Abnormal posture detection apparatus

Abstract

To provide an abnormal posture detection apparatus capable of detecting an abnormal posture without requiring machine learning of skeletal data.SOLUTION: An abnormal posture detection apparatus includes: a skeletal position acquisition unit which acquires three-dimensional skeletal position of a person; a vector acquisition unit which acquires, based on the three-dimensional skeletal position, a perpendicular vector with respect to a floor surface on which the person exists, a right-leg vector indicating an orientation of the right leg of the person, and a left-leg vector indicating an orientation of the left leg of the person; a calculation unit which calculates a right-leg angle formed by the perpendicular vector and the right-leg vector, and a left-leg angle formed by the perpendicular vector and the left-leg vector; and a determination unit which determines, when both right- and left-leg angles are smaller than a preset specified angle, that the person is in an abnormal posture, and controls a predetermined warning device so as to issue a warning about the abnormal posture.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an abnormal posture detection device. [Background technology]

[0002] Conventionally, there are known techniques for detecting a person's posture based on the person's skeletal data. For example, Patent Document 1 discloses a technique for performing machine learning on skeletal data to which labels indicating abnormal postures have been previously assigned, and for detecting abnormal postures of a person using the resulting learning model. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-55077 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the technology in Patent Document 1 requires manual labeling of skeletal data, which is time-consuming. Also, when preparing posture data, which is the basis of skeletal data, by photographing, a person must actually assume an abnormal posture, which is dangerous.

[0005] An object of one aspect of the present disclosure is to provide an abnormal posture detection device that can detect abnormal postures without requiring machine learning of skeletal data. [Means for solving the problem]

[0006] An abnormal posture detection device according to one embodiment of the present disclosure includes a skeletal position acquisition unit that acquires a three-dimensional skeletal position of a person; a vector acquisition unit that acquires, based on the three-dimensional skeletal position, a vertical vector that is perpendicular to a floor surface on which the person is located, a right foot vector that indicates the direction of the person's right foot, and a left foot vector that indicates the direction of the person's left foot; a calculation unit that calculates the right foot angle formed by the vertical vector and the right foot vector, and the left foot angle formed by the vertical vector and the left foot vector; and a determination unit that, if both the right foot angle and the left foot angle are less than a predetermined specified angle, determines that the person has an abnormal posture and controls a specified notification device to issue a notification to that effect. [Effects of the Invention]

[0007] According to the present disclosure, abnormal postures can be detected without requiring machine learning of skeletal data. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a block diagram illustrating a configuration of an abnormal posture detection system according to an embodiment of the present disclosure. [Figure 2] FIG. 1 is a diagram illustrating an example of a three-dimensional skeletal position according to an embodiment of the present disclosure. [Figure 3] 1 is a diagram illustrating an example of a vertical vector, a right foot vector, and a left foot vector according to an embodiment of the present disclosure. [Figure 4] 1 is a flowchart illustrating an operation of an abnormal posture detection device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0010] First, the configuration of an abnormal posture detection system 1 according to this embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the configuration of the abnormal posture detection system 1.

[0011] In this embodiment, the case where the target for detecting abnormal posture is a person (e.g., a worker) in a workplace such as a factory will be described as an example, but is not limited to this. Also, in this embodiment, the case where the abnormal posture is a fall will be described as an example, but is not limited to this.

[0012] 1, the abnormal posture detection system 1 includes an abnormal posture detection device 10, a camera 20, and a notification device 30. The abnormal posture detection device 10 is connected to each of the camera 20 and the notification device 30 so as to be able to communicate with each other.

[0013] The camera 20 is installed in, for example, a workplace and captures the entire body of a person present there. The camera 20 outputs image data obtained by capturing the image to the abnormal posture detection device 10.

[0014] The abnormal posture detection device 10 detects a fall of a person based on image data input from the camera 20. If a fall is detected, the abnormal posture detection device 10 controls the notification device 30 to notify the person that a fall has occurred. Details of the abnormal posture detection device 10 will be described later.

[0015] The notification device 30 issues a notification that a person has fallen under the control of the abnormal posture detection device 10. The notification device 30 may be installed in the workplace where the camera 20 is installed, or in a location separate from the workplace. Examples of the notification device 30 include a display, a lamp, and a speaker. Examples of the notification mode by the notification device 30 include displaying an image on a display, turning on a lamp, and outputting sound from a speaker. These may be used in combination.

[0016] The configuration of the abnormal posture detection system 1 has been described above.

