Device to be deployed in a disaster area for detecting live subjects
The device with a spherical microphone array and outer protection layer addresses the challenge of detecting and locating survivors in post-disaster scenarios by effectively processing sound signals and overcoming environmental interference, thus enhancing search and rescue operations.
Patent Information
- Application Number
- PCT/CN2023/135348
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-11-30
- Publication Date
- 2025-06-05
AI Technical Summary
In post-disaster scenarios, it is challenging for search and rescue personnel to detect and locate survivors due to difficult access conditions, such as rubble, debris, and secondary disasters like aftershocks and mudslides, which hinder the effective use of visual detection methods and traditional sound signal pickup equipment.
A device equipped with a spherical microphone array and an outer protection layer, designed to be launched or dropped into disaster areas, uses voice acoustic signal perception and localization to detect and locate survivors by processing sound signals and transmitting them back to a command center for analysis.
The device effectively detects and locates survivors in challenging disaster environments by overcoming access limitations and environmental interference, such as wind noise, thereby enhancing the efficiency of search and rescue operations.
Smart Images

Figure CN2023135348_05062025_PF_FP_ABST
Abstract
Description
无标题
[0001] PATENT APPLICATION
[0002] For
[0003] DEVICE TO BE DEPLOYED IN A DISASTER AREA FOR DETECTING LIVE SUBJECTS
[0004] Inventors:
[0005] Jingdong Chen
[0006] Gongping Huang
[0007] DEVICE TO BE DEPLOYED IN A DISASTER AREA FOR DETECTING LIVE SUBJECTSTECHNICAL FIELD
[0008] The present disclosure relates to detecting live subjects in post-disaster search and rescue operations using voice acoustic signal perception and localization, and more particularly to using a microphone array acoustic signal sensing system that may be launched or dropped from the air into a disaster area that would otherwise be difficult to reach and / or enter for search and rescue personnel.BACKGROUND
[0009] Natural disasters, such as earthquakes, can be devastating and may cause a large number of casualties in the disaster area. Locating and rescuing survivors in the aftermath of such a disaster can be dangerous and time-consuming tasks. As an initial matter, whether or not there are any survivors in the disaster area must be determined. Furthermore, to the extent that there are any survivors in the disaster area they must be located. However, under actual disaster conditions, it may be very difficult for human (or even robotic) searchers and / or rescuers to enter the disaster area without the knowledge of whether there are survivors or the locations of the survivors, because the disaster area is often affected by secondary disasters such as aftershocks, mudslides, and / or building collapses, making it difficult for disaster relief personnel / equipment to enter the disaster area. Moreover, in the early stages of any disaster relief operations, the available search and rescue personnel / resources may often be limited and, therefore, it may be difficult to quickly search a large disaster area to locate and rescue any survivors.BRIEF DESCRIPTION OF THE DRAWINGS
[0010] The present disclosure is illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings.
[0011] FIG. 1 shows a diagram illustrating a sensing device to be deployed to a disaster area for detecting live subjects, according to implementations of the disclosure.
[0012] FIG. 2 shows an outer protection layer comprising an anti-collision and anti-drop protective shell for the device to be deployed to the disaster area for detecting live subjects, according to implementations of the disclosure.
[0013] FIG. 3 shows a diagram illustrating a geometry for a microphone array housed in the device to be deployed to the disaster area for detecting live subjects, according to implementations of the disclosure.
[0014] FIG. 4 shows a diagram illustrating the device being launched into the disaster area for detecting live subjects, according to implementations of the disclosure.
[0015] FIG. 5 shows a diagram illustrating the device being dropped from the air into the disaster area for detecting live subjects, according to the present disclosure.
[0016] FIG. 6 shows a flow diagram of a method for deploying the device to the disaster area for detecting live subjects, according to implementations of the disclosure.
[0017] FIG. 7 shows a flow diagram of a method for processing sound signals captured by the device in the disaster area, according to implementations of the present disclosure.
