Voice recognition partition management method and system based on machine vision, and medium

Through the voice recognition partition management method based on machine vision, children's occupants are detected and voice command blocked areas are set, which solves the problem that voice commands affect drivers when children ride, and improves driving safety and user experience.

CN119091422APending Publication Date: 2024-12-06GAC HONDA AUTOMOBILE CO LTD +1

Patent Information

Application Number
CN202411093659.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The prior art may issue voice commands when children ride in a car, resulting in reduced driving safety. Disabling voice recognition function requires the driver to make subjective judgments, increasing the driver's burden and affecting the user experience.

Method used

Using a voice recognition partition management method based on machine vision, by obtaining the image information of the passenger compartment, detecting and determining whether there are children, setting a voice command blocking area, positioning the voice output location, and determining whether it is in the blocked area. If it is not there, voice recognition will be performed. and respond to avoid the impact of improper instructions from children’s occupants on the driver.

Benefits of technology

It improves driving safety, reduces the burden on drivers, and does not affect other passengers' voice recognition functions, improving users' driving experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119091422A_ABST
    Figure CN119091422A_ABST
Patent Text Reader

Abstract

The invention discloses a voice recognition partition management method and system based on machine vision and a medium, and the method comprises the steps: obtaining first image information of a passenger compartment of a target vehicle, and determining whether a child passenger exists in the passenger compartment or not according to the first image information; when the child passenger exists in the passenger compartment, determining that a compartment area where the child passenger is located is a voice instruction shielding area; in response to a voice control instruction of the target vehicle, performing sound source positioning on the voice control instruction to determine a voice sending position of the voice control instruction, and judging whether the voice sending position is located in the voice instruction shielding area or not; and when the voice sending position is not located in the voice instruction shielding area, identifying and responding to the voice control instruction. The driving safety and the driving experience of the user are improved, and the method can be widely applied to the technical field of vehicle control.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to a method, system and medium for voice recognition zoning management based on machine vision. Background Art

[0002] With the development of intelligent networking of automobiles, vehicle monitoring and control technologies are becoming more and more intelligent, bringing more and more rich driving experience to drivers and passengers. At present, most cars have voice recognition function, which can be activated by specific wake-up words or pressing switches, and the vehicle can be controlled by voice to adjust the air conditioning temperature, open and close various actuators, and navigate. However, the existing technology has the following problems: children may issue voice commands to make the vehicle perform different operations when riding in the car, which will affect the driver and thus affect driving safety; even if the voice recognition function is disabled when there are child passengers, the driver needs to make subjective judgments and disable and start the voice recognition function, which increases the burden on the driver and affects the normal use of the voice recognition function by other passengers, thus affecting the user's driving experience. Summary of the invention

[0003] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0004] To this end, an object of an embodiment of the present invention is to provide a voice recognition zoning management method based on machine vision, which improves driving safety and user driving experience.

[0005] Another object of an embodiment of the present invention is to provide a voice recognition zoning management system based on machine vision.

[0006] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present invention include:

[0007] In a first aspect, an embodiment of the present invention provides a method for managing speech recognition zones based on machine vision, comprising the following steps:

[0008] Acquire first image information of a passenger compartment of a target vehicle, and determine whether there is a child passenger in the passenger compartment according to the first image information;

[0009] When there is a child passenger in the passenger cabin, determining the cabin area where the child passenger is located as a voice command shielding area;

[0010] In response to the voice control command of the target vehicle, performing sound source localization on the voice control command to determine the voice issuing position of the voice control command, and determining whether the voice issuing position is located in the voice command shielding area;

[0011] When the voice emitting position is not located in the voice command shielding area, the voice control command is recognized and responded to.

[0012] Further, in one embodiment of the present invention, determining whether there is a child passenger in the passenger compartment according to the first image information specifically includes:

[0013] Performing face detection on the first image information to obtain a plurality of face image information;

[0014] Inputting the facial image information into a pre-trained child face recognition model to obtain a child face recognition result;

[0015] It is determined whether there is a child passenger in the passenger compartment according to the child face recognition result; if there is a child passenger, the cabin area where the child passenger is located is determined according to the child face recognition result and the first image information.

