Device and method for detecting target object based on multiple radars

Abstract

The invention provides a target object detection device and detection method based on multiple radars. In the detection method, a first detection result corresponding to a first detection space and a second detection result corresponding to a second detection space are received. And in response to the first detection result, indicating that a target object located in the first detection space moves towards an overlapping region between the first detection space and the second detection space, and judging that the first detection space enters a first state. And outputting first information in response to judging that the first detection space enters the first state. And in response to the second detection result indicating that the target object not in the second detection space appears in the overlapping area, judging that the second detection space enters a second state. And outputting second information in response to judging that the second detection space enters the second state.

Description

Technical Field

[0001] The present invention relates to a radar detection technology, and in particular to a target object detection device and a detection method based on multiple radars. Background Art

[0002] Due to social changes and aging, more and more elderly people live alone. How to care for these elderly people living alone has become a major problem that today's society must face. In addition to using social groups such as social service personnel or volunteers to conduct visits, if there is a care device with a remote detection function, it can immediately assist the care recipient in an emergency. Existing remote detection devices are mainly wearable devices or imaging devices. When installing a position detection device in a private indoor space, in order to reduce the invasion of the privacy of the care recipient, radar can be used to detect the care recipient to avoid the care recipient's image being recorded. However, when the living environment of the care recipient includes multiple spaces, the detection range of a single radar cannot fully cover the living environment. Therefore, it is usually necessary to set up a dedicated radar for each independent space. Therefore, how to integrate the information of multiple radar systems to effectively detect the care recipient is one of the important topics in this field. Summary of the invention

[0003] The present invention provides a target object detection device and a detection method based on multiple radars, which can integrate the detection results from multiple radars to provide correct information for users.

[0004] According to an embodiment of the present invention, a target object detection device based on multiple radars includes a human-machine interface, a transceiver, and a processor. The transceiver receives a first detection result corresponding to a first detection space and a second detection result corresponding to a second detection space from multiple radars. The processor is coupled to the human-machine interface and the transceiver, and is configured to execute: in response to the first detection result indicating that the target object located in the first detection space moves to the overlapping area between the first detection space and the second detection space, the first detection space is judged to enter a first state; in response to the judgment that the first detection space enters the first state, a first information is output through the human-machine interface, wherein the first information indicates that the target object is located in the first detection space; in response to the second detection result indicating that the target object not in the second detection space appears in the overlapping area, the second detection space is judged to enter a second state; and in response to the judgment that the second detection space enters the second state, a second information is output through the human-machine interface, wherein the second information indicates that the target object is not in the second detection space.

[0005] According to an embodiment of the present invention, a method for detecting a target object based on multiple radars is provided. The method comprises: receiving a first detection result corresponding to a first detection space and a second detection result corresponding to a second detection space from multiple radars; in response to the first detection result indicating that a target object located in the first detection space moves toward an overlapping area between the first detection space and the second detection space, determining that the first detection space enters a first state; in response to determining that the first detection space enters the first state, outputting first information through a human-machine interface, wherein the first information indicates that the target object is located in the first detection space; in response to the second detection result indicating that a target object not in the second detection space appears in the overlapping area, determining that the second detection space enters a second state; and in response to determining that the second detection space enters the second state, outputting second information through the human-machine interface, wherein the second information indicates that the target object is not in the second detection space.

[0006] Based on the above, the present invention can integrate the detection results of multiple radars to quickly and accurately determine the space where the target object is located and the state of the target object. The present invention can also provide a variety of information for users to view through the human-machine interface, helping users to quickly understand the state of the target object or the detection space. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 A schematic diagram of a target object detection device based on multiple radars is shown as an embodiment of the present invention;

[0008] Figure 2 A schematic diagram illustrating a detection area according to an embodiment of the present invention;

[0009] Figure 3 A flow chart of a method for detecting a target person is shown for one embodiment of the present invention;

[0010] Figure 4A , Figure 4B and Figure 4C A schematic diagram illustrating changes in a bounding box according to an embodiment of the present invention;

[0011] Figure 5 A schematic diagram of a first state machine of a detection space is shown for one embodiment of the present invention;

[0012] Figure 6 A schematic diagram of a second state machine of the detection space is depicted for one embodiment of the present invention;

[0013] Fig. 7A and Figure 7B A schematic diagram illustrating a first example of state transition of a detection space according to an embodiment of the present invention;

[0014] Fig. 8A and Figure 8BA schematic diagram illustrating a second example of state transition of a detection space according to an embodiment of the present invention;

