Kick operation sensing device and method

Abstract

To provide a kick operation sensing device which has a wide sensing distance and is resistant to influence of a peripheral environment by sensing user's kick operation on the basis of a radar signal.SOLUTION: A device for sensing kick operation by using a radar signal related to an embodiment of the present invention includes a transmission and reception part for transmitting the radar signal toward an object and receiving the radar signal reflected from the object, a characteristic derivation part for deriving characteristic information for the object on the basis of the radar signal, an operation collection part for determining the existence / nonexistence of an approach to a kick operation determination state on the basis of the characteristic information, and a kick operation determination part for determining whether operation of the object is effective kick operation on the basis of the collected characteristic information in the case of approaching the kick operation determination state.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an apparatus and method for detecting a kicking motion of a target object using a radar signal. [Background technology]

[0002] The technology for opening and closing the back door (also known as tailgate) of a vehicle provides important convenience in daily life. Opening and closing a vehicle's tailgate is particularly useful when the user is carrying luggage or has both hands free. In response to this need, various sensor-based automatic opening and closing systems have been developed. One of the most widely used technologies today is a system that utilizes ultrasonic sensors.

[0003] Ultrasonic sensor-based systems detect specific user movements to enable touchless opening and closing of vehicle tailgates. While such systems offer great convenience when both hands are limited, they have several limitations and problems.

[0004] The main problem with ultrasonic sensors is their limited sensing distance. Because the sensing range is relatively short, they can only be detected if the user is close enough to the sensor. This requires the user to make large or precise movements intentionally, which can be particularly challenging when carrying luggage or in awkward situations.

[0005] Additionally, ultrasonic sensors are highly susceptible to the surrounding environment. Environmental factors such as animal movement or heavy rain can cause false detections, reducing the reliability of the system. False detections can confuse users or result in unpredictable tailgate opening and closing, which can lead to safety issues.

[0006] To overcome these problems, a kick motion detection device using radar technology has been proposed, which has a wider detection range and is more resistant to environmental influences. However, a kick sensor using radar requires advanced algorithms and signal processing technology, and a method for processing erroneous signals caused by interference from the surrounding environment is also required. Summary of the Invention [Problem to be solved by the invention]

[0007] To solve the above-mentioned problems, the present invention provides a kicking motion detection device that detects a user's kicking motion based on a radar signal, thereby having a wide detection distance and being resistant to the influence of the surrounding environment.

[0008] The present invention provides a kick motion detection device that can improve the accuracy of kick motion detection by removing unnecessary noise in the process of detecting a kick motion using a radar signal.

[0009] The present invention provides a kick motion detection device that can distinguish user actions based on various information and recognize kick motions within an effective range, thereby preventing the tailgate from being opened or closed due to erroneous operation.

[0010] However, the technical objectives to be achieved by this embodiment are not limited to the above-mentioned technical objectives, and other technical objectives may also exist. [Means for solving the problem]

[0011] As a means for achieving the above technical object, one embodiment of the present invention provides an apparatus for detecting a kicking motion using a radar signal, the apparatus including: a transceiver unit that transmits a radar signal toward a target object and receives the radar signal reflected from the target object; a feature deriving unit that derives feature information about the target object based on the radar signal; an action collecting unit that determines whether or not to enter a kicking motion judgment state based on the feature information; and a kicking motion judgment unit that determines whether or not the action of the target object is a valid kicking motion based on the feature information when the kicking motion judgment state has been entered.

[0012] The above-described solutions are merely exemplary and should not be construed as limiting the present invention. In addition to the exemplary embodiments described above, there may be additional embodiments as described in the drawings and detailed description of the invention. [Effects of the Invention]

[0013] According to any one of the means for solving the problems of the present invention described above, the present invention can provide a kick motion detection device that detects a user's kick motion based on a radar signal, thereby having a wide detection distance and being resistant to the influence of the surrounding environment.

[0014] The present invention can improve the accuracy of kicking motion detection by removing unnecessary noise in the process of detecting a kicking motion using a radar signal.

