104 results about "Auditory sense" patented technology

The invention provides a method and device for realizing visual and auditory synchronous perception, and the method comprises the steps: obtaining the relative position information between a played video image and an audience and the type of a room where the audience is located under the condition that a video application is started; determining a volume adjustment gain based on the acquired relative position information and the type of the room where the audience is located; adjusting the sound to be played of the video application according to the volume adjustment gain; when the video is played, the relative orientation and distance between the image and the audience can be obtained, the type of the room can be judged, the audio signal to be played is dynamically adjusted according to the orientation and distance between the audience and the image and the type of the room, and the virtual sound image synchronously changing with the image is generated. The audience can obtain the same spatial perception in auditory sense and visual sense, and the immersion of video application is increased.

The invention discloses an emotion analysis method and system based on multi-mode electroencephalogram eye movement fusion. An emotional induction stimulation sequence is alternately or synchronously displayed through a stimulation presentation module according to preset time sequences such as 5-second vision and 3-second auditory sense, a 64 conductive electrode cap (10-20 system layout, the sampling rate is larger than or equal to 1000 Hz) is triggered to collect electroencephalogram data of a prefrontal lobe, a temporal lobe and the like, and meanwhile eye movement data are obtained through an infrared pupil tracking technology (the sampling frequency is larger than or equal to 120 Hz). 0.5-70 Hz band-pass filtering and ICA artifact removal processing are carried out on the electroencephalogram data, smooth interpolation and Kalman filtering optimization are carried out on the eye movement data, and then electroencephalogram alpha / beta / gamma wave power spectrums, eye movement pupil change rates and other characteristics are extracted respectively. A Transform model based on an attention mechanism is adopted, deep fusion of electroencephalogram eye movement features is realized through feature embedding and multi-head self-attention calculation, and emotion recognition accuracy greater than or equal to 85% is achieved through confusion matrix optimization and five-fold cross validation in combination with an SVM or DNN classifier.

The invention relates to the technical field of foot type robots, in particular to a humanoid robot capable of performing amphibious operation. The invention relates to a pair of health-care underwear which comprises an upper body structure and a lower body structure, the upper body structure is connected with the lower body structure through a waist assembly, the upper body structure comprises a chest assembly connected with the waist assembly, arm assemblies are arranged on the left side and the right side of the chest assembly respectively, and all the arm assemblies are connected with the chest assembly through shoulder assemblies. The front end of each arm assembly is provided with a hand assembly. The upper half body collects information through visual sense and auditory sense, and executes commands through the control mechanism to carry out processing tasks of related operations. The lower half body adopts a five-degree-of-freedom driving mode, so that the problem of convenient underwater movement of the humanoid robot is effectively solved, the angle of the humanoid robot can be adjusted at will underwater, the upper half body of the humanoid robot can execute commands conveniently, meanwhile, the robot can be suitable for amphibious working scenes, the universality of the robot is improved, and the application range of the robot is widened. The problems in the prior art are solved.

The invention discloses a video translation method and a related device, and relates to the technical field of video processing, and the method comprises the steps: obtaining a to-be-translated original video, carrying out the voice synthesis through the voiceprint features and emotion labels of a speaker in the original video, and obtaining the voice data of a target language, the method comprises the following steps: acquiring a target language, replacing original voice data in an original video with the voice data of the target language to obtain an initial translated video, performing speaker mouth area image synthesis by using the voice data of the target language to obtain a synthesized image of the speaker mouth area, and finally fusing the synthesized image of the speaker mouth area with the initial translated video to obtain a speaker mouth area image. And obtaining a final translated video. According to the scheme, the original sound of the video can be restored as much as possible, the speaking state of a character in the original video can be fitted as much as possible, and natural transition of a lip picture before and after the lip picture is lost or appears in the final translated video can be ensured, so that the auditory sense and visual sense of a user can be improved.

The invention belongs to the field of rehabilitation training, and particularly relates to a training method for preventing a cerebral apoplexy patient from falling down, which comprises the steps of dynamic risk assessment, graded training starting, double-task execution, self-adaptive adjustment and environment simulation training. The bottleneck of balance function training is broken through, and the problem of cognition-motion separation is solved; three-level cognitive interference quantitative control is adopted (vision: the light spot moving frequency is 0.1-3 Hz; auditory sense: N-back task difficulty is self-adaptive at 1-4 levels; tactile sense: sole asymmetric vibration), double-task load ratio dynamic adjustment, and radically cure insufficient individual adaptation; and the four-level risk grading model is matched with an adaptive adjustment mechanism. Through a multi-modal closed-loop training system, the problems of subjective evaluation, single training, protection lag and the like in the field of cerebral apoplexy falling prevention are solved, the falling risk reduction effect is good, and remarkable technical breakthrough and market irreplaceability are achieved.