[0015] Fig.9A and Fig. 9B A schematic diagram illustrating a third example of state transition of a detection space according to an embodiment of the present invention;

[0016] Fig. 10A and Fig. 10B A schematic diagram illustrating a fourth example of state transition of a detection space according to an embodiment of the present invention;

[0017] Fig.11A and Fig. 11B is a schematic diagram illustrating a fifth example of state transition of a detection space according to an embodiment of the present invention;

[0018] Fig.12 A schematic diagram of a graphical user interface displayed on a human-machine interface is shown for one embodiment of the present invention;

[0019] Fig.13 A schematic diagram illustrating icons of a graphical user interface according to an embodiment of the present invention;

[0020] Fig.14 A schematic diagram illustrating icons of a graphical user interface according to an embodiment of the present invention;

[0021] Fig.15 A flow chart of a method for detecting a target person based on multiple radars is shown as an embodiment of the present invention.

[0022] Explanation of symbols

[0023] 100: Detection device

[0024] 11, 12: Radar

[0025] 110: Processor

[0026] 1100: Graphical User Interface

[0027] 120: Human-machine interface

[0028] 121, 122, 123, 124, 125, 126: Icon

[0029] 130: Transceiver

[0030] 20: Target Person

[0031] 200: Detection area

[0032] 210, 220: Detection Space

[0033] 300: Overlapping area

[0034] 400: Preset area

[0035] 41, 42, 43, 44, 45, 46, 47, 48, 49: Bounding box

[0036] 500, 600: State machine

[0037] S1, S2, S3, S4, S5, S6: Status

[0038] T1, T2, T3, T4, T5, T6, T7, T8, T9, T10, T11, T12, T13, T14, T15, T16: Transfer conditions

[0039] S301, S302, S303, S304, S305, S306, S307, S308, S309, S310, S151, S152, S153, S154, S155: Steps DETAILED DESCRIPTION

[0040] Figure 1 A schematic diagram of a multi-radar based target object detection device 100 is shown according to an embodiment of the present invention. The detection device 100 may include a processor 110 , a human-machine interface 120 , and a transceiver 130 .

[0041] The processor 110 is, for example, a central processing unit (CPU), or other programmable general-purpose or special-purpose micro control unit (MCU), microprocessor, digital signal processor (DSP), programmable controller, application specific integrated circuit (ASIC), graphics processing unit (GPU), image signal processor (ISP), image processing unit (IPU), arithmetic logic unit (ALU), complex programmable logic device (CPLD), field programmable gate array (FPGA), or other similar elements or combinations thereof. The processor 110 can be coupled to the human-machine interface 120 and the transceiver 130, and access and execute various modules and applications stored in the storage medium.

[0042] The human machine interface (HMI) 120 is used to receive information input from a user or output information for the user's reference. The human machine interface 120 may include a device such as a touch screen.

[0043] The transceiver 130 transmits or receives signals in a wireless or wired manner. The transceiver 130 may also perform operations such as low noise amplification, impedance matching, mixing, up or down frequency conversion, filtering, amplification, and the like. The detection device 100 may be communicatively connected to a plurality of radars respectively arranged at a plurality of locations through the transceiver 130, and receive detection results of each radar on the detection space from the plurality of radars.

[0044] Figure 2According to an embodiment of the present invention, a schematic diagram of a detection area 200 is depicted. For example, the target object detected by the detection device 100 may be a target person (or a person under care) 20, and the detection area 200 may be, for example, an area where the target person 20 lives. In the following embodiments, it is assumed that the detection area 200 includes two independent detection spaces 210 and 220, and the detection space 210 and the detection space 220 overlap in the overlapping area 300. The detection space 210 may include a preset area 400. The preset area 400 may be included in the detection space 210 or the detection space 220, wherein the preset area 400 is, for example, an entrance and exit of the detection area 200. The radar 11 may be configured to monitor the detection space 210 and generate corresponding detection results. The radar 12 may be configured to monitor the detection space 220 and generate corresponding detection results. The detection device 100 can receive the detection result corresponding to the detection space 210 and the detection result corresponding to the detection space 220 from the radar 11 and the radar 12 respectively through the transceiver 130. The radar 11 or the radar 12 is, for example, a continuous wave radar (CW) for detecting information including the physiological state (e.g., breathing or heartbeat) of the target person 20, a frequency modulated continuous wave (FMCW) radar for detecting the movement of the target person 20 or for generating the detection result of the detection space, or an impulse radio ultra-wideband (IR-UWB) radar, etc., but the present invention is not limited thereto.

