusting and controlling a trunk. Background Art
[0002] With the rapid development of the automobile industry, the intelligence and comfort of vehicles in use have gradually attracted the attention of vehicle users, especially the intelligence level of the trunk in use, which is regarded by more and more users as an extremely important indicator of vehicle intelligence and comfort.
[0003] In the prior art, the intelligent design of the vehicle trunk is usually limited to the intelligent sensing opening function, such as the most common "one-kick" function, that is, the contactless trunk automatic opening function. The designed foot motion sensing electric tailgate is also indispensable for smart models. However, the existing trunk-related intelligent design is still only centered around the contactless opening function, and still lacks intelligent adjustment and adaptive design of the storage space inside the vehicle trunk.
[0004] Therefore, how to design an intelligent adjustment method for the trunk to improve the intelligence level of the trunk storage function and the comfort of users is an urgent problem to be solved. Summary of the invention
[0005] Based on this, the purpose of the present invention is to provide a trunk adaptive adjustment control method, system and computer equipment, which detects and identifies the user's human posture characteristics and human behavior characteristics to predict the user's trunk usage intention in advance, and then identifies the shape characteristics and size characteristics of the user's carried items to understand the user's storage needs, thereby adjusting the vehicle's rear seat posture and the vehicle's rear shelf posture to adapt to the user's storage needs and reasonably adjust the overall space utilization of the trunk, thereby avoiding the problem of the user needing to manually adjust the trunk storage space due to the large items carried, and also avoiding the problem of the items in the storage space being displaced or collided during driving due to the large size of the storage space. The present invention greatly improves the intelligence level of the vehicle trunk storage function and user comfort.
[0006] The present invention provides a trunk adaptive adjustment control method, comprising: When a user signal is detected, it is determined whether the user intends to approach; When it is determined that the user has an intention to approach, user behavior recognition is performed to determine whether the user has an intention to use the trunk, and the user behavior recognition is used to identify the user's human posture characteristics and human behavior characteristics; When it is determined that the user intends to use the trunk, the user's holding state recognition is performed to determine the user's placement needs. The user's holding state recognition is used to identify the shape and size characteristics of the items carried by the user; Adjust the posture of the vehicle's rear seats and the vehicle's rear shelf according to the user's storage needs to complete adaptive adjustment of the trunk space.
[0007] In summary, according to the above-mentioned trunk adaptive adjustment control method, by detecting and identifying the user's human posture characteristics and human behavior characteristics, the user's trunk usage intention can be predicted in advance, and then the shape characteristics and size characteristics of the user's carried items can be identified to understand the user's placement needs, thereby adjusting the vehicle's rear seat posture and the vehicle's rear shelf posture to adapt to the user's placement needs and reasonably adjust the overall space utilization of the trunk, thereby avoiding the problem of the user needing to manually adjust the trunk storage space due to the large items carried, and also avoiding the problem of the items in the storage space being displaced or collided during driving due to the large size of the storage space. The present invention greatly improves the intelligence level of the vehicle trunk storage function and user comfort. Specifically, when a user signal is detected, it is determined whether the user has an intention to approach, thereby avoiding misjudgment caused by the user approaching when not in use, and improving overall accuracy and efficiency. When it is determined that the user has an intention to approach, user behavior recognition is performed to determine whether the user has an intention to use the trunk. The user behavior recognition is used to identify the user's body posture characteristics and body behavior characteristics, and identify in advance whether the user needs to use the trunk, so as to improve response efficiency and avoid energy loss caused by misjudgment. When it is determined that the user has an intention to use the trunk, the user's holding state recognition is performed to determine the user's placement needs. The user's holding state recognition is used to identify the shape characteristics and size characteristics of the items carried by the user, and the user's placement needs are anticipated, which improves the efficiency of the overall trunk storage space adjustment. The posture of the vehicle's rear seats and the posture of the vehicle's rear shelf are adjusted according to the user's placement needs to complete the adaptive adjustment of the trunk space. The present invention greatly improves the intelligence level and user comfort of the vehicle's trunk storage function.
[0008] Furthermore, when the user signal is detected, the step of determining whether the user has an approaching intention specifically includes: When a wireless signal is detected to be within the vehicle detection radius, the wireless signal is identified to determine whether it is a wireless signal of the user corresponding to the current vehicle, wherein the wireless signal includes a vehicle key signal and a signal of an authenticated wireless communication device; If it is determined that the wireless signal is a wireless signal of the user corresponding to the current vehicle, the user audio and video collection in the direction of the wireless signal is started to perform user face recognition and voiceprint recognition; If the user face recognition is determined to be an authenticated face or the user voiceprint recognition is determined to be an authenticated voiceprint, the transmission source moving path of the wireless signal is calculated to determine whether the transmission source moving path meets the preset approach path standard; If the moving path of the transmitting source meets the preset approach path standard, it is determined that the user has an approach intention.