The invention provides an industrial robot self-adaptive grabbing method based on multi-modal sensing, which comprises the following steps of: 1, acquiring multi-modal data of an object and an environment through a multi-modal sensing module; the multi-mode sensing module comprises at least two sensing modules of a visual sensing unit, a touch sensing unit, a force sensing unit and an auditory sensing unit; 2, preprocessing and feature extraction are carried out on the multi-modal data, feature information of different modals is fused through a multi-modal fusion algorithm, and comprehensive object description information is generated; 3, generating an optimal grabbing strategy based on the comprehensive object description information; wherein the grabbing strategy comprises the position and posture of a grabbing point, a grabbing path and grabbing force; and fourthly, the industrial robot executes the optimal grabbing strategy, the first step to the third step are repeated, and the grabbing strategy is adjusted in a self-adaptive mode till grabbing is completed. Stable and efficient grabbing can be achieved.

The invention discloses a massage quantization glove based on multi-signal fusion and a real-time feedback control system thereof. The massage quantization glove comprises a glove body, a double-layer differential sensing unit, a perturbation excitation unit, a motion detection unit, a signal processing and fusion unit and a feedback interaction unit. The double-layer differential sensing unit is composed of an outer-layer pressure sensing film, an isolation elastic layer and an inner-layer pressure sensing film and is used for collecting overall contact force and differential response signals. The perturbation excitation unit applies low-amplitude disturbance in the massage process, so that soft tissue viscoelasticity characteristics are extracted; the motion detection unit collects hand motion information and performs inertia compensation; the signal processing and fusion unit is used for denoising and analyzing the multi-source signal to generate a dose index and a hardness grade; and the feedback interaction unit prompts an operator through visual sense, auditory sense or tactile sense. Real-time quantification and feedback of massage dosage are realized, tissue hardness change can be reflected, excessive massage is avoided, curative effect consistency is improved, and massage operation standardization is promoted.

The utility model relates to an image reading machine which can integrate a picture or a drawn pattern with voice made aiming at a story which occurs in the picture or the drawn pattern or is worthy of being memorized, and carries a previous memory event. The photo album comprises a host box and a plurality of photo album pages recording photos of previous commemorative events or patterns drawn by individuals, and a main control circuit board with a voice recording module and a storage module and a voice player are arranged in the host box. A user stores voice instructions or voice annotations made for photos or patterns in the storage module through the voice recording module, and each photo album page is provided with a voice starting key electrically connected with the main control circuit board through a thin film circuit. After a user presses the voice starting key, the main control circuit board plays voice instructions or voice annotations which are stored in the storage module and correspond to the photo album page through the voice player. When a memory purchaser browses a certain album page, the memory purchaser can be fully aroused to the events recorded in the image data through visual sense and auditory sense.

The invention belongs to the technical field of medical instrument control, and particularly discloses a single-line digital audio output control system of high-frequency surgical equipment, which comprises the steps of constructing a multi-dimensional parameter fused state perception and semantic audio feedback mechanism, accurately identifying the working mode, the power level and the output stability of the equipment through auditory sense, and controlling the output of the high-frequency surgical equipment according to the state perception and semantic audio feedback mechanism. The operation burden and the misjudgment risk in a complex operation environment are effectively reduced; transmission of audio, data and a power supply is integrated by adopting a single-line digital audio bus, so that the internal structure and the electromagnetic compatibility of equipment are optimized fundamentally; by establishing a set of self-adaptive safety closed loop from communication quality monitoring to power and audio cooperative control, the health condition of a communication link can be actively monitored, and when it is detected that the communication quality is reduced, protective measures such as power reduction and safety alarm are automatically triggered, and the potential control failure risk is eliminated in the bud.