[0018] FIG. 8 shows a block diagram illustrating a machine, in the example form of a computer system, within which a set or sequence of instructions may be executed to cause the machine to perform any one of the methodologies discussed herein.DETAILED DESCRIPTION
[0019] In the immediate aftermath of a disaster (e.g., earthquake) , cameras carried by airborne drones may be used to perform a search the disaster area for any survivors (e.g., people) of the disaster. For example, the drone-based cameras may be used for correlation-based visual target searches for any survivors in the disaster area. However, in many post-disaster situations, the drone-based cameras may not be able to visually detect survivors due to the survivors being blocked or buried by rubble or debris in the disaster area. In these situations, a more effective method for searching for the blocked or buried survivors may include listening for sound signals from the survivors. However, the acquisition of sound signals in the disaster area may be very difficult because of the post-disaster conditions. For example, it may be difficult for search and rescue personnel / equipment to enter the disaster area and, therefore, if the sound signal pickup equipment (e.g., microphones) is too far from the sound source (e.g., a survivor) , the useful signal (e.g., voice of a survivor) may be very difficult to detect in a complex post-disaster sound environment. In this type of situation, it may be very difficult (or even impossible) to carry out effective sound signal pickup and sound source positioning.
[0020] Unmanned arial vehicles (UAV) hoisting microphone arrays may be used for post-disaster search and rescue operations. For example, a UAV hoisting a microphone array may first fly to the disaster area, hover in a suitable position to be able to position the microphone array (e.g., via a cable) as close as possible to any possible sound sources but also far enough from the UAV so that it is not affected by the radiation sound signal of the UAV. The shape of the microphone array may then be adjusted (e.g., by unfolding the array) according to the position of the UAV relative to the desired sound source to obtain the best microphone array sound signal pickup performance.
[0021] However, the use of UAVs hoisting microphone arrays to search for sound signals from survivors in a disaster area may face many challenges. For example, under some extreme conditions, due to geographical location and / or weather (such as high wind, heavy rain, fire, etc. ) , airborne drones may not be able to enter the disaster area for search and rescue operations. In some environments, proximity of the microphone array to the sound source (e.g., survivor on the ground) may be difficult to achieve, such as environments including jungle trees or very uneven hills / mountains under the airborne drone. Furthermore, the wind in the air may strong enough to produce wind noise that can interfere with the pickup of sound signals by the sensors of the microphone array. In the case of strong wind, the suspended microphone array (e.g., suspended via a cable) may be shaken by the wind and perform poorly with regard to locating a position of a sound source or may even fail to function at all.
[0022] As noted above, after major disasters, secondary disasters such as aftershocks, mudslides, and building collapses may make it difficult for search and rescue personnel / equipment to enter the disaster area and, in the early stages of disaster relief, available search and rescue resources may be very limited, making it difficult to carry out search and rescue operations over large disaster areas. Accordingly, a microphone array that can be launched (e.g., by equipment such as compressed air or artillery barrels) or dropped from the air (e.g., by equipment such as drones, helicopters, balloons) into disaster areas instead of other search and rescue personnel / equipment (or as an auxiliary means to assist other search and rescue personnel / equipment) could be useful in post-disaster search and rescue operations.
[0023] FIG. 1 shows a diagram illustrating a device 100 to be deployed to a disaster area for detecting live subjects, according to implementations of the disclosure.
[0024] A device 100 for detecting and locating acoustic signals from surviving subjects in a disaster area (e.g., the sound of a person calling for help) may be launched (e.g., from a cannon) or dropped from the air (e.g., from a drone) into the disaster area. The device 100 may include an outer protection layer 1 comprising an anti-collision and anti-drop protective shell (e.g., made of rubber or other such material) . In one implementation, the device 100 may be in the form of a sphere or a rounded ball so that the device 100 when dropped from the air may roll on the ground. The device 100 may also include a spherical microphone array (see FIG. 3) equipped with a microphone array pickup unit. The spherical microphone array may be protected by the outer protection layer 1 to ensure that it is not damaged and continues to function normally after a long-distance high-altitude launch or drop into the disaster area. The spherical microphone array may include multiple microphones 4 for detecting sound signals in the disaster area. During search and rescue operations, multiple channels of microphone sensors may be sampled simultaneously for subsequent array signal processing and enhancement (e.g., beam forming) and for sound source localization.