[0015] The present invention classifies user actions based on various information and recognizes kick actions within an effective range, thereby preventing the tailgate from opening or closing due to erroneous actions. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a block diagram of a kick motion detection system according to an embodiment of the present invention; [Figure 2] 1 is a block diagram of a kick motion detection device according to an embodiment of the present invention; [Figure 3]10 is an exemplary diagram illustrating a process of generating distance-Doppler map information according to an embodiment of the present invention. [Figure 4] 10 is an exemplary diagram illustrating a process of deriving feature information from distance-Doppler map information according to an embodiment of the present invention. FIG. [Figure 5] 10 is an exemplary diagram illustrating a process of storing feature information in a buffer according to an embodiment of the present invention; [Figure 6] 10 is an exemplary diagram illustrating a process of deriving azimuth angle information according to an embodiment of the present invention; [Figure 7] 10 is a flowchart illustrating a process of storing feature information in a buffer according to an embodiment of the present invention. [Figure 8] 10 is an exemplary diagram illustrating a change amount of distance information for each frame according to an embodiment of the present invention; [Figure 9] 10 is an exemplary code fragment for explaining a process of classifying actions based on a change in distance information according to an embodiment of the present invention; [Figure 10] 10 is an exemplary diagram illustrating a change amount of speed information for each frame according to an embodiment of the present invention; [Figure 11] 10 is an exemplary view illustrating an effective range of kick motion detection according to an embodiment of the present invention; FIG. [Figure 12] 10 is an exemplary diagram illustrating a process of checking buffer information according to an embodiment of the present invention; [Figure 13] 10 is an exemplary code fragment for explaining a process for determining a valid kicking action according to one embodiment of the present invention. [Figure 14] 10 is an exemplary diagram illustrating a critical point of an effective range according to an embodiment of the present invention; FIG. [Figure 15] 1 is a flowchart illustrating a method for detecting a kick motion according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0017] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] The present invention will now be described in detail with reference to the accompanying drawings so that those skilled in the art can easily understand and practice the present invention. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. In the drawings, parts that are not relevant to the description are omitted in order to clearly explain the present invention, and like reference numerals are used to refer to like parts throughout the specification.

[0018] Throughout the specification, when a part is said to be "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another element interposed therebetween. Furthermore, when a part is said to "comprise" a certain component, this does not mean excluding other components, but may further include other components, unless otherwise specified, and should be understood as not precluding the presence or possibility of addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0019] In the present specification, the term "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both hardware and software. Also, one unit may be realized using two or more pieces of hardware, and two or more units may be realized by one piece of hardware.

[0020] In the present specification, some of the operations and functions described as being performed by a terminal or device may instead be performed by a server connected to the terminal or device, and similarly, some of the operations and functions described as being performed by a server may instead be performed by a terminal or device connected to the server.

[0021] The functionality provided by the components described herein may be embodied in processing circuitry, including general-purpose processors, special-purpose processors, integrated circuits, ASICs (Application Specific Integrated Circuits), CPUs (Central Processing Units), circuits, and / or combinations thereof, programmed to provide the functionality. A processor includes transistors and other circuitry and is considered a circuit or processing circuit. A processor may also be a programmed processor that executes a program stored in a memory.

[0022] In the present specification, a circuit, a part, a unit, or a means is hardware that is programmed to realize or executes the described functions, which may be all hardware disclosed in the present specification or any hardware known to be programmed to realize or execute the functions.

[0023] When the hardware is a processor considered to be a circuit type, the circuit, the part, means or unit is a combination of hardware and software used to configure the hardware and / or processor.

[0024] Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

[0025] FIG. 1 is a diagram illustrating the configuration of a kick motion detection system according to an embodiment of the present invention.

[0026] As shown in FIG. 1, the kick motion detection system 1 may include a kick motion detection device 100 and a radar 110 .

[0027] The components of the kick motion detection system 1 in Fig. 1 are generally connected via a network. For example, as shown in Fig. 1, the kick motion detection device 100 and the radar 110 may be connected simultaneously or at intervals.

[0028] A network refers to a connection structure that enables information exchange between nodes such as terminals and servers, and includes a local area network (LAN), a wide area network (WAN), the Internet (WWW), a wired and wireless data communication network, a telephone network, a wired and wireless television communication network, etc. Examples of wireless data communication networks include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Bluetooth communication, infrared communication, ultrasonic communication, visible light communication (VLC), LiFi, etc.

[0029] The kick motion detection device 100 can analyze a radar signal reflected from a target object 111 using a radar 110. The kick motion detection device 100 can detect whether or not a kick motion has been made by the target object 111 based on a radar signal that is changed when the target object 111 makes a kick motion from the rear of a vehicle (e.g., a car) to the bottom of a tailgate. For example, the kick motion detection device 100 is disposed at the bottom rear of the car, and can transmit a radar signal toward the target object 111 through the radar 110 and receive a radar signal reflected from the target object 111.

[0030] The kick motion detection device 100 can determine the kick motion of the target object 111 using the radar 110 .

[0031] Therefore, by using the kick motion detecting device 100, even if the target object 111 does not carry or wear a separate device for detecting the kick motion, the kick motion can be accurately determined.

[0032] The kick motion detection device 100 may have a radar 110 attached thereto or may have a radar built therein to detect a kick motion of a target object 111. In addition, at least some elements of the kick motion detection device 100 may be disposed in a space separated from the radar 110 and may communicate with the radar 110 wirelessly or via a wired connection via a network to detect a kick motion of a target object 111. In the following description, the transmitter / receiver of the kick motion detection device 100 may be described as a configuration corresponding to the radar 110 of FIG. 1.

[0033] Each component of the kick motion detection device 100 will be described below.

[0034] FIG. 2 is a diagram showing the configuration of a kick motion detection device 100 according to an embodiment of the present invention.