[0045] Figure 3 According to an embodiment of the present invention, a flow chart of a method for detecting a target person is shown, wherein the method may be performed as follows: Figure 1 The detection device 100 is shown implemented.

[0046] In step S301, the processor 110 may determine whether the target person 20 is in the detection space (e.g., detection space 210 or 220) based on the detection result of the radar (e.g., radar 11 or 12). If the target person 20 is in the detection space, the process proceeds to step S302. If the target person 20 is not in the detection space, the process proceeds to step S308. In one embodiment, the processor 110 may determine that the target person 20 is in the detection space based on the fact that the detection result of the radar includes information related to the physiological state of the target person 20, and may determine that the target person 20 is not in the detection space based on the fact that the detection result does not include information related to the physiological state of the target person.

[0047] In step S302 , the processor 110 may display information indicating that the target person 20 is in the detection space through the human-machine interface 120 for the user's reference.

[0048] In step S303, the processor 110 can count the target person 20's stay time in the detection space based on the target person 20 being in the detection space, and determine whether the stay time is too long (e.g., the stay time is greater than a threshold or an upper limit), too short (e.g., the stay time is less than a threshold or a lower limit), or normal (e.g., the stay time is less than or equal to an upper limit and greater than or equal to a lower limit). If the stay time is too short, the process proceeds to step S304. If the stay time is too long, the process proceeds to step S305. If the stay time is normal, the process proceeds to step S306.

[0049] In step S304 , the processor 110 may display a warning message through the human-machine interface 120 indicating that the target person 20 has stayed in the detection space for too short a time.

[0050] In step S305 , the processor 110 may display a warning message through the human-machine interface 120 indicating that the target person 20 has stayed in the detection space for too long.

[0051] In step S306, the processor 110 can determine whether the target person 20 falls in the detection space according to the detection result. If it is determined that the target person 20 falls, the process proceeds to step S307. If it is determined that the target person 20 does not fall, step S301 is re-executed after a period of time.

[0052] Specifically, the processor 110 can obtain multiple points of point cloud data corresponding to multiple time points from the radar detection results of the target person 20 and the detection space, and perform object detection on the multiple points of point cloud data to generate multiple bounding boxes corresponding to the multiple time points. The processor 110 can determine whether the person has fallen according to the changes in the bounding boxes.

[0053] In one embodiment, the processor 110 may determine the speed, height, or tilt change of the target person 20 according to the multiple bounding boxes, and determine whether the target person 20 falls according to the speed, height, or tilt change.

[0054] Figure 4A , Figure 4B and Figure 4C A schematic diagram showing the change of a bounding box according to an embodiment of the present invention is shown. Figure 4A , assuming that the processor 110 obtains the bounding boxes 41, 42, and 43 corresponding to the point cloud of the target person 20 in time sequence. The processor 110 can determine the speed of the target person 20 during a preset period (e.g., 5 seconds) according to the bounding boxes 41, 42, and 43. If the speed of the target person 20 is greater than a threshold value (e.g., 50 cm / s), the processor 110 can determine that the target person 20 may fall.

[0055] Reference Figure 4B, assuming that the processor 110 obtains the bounding boxes 44, 45, and 46 corresponding to the target person 20 in a time sequence. The processor 110 can determine the height of the centroid or center of gravity of the target person 20 according to the bounding boxes 44, 45, and 46. If the height of the centroid or center of gravity of the target person 20 is less than a threshold value (e.g., 50 cm), the processor 110 can determine that the target person 20 may fall.

[0056] Reference Figure 4C , assuming that the processor 110 obtains the bounding boxes 47, 48, and 49 corresponding to the point cloud of the target person 20 in chronological order. The processor 110 can determine the inclination change of the target person 20 according to the bounding boxes 47, 48, and 49. If the inclination change of the target person 20 is greater than a threshold value (e.g., 45 degrees), the processor 110 can determine that the target person 20 may fall.

[0057] Back to Figure 3 In step S307, the processor 110 may display information indicating that the target person 20 may fall through the human-machine interface 120 for the user's reference.

[0058] In step S308 , the processor 110 may display information indicating that the target person 20 is not in the detection space through the human-machine interface 120 for the user's reference.