[0025] The outer protection layer 1 may include a plurality of first holes 2 comprising waterproof, fireproof and anti-high temperature holes. For example, each of the plurality of first holes 2 may be sealed by a film that is waterproof, fireproof, and heat resistant to ensure that the microphone array may not be damaged by water and / or fire when entering the disaster area, and continues to function normally in the disaster area by picking up sound signals around the device 100. The device 100 may also include an inner shell layer 3 comprising a plurality of second holes 8 that are aligned with the plurality of first holes 2. The inner shell layer 3 may house the microphones 4 of the spherical microphone array and the microphones 4 may detect sound signals around the device 100 across the aligned plurality of first holes 2 of the outer protection layer 1 and the plurality of second holes 8 of the inner shell layer 3. The inner shell layer 3 may also house a power management circuit 5. For example, the power management circuit 5 may comprise a power source to supply electrical power to the microphones 4 of the spherical microphone array as well as to other elements of device 100 such as: a data acquisition circuit 6, a wireless transmission circuit 7, a geomagnetic sensor 10, and a plurality of GPS circuits 9 corresponding to each of the microphones 4 of the spherical microphone array.
[0026] The data acquisition circuit 6 may store the signals captured by the microphones and / or may include analog-to-digital converter (ADC) circuit for converting the captured signals into a digital format that may be used to locate the sound source, or transmit (e.g., via wireless transmission circuit 7) the detected sound signals back to a search and rescue command center where a processing device of the command center may analyze the detected sound signals. In one implementation, the data acquisition circuit 6 may further include data signal processing (DSP) circuit that may perform beamforming operations using the digital signals to determine the location of a sound source. Alternatively, the wireless transmission circuit 7 may transmit the detected sound signals from the disaster area back to the search and rescue command center and may also provide important information from the data acquisition circuit (e.g., sound source location if available) for search and rescue operations.
[0027] FIG. 2 shows an outer protection layer 1 comprising an anti-collision and anti-drop protective shell for the device 100 to be deployed to the disaster area for detecting live subjects, according to implementations of the disclosure.
[0028] As noted above, the outer protection layer 1 allows the device 100 to be launched (e.g., from a cannon) or dropped from the air (e.g., from a drone) into the disaster area. To this end, the outer protection layer 1 may include an anti-collision and anti-drop protective shell made of rubber or some other such material (e.g., silicone) . As noted above, the outer protection layer 1 may include a plurality of first holes 2 comprising waterproof, fireproof and anti-high temperature holes that may help ensure that the microphone array may not be damaged by water and / or fire when entering the disaster area. Also as noted above, the first plurality of holes 2 may be aligned with a plurality of second holes 8 of the inner shell layer 3 which are themselves aligned with the microphones 4 of the spherical microphone array. In this configuration the microphones 4 of the spherical microphone array may detect sound signals around the device 100 through the aligned holes of the outer protection layer 1 and the inner shell layer 3 as explained more fully below with respect to FIG. 3.
[0029] In one implementation, each microphone 4 may be fixedly attached to a corresponding second hole 8. For example, each microphone 4 may be in the form of cylinder with threads so that the microphone 4 may be screwed into the corresponding second hole 8. Because the locations of second holes 8 on the inner shell 3 are predetermined at fixed positions, the relative positions of microphones 4 in the microphone array are also fixed.
[0030] FIG. 3 shows a diagram illustrating a geometry for a microphone array 300 housed in the device 100 to be deployed to the disaster area for detecting live subjects, according to implementations of the disclosure.