[0035] 2, the kick motion sensing device 100 may include a transceiver unit 210, a filtering unit 220, a feature deriving unit 230, a motion collecting unit 240, and a kick motion determining unit 250. However, the above components 210 to 250 are merely illustrative of components that may be controlled by the kick motion sensing device 100.

[0036] The transceiver 210 may transmit a radar signal toward a target object and receive a radar signal reflected from the target object.

[0037] The filtering unit 220 can generate a peak signal by filtering the radar signal.

[0038] The feature deriving unit 230 may derive feature information about the target object based on the radar signal.

[0039] The action collection unit 240 can determine whether or not to enter the kick action determination state based on the feature information.

[0040] When entering the kick motion determination state, the kick motion determination unit 250 may determine whether the motion of the target object is a valid kick motion based on the feature information.

[0041] FIG. 3 is an exemplary diagram illustrating a process of generating range-Doppler map information according to an embodiment of the present invention.

[0042] The filtering unit 220 generates range-Doppler map information based on the radar signal, and filters the range-Doppler map information to derive a peak signal.

[0043] Furthermore, the filtering unit 220 can remove noise from the range-Doppler map and derive signals having an intensity equal to or greater than a predetermined threshold value as the peak signals.

[0044] 3 shows a process in which the filtering unit 220 generates distance-Doppler map information from a radar signal to derive a peak signal based on the radar signal. The filtering unit 220 can generate distance-Doppler map information through a pre-processing process that processes the radar signal, which is raw data acquired from the radar.

[0045] The filtering unit 220 receives the radar signal reflected from the target object and samples the received radar signal for each chirp using an ADC (Analog-to-Digital Converter) to generate a digital signal 310. In this process, the sampled data for each chirp forms the structure of the original radar signal.

[0046] The filtering unit 220 then applies a two-dimensional fast Fourier transform (2D-FFT) to the digital signal. Through this Fourier transform, the digital signal is converted from the time domain to the range-Doppler domain. The first Fourier transform converts the time domain signal into the range domain 320 to extract distance information to each target object. The second Fourier transform analyzes changes in Doppler frequency for each distance to obtain velocity information 330 of the target object.

[0047] In a range-Doppler map, signal strength with distance can be displayed on the horizontal axis and Doppler frequency on the vertical axis.

[0048] The converted distance-Doppler map information shows the distance and speed information of the object that reflected the radar signal as two-dimensional data, and can provide important information for detecting specific events such as kicking.Furthermore, the distance-Doppler map information is analyzed by a kicking detection algorithm to determine whether a kicking motion has been detected.

[0049] FIG. 4 is an exemplary diagram illustrating a process of deriving feature information from distance-Doppler map information according to an embodiment of the present invention.

[0050] 4 illustrates a process in which the filtering unit 220 derives a peak signal 402, which is a filtered radar signal, from a two-dimensional range-Doppler map 401. The filtering unit 220 may filter some data from the range-Doppler map 401. More specifically, the filtering unit 220 may derive the peak signal 402 from the range-Doppler map 401 by applying a Constant False Alarm Rate (CFAR) algorithm. The filtering unit 220 may select a surrounding area that is not the target object and calculate the average signal strength of the selected area. Thereafter, the filtering unit 220 may dynamically determine a threshold value for distinguishing the signal for the target object from noise based on the calculated average noise level. Here, the threshold value is adjusted in proportion to the surrounding noise level, thereby maintaining consistent signal detection performance even in various environments.

[0051] Meanwhile, in another embodiment of the present invention, the filtering unit 220 can derive a peak signal from the distance-Doppler map 401 using a method that uses a threshold based on a histogram in addition to the above-mentioned CFAR algorithm.

[0052] The filtering unit 220 scans the entire range-Doppler map 401 and can regard a signal that exceeds a set critical value as a filtered radar signal, i.e., a peak signal 402 .

[0053] The feature deriving unit 230 may derive feature information 403 from the peak signal 402. The feature information 403 derived from the peak signal 402 may include at least one of azimuth angle information on the azimuth angle at which the target object 111 is located relative to the kick motion detecting device 100, distance information on the range between the kick motion detecting device 100 and the target object 111, speed information on the motion speed of the target object 111, and strength information on the power at which the target object moves.

[0054] FIG. 5 is an exemplary diagram illustrating a process of storing feature information in a buffer according to an embodiment of the present invention.

[0055] The feature deriving unit 230 may derive at least one of distance information R relating to the distance between the kick motion detecting device 100 and the target object and speed information V relating to the motion speed of the target object from the peak signal 501. Furthermore, the feature deriving unit 230 may derive azimuth angle information θ relating to the azimuth angle at which the target object is located with respect to the kick motion detecting device 100 based on the phase difference between the radar signals. Such feature information may be generated corresponding to the peak signal generated for each frame.