[0059] In step S309, the processor 110 can count the time when the target person 20 leaves the detection space based on the fact that the target person 20 is not in the detection space, and determine whether the time when the target person 20 leaves the detection space is too long (for example, the time when the target person 20 leaves the detection space is greater than a threshold or an upper limit). If the time when the target person 20 leaves the detection space is too long, the process proceeds to step S310. If the time when the target person 20 leaves the detection space is not too long, the process proceeds to step S301 again after a period of time.

[0060] In step S310 , the processor 110 may display information indicating that the target person 20 has been away for too long through the human-machine interface 120 for the user's reference.

[0061] Figure 5 According to an embodiment of the present invention, a schematic diagram of a first state machine 500 of a detection space (e.g., detection space 210 or 220) is shown. The processor 110 can determine the current state of the detection space according to the detection results of each radar and the state machine 500, and output corresponding information according to the state of the detection space through the human-machine interface 120, wherein the information is used to indicate whether the target person is located in the detection space. Taking the detection space 210 as an example, the state machine 500 can include the following states and transition conditions.

[0062] State S1: the target person 20 fades out of the detection space 210. When the detection space 210 is in the state S1, the processor 110 outputs information indicating that the target person 20 is in the detection space 210 through the human-machine interface 120.

[0063] State S2: the target person 20 fades into the detection space 210. When the detection space 210 is in the state S2, the processor 110 outputs information indicating that the target person 20 is not in the detection space 210 through the human-machine interface 120.

[0064] State S3: the target person 20 is not detected in the detection space 210 . When the detection space 210 is in state S3 , the processor 110 outputs information indicating that the target person 20 is not in the detection space 210 through the human-machine interface 120 .

[0065] State S4: the target person 20 is detected in the detection space 210 . When the detection space 210 is in state S4 , the processor 110 outputs information indicating that the target person 20 is in the detection space 210 through the human-machine interface 120 .

[0066] State S5: the target person 20 is about to leave the detection space 210 . When the detection space 210 is in state S5 , the processor 110 outputs information indicating that the target person 20 is in the detection space 210 through the human-machine interface 120 .

[0067] State S6: the target person 20 is about to enter the detection space 210. When the detection space 210 is in state S6, the processor 110 outputs information indicating that the target person 20 is not in the detection space 210 through the human-machine interface 120.

[0068] Transition condition T1: When the detection space 210 is in state S4, the detection result indicates that the target person 20 in the detection space 210 moves from the detection space 210 to the overlapping area 300. The processor 110 may determine that the detection space 210 switches from state S4 to state S1 when the transition condition T1 is satisfied.

[0069] Transition condition T2: When the detection space 210 is in state S1, the detection result indicates that the target person 20 disappears from the detection space 210. The processor 110 may determine that the detection space 210 switches from state S1 to state S3 when the transition condition T2 is satisfied.

[0070] Transition condition T3: When the detection space 210 is in state S1, the detection result indicates that the target person 20 moves from the overlapping area 300 to the detection space 210. The processor 110 may determine that the detection space 210 switches from state S1 to state S4 when the transition condition T3 is satisfied.

[0071] Transition condition T4: When the detection space 210 is in state S2, the detection result indicates that the target person 20 moves from the overlapping area 300 to the detection space 210. The processor 110 may determine that the detection space 210 switches from state S2 to state S4 when the transition condition T4 is satisfied.

[0072] Transition condition T5: When the detection space 210 is in state S2, the detection result indicates that the target person 20 disappears from the detection space 210. The processor 110 may determine that the detection space 210 switches from state S2 to state S3 when the transition condition T5 is satisfied.

[0073] Transition condition T6: When the detection space 210 is in state S3, the detection result indicates that the target person 20 not in the detection space 210 appears in the overlapping area 300. The processor 110 may determine that the detection space 210 switches from state S3 to state S2 when the transition condition T6 is satisfied.

[0074] Transition condition T7: When the detection space 210 is in state S4, the detection result indicates that the target person 20 in the detection space 210 disappears from the detection space 210. The processor 110 may determine that the detection space 210 switches from state S4 to state S5 when the transition condition T7 is satisfied.

[0075] Transition condition T8: When the detection space 210 is in state S5, the detection result indicates that the target person 20 appears in the detection space 210. The processor 110 may determine that the detection space 210 switches from state S5 to state S4 when the transition condition T8 is satisfied.

[0076] Transition condition T9: When the detection space 210 is in state S5, the detection result indicates that the target person 20 is not detected in the detection space 210 (ie, the target person 20 does not appear in the detection space 210). The processor 110 may determine that the detection space 210 switches from state S5 to state S3 when the transition condition T9 is satisfied.