[0016] Further, in one embodiment of the present invention, determining whether there is a child passenger in the passenger compartment according to the first image information specifically includes:

[0017] Performing human body detection on the first image information to obtain a plurality of human body image information;

[0018] Inputting the human body image information into a pre-trained human body age recognition model to obtain a human body age recognition result;

[0019] Determine whether there is a child passenger in the passenger compartment according to the human age recognition result; if there is a child passenger, determine the cabin area where the child passenger is located according to the human age recognition result and the first image information.

[0020] Furthermore, in one embodiment of the present invention, a microphone array is disposed in the target vehicle, and the microphone array includes a plurality of microphones, and each of the microphones is disposed in each partition of the target vehicle.

[0021] Further, in one embodiment of the present invention, in response to the voice control instruction of the target vehicle, performing sound source localization on the voice control instruction to determine the voice issuing position of the voice control instruction specifically includes:

[0022] When the microphone array detects the voice control instruction, determining the signal reception time and / or signal strength of each microphone receiving the voice control instruction;

[0023] The partition where the microphone having the earliest signal reception time and / or the strongest signal strength is located is determined as the voice emitting location.

[0024] Furthermore, in one embodiment of the present invention, the speech recognition zone management method further includes the following steps:

[0025] When the voice issuing position is within the voice command shielding area, the voice control command is input into a pre-trained voice age recognition model to obtain a voice age recognition result;

[0026] determining whether the voice control instruction is issued by the child passenger according to the voice age recognition result;

[0027] When the voice control command is not issued by the child passenger, recognizing and responding to the voice control command;

[0028] When the voice control command is issued by the child passenger, an incorrect operation reminder message is generated and broadcasted.

[0029] Furthermore, in one embodiment of the present invention, the speech recognition zone management method further includes the following steps:

[0030] When there is no child passenger in the passenger compartment and the target vehicle currently has a voice command shielding area, reset the voice command shielding area to a normal area

[0031] In a second aspect, an embodiment of the present invention provides a voice recognition partition management system based on machine vision, including:

[0032] an occupant detection module, configured to obtain first image information of a passenger compartment of a target vehicle, and determine whether a child occupant exists in the passenger compartment according to the first image information;

[0033] a shielding area determination module, for determining, when there is a child passenger in the passenger cabin, a cabin area where the child passenger is located as a voice command shielding area;

[0034] a voice emission position determination module, for responding to the voice control command of the target vehicle, performing sound source localization on the voice control command to determine the voice emission position of the voice control command, and determining whether the voice emission position is located within the voice command shielding area;

[0035] The voice command response module is used to identify and respond to the voice control command when the voice emitting position is not within the voice command shielding area.

[0036] In a third aspect, an embodiment of the present invention provides a speech recognition partition management device based on machine vision, comprising:

[0037] at least one processor;

[0038] at least one memory for storing at least one program;

[0039] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned machine vision-based speech recognition partition management method.

[0040] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores a program executable by a processor, and the program executable by the processor is used to execute the above-mentioned machine vision-based speech recognition partition management method when executed by the processor.

[0041] The advantages and beneficial effects of the present invention will be partly given in the following description, partly become apparent from the following description, or be understood through the practice of the present invention:

[0042] The embodiment of the present invention obtains the first image information of the passenger compartment of the target vehicle, and determines whether there is a child passenger in the passenger compartment according to the first image information. When there is a child passenger in the passenger compartment, the cabin area where the child passenger is located is determined as a voice command shielding area. In response to the voice control command of the target vehicle, the voice control command is localized to determine the voice issuing position of the voice control command, and it is determined whether the voice issuing position is located in the voice command shielding area. When the voice issuing position is not located in the voice command shielding area, the voice control command is recognized and responded. The embodiment of the present invention recognizes whether there is a child passenger in the passenger compartment in real time when the vehicle is started or during driving, thereby performing intelligent zoning management of the vehicle's voice recognition function, avoiding direct response to the voice control command of the cabin area with child passengers, preventing the child passenger from issuing improper voice control commands to affect the driver, and improving driving safety; the driver does not need to make subjective judgments and disable and start the voice recognition function, which reduces the burden on the driver, and does not affect the normal use of the voice recognition function by other passengers, thereby improving the user's driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solution in the embodiments of the present invention, the following introduction is made to the drawings required for use in the embodiments of the present invention. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solution of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 A flowchart of a method for managing speech recognition partitions based on machine vision provided by an embodiment of the present invention;