[0031] A microphone array (MA) uses signal processing techniques to obtain a directional response to a source sound signal based on signals captured by microphones of the array (e.g., microphones 4 of microphone array 300) . The microphones of the MA may be arranged according to the microphone array’s geometry (e.g., microphones 4 of microphone array 300 arranged in a spherical array geometry) . As shown in FIG. 3, the microphones 4 of spherical microphone array 300 may protrude slightly from each of the plurality of second holes 8 of the inner shell layer 3 with which they are aligned to be closer to the plurality of first holes 1 of the outer protection layer 1 through which the microphones 4 detect sound signals around the device 100 in the disaster area. The spherical microphone array 300 may be communicatively coupled to a processing device (e.g., a digital signal processor (DSP) or a central processing unit (CPU) ) that includes circuits programmed to implement a beamformer to calculate an estimate of the sound source. For example, the data acquisition circuit 6 of device 100 may include such a processor or the captured sound signals may be transmitted (e.g., via wireless transmission circuit 7 of device 100) to a search and rescue command center that includes such a processor (e.g., processor 802 of computer system 800 of FIG. 8) .
[0032] Each microphone 4 may be associated with a microphone identifier and its relative location may be specified with respect to a coordinate system with the center of coordinate system being located at the center of the spherical microphone array 300. To determine the orientation of the coordinate system when the device 100 is stopped at a position, the device 100 may also include a geomagnetic sensor 10 housed within the inner shell layer 3 (not shown in FIG. 3) for determining an orientation of a coordinate system defined at a center of the device 100 with respect to a magnetic field of the Earth. The geomagnetic sensor 10 may include two directional sensors respectively mounted in an x-y plane and an x-z plane (e.g., as shown in FIG. 3) of the coordinate system defined at the center of the device 100.
[0033] The device 100 may also include a plurality of global positioning system (GPS) circuits, wherein the GPS circuits 9 determine a global position of the device 100 based on GPS signals received from satellites. Each of the GPS circuits 9 (not shown in FIG. 3) may be associated with and / or integrated with a corresponding microphone 4 of the spherical microphone array 300 to determine a location of the corresponding microphone 4 with respect to each of the other microphones 4 in the spherical microphone array 300.
[0034] The spherical microphone array 300 may enable direction finding (if the sound source is in the far field) or positioning (if the sound source is in the near field) with respect to a sound source relative to the coordinate system of the array 300. To determine the position or orientation of the sound source in real space, it may determine the position of the spherical microphone array 300 in real space and the orientation of the array’s coordinate system. The GPS circuits 9 and the geomagnetic sensor 10 described above may be used to obtain this information. As noted above, the number and position of the GPS circuits 9 are the same as the number and position of the microphones 4 of spherical microphone array 300. Accordingly, when the device 100 is launched or dropped into the disaster area, not only may global position coordinates for the device 100 be determined using satellites, but also, the relative position of each microphone 4 may be determined in order to know the position and steering of the coordinate system of the spherical microphone array 300. Before launch or air drop of device 100, the steering (e.g., azimuth) of the geomagnetic sensor 10 (e.g., two directional sensors respectively mounted in the x-y plane and the x-z plane) relative to the coordinate system of spherical microphone array 300 may be calibrated as the initial position. When the device 100 has been launched or dropped into the disaster area, the azimuth of the direction of the geomagnetic sensor 10 relative to the same reference point may again be observed in real-time, and then, based on the real-time position and initial position, the real-time position and steering of the coordinate system of the spherical microphone array 300 may be determined according to the coordinate rotation conversion formula with a spherical coordinate system.
[0035] FIG. 4 shows a diagram illustrating the device 100 being launched into the disaster area for detecting live subjects, according to implementations of the disclosure.
[0036] As noted above, the device 100 may be launched into a disaster area to sense acoustic signals from survivors of the disaster (e.g., the sound of a human being or an animal calling for help in the disaster area) and locate the source of the acoustic signals. As shown in FIG. 4, the device 100 may be launched by a mobile cannon 400 (e.g., including equipment such as compressed air or artillery barrels) into disaster areas instead of other search and rescue personnel / equipment or as an auxiliary means to assist other search and rescue personnel / equipment. Also as noted above, to ensure that the spherical microphone array 300 is not damaged after being launched over long distances and high altitude, the device 100 may be arranged within (and protected by) a robust bump and drop resistant outer protection layer 1 equipped with a plurality of first holes that are waterproof and fireproof to ensure that the microphones 4 of spherical microphone array 300 can effectively detect sound signals in the disaster area.