[0009] Furthermore, when it is determined that the user has an approaching intention, the step of performing user behavior recognition to determine whether the user has an intention to use the trunk specifically includes: When it is determined that the user intends to approach, the user image is collected; Dividing the user image into multiple single-frame user images according to a time sequence, selecting any user image from the single-frame user images, adjusting the brightness of the user image according to the parking environment, extracting human posture features of the user image, and judging whether the current user is likely to place an object according to the human posture features; If it is determined that the current user may place an object, the human skeleton joints of all single-frame user images are calibrated, and all single human skeleton joints are aggregated according to the time series and input into the graph convolutional neural network. The global time series feature is enhanced according to the context enhancement module to obtain human behavior characteristics; It is determined whether the current user intends to use the trunk based on the human behavior characteristics.
[0010] Furthermore, when it is determined that the user intends to use the trunk, the step of identifying the state of the user's holding items to determine the user's placement needs specifically includes: When it is determined that the user intends to use the trunk, the high-position and middle-position image acquisition of the trunk is started to obtain the image of the user's handheld object, and the shape characteristics of the user's handheld object are extracted, and then the remaining storage space status in the trunk is obtained to match the remaining storage space status with the shape characteristics, and determine whether the placement conditions are met; If it is determined that the insertion conditions are met, the trunk low-position image acquisition is started to identify the user's leg and foot movements and match the preset trunk opening action. When the user's leg and foot movements are consistent with the preset trunk opening action, the trunk storage space is opened; If it is determined that the placement condition is not met, the size characteristics of the object held by the user are obtained according to the image of the object held by the user, and the placement requirements of the current user are calculated.
[0011] Furthermore, the step of adjusting the posture of the rear seats and the posture of the rear shelf of the vehicle according to the user's storage requirements to complete the adaptive adjustment of the trunk space specifically includes: Acquire the storage requirements of the current user, and calculate the required adjustment size of the trunk storage space according to the storage requirements, so as to select the size level of the trunk storage space; If the selected trunk storage space size gear is the standard size gear, adjust the height of the vehicle's rear shelf to the highest position; If the selected trunk storage space size gear is the enlarged size gear, adjust the height of the vehicle's rear shelf to the highest position, adjust the rear seat cushions of the vehicle to move forward to the limit point, and adjust the backrests of the rear seat of the vehicle to tilt forward to be perpendicular to the cushions; If the trunk storage space size is selected to be the largest size, adjust the height of the vehicle's rear shelf to the highest position, adjust the cushions of the vehicle's rear seats to move forward to the limit point, and adjust the backrests of the vehicle's rear seats to tilt forward to a horizontal position.
[0012] Furthermore, the step of selecting the size of the trunk storage space may further include: Start the in-car image acquisition; Detect whether there is any object placed on the upper part of the rear shelf of the vehicle; If there is no placed object, the upper pressure of the rear shelf of the vehicle is detected to determine whether there is any unrecognized object. If the upper pressure of the rear shelf of the vehicle is detected to be lower than the preset pressure threshold, the rear shelf of the vehicle is adjusted according to the selected trunk storage space size gear; If there is any placed object, the shape and size characteristics of the placed object are identified to determine whether the placed object will limit the height adjustment of the rear shelf of the vehicle to the highest level. If it is determined that the placed object will limit the height adjustment of the rear shelf of the vehicle to the highest level, an anti-collision warning is issued; Then detect whether there is any object placed on the rear seat of the vehicle; If there is no object placed, the cushion pressure of the rear seat of the vehicle is detected to determine whether there is any unrecognized object placed. If the cushion pressure of the rear seat of the vehicle is detected to be lower than a preset pressure threshold, the rear seat of the vehicle is adjusted according to the selected trunk storage space size gear; If there is any placed object, the shape and size characteristics of the placed object are identified to determine whether the placed object will limit the inclination adjustment of the backrest of the rear seat of the vehicle. If it is determined that the placed object will limit the inclination adjustment of the backrest of the rear seat of the vehicle, an anti-pinch warning is issued.