[0045] Figure 2A structural block diagram of a speech recognition partition management system based on machine vision provided by an embodiment of the present invention;

[0046] Figure 3 A structural block diagram of a speech recognition partition management device based on machine vision provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limitations of the present invention. For the step numbers in the following embodiments, they are only provided for the convenience of explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0048] In the description of the present invention, the meaning of "a plurality" is two or more than two. If there is a description of "a first" or "a second", it is only used for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features. In addition, unless otherwise defined, all technical and scientific terms used in this document have the same meaning as those commonly understood by those skilled in the art.

[0049] Reference Figure 1 The embodiment of the present invention provides a method for managing speech recognition partitions based on machine vision, which specifically includes the following steps:

[0050] S101. Acquire first image information of a passenger compartment of a target vehicle, and determine whether there is a child passenger in the passenger compartment according to the first image information.

[0051] Specifically, when the target vehicle is started, the smart cockpit OMS camera of the target vehicle is started, and the first image information of the passenger compartment is continuously obtained through the smart cockpit OMS camera during the driving of the target vehicle, and then the first image information is transmitted to the smart cockpit domain controller. The first image information includes the face or body images of all passengers in the passenger compartment, which is used for the detection and identification of child passengers.

[0052] The embodiment of the present invention can detect the face, torso, height and other information of the occupants in the passenger compartment through a deep learning algorithm, thereby identifying whether there are child passengers in the passenger compartment.

[0053] As an optional implementation, determining whether there is a child passenger in the passenger compartment according to the first image information specifically includes:

[0054] S1011, performing face detection on the first image information to obtain a plurality of face image information;

[0055] S1012, inputting the facial image information into a pre-trained child face recognition model to obtain a child face recognition result;

[0056] S1013. Determine whether there is a child passenger in the passenger cabin based on the child face recognition result; if there is a child passenger, determine the cabin area where the child passenger is located based on the child face recognition result and the first image information.

[0057] Specifically, face detection is performed on the first image information to extract face image information. The pre-trained child face recognition model can be used to identify whether it is a child face. If so, it means that there is a child passenger in the passenger compartment. At this time, the cabin area where the child passenger is located can be determined according to the position of the identified child face in the first image information (such as the left rear area, the middle rear area, and the right rear area). When there are multiple child passengers, multiple cabin areas are obtained. It should be noted that the child face recognition model can adopt an existing related neural network model, and the embodiment of the present invention does not limit the specific model used.

[0058] As an optional implementation, determining whether there is a child passenger in the passenger compartment according to the first image information specifically includes:

[0059] S1014, performing human body detection on the first image information to obtain a plurality of human body image information;

[0060] S1015, inputting the human body image information into a pre-trained human body age recognition model to obtain a human body age recognition result;

[0061] S1016. Determine whether there is a child passenger in the passenger cabin based on the human age recognition result. If there is a child passenger, determine the cabin area where the child passenger is located based on the human age recognition result and the first image information.

[0062] Specifically, the first image information is subjected to human body detection and extraction to obtain human body image information. The human body age corresponding to the human body image information can be identified through a pre-trained human body age recognition model. If the identified human body age is less than 14 (or 12, 10, which can be set manually), it means that there is a child passenger in the passenger compartment. At this time, the cabin position of the child passenger can be determined according to the position of the identified child body in the first image information. When there are multiple child passengers, multiple cabin positions are obtained. It should be noted that the human body age recognition model can adopt an existing related neural network model, and the embodiment of the present invention does not limit the specific model used.

[0063] S102: When there is a child passenger in the passenger cabin, determine that the cabin area where the child passenger is located is a voice command shielding area.