[0037] FIG. 5 shows a diagram illustrating the device 100 being dropped from the air into the disaster area for detecting live subjects, according to the present disclosure.
[0038] As noted above, the device 100 may be dropped from the air into a disaster area to sense acoustic signals from survivors of the disaster (e.g., the sound of a person calling for help in the disaster area) and locate the source of the acoustic signals. As shown in FIG. 4, the device 100 may be dropped from the air by an airborne drone 500 (or by other equipment such as helicopters, balloons, etc. ) into disaster areas instead of other search and rescue personnel / equipment or as an auxiliary means to assist other search and rescue personnel / equipment. Also as noted above, to ensure that the spherical microphone array 300 is not damaged after being dropped over long distances, the device 100 may be arranged within (and protected by) a robust bump and drop resistant outer protection layer 1 equipped with a plurality of first holes that are waterproof and fireproof to ensure that the microphones 4 of spherical microphone array 300 can effectively detect sound signals in the disaster area.
[0039] FIG. 6 shows a flow diagram of a method 600 for deploying the device 100 to the disaster area for detecting live subjects, according to the present disclosure.
[0040] The method 600 may start, and then, at operation 602 may continue by deploying a device (e.g., device 100 of FIG. 1) to the disaster area (e.g., post-earthquake area) , wherein the device 100 comprises:
[0041] At operation 604, a housing comprising an outer protection layer 1 and an inner shell layer 3, the outer protection layer 1 fully and / or almost fully enclosing an outer surface of the inner shell layer 3, wherein the outer protection layer 1 comprises a plurality of first holes 2 and the inner shell layer includes a plurality of second holes 8 that are aligned with the plurality of first holes 2;
[0042] At operation 606, a data acquisition circuit 6 may directly process detected sound signals (e.g., detected by spherical microphone array 300 of FIG. 3) to help locate the sound source, or transmit (e.g., via wireless transmission circuit 7) the detected sound signals back to a search and rescue command center where a processing device of the command center (e.g., processor 802 of computer system 800 of FIG. 8) may analyze the detected sound signals;
[0043] At operation 608, a wireless transmission circuit 7may transmit the detected sound signals from the disaster area back to the search and rescue command center and may also provide important information from the data acquisition circuit (e.g., estimated parameters of sound source location if available) for search and rescue operations; and
[0044] At operation 610, a microphone array 300 comprising a plurality of microphones 4, wherein the plurality of microphones are fixedly arranged and aligned with the plurality of second holes 8 of inner shell layer 3, and wherein the microphone array 300, the data acquisition circuit 6, and the wireless transmission circuit 7 are enclosed inside the housing (e.g., housed inside the inner shell layer 3 inside the outer protection layer 1) . The method 600 may then end.
[0045] FIG. 7 shows a flow diagram of a method 700 for processing sound signals captured by the device (e.g., device 100 of FIG. 1) in the disaster area (e.g., post-earthquake area) , according to implementations of the present disclosure.
[0046] The method 700 may start (e.g., responsive to a start signal, each of the plurality of microphones 4 of spherical microphone array 300 may to capture a corresponding sound signal and transmit the corresponding sound signal to the data acquisition circuit 6, and the data acquisition circuit 6 is to convert each corresponding sound signal into a corresponding digital signal) , and then, at operation 702 may continue by transmitting the digital signals (e.g., based on detected sound signals) , the orientation (e.g., based on the geomagnetic sensor 10 described above) , and the global position (e.g., based on the GPS circuits 9 described above) to a central system (e.g., search and rescue command center) , and wherein the central system includes a processing device (e.g., processor 802 of computer system 800 of FIG. 8) that is to:
[0047] At operation 704, applying a beamformer to the digital signals to generate enhanced digital signals. The complexity of the actual disaster area environment may result in detected sound signals that are very weak and may require a more powerful processing unit (e.g., than is available on the device 100) to use microphone array enhancement technology to design beams pointing in different directions (e.g., with respect to the coordinate system of microphone array 300 in device 100 as explained above) and corresponding post-filters to enhance the signal in each direction.