[0013] Furthermore, the step of adjusting the posture of the rear seats and the posture of the rear shelf of the vehicle according to the user's storage requirements to complete the adaptive adjustment of the trunk space further includes: When the user is in the car, the system detects the user's voice and gestures in real time to identify the user's request to place items. If the user's storage request is recognized, the trunk storage space is calculated to determine whether the trunk can be placed; If it is determined that the trunk can be placed, the shape and size characteristics of the object held by the user are identified, so as to calculate the height of the rear shelf of the vehicle and the inclination angle of the backrest of the rear seat of the vehicle that need to be adjusted according to the shape and size characteristics; When the required adjustment height of the vehicle's rear shelf board and the vehicle's rear seat backrest inclination angle both meet driving safety requirements, adjust the vehicle's rear shelf board height and the vehicle's rear seat backrest inclination angle to allow the user to complete trunk storage in the vehicle.
[0014] The present invention provides a trunk adaptive adjustment control system, comprising: A detection module, used to determine whether the user has an approaching intention when a user signal is detected; A recognition module, for performing user behavior recognition when it is determined that the user intends to approach the trunk, so as to determine whether the user intends to use the trunk, wherein the user behavior recognition is used to recognize the user's body posture characteristics and body behavior characteristics; When it is determined that the user intends to use the trunk, the user's holding state recognition is performed to determine the user's placement needs. The user's holding state recognition is used to identify the shape and size characteristics of the items carried by the user; The adjustment module is used to adjust the posture of the vehicle's rear seats and the posture of the vehicle's rear shelf according to the user's storage needs, so as to complete the adaptive adjustment of the trunk space.
[0015] The present invention also provides a storage medium, wherein the storage medium stores one or more programs, and when the programs are executed by a processor, the trunk adaptive adjustment control method as described above is implemented.
[0016] The present invention also provides a computer device, the computer device comprising a memory and a processor, wherein: The memory is used to store computer programs; When the processor is used to execute the computer program stored in the memory, the above-mentioned trunk adaptive adjustment control method is implemented. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 This is a flow chart of the trunk adaptive adjustment control method proposed in the first embodiment of the present invention; Figure 2 This is a flow chart of a trunk adaptive adjustment control method proposed in a second embodiment of the present invention; Figure 3 This is a schematic structural diagram of a trunk adaptive adjustment control system proposed in the third embodiment of the present invention.
[0018] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION
[0019] In order to facilitate understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are provided in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.
[0020] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.
[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.
[0022] See also Figure 1 , which is a flow chart of a trunk adaptive adjustment control method according to a first embodiment of the present invention, the trunk adaptive adjustment control method comprises steps S01 to S04, wherein: Step S01: when a user signal is detected, determining whether the user has an approaching intention; It should be noted that in this embodiment, when a wireless signal is detected to appear in the vehicle detection radius, the wireless signal is identified to determine whether it is a wireless signal of the user corresponding to the current vehicle, and the wireless signal includes a vehicle key signal and an authenticated wireless communication device signal; If it is determined that the wireless signal is a wireless signal of the user corresponding to the current vehicle, the user audio and video collection in the direction of the wireless signal is started to perform user face recognition and voiceprint recognition; If the user face recognition is determined to be an authenticated face or the user voiceprint recognition is determined to be an authenticated voiceprint, the transmission source moving path of the wireless signal is calculated to determine whether the transmission source moving path meets the preset approach path standard; If the moving path of the transmitting source meets the preset approach path standard, it is determined that the user has an approach intention.
[0023] Step S02: when it is determined that the user has an approaching intention, user behavior recognition is performed to determine whether the user has an intention to use the trunk, wherein the user behavior recognition is used to identify the user's body posture characteristics and body behavior characteristics; It should be noted that in this embodiment, when it is determined that the user has an approaching intention, the user image is collected; Dividing the user image into multiple single-frame user images according to a time sequence, selecting any user image from the single-frame user images, adjusting the brightness of the user image according to the parking environment, extracting human posture features of the user image, and judging whether the current user is likely to place an object according to the human posture features; If it is determined that the current user may place an object, the human skeleton joints of all single-frame user images are calibrated, and all single human skeleton joints are aggregated according to the time series and input into the graph convolutional neural network. The global time series feature is enhanced according to the context enhancement module to obtain human behavior characteristics; It is determined whether the current user intends to use the trunk based on the human behavior characteristics.
