Movement support device

Abstract

To realize a movement support device capable of providing movement support at an appropriate timing in accordance with a user's travel speed.SOLUTION: A movement support device 1 is worn on at least one of the user's shoulders or neck, and comprises: an imaging unit 20 that images an area in front of the user; an object detection unit 40a that detects an object in the image on the basis of the image captured by the imaging unit 20; and a walking speed calculation unit 40b that calculates the user's walking speed on the basis of a guidance block 30a in the objects detected by the object detection unit 40a, and a predetermined stationary object (for example, a utility pole 31). The walking speed calculation unit 40b calculates the user's walking speed on the basis of a rate of change per unit time in the number of guidance blocks 30a that are located closer to the user than the predetermined stationary object (utility pole 31) serving as a reference in an image 21.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to a mobility assistance device. [Background technology]

[0002] Conventionally, mobility support devices for assisting visually impaired people in traveling have been known. For example, the mobility support device described in Patent Document 1 captures an image including the ground in front of the user and extracts braille block information from the image by analyzing (image processing) the data related to the image. The braille block information includes at least one of the position and size of the braille blocks. Here, the mobility support device calculates the direction and distance of the braille blocks based on the braille block information, and notifies the user of the distance and direction of obstacles based on the calculated direction and distance of the braille blocks. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-49253 Summary of the Invention [Problem to be solved by the invention]

[0004] Such notification to the user is preferably performed at a timing according to the user's walking speed. For example, if the device is configured to notify the user of the presence of an obstacle when the distance from the user to the obstacle falls below a predetermined value, if the user's walking speed is fast, the time from the notification to reaching the obstacle may be short, which may cause the user anxiety. On the other hand, if the user's walking speed is slow, the time from the notification to reaching the obstacle may be long, which may cause the user anxiety. The mobility assistance device described in Patent Document 1 above does not perform notifications taking the user's running speed into consideration, so there is room for improvement.

[0005] Therefore, an object of the present invention is to realize a mobility assistance device that can provide mobility assistance at appropriate timing according to the user's running speed. [Means for solving the problem]

[0006] (1) The mobility support device of the present invention, which is provided to solve the above-mentioned problems, is a mobility support device worn on at least one of the user's shoulders and neck, and includes an imaging unit that captures an image of the front side of the user, a target detection unit that detects targets in the image based on the image captured by the imaging unit, and a walking speed calculation unit that calculates the walking speed of the user based on guide blocks among the targets detected by the target detection unit and predetermined stationary targets, and is characterized in that the walking speed calculation unit calculates the walking speed based on the change per unit time in the number of guide blocks that are located closer to the user in the image than the predetermined stationary target that serves as a reference.

[0007] The mobility assistance device described above detects targets in an image captured by the imaging unit based on the image. The walking speed calculation unit calculates the walking speed based on the change per unit time in the number of guide blocks located closer to the user than a predetermined reference stationary target in the image captured by the imaging unit. In this manner, the mobility assistance device of the present invention can calculate the user's walking speed based on the image captured by the imaging unit. Therefore, when providing mobility assistance such as notifications about Braille blocks, the mobility assistance device of the present invention can perform the assistance at a timing that corresponds to the user's running speed. Furthermore, because the mobility assistance device of the present invention calculates the user's walking speed using the image captured by the imaging unit, there is no need to provide a separate sensor or the like for calculating the walking speed. Therefore, the mobility assistance device of the present invention can be realized with an inexpensive configuration. Furthermore, although the user's walking speed changes depending on the road surface conditions (such as slope), the mobility assistance device of the present invention can provide mobility assistance at an appropriate timing even when the user's walking speed changes.

[0008] (2) The number of the guide blocks may be determined as the number of guide blocks that are located closer to the user than a virtual line that passes through a specified location of the specified stationary target and a specific location of the guide block that is closest to the specified stationary target in the image.

[0009] In this way, the mobility support device of the present invention can easily calculate the number of guide blocks (the number of guide blocks that are closer to the user than the predetermined stationary target) based on the virtual straight line, even if the predetermined stationary target serving as a reference and the guide blocks are arranged at a distance from each other. In other words, the mobility support device of the present invention can easily calculate the user's walking speed based on the virtual straight line, even if the predetermined stationary target serving as a reference and the guide blocks are arranged at a distance from each other.