The invention relates to the technical field of headphones, in particular to a high-quality sound-quality open headphone with an adjustable sound output angle, which comprises a headband, two headphone bodies and two circular ring brackets, the two ends of the headband are respectively connected with an upper rotating shaft, each upper rotating shaft is respectively connected with one headphone body, and the headphone bodies can rotate around the upper rotating shafts; a circuit board is arranged in the accommodating space, the circuit board comprises a control circuit, the control circuit comprises a Bluetooth main control circuit and an audio processing circuit, and the audio processing circuit is connected with the Bluetooth main control circuit; a first loudspeaker and a second loudspeaker are arranged between the front cover and the inner shell, the first loudspeaker and the second loudspeaker are concentrically arranged, the second loudspeaker is located on the front side of the first loudspeaker, and the first loudspeaker and the second loudspeaker are jointly connected to an audio processing circuit. Compared with the prior art, the open headphone with the adjustable sound output angle and the high-quality sound quality has the advantages that the problem of poor sound quality experience caused by the fact that the open headphone is not attached to ears when being worn can be solved, the auditory sense experience of a user can be improved, and the requirement of high-quality auditory enjoyment can be met on the premise that the user feels more comfortable.

The utility model discloses a creative plush pendant with a sound box, which comprises a sound box body wrapped in a plush piece to form the creative and novel plush pendant, a user can touch the soft plush with fingers while enjoying music and relaxing, and the plush pendant is convenient to use. Various super-unwanted and cute cartoon patterns designed on the panel can be seen, three relaxation feelings of auditory sense, tactile sense and visual sense are brought to a user, the emotion is effectively soothed, the mood is stabilized, the user feels comfortable, depression is relieved, and very high emotion value is provided for the user; when going out, the clothes hanger can be hung on a bag and is convenient to carry.

The invention discloses a manufacturing method of a medicine use manual for visually impaired people, and the manufacturing method of the medicine use manual comprises the following steps: 1, determining the content information of medicines; step 2, performing braille translation and determining audio; step 3, making a manual; step 4, carrying out pilot distribution; step 5, performing improvement and large-scale distribution; according to the manufacturing method of the medication manual for the visually impaired people, a brand new medication guidance mode is provided for the visually impaired people through combination of braille alphabets and audios and two sensory experiences of tactile sense and auditory sense. The innovation breaks through a traditional medication guidance mode depending on vision, so that medication information is more diversified, and inclusiveness is higher. The barrier-free design concept is throughout the whole project, and the use requirements of visually impaired people are fully considered. Therefore, the barrier in the traditional product design can be broken, and the social inclusiveness and peaceability can be promoted.

The invention discloses a man-machine interaction system and method for cross-channel time processing of developmental reading disorder. The man-machine interaction system comprises an evaluation unit which is used for collecting personal information of a user and evaluation results of audio-visual simultaneous judgment; the parameter configuration unit is connected with the evaluation unit, is provided with a preset element library and a preset rule library, and is used for configuring a practice interaction task and a formal interaction task with preset difficulty for the user based on the evaluation record; the exercise task unit and the formal task unit are both connected with the parameter configuration unit so as to perform man-machine interaction with the user based on the exercise interaction task and the formal interaction task according to the sequence of first connection and then formal; and the feedback unit is connected with the formal task unit so as to obtain man-machine interaction data of finishing the formal interaction task by the user and feed back an interaction result to the user. The method aims at the underlying logic of the time processing defect, stimulates the visual sense and the auditory sense at the same time, and promotes the improvement of the audio-visual integration ability of children.

The invention discloses a head-mounted multi-sensory steady-state stimulation nerve regulation and control device. The device comprises light stimulation glasses and sound and electricity stimulation earphones, the photostimulation glasses comprise a main frame, a control circuit, an LED lamp strip, a rechargeable battery and shading lenses, the main frame is provided with a first control button group and a second control button group, the first control button group is used for adjusting the light intensity of the LED lamp strip and the current of the acoustoelectric stimulation earphone, and the second control button group is used for adjusting the volume of the acoustoelectric stimulation earphone. According to the device, various steady-state rhythm stimulation such as light, sound and electricity is applied to a patient through cooperation of the light stimulation glasses and the sound and electricity stimulation earphone, tinnitus responsibility brain area nerve electrical activity is adjusted through visual sense, auditory sense, somatosensory sense and other multi-mode sense noninvasiveness, the light intensity, the sound intensity and the electricity intensity are adjusted in combination with real-time conditions, and the tinnitus responsibility brain area nerve electrical activity is adjusted. The effect of treating tinnitus is achieved by regulating and controlling abnormal electroencephalogram activity, and the tinnitus treatment effect which is safer, noninvasive, individualized and easy and convenient to implement is achieved.