[0024] Step S03: When it is determined that the user intends to use the trunk, the user's holding state recognition is performed to determine the user's placement requirements. The user's holding state recognition is used to identify the shape and size characteristics of the items carried by the user; It should be noted that in this embodiment, when it is determined that the user intends to use the trunk, the high-position and middle-position image acquisition of the trunk is turned on to obtain the image of the user's handheld object, and extract the shape characteristics of the user's handheld object, and then obtain the remaining storage space status in the trunk, so as to match the remaining storage space status with the shape characteristics and determine whether the placement conditions are met; If it is determined that the insertion conditions are met, the trunk low-position image acquisition is started to identify the user's leg and foot movements and match the preset trunk opening action. When the user's leg and foot movements are consistent with the preset trunk opening action, the trunk storage space is opened; If it is determined that the placement condition is not met, the size characteristics of the object held by the user are obtained according to the image of the object held by the user, and the placement requirements of the current user are calculated.
[0025] Step S04: adjusting the posture of the rear seats and the posture of the rear shelf of the vehicle according to the user's storage needs to complete the adaptive adjustment of the trunk space; It should be noted that in this embodiment, the storage requirements of the current user are obtained, and the required adjustment size of the trunk storage space is calculated according to the storage requirements, so as to select the size level of the trunk storage space; If the selected trunk storage space size gear is the standard size gear, adjust the height of the vehicle's rear shelf to the highest position; If the selected trunk storage space size gear is the enlarged size gear, adjust the height of the vehicle's rear shelf to the highest position, adjust the rear seat cushions of the vehicle to move forward to the limit point, and adjust the backrests of the rear seat of the vehicle to tilt forward to be perpendicular to the cushions; If the selected trunk storage space size gear is the maximum size gear, adjust the height of the vehicle's rear shelf to the highest position, adjust the cushion of the vehicle's rear seat to move forward to the limit point, and adjust the backrest of the vehicle's rear seat to tilt forward to a horizontal position; In this embodiment, the step of selecting the size of the trunk storage space further includes: Start the in-car image acquisition; Detect whether there is any object placed on the upper part of the rear shelf of the vehicle; If there is no placed object, the upper pressure of the rear shelf of the vehicle is detected to determine whether there is any unrecognized object. If the upper pressure of the rear shelf of the vehicle is detected to be lower than the preset pressure threshold, the rear shelf of the vehicle is adjusted according to the selected trunk storage space size gear; If there is any placed object, the shape and size characteristics of the placed object are identified to determine whether the placed object will limit the height adjustment of the rear shelf of the vehicle to the highest level. If it is determined that the placed object will limit the height adjustment of the rear shelf of the vehicle to the highest level, an anti-collision warning is issued; Then detect whether there is any object placed on the rear seat of the vehicle; If there is no object placed, the cushion pressure of the rear seat of the vehicle is detected to determine whether there is any unrecognized object placed. If the cushion pressure of the rear seat of the vehicle is detected to be lower than a preset pressure threshold, the rear seat of the vehicle is adjusted according to the selected trunk storage space size gear; If there is any placed object, the shape and size characteristics of the placed object are identified to determine whether the placed object will limit the inclination adjustment of the backrest of the rear seat of the vehicle. If it is determined that the placed object will limit the inclination adjustment of the backrest of the rear seat of the vehicle, an anti-pinch warning is issued.
[0026] It should be noted that in this embodiment, when the user is in the car, the user's voice and control gestures are detected in real time to identify the user's placement request; If the user's storage request is recognized, the trunk storage space is calculated to determine whether the trunk can be placed; If it is determined that the trunk can be placed, the shape and size characteristics of the object held by the user are identified, so as to calculate the height of the rear shelf of the vehicle and the inclination angle of the backrest of the rear seat of the vehicle that need to be adjusted according to the shape and size characteristics; When the required adjustment height of the vehicle's rear shelf board and the vehicle's rear seat backrest inclination angle both meet driving safety requirements, adjust the vehicle's rear shelf board height and the vehicle's rear seat backrest inclination angle to allow the user to complete trunk storage in the vehicle.