[0048] At operation 706, detecting, based on the enhanced digital signal using an analysis model, whether the captured sound signals contain abnormal acoustic sound signals. The enhanced signal may be used to determine whether there is an abnormal signal (e.g., different from the expected background noise of the post-disaster environment) , and if there is an abnormal signal, it may be determined whether it is a distress signal as described below.
[0049] At operation 708, responsive to determining that the captured sound signals contain the abnormal acoustic sound signals, determining that the abnormal acoustic sound signals indicate a sound from an at-risk subject. For example, by combining signal analysis and / or listening with human ears it may be determined that a captured sound signal indicates a sound from an at-risk subject, for example, a trapped person. If it is judged that the captured sound signal is suspected to be a distress signal, then the sound source for the captured sound signal may be located as explained below.
[0050] At operation 710, determining a location of the at-risk subject based on the orientation and the global position of the device. As explained in detail above with respect to FIG. 3, the geomagnetic sensor 10 arranged with respect to the coordinate system of the spherical microphone array 300 of device 100 and the GPS circuits 9 corresponding to each of the microphones 4 of the microphone array 300 may be used to accurately locate the sound source that emits the abnormal sound signal.
[0051] FIG. 8 is a block diagram illustrating a machine in the example form of a computer system 800, within which a set or sequence of instructions may be executed to cause the machine to perform any one of the methodologies discussed herein.
[0052] In alternative embodiments, the machine operates as a standalone device or may be connected (e.g., networked) to other machines. In a networked deployment, the machine may operate in the capacity of either a server or a client machine in server-client network environments, or it may act as a peer machine in peer-to-peer (or distributed) network environments. The machine may be an onboard vehicle system, wearable device, personal computer (PC) , a tablet PC, a hybrid tablet, a personal digital assistant (PDA) , a mobile telephone, or any machine capable of executing instructions (sequential or otherwise) that specify actions to be taken by that machine. Further, while only a single machine is illustrated, the term “machine” shall also be taken to include any collection of machines that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein. Similarly, the term “processor-based system” shall be taken to include any set of one or more machines that are controlled by or operated by a processor (e.g., a computer) to individually or jointly execute instructions to perform any one or more of the methodologies discussed herein.
[0053] Example computer system 800 includes at least one processor 802 (e.g., a central processing unit (CPU) , a graphics processing unit (GPU) or both, processor cores, compute nodes, etc. ) , a main memory 804 and a static memory 806, which communicate with each other via a link 808 (e.g., bus) . The computer system 800 may further include a video display unit 810, an alphanumeric input device 812 (e.g., a keyboard) , and a user interface (UI) navigation device 814 (e.g., a mouse) . In one embodiment, the display device 810, input device 812 and UI navigation device 814 are incorporated into a touch screen display. The computer system 800 may additionally include a storage device 816 (e.g., a drive unit) , a signal generation device 818 (e.g., a speaker) , a network interface device 820, and one or more sensors 821, such as a global positioning system (GPS) sensor, compass, accelerometer, gyrometer, magnetometer, or another sensor.
[0054] The storage device 816 includes a machine-readable medium 822 on which is stored one or more sets of data structures and instructions 824 (e.g., software) embodying or utilized by any one or more of the methodologies or functions described herein. The instructions 824 may also reside, completely or at least partially, within the main memory 804, static memory 806, and / or within the processor 802 during execution thereof by the computer system 800, with the main memory 804, static memory 806, and the processor 802 also constituting machine-readable media.
[0055] While the machine-readable medium 822 is illustrated in an example embodiment to be a single medium, the term “machine-readable medium” may include a single medium or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) that store the one or more instructions 824. The term “machine-readable medium” shall also be taken to include any tangible medium that is capable of storing, encoding or carrying instructions for execution by the machine and that cause the machine to perform any one or more of the methodologies of the present disclosure or that is capable of storing, encoding or carrying data structures utilized by or associated with such instructions. Specific examples of machine-readable media include volatile or non-volatile memory, including but not limited to, by way of example, semiconductor memory devices (e.g., electrically programmable read-only memory (EPROM) , electrically erasable programmable read-only memory (EEPROM) ) and flash memory devices; magnetic disks such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks.