[0056] That is, the motion detecting device 100 divides the received radar signal into frames and filters the divided frame-by-frame radar signal to generate a peak signal for each frame, and further derives characteristic information from the peak signals generated for each frame.

[0057] The feature information generated in units of frames may be classified into distance information R, speed information V, and azimuth angle information θ, and each piece of feature information may be stored in a corresponding buffer. The distance information R may be stored in a distance buffer 502, the speed information V may be stored in a speed buffer 503, and the azimuth angle information θ may be stored in an azimuth angle buffer 504. In this case, each storage area partitioning the buffer may store feature information corresponding to one frame unit.

[0058] FIG. 6 is an exemplary diagram illustrating a process of deriving azimuth angle information according to an embodiment of the present invention.

[0059] The feature deriving unit 230 may derive azimuth angle information θ for the azimuth angle at which the target object is located with respect to the kick motion detecting device 100 based on the phase difference between the radar signals.

[0060] 6 is a diagram illustrating an example in which the transceiver unit 210 of the kick motion detection device 100 has a 1Tx-4Rx structure. That is, the transceiver unit 210 may include one transmitter (not shown) and four receivers Rx1 to Rx4. Furthermore, the internal distance between each of the receivers Rx1 to Rx4 may be defined as d. However, this is merely an example, and the transceiver unit 210 may include other numbers of transmitters or receivers, and the distance between the receivers may also vary depending on the usage environment and design method of the kick motion detection device 100.

[0061] 6, a phase difference occurs between the received radar signals depending on the angle of the radar signals incident on the receivers Rx1 to Rx4. Using this, the feature deriving unit 230 can derive azimuth angle information of the target object 111 based on the difference in direction of arrival between the receivers Rx1 to Rx4. For this purpose, a Bartlett or MUSIC algorithm can be used.

number

[0062] where d ij sinθ means the phase difference due to the antenna distance between the i-th receiver Rx and the j-th receiver Rx, d means the internal distance between the receivers Rx, and θ M denotes the Mth detection angle, λ denotes the wavelength of the radar signal, and Y denotes the FFT signal of each channel.

[0063] The feature derivation unit 230 can perform matrix multiplication of the complex conjugate of the steering vector and the Fast Fourier Transform (FFT) signal (Y) between each channel through the above equation (Equation 1).

[0064] Here, the steering vector means the phase difference of the radio wave signal according to the angle of the radar signal arriving at each receiver Rx. Furthermore, for the same peak signal in the range-Doppler map, the FFT data at the transmitter-receiver Tx-Rx of each channel can be expressed as Y.

[0065] The feature deriving unit 230 can obtain a power spectrum for the incident angle of each radar signal from the result of matrix multiplication, and derive each angular power spectrum. Furthermore, the feature deriving unit 230 can derive the angle of the point with the greatest power on each power spectrum as azimuth angle information.

[0066] Meanwhile, the feature deriving unit 230 can derive distance information and velocity information from peak signals derived from the distance-Doppler map.

number

[0067] In the above formula (Equation 2), Range Target means the distance between the kick motion detection device 100 and the target object 111, and R i means the range index value derived by the feature derivation unit 230 from the peak signal of the range-Doppler map information at time point i (or the i-th frame). Furthermore, ΔR means the range resolution. Furthermore, Velocity Target means the velocity of the target object 111, and D i denotes a Doppler index value derived from a peak signal of the range-Doppler map information at time point i (or the i-th frame) by the feature derivation unit 230. Furthermore, ΔV denotes velocity resolution.

[0068] The range resolution (ΔR) and velocity resolution (ΔV) can be derived using the following equation (Equation 3).

number

[0069] where C is the speed of light in m / s, λ is the wavelength in m, and N c means the number of chirps in the radar signal, and T c denotes the time interval between chirps of the radar signal.

[0070] FIG. 7 is a flowchart illustrating a process of storing feature information in a buffer according to an embodiment of the present invention.

[0071] The action collection unit 240 classifies the action of the target object 111 into a candidate action based on the feature information, and when the action is classified as a candidate action, stores the feature information in a buffer. Furthermore, the feature information may be derived for each of a plurality of frames and stored in the buffer.

[0072] The action collection unit 240 may classify the target object's action as the candidate action by comparing distance information among feature information of a previous frame with distance information among feature information of a current frame. Furthermore, the action collection unit 240 may determine that the kick action determination state has been entered when the number of feature information stored in the buffer reaches a predetermined threshold value.

[0073] In FIG. 7, step 701 may be a step in which the motion collection unit 240 performs initialization. In step 701, a distance buffer, a velocity buffer, and an azimuth buffer may be initialized. Furthermore, values ​​of TarCandiFlag, InFlag, and OutFlag may be initialized. Here, TarCandiFlag may mean a parameter indicating whether a candidate target object exists within the radar signal reception range of the kick motion detection device 100. That is, TarCandiFlag may be flag information indicating whether the motion of the target object is classified as a candidate motion. Furthermore, InFlag and OutFlag may be parameters indicating whether the kick motion of the target object is a motion toward the kick motion detection device 100 or a motion away from the kick motion detection device 100. The variable names of the parameters described below are arbitrarily assigned to distinguish their meanings and may have different names depending on the designer's intentions and design environment.