[0010] (3) A mobility assistance control unit is provided that, when an obstacle is detected by the target detection unit, executes mobility assistance control including notification control to notify the user that an obstacle has been detected, and when the walking speed calculated by the walking speed calculation unit is faster than a predetermined value, the mobility assistance control unit executes the notification control at an earlier timing than when the walking speed is slower than the predetermined value.

[0011] In this way, when the traveling speed is faster than a predetermined value, the mobility assistance device of the present invention notifies the user of the presence of an obstacle at an early timing, allowing the user to respond to the obstacle with ample time to react. On the other hand, when the traveling speed is slower than a predetermined value, the mobility assistance device notifies the user of the presence of an obstacle at a late timing, preventing the user from feeling anxious because the user is unable to reach the obstacle despite the notification. In other words, by doing this, the mobility assistance device of the present invention can control the notification at an appropriate timing according to the user's walking speed. [Effects of the Invention]

[0012] According to the present invention, it is possible to realize a mobility assistance device that can provide mobility assistance at appropriate timing according to the user's running speed. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a plan view of a mobility assistance device according to an embodiment of the present invention; [Figure 2] 1 is a block diagram of a mobility assistance device according to an embodiment of the present invention; [Figure 3] 1 is an example of an image captured by a camera of a mobility assistance device according to an embodiment of the present invention. [Figure 4] 10A and 10B are diagrams for explaining a method for calculating walking speed based on images, in which (a) is an image captured at a predetermined timing, and (b) is an image captured a predetermined time after the image in (a). [Figure 5] 10 is a flowchart illustrating an example of a walking speed calculation process according to the present embodiment. [Figure 6] 10A and 10B are diagrams illustrating a method for calculating the walking speed of a mobile device according to a modified example of the present embodiment, and are images captured at predetermined timings. [Figure 7] 7 is a diagram for explaining a method for calculating the walking speed of a mobile device according to a modified example of this embodiment, and is an image captured a predetermined time after the image of FIG. 6. FIG. [Figure 8] 10 is a flowchart showing an example of a traveling speed calculation process executed by a travel assistance device according to a modified example. DETAILED DESCRIPTION OF THE INVENTION

[0014] <<Embodiment>> Hereinafter, a mobility support device 1 according to one embodiment of the present invention will be described in detail with reference to the drawings. Note that each drawing is a schematic representation for ease of understanding, and may differ in actual size.

[0015] As shown in Fig. 1, a mobility support device 1 of this embodiment is intended to support the mobility of, for example, a visually impaired user. The mobility support device 1 is configured as a terminal (hereinafter, the mobility support device 1 may also be referred to as a terminal 1). As shown in Fig. 2, the mobility support device 1 includes an imaging unit 20, a control unit 40, a notification unit 45, etc.

[0016] The terminal 1 (mobility support device 1) is worn by a user. The terminal 1 includes a battery 11. The imaging unit 20 and the battery 11 are housed inside a housing that constitutes the mobility support device 1. The terminal 1 should be able to be worn stably without causing any strain to the user. In this embodiment, the terminal 1 is a wearable terminal that can be worn on at least one of both shoulders or around the neck. In the example shown in FIG. 1, the terminal 1 is a wearable terminal that can be worn around the neck and over both shoulders. In this embodiment, the terminal 1 is formed in an inverted U-shape and can be worn around the user's neck. The terminal 1 also includes an imaging unit 20 that can capture an image of an area in front of the user when in use. The terminal 1 includes the battery 11, and the power supplied from the battery 11 can operate the imaging unit 20, the control unit 40, the notification unit 45, and other components that constitute the mobility support device 1.

[0017] As shown in FIG. 1, the imaging unit 20 is configured with, for example, a camera, and can capture an image of the area in front of the user. In this embodiment, the imaging unit 20 is provided, for example, on one side of the front end of the terminal 1. The imaging unit 20 can capture an image 21 as shown in FIG. 3 by capturing an image of the area in front of the user. In this embodiment, the image 21 includes images of a plurality of tactile paving blocks (guidance blocks 30a), utility poles 31, plants 32, and other stationary landmarks 33. The image 21 (see FIG. 3) captured by the imaging unit 20 is transmitted as image data to the control unit 40 via a wired or wireless connection, and is used for image analysis (image processing).