[0027] In summary, according to the above-mentioned trunk adaptive adjustment control method, by detecting and identifying the user's human posture characteristics and human behavior characteristics, the user's trunk usage intention can be predicted in advance, and then the shape characteristics and size characteristics of the user's carried items can be identified to understand the user's placement needs, thereby adjusting the vehicle's rear seat posture and the vehicle's rear shelf posture to adapt to the user's placement needs and reasonably adjust the overall space utilization of the trunk, thereby avoiding the problem of the user needing to manually adjust the trunk storage space due to the large items carried, and also avoiding the problem of the items in the storage space being displaced or collided during driving due to the large size of the storage space. The present invention greatly improves the intelligence level of the vehicle trunk storage function and user comfort. Specifically, when a user signal is detected, it is determined whether the user has an intention to approach, thereby avoiding misjudgment caused by the user approaching when not in use, and improving overall accuracy and efficiency. When it is determined that the user has an intention to approach, user behavior recognition is performed to determine whether the user has an intention to use the trunk. The user behavior recognition is used to identify the user's body posture characteristics and body behavior characteristics, and identify in advance whether the user needs to use the trunk, so as to improve response efficiency and avoid energy loss caused by misjudgment. When it is determined that the user has an intention to use the trunk, the user's holding state recognition is performed to determine the user's placement needs. The user's holding state recognition is used to identify the shape characteristics and size characteristics of the items carried by the user, and the user's placement needs are anticipated, which improves the efficiency of the overall trunk storage space adjustment. The posture of the vehicle's rear seats and the posture of the vehicle's rear shelf are adjusted according to the user's placement needs to complete the adaptive adjustment of the trunk space. The present invention greatly improves the intelligence level and user comfort of the vehicle's trunk storage function.
[0028] See also Figure 2 , which is a flow chart of a trunk adaptive adjustment control method according to a second embodiment of the present invention, the trunk adaptive adjustment control method comprises steps S11 to S16, wherein: Step S11: when a wireless signal is detected to appear in the vehicle detection radius, the wireless signal is identified to determine whether it is a wireless signal of the user corresponding to the current vehicle, the wireless signal includes a vehicle key signal and a signal of an authenticated wireless communication device, if the wireless signal is determined to be a wireless signal of the user corresponding to the current vehicle, the user audio and video collection in the direction of the wireless signal is started to perform user face recognition and voiceprint recognition, if the user face recognition is determined to be an authenticated face or the user voiceprint recognition is determined to be an authenticated voiceprint, the wireless signal is subjected to a calculation of the transmission source moving path to determine whether the transmission source moving path meets the preset approach path standard, if the transmission source moving path meets the preset approach path standard, it is determined that the user has an approach intention; It should be noted that meeting the preset approach path standard in the present invention means that the mean vector direction of the user's emission source moving path points to the vehicle, or is consistent with the user's leaving path during this parking.
[0029] Step S12: when it is determined that the user has an intention to approach, the user image is collected, and the user image is divided into multiple single-frame user images according to the time series, and any user image in the single-frame user image is selected, and the brightness of the user image is adjusted according to the parking environment, and then the human posture features of the user image are extracted, and it is determined whether the current user has the possibility of placing objects according to the human posture features. If it is determined that the current user has the possibility of placing objects, the human skeleton joint points are calibrated for all single-frame user images, and all single human skeleton joint points are aggregated according to the time series and input into the graph convolutional neural network. The global time series feature enhancement is performed according to the context enhancement module to obtain the human behavior features, and it is determined whether the current user has the intention to use the trunk according to the human behavior features; Step S13: when it is determined that the user intends to use the trunk, the high-position and middle-position image acquisition of the trunk is started to obtain the image of the user's handheld object, and the shape features of the user's handheld object are extracted, and then the remaining storage space status in the trunk is obtained to match the remaining storage space status with the shape features, and determine whether the placement conditions are met. If it is determined that the placement conditions are met, the low-position image acquisition of the trunk is started to identify the user's leg and foot movements, and match the preset trunk opening movement. When the user's leg and foot movements are consistent with the preset trunk opening movement, the trunk storage space is opened. If it is determined that the placement conditions are not met, the size features of the user's handheld object are obtained according to the image of the user's handheld object, and the current user's placement needs are calculated; It should be noted that the preset trunk opening action in the present invention includes the user's kicking action, the sweeping action of the foot and other leg and foot movement actions.