[0074] In step 702, the action collection unit 240 checks whether the value of TarCandiFlag is a predetermined value (e.g., 0U). If it is, the action collection unit 240 proceeds to step 703; if not, the action collection unit 240 proceeds to step 706.

[0075] In step 703, the motion collection unit 240 may derive velocity information from the characteristic information of the radar signal. Furthermore, it may determine whether the velocity information value is less than 0 and greater than KR_COL_TARCAND_VEL_MIN. Here, KR_COL_TARCAND_VEL_MIN refers to a minimum velocity standard for determining that the motion of the target object 111 detected by the kick motion detection device 100 is a kick motion. The value of KR_COL_TARCAND_VEL_MIN may be determined based on the kick speed of an average person. The motion collection unit 240 may determine a kick speed at which a kick motion can be performed within a limited time. That is, to determine a motion approaching the kick motion detection device 100, the motion collection unit 240 may classify the motion of the target object as a candidate motion when the velocity information value is measured to be less than 0 and when velocity information satisfying a minimum velocity condition is detected. If the above conditions are met, step 704 is performed; otherwise, step 705 is performed.

[0076] In step 704, when the motion of the target object 111 approaching the kick motion detection device 100 is classified as a candidate motion, the motion collection unit 240 may store feature information corresponding to the motion in a buffer. More specifically, feature information (MSMT) corresponding to the frame at which the motion of the target object 111 is classified as a candidate motion may be stored in the buffer. In this case, the feature information (MSMT) may include distance information, speed information, and azimuth angle information of the frame. Thereafter, the motion collection unit 240 may set the values ​​of TarCandiFlag and InFlag to predetermined values ​​(e.g., 1U). Thereafter, the process proceeds to step 705.

[0077] In step 705, the action collection unit 240 performs an operation (BufferScan) to check whether any buffers are full, and whether the current frame value is equal to or greater than the maximum frame value (MaxFrame). If both of these conditions are met, the process proceeds to step 711; if not, the frame count is incremented and step 702 is repeated for the radar signal of the next frame. Here, step 711 may refer to a kick action determination state, which will be described in more detail below.

[0078] In step 706, the action collection unit 240 may check whether the value of InFlag is a predetermined value (e.g., 1U). If it is, it is interpreted as a motion approaching the kick motion detection device 100, and the process may proceed to step 708. On the other hand, if it is not, it is interpreted as a motion approaching the kick motion detection device 100, and the process may proceed to step 707.

[0079] In step 707, the action collection unit 240 may check whether the value of OutFlag is a predetermined value (e.g., 1U). If it is, it is interpreted as a motion of moving away from the kick motion detection device 100, and the process proceeds to step 709. On the other hand, if it is not, it is interpreted as a motion of moving away from the kick motion detection device 100, and the process may return to the initial setting step 701.

[0080] In step 708, the action collection unit 240 may determine whether the action of the target object 111 is a continuous action of approaching the kick action detection device 100. That is, the action collection unit 240 may determine whether the value of velocity information is less than 0 and the absolute value of the velocity information is greater than KR_COL_TARCAND_VEL_MIN. Furthermore, the action collection unit 240 may determine whether the value of distance information at a previous point in time (or a previous frame) is greater than the value of distance information at a current point in time (or a current frame) based on the data stored in the distance buffer. If the above conditions are met, the process proceeds to step 704; otherwise, the process proceeds to step 709.

[0081] In step 709, if OutFlag is a specified value (e.g., 1U) (step 707) or if the condition that there is no motion approaching the kick motion detection device 100 is met (step 708), the motion collection unit 240 may determine whether there is a motion moving away from the kick motion detection device 100. The motion collection unit 240 may check whether the value of velocity information is greater than 0 and the absolute value of the velocity information is greater than KR_COL_TARCAND_VEL_MIN. Furthermore, the motion collection unit 240 may check whether the value of distance information at a previous point in time (or a previous frame) is less than the value of distance information at the current point in time (or a current frame) based on the data stored in the distance buffer. If the above conditions are met, the process proceeds to step 710. If the above conditions are not met, the process returns to the initial setting step 701.

[0082] In step 710, if the motion of the target object 111 moving away from the kick motion detection device 100 is classified as a candidate motion, the motion collection unit 240 may store feature information corresponding to the motion in a buffer. More specifically, feature information (MSMT) corresponding to the frame at which the motion of the target object 111 is classified as a candidate motion may be stored in the buffer. In this case, the feature information (MSMT) may include distance information, speed information, and azimuth angle information of the frame. Thereafter, the motion collection unit 240 may set the value of InFlag to a predetermined value (e.g., 0U) and the value of OutFlag to a predetermined value (e.g., 1U). Thereafter, step 705 may be performed.