[0017] Next, the configuration of the abnormal posture detection device 10 according to this embodiment will be described with reference to FIG.

[0018] Although not shown in the drawings, the abnormal posture detection device 10 has, as hardware, for example, a CPU (Central Processing Unit), a ROM (Read Only Memory) that stores computer programs, a RAM (Random Access Memory) that is a working memory, etc. Each unit described below is realized by the CPU reading out a computer program from the ROM and executing it in the RAM.

[0019] As shown in FIG. 1, the abnormal posture detection device 10 includes a skeleton position acquisition unit 110, a vector acquisition unit 120, a calculation unit 130, and a determination unit 140.

[0020] The skeleton position acquisition unit 110 acquires the three-dimensional skeleton position of a person based on image data from the camera 20.

[0021] This acquisition method can be performed using known techniques. For example, a method of capturing an RGB image of a person and inputting it into a machine learning model capable of estimating a three-dimensional skeletal position, a method of preparing a pair of a depth image and an RGB image of a person, inputting the RGB image into a machine learning model capable of estimating a two-dimensional skeletal position, acquiring the two-dimensional skeletal position, and then associating the two-dimensional skeletal position with the depth image, or a method of preparing a depth image of a person and inputting it into a machine learning model capable of estimating a two-dimensional skeletal position or a three-dimensional skeletal position on the depth image may be used.

[0022] Here, the three-dimensional skeleton position acquired by the skeleton position acquisition unit 110 will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the three-dimensional skeleton position.

[0023] In FIG. 2, the area above the pelvic center, the right groin, and the left groin corresponds to the person's upper body, and the area below the pelvic center, the right groin, and the left groin corresponds to the person's lower body. In the following description, the upper three-dimensional skeletal position of the lower body is referred to as the "upper skeletal position," and the lower three-dimensional skeletal position of the lower body is referred to as the "lower skeletal position." Examples of upper skeletal positions include the right groin and the left groin, or the pelvic center. Examples of lower skeletal positions include the right foot and the left foot. The right foot and the left foot may be any part below the ankle, and may be, for example, the ankle, the toe, or the heel.

[0024] An example of a three-dimensional skeletal position has been described above. Now, we will return to the description of FIG.

[0025] Based on the three-dimensional skeleton position acquired by the skeleton position acquisition unit 110, the vector acquisition unit 120 acquires a vertical vector perpendicular to the floor surface on which the person is standing, a right foot vector indicating the direction of the person's right foot, and a left foot vector indicating the direction of the person's left foot.

[0026] Here, the vertical vector, right foot vector, and left foot vector acquired by the vector acquisition unit 120 will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the vertical vector, right foot vector, and left foot vector in a virtual three-dimensional space coordinate system. The three-dimensional skeletal position shown in Fig. 3 indicates the three-dimensional skeletal position of a person when they fall.

[0027] The solid arrow a is an example of a vertical vector. As shown in Fig. 3, the vertical vector is a vector that points in the vertical direction from the floor surface (xy plane) on which the person is standing.

[0028] The dotted arrow b is an example of a right foot vector. As shown in Figure 3, the right foot vector is a vector that points from the right hip, which is the upper skeletal position, to the right foot, which is the lower skeletal position.

[0029] The dotted arrow c is an example of a left foot vector. As shown in Figure 3, the left foot vector is a vector that points from the base of the left foot, which is the upper skeletal position, to the left foot, which is the lower skeletal position.

[0030] When the upper skeleton position is the center of the pelvis, the right foot vector is a vector directed from the center of the pelvis to the right foot, and the left foot vector is a vector directed from the center of the pelvis to the left foot.

[0031] Above, examples of various vectors have been explained. Now, we will return to the explanation of FIG.

[0032] The calculation unit 130 calculates the angle between the vertical vector and the right foot vector (hereinafter referred to as the right foot angle), and the angle between the vertical vector and the left foot vector (hereinafter referred to as the left foot angle).

[0033] The determination unit 140 determines whether or not both the right foot angle and the left foot angle are less than a predetermined specified angle.

[0034] The specified angle here is, for example, the lower limit of a range of angles (for example, obtuse angles) at which a person will not fall, which is set based on the results of experiments or simulations conducted in advance.

[0035] If both the right foot angle and the left foot angle are less than the specified angle, the determination unit 140 determines that the person has fallen.

[0036] Then, the determination unit 140 controls the notification device 30 to issue a notification indicating that a person has fallen (hereinafter referred to as a "fall notification"). As a result, the notification device 30 issues the fall notification by, for example, displaying an image, outputting a sound, turning on a lamp, etc.