[0077] Transition condition T10: When the detection space 210 is in state S6, the detection result indicates that the target person 20 has not disappeared from the detection space 210. The processor 110 may determine that the detection space 210 switches from state S6 to state S4 when the transition condition T10 is satisfied.

[0078] Transition condition T11: When the detection space 210 is in state S6, the detection result indicates that the target person 20 disappears from the detection space 210. The processor 110 may determine that the detection space 210 switches from state S6 to state S3 when the transition condition T11 is satisfied.

[0079] Transition condition T12: When the detection space 210 is in state S3, the detection result indicates that the target person 20 not in the detection space 210 appears in the detection space 210. The processor 110 may determine that the detection space 210 switches from state S3 to state S6 when the transition condition T12 is satisfied.

[0080] Transition condition T13: When the detection space 210 is in state S4, the detection result indicates that the target person 20 located in the detection space 210 appears in the detection space 210. The processor 110 may determine that the detection space 210 switches from state S4 to state S4 when the transition condition T13 is satisfied.

[0081] Transition condition T14: When the detection space 210 is in state S3, the detection result indicates that the target person 20 not in the detection space 210 appears in the detection space 210. The processor 110 may determine that the detection space 210 switches from state S3 to state S3 when the transition condition T14 is satisfied.

[0082] Figure 6 According to an embodiment of the present invention, a schematic diagram of a second state machine 600 of a detection space (e.g., detection space 210 or 220) is shown. The processor 110 can determine the current state of the detection space according to the detection results of each radar and the state machine 600, and output corresponding information according to the state of the detection space through the human-machine interface 120, wherein the information is used to indicate whether the target person is located in the detection space. Taking the detection space 210 as an example, compared with the state machine 500, the state machine 600 further includes the following transfer conditions.

[0083] Transition condition T15: When the detection space 210 is in state S4, the detection result indicates that the target person 20 in the detection area 200 disappears from the preset area 400. The processor 110 may determine that the detection space 210 switches from state S4 to state S3 when the transition condition T15 is satisfied.

[0084] Transition condition T16: When the detection space 210 is in state S3, the detection result indicates that the target person 20 not in the detection space 210 appears in the preset area 400. The processor 110 may determine that the detection space 210 switches from state S3 to state S4 when the transition condition T16 is satisfied.

[0085] Fig. 7A and Figure 7B A schematic diagram of a first example of state transition of a detection space is shown according to an embodiment of the present invention, wherein Fig. 7A A state machine 500 corresponding to the detection space 210 is shown, and Figure 7BThe state machine 500 corresponding to the detection space 220 is shown. Assume that the target person 20 is located in the detection space 210. The state S4 of the detection space 210 indicates that the target person 20 is located in the detection space 210, and the state S3 of the detection space 220 indicates that the target person 20 is not in the detection space 220. In the case where the target person 20 does not move, the transition condition T13 of the detection space 210 and the transition condition T14 of the detection space 220 are respectively satisfied, so that the state of the detection space 210 switches back to the state S4, and the state of the detection space 220 switches to the state S3.

[0086] Fig. 8A and Figure 8B A schematic diagram of a second example of state transition of the detection space is shown according to an embodiment of the present invention, wherein Fig. 8A A state machine 500 corresponding to the detection space 210 is shown, and Figure 8B A state machine 500 corresponding to the detection space 220 is shown. Assume that the target person 20 is located in the detection space 210. The state S4 of the detection space 210 indicates that the target person 20 is located in the detection space 210, and the state S3 of the detection space 220 indicates that the target person 20 is not in the detection space 220. If the target person 20 appears in the overlapping area 300, the transition condition T1 of the detection space 210 and the transition condition T6 of the detection space 220 are satisfied, respectively, so that the state of the detection space 210 is switched to the state S1, and the state of the detection space 220 is switched to the state S2. Next, if the target person 20 disappears from the detection space 210 and moves from the overlapping area 300 to the detection space 220, the transition condition T2 of the detection space 210 and the transition condition T4 of the detection space 220 are satisfied, respectively, so that the state of the detection space 210 is switched to the state S3, and the state of the detection space 220 is switched to the state S4.