[0030] Step S14: obtaining the storage demand of the current user, calculating the required adjustment size of the trunk storage space according to the storage demand, so as to select the size gear of the trunk storage space; if the selected size gear of the trunk storage space is the standard size gear, adjusting the height of the rear shelf of the vehicle to the highest position; if the selected size gear of the trunk storage space is the increased size gear, adjusting the height of the rear shelf of the vehicle to the highest position, adjusting the cushion of the rear seat of the vehicle to move forward to the limit point, adjusting the backrest of the rear seat of the vehicle to tilt forward to be perpendicular to the cushion; if the selected size gear of the trunk storage space is the maximum size gear, adjusting the height of the rear shelf of the vehicle to the highest position, adjusting the cushion of the rear seat of the vehicle to move forward to the limit point, and adjusting the backrest of the rear seat of the vehicle to tilt forward to be horizontal; Step S15: Start the in-vehicle image acquisition, detect whether there is any placed object on the upper part of the rear shelf of the vehicle, if there is no placed object, detect the upper pressure of the rear shelf of the vehicle to determine whether there is any unrecognized placed object, if it is detected that the upper pressure of the rear shelf of the vehicle is lower than the preset pressure threshold, adjust the rear shelf of the vehicle according to the selected trunk storage space size gear, if there is any placed object, identify the shape and size characteristics of the placed object to determine whether the placed object will limit the height adjustment of the rear shelf of the vehicle to the maximum, if it is determined that the placed object will limit the height adjustment of the rear shelf of the vehicle to the maximum If the pressure is high, an anti-collision warning is given, and then the rear seats of the vehicle are detected to see if there are any objects placed. If there are no objects placed, the cushion pressure of the rear seats of the vehicle is detected to determine if there are any unrecognized objects placed. If the cushion pressure of the rear seats of the vehicle is detected to be lower than the preset pressure threshold, the rear seats of the vehicle are adjusted according to the selected size gear of the trunk storage space. If there are any objects placed, the shape and size characteristics of the objects placed are identified to determine whether the objects placed will limit the tilt adjustment of the backrest of the rear seats of the vehicle. If it is determined that the objects placed will limit the tilt adjustment of the backrest of the rear seats of the vehicle, an anti-pinch warning is given. It should be noted that the preset pressure threshold in the present invention is the rated resistance value that the rear shelf of the vehicle or the cushion part of the rear seat of the vehicle can withstand when moving on the track at the rated power.
[0031] Step S16: When the user is in the vehicle, the user's voice and control gestures are detected in real time to identify the user's placement request. If the user's placement request is identified, the trunk storage space is calculated to determine whether the trunk can be placed. If it is determined that the trunk can be placed, the shape characteristics and size characteristics of the object held by the user are identified to calculate the required adjustment of the height of the rear shelf board of the vehicle and the inclination angle of the back of the rear seat of the vehicle according to the shape characteristics and size characteristics. When the required adjustment of the height of the rear shelf board of the vehicle and the inclination angle of the back of the rear seat of the vehicle meet the driving safety requirements, the height of the rear shelf board of the vehicle and the inclination angle of the back of the rear seat of the vehicle are adjusted to enable the user to complete the trunk placement in the vehicle.
[0032] In summary, according to the above-mentioned trunk adaptive adjustment control method, by detecting and identifying the user's human posture characteristics and human behavior characteristics, the user's trunk usage intention can be predicted in advance, and then the shape characteristics and size characteristics of the user's carried items can be identified to understand the user's placement needs, thereby adjusting the vehicle's rear seat posture and the vehicle's rear shelf posture to adapt to the user's placement needs and reasonably adjust the overall space utilization of the trunk, thereby avoiding the problem of the user needing to manually adjust the trunk storage space due to the large items carried, and also avoiding the problem of the items in the storage space being displaced or collided during driving due to the large size of the storage space. The present invention greatly improves the intelligence level of the vehicle trunk storage function and user comfort. Specifically, when a user signal is detected, it is determined whether the user has an intention to approach, thereby avoiding misjudgment caused by the user approaching when not in use, and improving overall accuracy and efficiency. When it is determined that the user has an intention to approach, user behavior recognition is performed to determine whether the user has an intention to use the trunk. The user behavior recognition is used to identify the user's body posture characteristics and body behavior characteristics, and identify in advance whether the user needs to use the trunk, so as to improve response efficiency and avoid energy loss caused by misjudgment. When it is determined that the user has an intention to use the trunk, the user's holding state recognition is performed to determine the user's placement needs. The user's holding state recognition is used to identify the shape characteristics and size characteristics of the items carried by the user, and the user's placement needs are anticipated, which improves the efficiency of the overall trunk storage space adjustment. The posture of the vehicle's rear seats and the posture of the vehicle's rear shelf are adjusted according to the user's placement needs to complete the adaptive adjustment of the trunk space. The present invention greatly improves the intelligence level and user comfort of the vehicle's trunk storage function.