[0083] The kick action determination unit 250 can determine whether the action of the target object is a valid kick action based on a change in the distance to the target object for each frame and a change in the action speed of the target object for each frame.

[0084] The kick action determination unit 250 may classify the action of the target object into a proximity action of approaching the radar and a departure action of moving away from the radar based on a change in distance to the target object for each frame and a change in the motion speed of the target object for each frame, and derive a reference frame for classifying the proximity action and the departure action.

[0085] Furthermore, the kick action determination unit 250 can determine whether the target object is moving within an effective range based on azimuth angle information regarding the angle at which the target object is located and distance information regarding the distance between the radar and the target object, with respect to the kick action device.

[0086] FIG. 8 is an example diagram illustrating distance change information with respect to a change amount of distance information for each frame according to an embodiment of the present invention.

[0087] FIG. 8 illustrates a graph 801 showing the values ​​of distance information stored in the distance buffer for each time point (or frame).

[0088] 8, it can be seen that the distance between the target object 111 and the kick motion sensing device 100 decreases and then increases again starting from a certain point in time (or frame) 802. That is, in terms of the amount of change in the value of the distance information as time passes (or as frames increase) during the entire time period, it can be seen that the sign of the amount of change changes from negative (-) to positive (+) starting from point in time 802. This corresponds to the physical characteristics of the target object 111 kicking once and then pulling away.

[0089] FIG. 9 is an exemplary pseudo code for explaining a process of classifying actions based on the amount of change in distance information according to an embodiment of the present invention.

[0090] More specifically, FIG. 9 shows a similar code for identifying a point where the sign of the change amount of the distance information value due to the passage of time (or the increase of frames) is changed.

[0091] In the similar code in Figure 9, R1-R0 represent the initial distance change amount, BufferLastIndex represents the last index value of the buffer, and inv_grad_count represents a variable for counting the sign change of the distance change amount, i represents the buffer index value, Temp_grad represents the change amount of the previous distance information, and Comp_grad represents the change amount of the distance information to be compared.

[0092] The kick action determination unit 250 may check whether there is a change in the sign of the change in distance information while sweeping the buffer index. This check may be performed by checking whether the product of Temp_grad and Comp_grad is less than 0. After sweeping all the buffer indexes, the kick action determination unit 250 may check whether the value of inv_grad_count is a preset value (e.g., 1). The value of inv_grad_count may correspond to the number of changes in sign.

[0093] FIG. 10 is an exemplary diagram illustrating a change amount of rate information for each frame according to an embodiment of the present invention.

[0094] 10 is a diagram illustrating an example of a graph 1001 showing values ​​of speed information stored in a speed buffer by time point (or frame). It is assumed that FIG. 10 shows values ​​of speed information of a target object in the environment shown in FIG.

[0095] 10, it can be seen that the sign of the velocity due to the movement of the target object 111 changes from negative (-) to positive (+) at a certain point (or frame) 1002. This corresponds to the physical characteristics of the movement of the target object 111 kicking once and then releasing its body.

[0096] To derive the time point 1002, the kick action determination unit 250 derives the index i having the smallest value from the distance buffer, and then derives the speed information values ​​corresponding to the indexes on both sides of the i-th index from the speed buffer. That is, the kick action determination unit 250 checks the signs of the speed information values ​​of the i-1th index and the i+1th index. In this case, if the speed information value of the i-1th speed buffer is less than 0 and the speed information value of the i+1th speed buffer is greater than 0, the kick action determination unit 250 can derive the time point 1002 using the i-th frame as a reference frame.

[0097] Time point 1002 in Figure 10 may correspond to time point 802 in Figure 8. That is, the time point at which the sign of the change amount of distance information changes and the time point at which the sign of the speed information changes may be the same or similar to each other.

[0098] FIG. 11 is an exemplary diagram illustrating an effective range of kick motion detection according to an embodiment of the present invention.

[0099] The kicking motion of the target object can be classified into a proximity motion in which the target object's foot approaches the kicking motion detection device 1101 and a departure motion in which the target object's foot moves away from the kicking motion detection device 1101.

[0100] 11 is a diagram illustrating the directionality of a motion resulting from an approaching motion 1102 and the directionality of a motion resulting from a leaving motion 1103. Such kicking motions may be displayed on a two-dimensional map having vertical (X) and horizontal (Y) axes. The kicking motion determination unit 250 may check whether the difference in horizontal (Y) position between the approaching motion 1102 approaching the kicking motion detection device 1101 and the leaving motion 1103 leaving the kicking motion detection device 1101 exceeds a critical value. The horizontal critical value may correspond to the physical characteristics of a kicking motion in which a target object kicks in a straight line and then returns to its original point when the approaching motion 1102 and the leaving motion 1103 are performed.