[0087] Fig.9A and Fig. 9B A schematic diagram of a third example of state transition of the detection space is shown according to an embodiment of the present invention, wherein Fig.9A A state machine 500 corresponding to the detection space 210 is shown, and Fig. 9BA state machine 500 corresponding to the detection space 220 is shown. Assume that the target person 20 is located in the detection space 210. The state S4 of the detection space 210 indicates that the target person 20 is located in the detection space 210, and the state S3 of the detection space 220 indicates that the target person 20 is not in the detection space 220. If the target person 20 appears in the overlapping area 300, the transition condition T1 of the detection space 210 and the transition condition T6 of the detection space 220 are satisfied, respectively, so that the state of the detection space 210 is switched to the state S1, and the state of the detection space 220 is switched to the state S2. Next, if the target person 20 moves from the overlapping area 300 to the detection space 210 and disappears from the detection space 220, the transition condition T3 of the detection space 210 and the transition condition T5 of the detection space 220 are satisfied, respectively, so that the state of the detection space 210 is switched to the state S4, and the state of the detection space 220 is switched to the state S3.

[0088] Fig. 10A and Fig. 10B A schematic diagram of a fourth example of state transition of the detection space is shown according to an embodiment of the present invention, wherein Fig. 10A A state machine 500 corresponding to the detection space 210 is shown, and Fig. 10B The state machine 500 corresponding to the detection space 220 is shown. Assume that the target person 20 is located in the detection space 210. The state S4 of the detection space 210 indicates that the target person 20 is located in the detection space 210, and the state S3 of the detection space 220 indicates that the target person 20 is not in the detection space 220. If the target person 20 disappears from the detection space 210 and appears in the detection space 220, the transition condition T7 of the detection space 210 and the transition condition T12 of the detection space 220 are satisfied, respectively, so that the state of the detection space 210 is switched to the state S5, and the state of the detection space 220 is switched to the state S6. Then, if the target person 20 still does not appear in the detection space 210 after a period of time, and the target person 20 still does not disappear from the detection space 220 after a period of time, the transfer condition T9 of the detection space 210 and the transfer condition T10 of the detection space 220 are respectively satisfied, so that the state of the detection space 210 is switched to state S3, and the state of the detection space 220 is switched to state S4.

[0089] Fig.11A and Fig. 11B A fifth example of state transition of the detection space is shown in accordance with an embodiment of the present invention, wherein Fig.11A A state machine 500 corresponding to the detection space 210 is shown, and Fig. 11BA state machine 500 corresponding to the detection space 220 is shown. Assume that the target person 20 is located in the detection space 210. The state S4 of the detection space 210 indicates that the target person 20 is located in the detection space 210, and the state S3 of the detection space 220 indicates that the target person 20 is not in the detection space 220. If the target person 20 disappears from the detection space 210 and appears in the detection space 220, the transition condition T7 of the detection space 210 and the transition condition T12 of the detection space 220 are satisfied, respectively, so that the state of the detection space 210 switches to the state S5, and the state of the detection space 220 switches to the state S6. Next, if the target person 20 appears in the detection space 210 and disappears from the detection space 220, the transition condition T8 of the detection space 210 and the transition condition T11 of the detection space 220 are satisfied, respectively, so that the state of the detection space 210 switches to the state S4, and the state of the detection space 220 switches to the state S3.

[0090] Fig.12 According to an embodiment of the present invention, a schematic diagram of a graphical user interface 1100 displayed by the human-machine interface 120 is shown. The graphical user interface 1100 can be used to display icons indicating the physiological state of the target person, and can be used to display icons indicating the occupancy of an area in a detection space (e.g., detection space 210 or 220). For example, the graphical user interface 1100 may include an icon 121 for indicating the number and name of the detection space, an icon 122 for indicating the occupancy of a bed in the detection space, an icon 123 for indicating the physiological state of the target person 20, such as heartbeat or breathing, an icon 124 for indicating the occupancy of areas such as a bedroom, a living room, a kitchen, or a toilet, an icon 125 for indicating whether the target person 20 exists in the detection space, and an icon 126 for indicating the residence time of the target person 20 in the detection space.

[0091] Fig.13 According to an embodiment of the present invention, a schematic diagram of an icon 124 of a graphical user interface is depicted. For a region in a detection space (e.g., a bedroom, a living room, a kitchen, or a toilet), the icon 124 may be used to indicate the occupancy status or related events of the region, such as the region being occupied, the region being unoccupied, an emergency occurring in the region, a fall occurring in the region, the radar used to monitor the region being disconnected, or the target person staying in the region for too long.

[0092] Fig.14 According to an embodiment of the present invention, a schematic diagram of an icon 125 of a graphical user interface is depicted. For a detection space, the icon 125 can be used to indicate the occupancy status or related events of the detection space, such as whether the detection space is occupied, the detection space is not occupied, the target person stays in the detection space for too long, the detection space is idle (e.g., unoccupied) for too long, or the radar used to monitor the detection space has been disconnected.