[0033] See also Figure 3 , which is a schematic diagram of the structure of a trunk adaptive adjustment control system proposed in a third embodiment of the present invention, and the system includes: A detection module 10, for determining whether the user has an approaching intention when a user signal is detected; The recognition module 20 is used to perform user behavior recognition when it is determined that the user has an approaching intention to determine whether the user has an intention to use the trunk, and the user behavior recognition is used to recognize the user's human posture characteristics and human behavior characteristics; When it is determined that the user intends to use the trunk, the user's holding state recognition is performed to determine the user's placement needs. The user's holding state recognition is used to identify the shape and size characteristics of the items carried by the user; The adjustment module 30 is used to adjust the posture of the rear seats and the posture of the rear shelf of the vehicle according to the user's storage needs, so as to complete the adaptive adjustment of the trunk space.
[0034] The present invention also provides a computer storage medium on which one or more programs are stored, and when the programs are executed by a processor, the above-mentioned trunk adaptive adjustment control method is implemented.
[0035] The present invention also proposes a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the above-mentioned trunk adaptive adjustment control method.
[0036] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain storage, communication, propagation or transmission of a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.
[0037] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.
[0038] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0039] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0040] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.
Claims
1. A trunk adaptive adjustment control method, characterized in that: include: When a user signal is detected, it is determined whether the user intends to approach; When it is determined that the user has an intention to approach, user behavior recognition is performed to determine whether the user has an intention to use the trunk, and the user behavior recognition is used to identify the user's human posture characteristics and human behavior characteristics; When it is determined that the user intends to use the trunk, the user's holding state recognition is performed to determine the user's placement needs. The user's holding state recognition is used to identify the shape and size characteristics of the items carried by the user; Adjust the posture of the vehicle's rear seats and the vehicle's rear shelf according to the user's storage needs to complete adaptive adjustment of the trunk space.
2. The trunk adaptive adjustment control method according to claim 1, characterized in that: The step of determining whether the user has an approaching intention when the user signal is detected specifically includes: When a wireless signal is detected to be within the vehicle detection radius, the wireless signal is identified to determine whether it is a wireless signal of the user corresponding to the current vehicle, wherein the wireless signal includes a vehicle key signal and a signal of an authenticated wireless communication device; If it is determined that the wireless signal is a wireless signal of the user corresponding to the current vehicle, the user audio and video collection in the direction of the wireless signal is started to perform user face recognition and voiceprint recognition; If the user face recognition is determined to be an authenticated face or the user voiceprint recognition is determined to be an authenticated voiceprint, the transmission source moving path of the wireless signal is calculated to determine whether the transmission source moving path meets the preset approach path standard; If the moving path of the transmitting source meets the preset approach path standard, it is determined that the user has an approach intention.
3. The trunk adaptive adjustment control method according to claim 1, characterized in that: When it is determined that the user has an approaching intention, the step of performing user behavior recognition to determine whether the user has an intention to use the trunk specifically includes: When it is determined that the user intends to approach, the user image is collected; Dividing the user image into multiple single-frame user images according to a time sequence, selecting any user image from the single-frame user images, adjusting the brightness of the user image according to the parking environment, extracting human posture features of the user image, and judging whether the current user is likely to place an object according to the human posture features; If it is determined that the current user may place an object, the human skeleton joints of all single-frame user images are calibrated, and all single human skeleton joints are aggregated according to the time series and input into the graph convolutional neural network. The global time series feature is enhanced according to the context enhancement module to obtain human behavior characteristics; It is determined whether the current user intends to use the trunk based on the human behavior characteristics.
4. The trunk adaptive adjustment control method according to claim 1, characterized in that: When it is determined that the user intends to use the trunk, the step of identifying the state of the user's holding items to determine the user's placement needs specifically includes: When it is determined that the user intends to use the trunk, the high-position and middle-position image acquisition of the trunk is started to obtain the image of the user's handheld object, and the shape characteristics of the user's handheld object are extracted, and then the remaining storage space status in the trunk is obtained to match the remaining storage space status with the shape characteristics, and determine whether the placement conditions are met; If it is determined that the insertion conditions are met, the trunk low-position image acquisition is started to identify the user's leg and foot movements and match the preset trunk opening action. When the user's leg and foot movements are consistent with the preset trunk opening action, the trunk storage space is opened; If it is determined that the placement condition is not met, the size characteristics of the object held by the user are obtained according to the image of the object held by the user, and the placement requirements of the current user are calculated.