[0056] The instructions 824 may further be transmitted or received over a communications network 826 using a transmission medium via the network interface device 820 utilizing any one of a number of well-known transfer protocols (e.g., HTTP) . Examples of communication networks include a local area network (LAN) , a wide area network (WAN) , the Internet, mobile telephone networks, plain old telephone (POTS) networks, and wireless data networks (e.g., Wi-Fi, 3G, and 4G LTE / LTE-A or WiMAX networks) . Input / output controllers 828 may receive input and output requests from the central processor 802, and then send device-specific control signals to the devices they control (e.g., display device 810) . The input / output controllers 828 may also manage the data flow to and from the computer system 800. This may free the central processor 802 from involvement with the details of controlling each input / output device.
[0057] Language: In the foregoing description, numerous details are set forth. It may be apparent, however, to one of ordinary skill in the art having the benefit of this disclosure, that the present disclosure may be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form, rather than in detail, to avoid obscuring the present disclosure.
[0058] It should be borne in mind, however, that all of these and similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. Unless specifically stated otherwise as apparent from the following discussion, it is appreciated that throughout the description, discussions utilizing terms such as ″segmenting″ , ″analyzing″ , ″determining″ , ″enabling″ , “identifying, ” ″modifying″ or the like, refer to the actions and processes of a computer system, or similar electronic computing device, that manipulates and transforms data represented as physical (e.g., electronic) quantities within the computer system′sregisters and memories into other data represented as physical quantities within the computer system memories or other such information storage, transmission or display devices.
[0059] As used in this disclosure, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or” . That is, unless specified otherwise, or clear from context, “X includes A or B” is intended to mean any of the natural inclusive permutations. That is, if X includes A; X includes B; or X includes both A and B, then “X includes A or B” is satisfied under any of the foregoing instances. In addition, the articles “a” and “an” as used in this application and the appended claims should generally be construed to mean “one or more” unless specified otherwise or clear from context to be directed to a singular form. Moreover, use of the term “an embodiment” or “one embodiment” or “an implementation” or “one implementation” throughout is not intended to mean the same embodiment or implementation unless described as such.
[0060] It is to be understood that the above description is intended to be illustrative, and not restrictive. Many other implementations may be apparent to those of skill in the art upon reading and understanding the above description.
Claims
1.A device to be deployed in a disaster area for detecting live subjects, comprising:a housing comprising an outer protection layer and an inner shell layer, the outer protection layer enclosing an outer surface of the inner shell layer, wherein the outer protection layer comprises a plurality of first holes and the inner shell layer comprises a plurality of second holes that each is aligned with a corresponding first hole;a data acquisition circuit;a wireless transmission circuit; anda microphone array comprising a plurality of microphones, wherein the plurality of microphones are arranged at positions that are aligned with the plurality of second holes, and wherein the microphone array, the data acquisition circuit, and the wireless transmission circuit are enclosed inside the housing.2.The device of claim 1, further comprising a geomagnetic sensor, wherein the geomagnetic sensor is used to capture orientation data for determining an orientation of a coordinate system defined at a center of the device with respect to a magnetic field of the Earth.3.The device of claim 2, wherein the geomagnetic sensor comprises two directional sensors respectively mounted in an x-y plane and an x-z plane of the coordinate system defined at the center of the device.4.The device of claim 2, further comprising a plurality of global positioning system (GPS) circuits, wherein the GPS circuits determine a global position of the device based on GPS signals received from satellites.5.The device of claim 4, wherein each of the GPS circuits is associated with a corresponding microphone in the microphone array to determine a location of the corresponding microphone with respect to each of the other microphones in the microphone array.6.The device of claim 4, further comprising a power management circuit, wherein the power management circuit comprises a power source to supply electrical power to the microphone array, the data acquisition circuit, the wireless transmission circuit, the geomagnetic sensor, and the plurality of GPS circuits.7.The device of claim 1, wherein each of the plurality of microphones is to capture a corresponding sound signal and