[0064] Specifically, the intelligent cockpit domain controller records the cockpit area where the child passenger is located, which is the voice command shielding area. It should be noted that when there are child passengers in multiple cockpit areas, the voice command shielding area is composed of these multiple cockpit areas.

[0065] S103, in response to the voice control command of the target vehicle, performing sound source positioning on the voice control command to determine the voice issuing position of the voice control command, and determining whether the voice issuing position is located in the voice command shielding area.

[0066] Specifically, when there is a child passenger in the passenger compartment, the vehicle will no longer respond directly to the detected voice control commands, but will need to determine whether the voice is issued from a location within the voice command shielding area to prevent the child passenger from issuing inappropriate voice control commands that may affect the driver, thereby improving driving safety.

[0067] As a further optional implementation, a microphone array is disposed in the target vehicle, the microphone array includes a plurality of microphones, and each microphone is disposed in each partition of the target vehicle.

[0068] Specifically, the target vehicle can be divided into the main driving area, the co-pilot area, the left rear area, the right rear area and the middle rear area. At least one microphone is set in each partition to form a microphone array to collect and monitor the voice in the car.

[0069] As an optional implementation, in response to the voice control instruction of the target vehicle, the sound source of the voice control instruction is localized to determine the voice source position of the voice control instruction, which specifically includes:

[0070] S1031, when the microphone array detects a voice control instruction, determining a signal reception time and / or a signal strength of each microphone receiving the voice control instruction;

[0071] S1032: Determine the partition where the microphone with the earliest signal receiving time and / or the strongest signal strength is located as the voice emitting location.

[0072] Specifically, the embodiment of the present invention is equipped with at least one microphone in each partition of the target vehicle. According to the signal reception time and / or signal strength of the voice control instructions collected by each microphone, the partition where the microphone with the earliest signal reception time and / or the strongest signal strength is located can be judged as the voice emitting position (main driving area, co-pilot area, left rear area, right rear area or middle rear area).

[0073] S104: When the voice emitting position is not within the voice command shielding area, the voice control command is recognized and responded to.

[0074] Specifically, when the voice originating position is not within the voice command shielding area, it indicates that the voice control command is not issued by a child passenger, and the voice control command can be recognized and responded to normally. When the voice originating position is within the voice command shielding area, the voice control command can be directly ignored.

[0075] In some optional embodiments, taking into account the situation where an adult passenger is holding an infant in the vehicle, since there is an infant in the cabin area where the adult passenger is located, the cabin area will be determined as a voice command shielding area in the aforementioned steps. Therefore, the voice control command issued from the cabin area can be further identified to confirm whether it is issued by the child passenger. If not, the voice control command will be responded to in the same way.

[0076] As an optional implementation, the speech recognition partition management method further includes the following steps:

[0077] S105, when the voice issuing position is within the voice command shielding area, inputting the voice control command into a pre-trained voice age recognition model to obtain a voice age recognition result;

[0078] S106, determining whether the voice control command is issued by a child passenger according to the voice age recognition result;

[0079] S107, when the voice control command is not issued by a child passenger, identifying and responding to the voice control command;

[0080] S108: When the voice control command is issued by a child passenger, a wrong operation reminder message is generated and broadcasted.

[0081] Specifically, when the voice is issued in the voice command shielding area, the pre-trained voice age recognition model can identify the age of the occupant corresponding to the voice control command. If the identified occupant age is less than 14 (or 12, 10, which can be set manually), it means that the voice control command is issued by a child occupant. At this time, a misoperation reminder message can be generated to remind the child occupant and other caregivers; if the identified occupant age is greater than or equal to 14, it means that the voice control command is not issued by a child occupant, and the voice control command can be recognized and responded to. It should be noted that the voice age recognition model can adopt an existing related neural network model, and the embodiment of the present invention does not limit the specific model used.