5. The trunk adaptive adjustment control method according to claim 1, characterized in that: The step of adjusting the posture of the rear seats and the posture of the rear shelf of the vehicle according to the user's storage requirements to complete the adaptive adjustment of the trunk space specifically includes: Acquire the storage requirements of the current user, and calculate the required adjustment size of the trunk storage space according to the storage requirements, so as to select the size level of the trunk storage space; If the selected trunk storage space size gear is the standard size gear, adjust the height of the vehicle's rear shelf to the highest position; If the selected trunk storage space size gear is the enlarged size gear, adjust the height of the vehicle's rear shelf to the highest position, adjust the rear seat cushions of the vehicle to move forward to the limit point, and adjust the backrests of the rear seat of the vehicle to tilt forward to be perpendicular to the cushions; If the trunk storage space size is selected to be the largest size, adjust the height of the vehicle's rear shelf to the highest position, adjust the cushions of the vehicle's rear seats to move forward to the limit point, and adjust the backrests of the vehicle's rear seats to tilt forward to a horizontal position.
6. The trunk adaptive adjustment control method according to claim 5, characterized in that: The step of selecting the size of the trunk storage space may further include: Start the in-car image acquisition; Detect whether there is any object placed on the upper part of the rear shelf of the vehicle; If there is no placed object, the upper pressure of the rear shelf of the vehicle is detected to determine whether there is any unrecognized object. If the upper pressure of the rear shelf of the vehicle is detected to be lower than the preset pressure threshold, the rear shelf of the vehicle is adjusted according to the selected trunk storage space size gear; If there is any placed object, the shape and size characteristics of the placed object are identified to determine whether the placed object will limit the height adjustment of the rear shelf of the vehicle to the highest level. If it is determined that the placed object will limit the height adjustment of the rear shelf of the vehicle to the highest level, an anti-collision warning is issued; Then detect whether there is any object placed on the rear seat of the vehicle; If there is no object placed, the cushion pressure of the rear seat of the vehicle is detected to determine whether there is any unrecognized object placed. If the cushion pressure of the rear seat of the vehicle is detected to be lower than a preset pressure threshold, the rear seat of the vehicle is adjusted according to the selected trunk storage space size gear; If there is any placed object, the shape and size characteristics of the placed object are identified to determine whether the placed object will limit the inclination adjustment of the backrest of the rear seat of the vehicle. If it is determined that the placed object will limit the inclination adjustment of the backrest of the rear seat of the vehicle, an anti-pinch warning is issued.
7. The trunk adaptive adjustment control method according to claim 1, characterized in that: The step of adjusting the posture of the rear seats and the posture of the rear shelf of the vehicle according to the user's storage requirements to complete the adaptive adjustment of the trunk space further includes: When the user is in the car, the system detects the user's voice and gestures in real time to identify the user's request to place items. If the user's storage request is recognized, the trunk storage space is calculated to determine whether the trunk can be placed; If it is determined that the trunk can be placed, the shape and size characteristics of the object held by the user are identified, so as to calculate the height of the rear shelf of the vehicle and the inclination angle of the backrest of the rear seat of the vehicle that need to be adjusted according to the shape and size characteristics; When the required adjustment height of the vehicle's rear shelf board and the vehicle's rear seat backrest inclination angle both meet driving safety requirements, adjust the vehicle's rear shelf board height and the vehicle's rear seat backrest inclination angle to allow the user to complete trunk storage in the vehicle.
8. A trunk adaptive adjustment control system, characterized in that: include: A detection module, used to determine whether the user has an approaching intention when a user signal is detected; A recognition module, for performing user behavior recognition when it is determined that the user intends to approach the trunk, so as to determine whether the user intends to use the trunk, wherein the user behavior recognition is used to recognize the user's body posture characteristics and body behavior characteristics; When it is determined that the user intends to use the trunk, the user's holding state recognition is performed to determine the user's placement needs. The user's holding state recognition is used to identify the shape and size characteristics of the items carried by the user; The adjustment module is used to adjust the posture of the vehicle's rear seats and the posture of the vehicle's rear shelf according to the user's storage needs, so as to complete the adaptive adjustment of the trunk space.
9. A storage medium, characterized in that: The storage medium stores one or more programs, which, when executed by the processor, implement the trunk adaptive adjustment control method as described in any one of claims 1 to 7.
10. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein: The memory is used to store computer programs; When the processor is used to execute the computer program stored in the memory, the trunk adaptive adjustment control method described in any one of claims 1 to 7 is implemented.