[0037] The configuration of the abnormal posture detection device 10 has been described above.

[0038] Next, the operation of the abnormal posture detection device 10 will be described with reference to Fig. 4. Fig. 4 is a flowchart showing the operation of the abnormal posture detection device 10.

[0039] The flow shown in FIG. 4 starts when, for example, image data from the camera 20 is input to the abnormal posture detection device 10.

[0040] First, the skeleton position acquisition unit 110 acquires the three-dimensional skeleton position of a person based on input image data (step S1).

[0041] Next, the vector acquisition unit 120 acquires a vertical vector, a right foot vector, and a left foot vector based on the three-dimensional skeleton position acquired in step S1 (step S2).

[0042] Next, the calculation unit 130 calculates the right foot angle and the left foot angle based on the vertical vector, the right foot vector, and the left foot vector acquired in step S2 (step S3).

[0043] Next, the determination unit 140 determines whether or not both the right foot angle and the left foot angle calculated in step S3 are less than a specified angle (step S4).

[0044] If neither the right foot angle nor the left foot angle is less than the specified angle (step S4: NO), the abnormal posture detection device 10 determines that the person has not fallen. In this case, the flow returns to step S1. Then, the processing from step S1 onwards is performed based on the next new image data input.

[0045] On the other hand, if both the right foot angle and the left foot angle are less than the specified angle (step S4: YES), the abnormal posture detection device 10 determines that the person has fallen. In this case, the abnormal posture detection device 10 controls the notification device 30 to issue a notification that a fall has occurred (step S5). As a result, the notification device 30 issues a notification that a fall has occurred.

[0046] After step S5, the processes of steps S1 to S5 may be repeated.

[0047] As described above, the abnormal posture detection device 10 of this embodiment is characterized by having a skeletal position acquisition unit 110 that acquires the three-dimensional skeletal position of a person; a vector acquisition unit 120 that acquires, based on the three-dimensional skeletal position, a vertical vector that is perpendicular to the floor surface on which the person is located, a right foot vector that indicates the direction of the person's right foot, and a left foot vector that indicates the direction of the person's left foot; a calculation unit 130 that calculates the right foot angle formed by the vertical vector and the right foot vector, and the left foot angle formed by the vertical vector and the left foot vector; and a determination unit 140 that, if both the right foot angle and the left foot angle are less than a predetermined specified angle, determines that the person has an abnormal posture and controls a specified notification device 30 to issue a notification to that effect.

[0048] Due to this feature, the abnormal posture detection device 10 of this embodiment can detect an abnormal posture without requiring machine learning of skeletal data.

[0049] The present disclosure is not limited to the above-described embodiment, and various modifications are possible without departing from the spirit of the present disclosure. Modifications will be described below.

[0050] [Variation 1] In the embodiment, the skeleton position acquiring unit 110 acquires a three-dimensional skeleton position based on captured image data, but the present invention is not limited to this.

[0051] For example, a sensor capable of measuring the three-dimensional skeletal position may be attached to the person, and the skeletal position acquisition unit 110 may receive data indicating the measurement results from the sensor and acquire the three-dimensional skeletal position based on the data.

[0052] [Variation 2] In the embodiment, the case where the right foot angle and the left foot angle are used to determine whether or not a fall has occurred has been described as an example, but the present invention is not limited to this.

[0053] For example, the calculation unit 130 may measure (or estimate) the distance between the person's head and the floor surface (xy plane) based on the three-dimensional skeleton position of the person's head acquired by the skeleton position acquisition unit 110.

[0054] The determination unit 140 may then determine whether or not a fall has occurred based on the determination result of whether or not both the right foot angle and the left foot angle are less than a specified angle, and the determination result of whether or not the distance between the head and the floor surface is less than a specified distance.

[0055] The specified distance here is, for example, the upper limit of the range of distances from the floor to the head when a person is considered to have fallen, which is set based on the results of a previously conducted experiment or simulation.

[0056] Then, the determination unit 140 may determine that the person has fallen if both the right foot angle and the left foot angle are less than the specified angle and further the distance between the head and the floor surface is less than the specified distance.

[0057] As described above, by using the distance between the head and the floor in addition to the right foot angle and left foot angle, it is possible to further improve the accuracy of determining whether or not a fall has occurred.