The present invention discloses a silent communication system for acquiring information in a non-visual and non-auditory manner. The system includes an information receiving module and an information sending module. The information receiving module analyzes the received information and extracts signal features, generating an electrical stimulation signal corresponding to the signal features; the electrical stimulation signal is applied to the stimulation area of the information receiver in a non-invasive electrical stimulation manner, inducing the information receiver's brain to have a natural intuitive feeling for the non-stimulated area, allowing the information receiver to obtain the information content based on the natural intuitive feeling; the information sending module encodes and sends information in the form of actions, pictures, text, audio and video. The present invention can enable the information receiver to obtain information in the form of pictures, text, audio and video, while enabling the information sender to send the information content in the form of actions, pictures, text, audio and video, etc., and no sound or light signals are emitted during the information acquisition process. It is not restricted by spatial distance and has a good silent effect and confidentiality.

The utility model discloses a metal card bag, which is characterized in that a containing main body is provided with a containing cavity with an opening, and the containing cavity is used for storing cards. The movable assembly comprises a sliding cover, a sliding rail and a sliding block, the sliding cover is arranged on the front side plate, the sliding rail is located on the front side plate, and the sliding block is installed on the sliding cover so that the sliding cover can stably move along the sliding rail. The decompression device comprises a sounder and magnets, the sounder is arranged on the front side plate, the magnets are divided into a sliding magnet and a fixed magnet, the sliding magnet is installed on the sliding cover, and the fixed magnet is arranged on the front side plate. When the sliding cover slides, the sliding magnet and the fixed magnet interact with each other to cause the front side plate to vibrate, so that the sounder vibrates and makes a sound. A user can easily take out the card by repeatedly sliding the sliding cover, and can enjoy double experiences of auditory sense and tactile sense, so that the effect of relieving pressure is achieved. Therefore, the utility model not only meets the requirements of daily carrying and card storage of users, but also has the function of pressure relief.

The invention discloses a robot control method based on multi-modal perception and related equipment thereof, and belongs to the technical field of robots. According to the method, multi-modal sensing, hierarchical fusion processing, path planning and reinforcement learning decision collaborative mechanisms are introduced in the robot control process, so that the robot can realize more comprehensive and reliable environment cognition and autonomous control in a complex, dynamic and uncertain environment. Through carrying out synchronization and fusion processing on heterogeneous sensing information such as visual sense, auditory sense, tactile sense and force sense, richer environment information is obtained; through key feature extraction and evidence theory fusion, a relatively consistent environment state evaluation result can be formed when multi-source information has differences or conflicts. Planning a global optimal path through path planning in combination with environmental cost constraint, kinematics constraint and a risk assessment model; through continuous training and optimization of a motion control strategy, the control strategy can be adaptively updated according to operation data.

The invention relates to the technical field of virtual reality tactile feedback interaction, and discloses a virtual reality tactile feedback interaction system which comprises a contact module, a sensing module and a sensing information extraction and information feedback module. The contact module is arranged to be an electrical stimulation device and a flexible electrode array, the contact module is connected with the sensing module, and the contact module is used for collecting the reaction of people in contact with different objects and events in a virtual environment and providing the feeling close to reality for people; the sensing module comprises a corresponding driving circuit and is used for generating a signal representing parameters in the current virtual environment, and the skin of people is in contact with the virtual environment through the sensing module; the perceptual information extraction is used for tactile sensing, olfactory sensing and auditory sensing respectively; the information feedback module comprises a head-mounted virtual projection device, stimulation and tactile feedback are generated on the human body through an electrical stimulation device and a flexible electrode array, and rendered information is processed and transmitted to the feedback module.

The invention relates to the technical field of intelligent examination anti-cheating, and particularly discloses an intelligent examination anti-cheating monitoring system, which comprises a behavior cheating judgment module, an equipment cheating judgment module, a substitute examination cheating judgment module, an examination credit rating evaluation module and a database, according to the method, whether behavior cheating exists or not is judged by obtaining computer screen area pixel boundary coordinates and examinee behavior data, equipment cheating is judged by collecting body surface temperature data and analyzing the temperature rise rate, and cheating for an examinee is analyzed and judged by extracting iris texture features and obtaining gray value deviation. And finally evaluating the credit rating based on the historical examination data. According to the invention, a four-layer cross validation mechanism of visual sense-auditory sense-thermal inductance-biological characteristics is constructed, a single monitoring blind area can be covered by using multi-dimensional data complementation, a multi-source evidence chain is formed to improve the cheating identification accuracy, a comprehensive credit assessment system is established, and long-term supervision of examinees is realized.