[0101] The kick motion determination unit 250 can derive a reference frame to pair the approach motion 1102 and the departure motion 1103 to determine the distance difference in the lateral direction (Y).

[0102] FIG. 12 is an exemplary diagram illustrating a process of checking buffer information according to an embodiment of the present invention.

[0103] 12 illustrates that feature information is stored in a velocity buffer 1201, a distance buffer 1202, and an azimuth buffer 1203, as described above with reference to Fig. 8 and Fig. 10. The kick motion determination unit 250 can derive a reference frame 1204 based on the time point at which the sign of the change in distance information changes and the time point at which the sign of the velocity information changes.

[0104] The kick action determination unit 250 can derive a coordinate value in the horizontal direction (Y) of the effective range based on the value of the distance information for each index of the distance buffer.

number

[0105] In the above formula (4), Y imeans the horizontal coordinate value at time point i (or the i-th frame), and R i means the value of the distance information at time point i (or the i-th frame). i means the value of the azimuth angle information at time point i (or the i-th frame).

[0106] 12, the fourth index of the buffer is the point in time when the sign of the first velocity information value changes, which corresponds to the reference frame 1204. Based on the reference frame 1204, the third and fourth indexes, the second and fifth indexes, and the first and sixth indexes may be paired with each other. The kick motion determination unit 250 may calculate the lateral distance difference (ΔY) between the corresponding pairs of indexes.

number

[0107] In the above equation (Equation 5), ΔY means the lateral distance difference between the corresponding index pairs, and Y in-kick is the horizontal coordinate of the proximity movement in the corresponding index pair, and Y out-kick KR_DET_DIFF_POSY_MARGIN denotes a horizontal coordinate value of the separation operation of the corresponding index pair. Furthermore, KR_DET_DIFF_POSY_MARGIN denotes a critical value of the horizontal effective range. The critical value of the horizontal effective range may be determined in various ways based on the designer's intention, design environment, and performance of the transceiver unit 210.

[0108] FIG. 13 is an exemplary code fragment for illustrating a process for determining a valid kicking action according to one embodiment of the present invention.

[0109] In FIG. 13, KR_DET_DIFF_POSY_MARGIN means the critical value of the effective range in the lateral direction.

[0110] FIG. 14 is an exemplary diagram illustrating a critical point of an effective range according to an embodiment of the present invention.

[0111] 14 illustrates a graph 1401 showing pairs of approach and departure movements of a target object as a function of horizontal distance difference. It can be seen that for pairs 1402 of approach and departure movements generated for a movement of kicking in a straight line and then returning to the starting point, the horizontal distance difference for most of them does not exceed a critical point 1403.

[0112] FIG. 15 is a flowchart illustrating a method for detecting a kicking motion according to an embodiment of the present invention.

[0113] The kick motion detection method using radar shown in Figure 15 includes steps that are processed in time series according to the embodiments shown in Figures 1 to 14. Therefore, even if the content is omitted below, it also applies to the kick motion detection method using the kick motion detection device according to the embodiments shown in Figures 1 to 14.

[0114] As shown in FIG. 15, the kick motion detection method may include step S100 of transmitting a radar signal toward a target object, step S200 of receiving the radar signal reflected from the target object, step S300 of deriving feature information about the target object based on the radar signal, step S400 of determining whether to enter a kick motion determination state based on the feature information, and step S500 of determining whether the motion of the target object is a valid kick motion based on the collected feature information if the kick motion determination state has been entered.

[0115] Furthermore, the method may further include a step of generating a peak signal by filtering the radar signal (not shown), and the step S300 of deriving feature information may be a step of deriving feature information for the target object based on the peak signal.

[0116] Furthermore, the step of generating the peak signal may be a step of generating range-Doppler map information based on the radar signal, and filtering the range-Doppler map information to derive the peak signal.

[0117] The kick motion detection method described above may be implemented in the form of a computer program stored in a computer-readable recording medium that is executed by a computer or a recording medium containing computer-executable instructions.The kick motion detection method described above may be implemented in the form of a computer program stored in a computer-readable recording medium that is executed by a computer.

[0118] The computer-readable recording medium may be any solvent-compatible medium accessible by a computer, including both volatile and nonvolatile media, and both separable and non-separable media. The computer-readable recording medium may also include computer storage media. The computer storage media includes both volatile and nonvolatile, separable and non-separable media embodied in any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data.

[0119] The kick motion detection method described above may be further divided into additional steps or combined into fewer steps in accordance with the embodiments described above with reference to Figures 1 to 14. Also, some steps may be omitted as necessary, and the sequence between steps may be switched.

[0120] The above description of the present invention is for illustrative purposes only, and those skilled in the art will appreciate that the present invention may be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. Therefore, it should be understood that the above-described embodiments are illustrative in all respects and are not limiting. For example, each component described as a single component may be implemented in a distributed form, and similarly, components described as distributed may be implemented in a combined form.