[0018] The control unit 40 is configured with a microcomputer or the like having a CPU (Central Processing Unit), RAM (Random Access Memory), ROM (Read Only Memory), etc., and is capable of performing image processing of captured images acquired from the imaging unit 20 and control related to mobility assistance in the mobility assistance device 1. The control unit 40 includes a target detection unit 40a, a walking speed calculation unit 40b, and a mobility assistance control unit 40c, which are configured by the CPU in the control unit 40. The control unit 40 also includes a guide block number storage area 40d, a walking speed storage area 40e, a notification timing threshold (normal) storage area 40f, and a notification timing threshold (high speed) storage area 40g. The guide block number storage area 40d and the walking speed storage area 40e are each stored in a predetermined storage area of ​​the RAM. Meanwhile, the notification timing threshold (normal) storage area 40f and the notification timing threshold (high speed) storage area 40g are each stored in a predetermined storage area of ​​the ROM.

[0019] The target detection unit 40a in the control unit 40 detects targets in the image 21 (see FIG. 3). The walking speed calculation unit 40b calculates the walking speed of the user based on the image captured by the imaging unit 20. The travel assistance control unit 40c executes travel assistance control in the travel assistance device 1. These will be described later. Note that each of the units 40a to 40c in the control unit 40 may be configured as an individual computer.

[0020] In this embodiment, the notification unit 45 is configured as a speaker (including earphones) and can guide the user to the braille blocks T and issue notifications (such as issuing an alarm) regarding warnings about obstacles by voice. That is, the notification unit 45 supports the user's movement by guiding the user to the braille blocks (guide blocks 30a: see Figures 3 and 7, etc., warning blocks 30b: see Figure 7, etc.) and notifying the user of the presence or absence of obstacles.

[0021] The above is the configuration of the movement support device 1 according to one embodiment of the present invention, and next, one embodiment of the operation of the movement support device 1 will be described in detail with reference to Figures 2 to 4. In addition to the operation, each configuration (each unit 40a to 40c) of the control unit 40 will also be described.

[0022] The timing of notifying the user of the presence of an obstacle and the timing of performing guidance based on the tactile paving blocks (guide blocks 30a: see FIGS. 3 and 7, etc., warning blocks 30b: see FIG. 7, etc.) are preferably changed depending on the user's walking speed. For example, assume that a mobility assistance device notifies the user when an obstacle is present within 5 meters of the user. In this case, even if the timing is appropriate for a user with a fast walking speed, a user with a slow walking speed may feel anxious because they have difficulty reaching the obstacle despite the notification. In this way, it is preferable to change the execution timing of mobility assistance control depending on the user's walking speed. Therefore, when performing the above-mentioned mobility assistance control, the mobility assistance device 1 according to this embodiment is configured to calculate the walking speed based on an image (e.g., image 21) captured by the imaging unit 20, and change the execution timing of mobility assistance control based on the calculated walking speed.

[0023] (Target detection section) For example, when an image 21 in FIG. 3 is captured by the imaging unit 20 of the mobility support device 1 (terminal 1) worn around the neck of a user, image data corresponding to the image 21 is transmitted to the control unit 40. This image data includes position information (coordinates) and brightness information of each pixel. Here, the position information is, for example, information on X and Y coordinates, with the horizontal direction in FIG. 3 being the X direction, the vertical direction being the Y direction, and the origin being the upper left pixel.

[0024] The target detection unit 40a of the control unit 40 detects targets in the image 21 by performing image processing on the image data transmitted from the imaging unit 20, and includes a bounding box detection unit 40a1 and a reference point derivation unit 40a2. For example, the targets may be braille blocks (guidance blocks 30a: see Figures 3 and 7, etc., warning blocks 30b: see Figure 7, etc.), utility poles 31, plants 32, other stationary targets (e.g., stationary targets 33), people (dynamic targets), and vehicles (dynamic targets). These targets can be detected by identifying their shape (linear or uneven shape) and brightness (color) based on the position information and brightness information of each pixel included in the image data.

[0025] The bounding box detection unit 40a1 detects targets in an image captured by the imaging unit 20 as bounding boxes with sides in the horizontal and vertical directions. Specifically, when an image is captured by the imaging unit 20, image data representing the image is transmitted to the control unit 40. After acquiring the image data of the image, the target detection unit 40a recognizes each target using a technique such as image matching. When the target detection unit 40a recognizes the presence of a target in the image, it sets a rectangular bounding box for the target. Here, the bounding box is set so as to surround the entire target in the image in a rectangular shape, regardless of whether the target is tilted or not. The bounding box detection unit 40a1 detects the set bounding box and acquires the coordinates of each vertex of the bounding box.