[0093] Fig.15 According to an embodiment of the present invention, a flow chart of a method for detecting a target object based on multiple radars is shown, wherein the method can be performed as follows: Figure 1 The detection device 100 shown is implemented. In step S151, a first detection result corresponding to a first detection space and a second detection result corresponding to a second detection space are received from a plurality of radars. In step S152, in response to the first detection result indicating that a target object located in the first detection space moves to an overlapping area between the first detection space and the second detection space, it is determined that the first detection space enters a first state. In step S153, in response to the determination that the first detection space enters the first state, first information is output through a human-machine interface, wherein the first information indicates that the target object is located in the first detection space. In step S154, in response to the second detection result indicating that a target object not in the second detection space appears in the overlapping area, it is determined that the second detection space enters a second state. In step S155, in response to the determination that the second detection space enters the second state, second information is output through a human-machine interface, wherein the second information indicates that the target object is not in the second detection space.

[0094] In summary, the present invention has the following effects: the present invention can integrate the detection results from multiple detection devices to provide users with real-time information on the location and status of the target person; the present invention has high scalability and flexibility, and can flexibly configure the number and location of radars according to different application environments to achieve monitoring of spaces of different sizes; the human-machine interface of the present invention can display the status of multiple devices for users to quickly understand the field conditions; the present invention can notify the user in real time when the status of the target person is abnormal, so that the emergency can be handled as soon as possible; the present invention can automatically detect the status of each space to reduce the cost of human resources; the information integrated by the present invention can be applied to such as crowd statistics, behavior analysis or activity record analysis, etc., to improve the application value of the detection results.

Claims

1. A target object detection device based on multiple radars, comprising: Human-machine interface; a transceiver that receives a first detection result corresponding to a first detection space and a second detection result corresponding to a second detection space from a plurality of radars; as well as A processor is coupled to the human-machine interface and the transceiver and is configured to execute: In response to the first detection result indicating that the target object located in the first detection space moves toward an overlapping area between the first detection space and the second detection space, determining that the first detection space enters a first state; In response to determining that the first detection space enters the first state, outputting first information through the human-machine interface, wherein the first information indicates that the target object is located in the first detection space; In response to the second detection result indicating that the target object not in the second detection space appears in the overlapping area, determining that the second detection space enters a second state; as well as In response to determining that the second detection space enters the second state, second information is output through the human-machine interface, wherein the second information indicates that the target object is not in the second detection space.

2. The detection device of claim 1, wherein the processor is further configured to execute: In response to the first detection result indicating that the target object disappears from the first detection space, determining that the first detection space enters a third state from the first state; and In response to determining that the first detection space enters the third state, third information is output through the human-machine interface, wherein the third information indicates that the target object is not in the first detection space.

3. The detection device of claim 2, wherein the processor is further configured to execute: In response to the second detection result indicating that the target object moves from the overlapping area to the second detection space, determining that the second detection space enters a fourth state from the second state; and In response to determining that the second detection space enters the fourth state, fourth information is output through the human-machine interface, wherein the fourth information indicates that the target object is located in the second detection space.

4. The detection device of claim 1, wherein the processor is further configured to execute: In response to the first detection result indicating that the target object moves from the overlapping area to the first detection space, determining that the first detection space enters a fourth state from the first state; and In response to determining that the first detection space enters the fourth state, the first information is output through the human-machine interface.

5. The detection device of claim 4, wherein the processor is further configured to execute: In response to the second detection result indicating that the target object disappears from the second detection space, determining that the second detection space enters a third state from the second state; and In response to determining that the second detection space enters the third state, the second information is output through the human-machine interface.

6. The detection device of claim 1, wherein the processor is further configured to execute: In response to the first detection result indicating that the target object located in the first detection space disappears from the first detection space, determining that the first detection space enters a fifth state; and In response to determining that the first detection space enters the fifth state, the first information is output through the human-machine interface.

7. The detection device of claim 6, wherein the processor is further configured to execute: In response to the first detection result indicating that the target object appears in the first detection space, determining that the first detection space enters a fourth state from the fifth state; and In response to determining that the first detection space enters the fourth state, the first information is output through the human-machine interface.

8. The detection device of claim 6, wherein the processor is further configured to execute: In response to the first detection result indicating that the target object does not appear in the first detection space, determining that the first detection space enters the third state from the fifth state; and In response to determining that the first detection space enters the third state, third information is output through the human-machine interface, wherein the third information indicates that the target object is not in the first detection space.