The invention discloses an interaction method and device based on music, electronic equipment and a readable medium. The method comprises the steps that in response to operation on a first interactive UI control or a second interactive UI control, target music used for showing the social contact state of a target virtual character is played, social contact state elements corresponding to the target music are visually shown in a graphic interaction interface, and the social contact state elements are used for showing the social contact state of the target virtual character. The social state comprises at least one or more of emotion, world view and interest, and the visual performance is performed through at least one or more of a virtual scene, an interactive UI control and a non-interactive UI. The user can show the social state of the current user through the played target music, the social state elements displayed on the image interaction interface and the like. Other users can visually know the social state of the user through visual sense and auditory sense, and the social experience of the user is enhanced in a music mode while the game requirement of the user is met.

The invention discloses a lactation control method and device, a terminal, a system, a medium and a product, and relates to the technical field of breast pumps, and the lactation control method comprises the steps that lactation detection data of a user is acquired, and the playing content of playing equipment is adjusted based on the lactation detection data, the audio and video content matched with the lactation stage is played through the playing device, comfortable experience is created from multiple dimensions such as visual sense and auditory sense, the mood of a user is effectively relieved, then a positive stimulation effect is generated on lactation secretion, the lactation secretion amount is increased, and the lactation efficiency is improved.

The embodiment of the invention discloses a speech enhancement method and device in magnetic resonance imaging and a magnetic resonance imaging system. The method comprises the following steps: acquiring a time domain sound signal in an MR scanning room in real time; converting the time domain sound signal into a frequency domain to obtain a frequency domain sound signal; inputting the frequency domain sound signal into a band-pass filter of which the filtering bandwidth is equal to the filtering bandwidth of human auditory sense, and inputting the frequency domain sound signal after band-pass filtering into a first artificial intelligence module for noise elimination to obtain a first frequency domain clean sound signal; and converting the frequency domain first clean sound signal from the frequency domain to the time domain to obtain a time domain clean sound signal. According to the embodiment of the invention, the voice quality of internal communication in MR imaging is improved.

The invention discloses a multi-modal marketing copywriting generation method based on images and texts, and the method specifically comprises the following steps: 1, judging whether historical data contains user preference information or not, and extracting the user preference information and keywords in the preference information from the historical data; 2, projecting information of different modes such as language and visual and auditory sense into the mutually associated common subspace, realizing collaborative representation of multi-mode data, and providing a shared semantic subspace for marketing copywriting generation; and 3, generating a marketing document by utilizing the picture feature vector of the commodity, the character description feature vector of the commodity and the shared semantic subspace of the customer preference information. According to the method, the features of the commodity picture and the description text are extracted, and the image-text sharing semantic subspace is constructed, so that interests and preferences of the user can be accurately identified, marketing documents conforming to different user preferences are generated, and the internal and external feature display effect of the commodity is improved.

The utility model provides a spinning drum. The spinning drum comprises a base, a rotary drum and a plurality of balls. The base serves as a basic supporting part of the whole device, has enough strength and stability and can be stably placed on any flat surface, and stability and safety of the whole spinning drum in the using process are guaranteed. The rotary drum is rotatably connected to the base, and a child can rotate the drum body personally, so that the movement track and the speed change of the rotary drum can be visually observed, the basic rule of object movement can be felt through personally practicing, and the child can be effectively promoted to perceive and understand the material world during playing. The spinning drum is mainly characterized in that a cavity is formed in the rotary drum, and a plurality of balls are arranged in the cavity in bulk. Along with the rotation of the rotary drum, the balls roll and collide in the cavity to make a sound. The sound not only can attract the attention of the children, but also can stimulate the auditory sense of the children, thereby effectively reducing the boring feeling of the children in the playing process, and enabling the attention of the children to be more focused on the spinning drum.

The invention discloses an infant neural development state analysis method and system, and belongs to the technical field of computer vision, and the method comprises the following steps: S1, data collection preparation; s2, collecting active motion data of the whole body; s3, collecting local induced motion data; and S4, multi-motion feature extraction and fusion decision making. On the basis of whole body spontaneous motion data acquisition and analysis, local motion data acquisition and analysis induced by visual and auditory sense organs are added, multi-modal behavioral features are obtained, and clinical classification accuracy is improved through later-stage fusion decision making of the modal features.