[0026] The coordinates of the image 21 are set with the upper left vertex of the image 21 as the origin (0,0). As a result, the coordinates of each vertex of the bounding box can be expressed as XY coordinates, with the left-right direction on the paper as the X direction and the up-down direction on the paper as the Y direction.

[0027] Here, when the image 21 shown in Fig. 3 is captured, the target detection unit 40a recognizes the multiple guide blocks 30a, utility pole 31, shrubs 32, and other stationary targets 33 as targets by image matching or the like. At this time, the target detection unit 40a also sets bounding boxes X1 and X2 for each of the targets 30a, 31 to 33. Note that in Fig. 3, bounding boxes X1 and X2 are displayed only for the utility pole 31 and a portion of each guide block 30a.

[0028] The bounding box detection unit 40a1 detects the set bounding boxes X1 and X2, and obtains the coordinates of each vertex of each of the bounding boxes X1 and X2.

[0029] The reference point derivation unit 40a2 derives a reference point S for determining the installation position for at least a portion of the bounding box X1 of the multiple guide blocks 30a detected by the bounding box detection unit 40a1. The reference point derivation unit 40a2 derives, for example, the center of the bounding box X1 of each guide block 30a as the reference point S (see FIG. 3). The reference point S is not limited to the center and can be set at any predetermined location within the bounding box X1.

[0030] (Walking speed calculation section) The walking speed calculation unit 40b calculates the walking speed of the user using a predetermined stationary target as a reference. Specifically, the walking speed calculation unit 40b calculates the walking speed of the user based on the change per unit time in the number of guide blocks 30a that are located closer to the user than the predetermined stationary target as a reference in the image 21. Here, the method for calculating the walking speed will be described in detail with reference to FIG. 4, using as an example a case where the predetermined stationary target as a reference is a utility pole 31. Note that in FIG. 4, only the guide blocks 30a and the utility pole 31 are displayed as targets out of the targets detected by the target detection unit 40a.

[0031] First, the walking speed calculation unit 40b finds the number of guide blocks 30a that are closer than the reference utility pole 31. At this time, the walking speed calculation unit 40b sets an imaginary straight line CL that overlaps with the side closer to the user (the side on the lower side in the up-down direction of the paper) of two sides parallel to the horizontal direction (X direction) of the bounding box X2 of the utility pole 31 acquired by the bounding box detection unit 40a1 in the image 21.

[0032] The virtual straight line CL can be set based on, for example, the coordinates of the four vertices of the bounding box X2 of the utility pole 31 acquired by the bounding box detection unit 40a1. Specifically, the walking speed calculation unit 40b sets the virtual straight line CL based on the coordinates of two vertices located at both ends of the side closer to the user (the side on the lower side in the vertical direction of the paper) out of the four vertices of the bounding box X2. Note that the virtual straight line CL in this embodiment is a straight line parallel to the X direction.

[0033] After setting the virtual straight line CL, the walking speed calculation unit 40b uses the virtual straight line CL as a reference line and derives the number of guide blocks 30a that are closer to the user than the reference line in the image 21. The walking speed calculation unit 40b repeatedly sets the virtual straight line CL and derives the number of guide blocks 30a at a predetermined cycle (for example, 1 second).

[0034] For example, Fig. 4(a) shows an image 21 captured by the imaging unit 20 at a predetermined timing for calculating the number of the guide blocks 30a. At this time, the number of guide blocks 30a located closer to the user than the virtual line CL is three. Therefore, based on the image 21, the walking speed calculation unit 40b derives "3" as the number of guide blocks 30a located closer to the user than the virtual line CL, and stores this number in a guide block number storage area 40d set in the RAM.

[0035] Furthermore, the walking speed calculation unit 40b also derives the number of guide blocks 30a that are closer to the user than the virtual line CL in the next period (the next period in which the number of guide blocks is calculated: 1 second later). FIG. 4(b) shows an image 21 captured by the imaging unit 20 in the next period (1 second later). At this time, the number of guide blocks 30a that are closer to the user than the virtual line CL is two. Therefore, based on the image 21, the walking speed calculation unit 40b derives "2" as the number of guide blocks 30a that are closer to the user than the virtual line CL. At this time, the walking speed calculation unit 40b stores the derived number of guide blocks 30a in the guide block number storage area 40d.