9. The detection device of claim 1, wherein the processor is further configured to execute: In response to the first detection result indicating that the target object in the first detection space disappears from a preset area in the first detection space, determining that the first detection space enters a third state; and In response to determining that the first detection space enters the third state, third information is output through the human-machine interface, wherein the third information indicates that the target object is not in the first detection space.

10. The detection device of claim 1, wherein the processor is further configured to execute: In response to the second detection result indicating that the target object that is not in the second detection space appears in the second detection space, determining that the second detection space enters a sixth state; and In response to determining that the second detection space enters the sixth state, the second information is output through the human-machine interface.

11. The detection device of claim 10, wherein the processor is further configured to execute: When the second detection space is in the sixth state, in response to the second detection result indicating that the target object disappears from the second detection space, determining that the second detection space enters a third state; and In response to determining that the second detection space enters the third state, the second information is output through the human-machine interface.

12. The detection device of claim 10, wherein the processor is further configured to execute: In response to the second detection result indicating that the target object has not disappeared from the second detection space, determining that the second detection space enters a fourth state from the sixth state; and In response to determining that the second detection space is located in the fourth state, fourth information is output through the human-machine interface, wherein the fourth information indicates that the target object is located in the second detection space.

13. The detection device of claim 1, wherein the processor is further configured to execute: In response to the target object that is not in the second detection space appearing in a preset area in the second detection space, determining that the second detection space enters a fourth state; and In response to determining that the second detection space enters the fourth state, fourth information is output through the human-machine interface, wherein the fourth information indicates that the target object is located in the second detection space.

14. The detection device of claim 1, wherein the processor is further configured to execute: A graphical user interface is outputted through the human-machine interface, wherein the graphical user interface displays a first icon for indicating a physiological state of the target object, wherein the physiological state includes at least one of a heartbeat and a respiratory rate.

15. A detection device as described in claim 14, wherein the graphical user interface further displays a second icon for indicating the occupancy status of an area in the first detection space, wherein the second icon is associated with at least one of the following: a bed, a bedroom, a living room, a kitchen, and a toilet, and the graphical user interface further displays whether the radar is disconnected.

16. The detection device of claim 1, wherein the processor is further configured to execute: In response to the first detection result indicating that the target object is located in the first detection space, calculating a residence time of the target object in the first detection space; In response to the dwell time being greater than a first threshold, outputting a first warning message through the human-machine interface; as well as In response to the dwell time being less than a second threshold, a second warning message is output through the human-machine interface.

17. The detection device of claim 1, wherein the processor is further configured to execute: determining whether the target object has fallen in the first detection space according to the first detection result; and In response to determining that the target object has fallen, a warning message is output through the human-machine interface.

18. The detection device of claim 1, wherein the processor is further configured to execute: In response to the first detection result indicating that the target object is about to leave the first detection space, calculating a departure time of the target object; and In response to the departure time being greater than a third threshold, outputting a warning message through the human-machine interface.

19. The detection device of claim 18, wherein the processor is further configured to execute: Obtaining a plurality of point clouds corresponding to a plurality of time points respectively from the first detection result; performing object detection on the plurality of point clouds to generate a plurality of bounding boxes respectively corresponding to the plurality of point clouds; determining a change in the inclination angle of the target object during a preset time period according to the plurality of bounding boxes; as well as In response to the tilt angle change being greater than a fourth threshold, it is determined that the target object has fallen.

20. The detection device of claim 19, wherein the processor is further configured to execute: determining a speed of the target object during the preset period of time or a height of the target object according to the plurality of bounding boxes; and In response to the height being smaller than a fifth threshold or the speed being larger than a sixth threshold, it is determined that the target object has fallen.

21. A method for detecting a target object based on multiple radars, comprising: receiving, from a plurality of radars, a first detection result corresponding to a first detection space and a second detection result corresponding to a second detection space; In response to the first detection result indicating that the target object located in the first detection space moves toward an overlapping area between the first detection space and the second detection space, determining that the first detection space enters a first state; In response to determining that the first detection space enters the first state, outputting first information through a human-machine interface, wherein the first information indicates that the target object is located in the first detection space; In response to the second detection result indicating that the target object not in the second detection space appears in the overlapping area, determining that the second detection space enters a second state; as well as In response to determining that the second detection space enters the second state, second information is output through the human-machine interface, wherein the second information indicates that the target object is not in the second detection space.

Images