transmit the corresponding sound signal to the data acquisition circuit, and the data acquisition circuit is to convert the corresponding sound signal into a corresponding digital signal.8.The device of claim 7, wherein the wireless transmission circuit is to transmit the digital signals, the orientation, and the global position to a central system, and wherein the central system includes a processing device that is to:apply a beamformer to the digital signals to generate enhanced digital signals;detect, based on the enhanced digital signal using an analysis model, whether the captured sound signals contain abnormal acoustic sound signals;responsive to determining that the captured sound signals contain the abnormal acoustic sound signals, determine that the abnormal acoustic sound signals indicate a sound from an at-risk subject; anddetermine a location of the at-risk subject based on the orientation and the global position of the device.9.The device of claim 1, wherein each of the plurality of first holes is waterproof, fireproof, and heat resistant.10.The device of claim 9, wherein each of the plurality of first holes is sealed by a film that is waterproof, fireproof, and heat resistant.11.A method for detecting live subjects in a disaster area, the method comprising:deploying a device to the disaster area, wherein the device comprises:a housing comprising an outer protection layer and an inner shell layer, the outer protection layer fully enclosing an outer surface of the inner shell layer, wherein the outer protection layer comprises a plurality of first holes and the inner shell layer comprises a plurality of second holes that each is aligned with a corresponding first hole;a data acquisition circuit;a wireless transmission circuit; anda microphone array comprising a plurality of microphones, wherein the plurality of microphones are arranged at positions that are aligned with the plurality of second holes, and wherein the microphone array, the data acquisition circuit, and the wireless transmission circuit are enclosed inside the housing.12.The method of claim 11, wherein deploying the device to the disaster area comprises launching the device into the disaster area or dropping the device into the disaster areas from air.13.The method of claim 11, wherein the device comprises a geomagnetic that is used to capture orientation data for determining an orientation of a coordinate system defined at a center of the device with respect to a magnetic field of the Earth.14.The method of claim 13, wherein the geomagnetic sensor comprises two directional sensors respectively mounted in an x-y plane and an x-z plane of the coordinate system defined at the center of the device.15.The method of claim 13, wherein the device comprises a plurality of global positioning system (GPS) circuits for determining a global position of the device based on GPS signals received from satellites.16.The method of claim 15, wherein each of the GPS circuits is associated with a corresponding microphone in the microphone array and the method further comprises determining a location of a microphone with respect to each of the other microphones in the microphone array based on the corresponding GPS circuits.17.The method of claim 15, wherein the device comprises a power management unit comprising a power source for supplying electrical power to the microphone array, the data acquisition circuit, the wireless transmission circuit, the geomagnetic sensor, and the plurality of GPS circuits.18.The method of claim 11, further comprising:capturing a corresponding sound signal with each of the plurality of microphones;transmitting the corresponding sound signals to the data acquisition circuit; andconverting the corresponding sound signals into corresponding digital signals with the data acquisition circuit.19.The method of claim 18, further comprising:transmitting the digital signals, the orientation, and the global position to a central system with the wireless transmission circuit, wherein the central system includes a processing device for:applying a beamformer to the digital signals to generate enhanced digital signals;detecting, based on the enhanced digital signal using an analysis model, whether the captured sound signals contain abnormal acoustic sound signals;determining that the abnormal acoustic sound signals indicate a sound from an at-risk subject based on determining that the captured sound signals contain the abnormal acoustic sound signals; anddetermining a location of the at-risk subject based on the orientation and the global position of the device.20.The method of claim 11, wherein each of the plurality of first holes is waterproof, fireproof, and heat resistant or wherein each of the plurality of first holes is sealed by a film that is waterproof, fireprooI, and heat resistant.
Citation Information
Patent Citations
Spherical following robot and following control method thereof
CN108297108A
Spherical inner detector and positioning system for pipeline leakage detection
CN114151737A
Audio and video fusion multi-speaker detection equipment
CN116233687A
System and method for human and animal detection in low visibility
US20220365200A1
Spherical robot for internal inspection of pipelines
WO2020065659A1