[0036] The number of guide blocks 30a located closer to the user than the virtual line CL can be calculated by various methods. For example, based on the XY coordinates of the reference point S of each guide block 30a derived by the reference point derivation unit 40a2, the number of reference points S located on the +Y side of the virtual line CL in the image 21 can be calculated as the number of guide blocks 30a located closer to the user than the virtual line CL.

[0037] The walking speed calculation unit 40b calculates the user's walking speed based on the amount of change per cycle (per unit time) in the number of guide blocks 30a derived in this way. In the example shown in FIG. 4, the number of guide blocks 30a derived this time is "2", and the number of guide blocks 30a derived previously is "3". Therefore, the amount of change in the number of guide blocks 30a per cycle (per unit time) is "1". Here, it can be estimated that (the amount of change "1") x (the length L of the guide blocks 30a in the Y direction) = (the distance P traveled by the user per cycle (1 second)).

[0038] Therefore, the walking speed calculation unit 40b calculates the user's running speed as follows: (distance P traveled by the user in one cycle (1 second)) ÷ time (1 cycle: 1 second) = (user's running speed). The dimensions of the guide block 30a are determined by standards, and the approximate length L of the guide block 30a in the Y direction can be determined based on these standards. When the walking speed calculation unit 40b calculates the walking speed, it stores the calculated walking speed in a walking speed memory area 40e set in a predetermined memory area of ​​the RAM.

[0039] (Mobility Assistance Control Unit) The travel assistance control unit 40c executes travel assistance control based on targets (obstacles, tactile paving blocks) detected by the target detection unit 40a. Here, travel assistance control includes control for notifying the user to guide them to the tactile paving blocks, control for notifying the user of the presence of an obstacle, and the like. For example, when the travel assistance control unit 40c recognizes an obstacle in the image 21 acquired by the imaging unit 20, it derives the distance between the obstacle and the user. The travel assistance control unit 40c determines the timing for executing travel assistance control based on the derived distance between the obstacle and the user and the user's walking speed calculated by the walking speed calculation unit 40b.

[0040] Specifically, when the walking speed calculated by the walking speed calculation unit 40b is slower than a predetermined value, the travel assistance control unit 40c executes notification control to notify the user of the presence of an obstacle when the distance between the user and the obstacle becomes shorter than a first threshold (3 m). On the other hand, when the walking speed calculated by the walking speed calculation unit 40b is equal to or greater than a predetermined value, the travel assistance control unit 40c executes notification control to notify the user of the presence of an obstacle when the distance between the user and the obstacle becomes shorter than a second threshold (5 m).

[0041] Here, a first threshold value (e.g., 3 [m]) that determines the notification timing when the walking speed calculated by the walking speed calculation unit 40b is slower than a predetermined value is stored in a notification timing threshold (normal) storage area 40f set in a predetermined storage area of ​​the ROM. Also, a second threshold value (e.g., 5 [m]) that determines the notification timing when the walking speed calculated by the walking speed calculation unit 40b is equal to or greater than the predetermined value is stored in a notification timing threshold (high speed) storage area 40g set in a predetermined storage area of ​​the ROM. Note that the first threshold value and the second threshold value can be changed as appropriate.

[0042] The timing at which the travel assistance control unit 40c executes notification control is not limited to the above example. For example, the travel assistance control unit 40c may be configured to increase the threshold value for the notification timing as the walking speed of the user calculated by the walking speed calculation unit 40b increases.

[0043] However, with this method of calculating the walking speed, it is possible that the calculation of the walking speed may become impossible halfway through. Therefore, the travel assistance control unit 40c can determine the execution timing of notification control using the first threshold (3 [m]) stored in the notification timing threshold (normal) storage area 40f, assuming that the calculation of the walking speed becomes impossible halfway through.

[0044] Furthermore, the timing of notification control when calculation of the user's walking speed becomes impossible midway can also be determined by other methods. For example, the travel assistance control unit 40c calculates the average value of the walking speeds calculated up until the time when calculation of the walking speed becomes impossible. Here, if the average value is slower than a predetermined value, the travel assistance control unit 40c determines the timing of notification control based on the first threshold value (3 [m]) described above. On the other hand, if the average value is equal to or greater than a predetermined value, the travel assistance control unit 40c determines the timing of notification control based on the second threshold value (5 [m]) described above. In this case, the control unit 40 may provide a storage area in the RAM for storing a predetermined number of walking speeds calculated by the walking speed calculation unit 40b.