The utility model belongs to the field of landscape devices, and particularly relates to an interactive landscape device based on five-sense experience, which comprises a base, two sides of the front side of the top of the base are fixedly connected with a rotating frame and a fixed box respectively, and the top of the fixed box is fixedly connected with a control seat. A touch screen and a control key are fixedly connected to the two sides of the front surface of the control seat correspondingly, and three aromatherapy boxes are fixedly connected to the bottom of an inner cavity of the fixed box from left to right in sequence; through the display screen, a user can conveniently know the landscape through vision, through a model installed on the limiting sleeve, the user can conveniently know the landscape through touch, through aromatherapy stored in the aromatherapy box, the user can conveniently know the landscape through smell, and through the loudspeaker, sound can be played, so that the user can conveniently know the landscape through auditory sense; the special food is stored in the food placing box, so that a user can conveniently know the landscape through the taste sense, and people can more comprehensively know the scenic spot condition through five senses by adopting multiple modes.

The invention relates to the field of man-machine interaction, in particular to a method for enhancing user space perception in augmented reality virtual pet interaction, which comprises the following steps executed in sequence: S1, constructing a space reference; s2, the multi-mode perception feedback stage comprises intelligent scheduling of auditory sense and tactile sense of the virtual pet; s3, the virtual pet behavior parameter control stage comprises the following steps: S31, taking the bearing plane as a motion constraint area of a virtual pet, performing reachability judgment on a target position, and when the target position exceeds the motion constraint area or falls into an unreachable area, executing the step S3; limiting the target position in the motion constraint area or projecting the target position to a nearest reachable point of a boundary; s32, when the walking speed, running speed, acceleration or single-frame displacement of the virtual pet reaches a preset upper limit, judging that the virtual pet is abnormal, and performing abnormality processing; intelligent scheduling is carried out in auditory sense and tactile sense, and the consistency of multi-mode feedback and visual sense in time sequence is ensured.

The invention discloses a tunnel traffic accident emergency escape unmanned aerial vehicle cooperative guidance system and method, and belongs to the technical field of tunnel safety emergency. The system comprises an unmanned aerial vehicle nest unit which is internally provided with an ejection mechanism and accommodates a plurality of foldable unmanned aerial vehicles, a guiding unmanned aerial vehicle which carries an SLAM navigator, a thermal imager, a projection lamp and an emergency material putting device, and a communication relay unmanned aerial vehicle which constructs a Mesh + optical communication redundant link. According to the control method, path planning is dynamically optimized based on a reinforcement learning algorithm, and visual sense-tactile sense-auditory sense multichannel guidance is realized in combination with UWB positioning and the adaptive projection lamp. According to the invention, the sensing precision of the complex environment is improved through multi-sensor fusion positioning, the communication delay is reduced through cooperation of the dual-frequency Mesh network and optical communication, the evacuation efficiency is improved through interaction of dynamic projection and the AR terminal, the problems of real-time positioning, communication coverage and accurate guidance in a tunnel fire scene are effectively solved, and the success rate of emergency rescue is remarkably improved.

The application discloses a small infant neural development state analysis method and system, and belongs to the technical field of computer vision, and comprises the following steps: S1, data collection preparation; S2, whole body active motion data collection; S3, local evoked motion data collection; S4, multi-motion feature extraction and fusion decision-making. On the basis of whole body spontaneous motion data collection and analysis, the application adds local motion data collection and analysis induced by visual and auditory senses, obtains multi-modal behavioral characteristics, and improves clinical classification accuracy through late fusion decision-making of modal characteristics.

The invention discloses an audio-visual integrated sensing system, and the system comprises a sensing module which responds to an excitation signal so as to emit a detection sound wave signal, and is used for receiving a reflection sound wave signal and a sound source sound wave signal at the same time; the signal processing module is connected with the sensing module and comprises a first filter circuit and a second filter circuit, the first filter circuit is used for extracting imaging sound wave signals in the reflected sound wave signals and the sound source sound wave signals, and the second filter circuit is used for extracting positioning sound wave signals in the reflected sound wave signals and the sound source sound wave signals; and the data processing module is used for acquiring environment structure information based on the imaging sound wave signal, acquiring sound source position information based on the positioning sound wave signal, fusing the environment structure information and the sound source position information and outputting a target three-dimensional image. According to the invention, a single sensing system is used for replacing a visual sensing system and an auditory sensing system which are separated from each other, and the system has a dual sensing function of generating an environment structure and a dynamic sound source in a three-dimensional space.