[0058] Furthermore, the calculation unit 130 may measure (or estimate) the distance between the position of the foot that is on the ground when the person is viewed from the side (x-axis) (hereinafter referred to as the landing position) and the position of the center of gravity of the human body (for example, the center of the pelvis), which is acquired by the skeleton position acquisition unit 110. Note that when both feet are on the ground, the landing position is set to, for example, the midpoint between the left and right feet.

[0059] The determination unit 140 may determine whether or not a fall has occurred based on the determination result of whether or not both the right foot angle and the left foot angle are less than a specified angle, and the determination result of whether or not the distance between the landing position and the center of gravity position of the human body is equal to or greater than a specified distance.

[0060] The specified distance here is, for example, the lower limit of the range of distances between the landing position at which a person begins to stagger or stumble and the center of gravity of the human body, which is set based on the results of experiments or simulations conducted in advance.

[0061] The determination unit 140 may then determine that a person has fallen if both the right foot angle and the left foot angle are less than a specified angle and further, the distance between the landing position and the center of gravity of the human body is equal to or greater than a specified distance.

[0062] As described above, by using the distance between the landing position and the center of gravity of the human body in addition to the right and left foot angles, it is possible to improve the accuracy of determining whether or not a fall has occurred. It is also possible to grasp postural instability such as unsteadiness or stumbling, which are signs of an impending fall.

[0063] [Variation 3] Since the posture when falling is similar to the posture when sitting on a chair or the like (hereinafter referred to as a sitting posture), it is not desirable to detect a sitting posture as a fall. Therefore, the detection operation described above (flow in FIG. 4) may be performed by narrowing the location and time period for detecting falls to a predetermined range.

[0064] Specifically, the above-mentioned detection operation may be performed excluding places where a sitting posture is assumed (for example, a work area or rest area where a chair is placed) and times when a sitting posture is assumed (for example, rest periods). This makes it possible to prevent a sitting posture from being detected as a fall and also to speed up the detection process. [Industrial Applicability]

[0065] The abnormal posture detection device of the present disclosure is useful in general technology for detecting human posture. [Explanation of symbols]

[0066] 1. Abnormal posture detection system 10. Abnormal posture detection device 20 Camera 30 Alarm device 110 Skeleton position acquisition unit 120 Vector Acquisition Unit 130 Calculation Unit 140 Judgment section

Claims

1. a skeleton position acquisition unit for acquiring a three-dimensional skeleton position of a person; a vector acquisition unit that acquires, based on the three-dimensional skeleton position, a vertical vector that is perpendicular to a floor surface on which the person is located, a right foot vector that indicates the direction of the person's right foot, and a left foot vector that indicates the direction of the person's left foot; a calculation unit that calculates a right foot angle formed by the vertical vector and the right foot vector, and a left foot angle formed by the vertical vector and the left foot vector; and a determination unit that determines that the person has an abnormal posture and controls a predetermined notification device to notify the person when both the right foot angle and the left foot angle are less than a predetermined specified angle. Abnormal posture detection device.

2. The abnormal posture is a fall, the three-dimensional skeleton position includes an upper three-dimensional skeleton position and a lower three-dimensional skeleton position of a lower body of the person, the upper three-dimensional skeletal position is the base of the right foot and the base of the left foot, or the center of the pelvis; the lower three-dimensional skeletal positions are a part below the right ankle and a part below the left ankle, the right foot vector is a vector directed from either the base of the right foot or the center of the pelvis to a portion below the right ankle, The left foot vector is a vector directed from either the base of the left foot or the center of the pelvis to a portion below the left ankle. The abnormal posture detection device according to claim 1 .

3. The three-dimensional skeleton position further includes a three-dimensional skeleton position of a head of the person; the calculation unit further measures a distance between the person's head and the floor surface based on the three-dimensional skeletal position of the head; the determination unit determines that the person has an abnormal posture when both the right foot angle and the left foot angle are less than a predetermined specified angle and also when the distance is less than a predetermined specified distance. The abnormal posture detection device according to claim 1 or 2.

4. the three-dimensional skeleton position further includes a landing position, which is a position of a foot that is on the ground when the person is viewed from the side, and a center of gravity position of the human body; the calculation unit further measures a distance between the landing position and a center of gravity of the human body based on the landing position and the center of gravity of the human body; the determination unit determines that the person has an abnormal posture when both the right foot angle and the left foot angle are less than a predetermined specified angle and when the distance is equal to or greater than a predetermined specified distance. The abnormal posture detection device according to claim 1 or 2.

Images