[0082] It should be recognized that the embodiments of the present invention can predetermine the voice command shielding area. When a voice control command is detected, it can be directly determined whether the issuing position is located in the voice command shielding area. When the voice issuing position is not located in the voice command shielding area, it can be quickly identified and responded to. When and only when the voice issuing position is located in the voice command shielding area, it is necessary to further identify the age of the occupant through a voice age recognition model. Compared with the solutions on the market that directly identify the age of the issuer of the voice control command, the response time of the voice control command is greatly reduced. In addition, the embodiments of the present invention will not respond to the corresponding voice control command only when the voice issuing position is located in the voice command shielding area and the age of the voice issuer is recognized to meet the preset conditions. Compared with the solutions on the market that directly identify the age of the issuer of the voice control command, the accuracy of voice recognition function shielding is greatly increased.

[0083] As an optional implementation, the speech recognition partition management method further includes the following steps:

[0084] S109: When there is no child passenger in the passenger compartment and the target vehicle currently has a voice command shielding area, reset the voice command shielding area to a normal area.

[0085] Specifically, when the vehicle starts, if it is detected that there is no child passenger in the passenger compartment, but the smart cockpit domain controller records a voice command shielding area (generated in the previous trip), the voice command shielding area can be reset to a normal area, making it easier for other passengers to use the voice recognition function, thereby improving the user's driving experience.

[0086] The above is a description of the method steps of the embodiment of the present invention. It can be appreciated that the embodiment of the present invention can identify in real time whether there are child passengers in the passenger compartment when the vehicle is started or during driving, thereby performing intelligent zoning management of the vehicle's voice recognition function, avoiding direct response to voice control commands in the cabin area where child passengers are present, preventing child passengers from issuing inappropriate voice control commands that affect the driver, and improving driving safety; there is no need for the driver to make subjective judgments and disable and start the voice recognition function, which reduces the burden on the driver and does not affect the normal use of the voice recognition function by other passengers, thereby improving the user's driving experience.

[0087] Reference Figure 2 The embodiment of the present invention provides a voice recognition partition management system based on machine vision, including:

[0088] An occupant detection module, used to obtain first image information of a passenger compartment of a target vehicle, and determine whether there is a child occupant in the passenger compartment according to the first image information;

[0089] A shielding area determination module, used for determining, when there is a child passenger in the passenger cabin, the cabin area where the child passenger is located as a voice command shielding area;

[0090] A voice emission position determination module is used to respond to the voice control command of the target vehicle, perform sound source localization on the voice control command to determine the voice emission position of the voice control command, and determine whether the voice emission position is located in the voice command shielding area;

[0091] The voice command response module is used to identify and respond to the voice control command when the voice is emitted from a location not within the voice command shielding area.

[0092] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0093] Reference Figure 3 The embodiment of the present invention provides a speech recognition partition management device based on machine vision, comprising:

[0094] at least one processor;

[0095] at least one memory for storing at least one program;

[0096] When the at least one program is executed by the at least one processor, the at least one processor implements the machine vision-based speech recognition partition management method.

[0097] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0098] An embodiment of the present invention further provides a computer-readable storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to execute the above-mentioned machine vision-based speech recognition partition management method.

[0099] A computer-readable storage medium of an embodiment of the present invention can execute a machine vision-based voice recognition partition management method provided by an embodiment of the method of the present invention, can execute any combination of implementation steps of the method embodiment, and has the corresponding functions and beneficial effects of the method.

[0100] The embodiment of the present invention also discloses a computer program product or a computer program, wherein the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes Figure 1 The method shown.

[0101] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the above-mentioned boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0102] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified to the contrary, one or more of the above-mentioned functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0103] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the above methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0104] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied 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 the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0105] 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 editable 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 above-mentioned program is printed, since the above-mentioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or processing in other suitable ways as necessary, and then stored in a computer memory.

[0106] 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, a plurality of 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 their combination: 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.

[0107] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. 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 may be combined in any one or more embodiments or examples in a suitable manner.

[0108] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0109] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A speech recognition partition management method based on machine vision, characterized in that: The following steps are involved: acquiring first image information of a passenger compartment of a target vehicle, and determining whether a child passenger is present in the passenger compartment based on the first image information; When there is a child passenger in the passenger cabin, determining the cabin area where the child passenger is located as a voice command shielding area; In response to the voice control command of the target vehicle, performing sound source localization on the voice control command to determine a voice issuing position of the voice control command, and determining whether the voice issuing position is within the voice command shielding area; When the voice emitting position is not located in the voice command shielding area, the voice control command is recognized and responded to.