[0121] The scope of the present invention is indicated by the claims set forth below rather than by the above detailed description, and all modifications and variations derived from the meaning and scope of the claims, as well as from the concept of equivalents thereof, should be interpreted as being included within the scope of the present invention. [Explanation of symbols]

[0122] 100:Kick motion detector 210: Transmitter / receiver 220: Filtering section 230: Feature derivation unit 240: Motion collection unit 250: Kick motion judgment unit

Claims

1. In a device that detects kicking motions using radar signals, a transceiver that transmits a radar signal toward a target object and receives the radar signal reflected from the target object; a feature deriving unit that derives feature information about the target object based on the radar signal; a motion collection unit that determines whether or not a kick motion determination state has been entered based on the feature information; a kick motion determination unit that determines whether the motion of the target object is a valid kick motion based on the feature information when the state is in the kick motion determination state; A kick motion detection device including:

2. a filtering unit that generates a peak signal by filtering the radar signal; The kick motion sensing device of claim 1 , wherein the feature deriving unit derives feature information about the target object based on the peak signal.

3. The filtering unit The kick motion sensing device according to claim 2, wherein range-Doppler map information is generated based on the radar signal, and the peak signal is derived by filtering the range-Doppler map information.

4. The filtering unit 4. The kick motion detecting device according to claim 3, wherein noise is removed from the distance-Doppler map, and a signal having an intensity equal to or greater than a predetermined threshold value is extracted as the peak signal.

5. 4. The kick motion detecting device of claim 3, wherein the feature deriving unit derives at least one of distance information regarding a distance between the kick motion detecting device and the target object and speed information regarding a motion speed of the target object from the peak signal.

6. The feature derivation unit The kick motion detecting device of claim 1 , wherein azimuth angle information on an azimuth angle at which the target object is located is derived based on the kick motion detecting device, based on a phase difference between the radar signals.

7. The characteristic information is 2. The kick motion detection device of claim 1, comprising at least one of azimuth information on an azimuth angle at which the target object is located relative to the kick motion detection device, distance information on a distance between the kick motion detection device and the target object, and speed information on a motion speed of the target object.

8. The action collection unit categorizing the target object's motion into candidate motions based on the feature information; The kick motion sensing device according to claim 7 , wherein if the kick motion is classified as the candidate motion, the feature information is stored in a buffer.

9. The kick motion detecting device of claim 8 , wherein the feature information is derived for each of a plurality of frames and stored in the buffer.

10. The action collection unit The kick motion detecting device of claim 9 , wherein the motion of the target object is classified into the candidate motions by comparing distance information among feature information of a previous frame with distance information among feature information of a current frame.

11. The action collection unit The kick motion detecting device of claim 8, wherein the device determines that the kick motion detecting state is entered when the number of feature information stored in the buffer reaches a predetermined threshold value.

12. The kick motion determination unit 2. The kick motion detection device of claim 1, wherein the device determines whether a motion of the target object is a valid kick motion based on distance change information regarding a change in distance to the target object for each frame and speed change information regarding a change in motion speed of the target object for each frame.

13. The kick motion determination unit 13. The kick motion detection device of claim 12, wherein the motion of the target object is classified into an approaching motion of approaching the kick motion detection device and a leaving motion of moving away from the kick motion detection device based on the distance change information and the speed change information, and a reference frame for distinguishing between the approaching motion and the leaving motion is derived.

14. The kick motion determination unit 13. The kick motion detection device of claim 12, wherein the determination as to whether the target object is moving within an effective range is based on azimuth angle information regarding an angle at which the target object is located relative to the kick motion detection device and distance information regarding a distance between a radar and the target object.

15. 1. A method for detecting kicking motions using radar signals, comprising: transmitting a radar signal toward a target object; receiving a radar signal reflected from the target object; deriving feature information about the target object based on the radar signal; determining whether or not to enter a kick motion determination state based on the characteristic information; If the state is in the kick motion determination state, determining whether the motion of the target object is a valid kick motion based on the feature information; A kick motion sensing method comprising:

16. further comprising filtering the radar signal to generate a peak signal; The kick motion sensing method of claim 15, wherein the deriving of the feature information comprises deriving the feature information for the target object based on the peak signal.

17. The step of generating a peak signal comprises: The kicking motion sensing method of claim 16, further comprising generating range-Doppler map information based on the radar signal, and filtering the range-Doppler map information to derive the peak signal.

18. In a device that uses radar to detect kicking motions, at least one processor; at least one memory containing computer program code; The at least one memory and the computer program code, through the at least one processor, cause the device to: Sends a radar signal to the target object, receiving a radar signal reflected from the target object; deriving feature information for the target object based on the radar signal; determining whether or not to enter a kick motion determination state based on the characteristic information; The kick motion detection device is configured to determine whether the motion of the target object is a valid kick motion based on the feature information when the kick motion determination state is entered.

Images