2. The method for voice recognition partition management based on machine vision according to claim 1, characterized in that: The determining whether there is a child passenger in the passenger compartment according to the first image information specifically includes: Performing face detection on the first image information to obtain a plurality of face image information; Inputting the facial image information into a pre-trained child face recognition model to obtain a child face recognition result; Determine whether there is a child passenger in the passenger compartment based on the child face recognition result; if there is a child passenger, determine the cabin area where the child passenger is located based on the child face recognition result and the first image information.

3. The method for voice recognition partition management based on machine vision according to claim 1, characterized in that: The determining whether there is a child passenger in the passenger compartment according to the first image information specifically includes: Performing human body detection on the first image information to obtain a plurality of human body image information; Inputting the human body image information into a pre-trained human body age recognition model to obtain a human body age recognition result; Determine whether there is a child passenger in the passenger compartment based on the human age recognition result; if there is a child passenger, determine the cabin area where the child passenger is located based on the human age recognition result and the first image information.

4. The method for voice recognition zone management based on machine vision according to claim 1, characterized in that: A microphone array is provided in the target vehicle, and the microphone array includes a plurality of microphones, each of which is respectively provided in a partition of the target vehicle.

5. The method for voice recognition partition management based on machine vision according to claim 4, characterized in that: The step of performing sound source localization on the voice control instruction in response to the voice control instruction of the target vehicle to determine the voice issuing position of the voice control instruction specifically includes: When the microphone array detects the voice control instruction, determining the signal reception time and / or signal strength of each microphone receiving the voice control instruction; The partition where the microphone with the earliest signal reception time and / or the strongest signal strength is located is determined as the voice emitting location.

6. The method for voice recognition partition management based on machine vision according to claim 1, characterized in that: The speech recognition partition management method further comprises the following steps: When the voice emitting position is within the voice command shielding area, the voice control command is input into a pre-trained voice age recognition model to obtain a voice age recognition result; determining whether the voice control command is issued by the child passenger according to the voice age recognition result; When the voice control command is not issued by the child passenger, recognizing and responding to the voice control command; When the voice control command is issued by the child passenger, an erroneous operation reminder message is generated and broadcast.

7. A method for managing speech recognition zones based on machine vision according to any one of claims 1 to 6, characterized in that: The speech recognition partition management method further comprises the following steps: When there is no child passenger in the passenger compartment and the target vehicle currently has a voice command shielding area, the voice command shielding area is reset to a normal area.

8. A voice recognition partition management system based on machine vision, characterized in that: include: an occupant detection module, configured to obtain first image information of a passenger compartment of a target vehicle and determine whether a child occupant is present in the passenger compartment based on the first image information; a shielding area determination module, configured to, when there is a child passenger in the passenger cabin, determine that the cabin area where the child passenger is located is a voice command shielding area; a voice emission position determination module, configured to respond to the voice control command of the target vehicle, perform sound source localization on the voice control command to determine the voice emission position of the voice control command, and determine whether the voice emission position is within the voice command shielding area; The voice command response module is used to identify and respond to the voice control command when the voice issuing position is not within the voice command shielding area.

9. A voice recognition partition management device based on machine vision, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the machine vision-based speech recognition partition management method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to execute the machine vision-based speech recognition partition management method according to any one of claims 1 to 7 when executed by the processor.

Citation Information

Patent Citations

  • Vehicle voice control method and device

    CN108327667A

  • In-vehicle voice control method

    CN111768776A

  • Data processing method and device, electronic equipment and storage medium

    CN113407758A

  • Vehicle control method and vehicle

    CN116442940A

  • Voice wake-up method, device and equipment, readable storage medium and vehicle

    CN117351950A

Cited By

  • Adjusting method of cabin controller, vehicle, storage medium and computer product

    CN119928680A

  • Vehicle-mounted fault-tolerant method for preventing Bluetooth control feedback from mistakenly touching mobile phone camera for photographing

    CN121310107A