[0045] (Walking speed calculation process) An example of the process for calculating the walking speed of the user (walking speed calculation process) will be described with reference to Fig. 5. Fig. 5 is a flowchart showing an example of the walking speed calculation process according to this embodiment.

[0046] In step S1, the imaging unit 20 captures an image of the area in front of the user wearing the mobility assistance device 1. Image data representing the image is then transmitted to the control unit .

[0047] Next, in step S2, the target detection unit 40a performs image processing on the image data acquired from the imaging unit 20 to detect targets (guiding blocks 30a, utility poles 31, shrubs 32, other stationary targets 33, etc.) within the image 21. At this time, the target detection unit 40a sets bounding boxes X1 and X2 for each detected target.

[0048] Next, in step S3, the bounding box detection unit 40a1 detects the bounding box X2 of the set utility pole 31 and the bounding box X1 of each guide block 30a. At this time, the reference point derivation unit 40a2 derives a reference point S for the bounding box X1 of each guide block 30a.

[0049] Next, in step S4, the walking speed calculation unit 40b sets a virtual line CL that overlaps with the line closest to the user (the line on the lower side of the page in FIG. 3 ) of two lines parallel to the horizontal direction (X direction) of the bounding box X2 of the utility pole 31 in the image 21, and then derives the number of guide blocks 30a that are closer to the user than the virtual line CL in the image 21. In this case, the number of guide blocks 30a can be the number of reference points S (reference points S of the bounding box X1) of the guide blocks 30a that are on the +Y side of the virtual line CL in the image 21. The walking speed calculation unit 40b stores the derived number of guide blocks 30a in the guide block number storage area 40d of the RAM.

[0050] Next, in step S5, the walking speed calculation unit 40b calculates the user's walking speed by comparing the number of guide blocks 30a calculated in the previous cycle, which is stored in the guide block number storage area 40d, with the number of guide blocks 30a calculated this time. Specifically, the walking speed calculation unit 40b calculates the amount of change between the number of guide blocks 30a calculated in the previous cycle and the number of guide blocks 30a calculated in the current cycle, and calculates the user's walking speed based on this amount of change, the length L of the guide blocks 30a, and the length of one cycle (1 second in this embodiment), as described above. The walking speed calculation unit 40b stores the calculated user's walking speed in the walking speed storage area 40e of RAM.

[0051] The movement support device 1 of this embodiment executes the processes of steps S1 to S6 at predetermined intervals (one second in this embodiment).

[0052] (Action and effect) The above is one embodiment of the mobility support device 1 of the present invention. Next, the effects achieved by the mobility support device 1 of this embodiment will be described below.

[0053] The above-described mobility support device 1 has the following characteristic configuration: Therefore, the mobility support device 1 can achieve the following unique effects that cannot be achieved by conventional techniques.

[0054] (a) The mobility support device 1 of this embodiment is a mobility support device 1 worn on at least one of the user's shoulders and neck, and includes an imaging unit 20 that captures an image in front of the user, a target detection unit 40a that detects targets within an image 21 captured by the imaging unit 20 based on the image 21, and a walking speed calculation unit 40b that calculates the user's walking speed based on guide blocks 30a among the targets detected by the target detection unit 40a and a predetermined stationary target (electric pole 31), and the walking speed calculation unit 40b is characterized in that it calculates the user's walking speed based on the amount of change per unit time (1 second in this embodiment) in the number of guide blocks 30a that are located closer to the user in the image 21 than the reference electric pole 31.

[0055] Specifically, in step S1 described above, the mobility support device 1 can acquire an image 21 of the front side of the user using the imaging unit 20. In step S2, the mobility support device 1 performs image processing (image analysis) on the image data acquired by the imaging unit 20 using the target detection unit 40a, thereby detecting targets in the image 21. In step S3, the bounding box detection unit 40a1 detects the bounding box X2 of the utility pole 31 and the bounding boxes X1 of each guide block 30a. In step S4, the walking speed calculation unit 40b derives the number of guide blocks 30a located closer to the user than the virtual line CL set based on the bounding box X2 of the utility pole 31. In step S6, the walking speed calculation unit 40b calculates the walking speed of the user based on the amount of change between the number of guide blocks 30a derived in the previous cycle and the number of guide blocks 30a derived in the current cycle.

[0056] The mobility support device 1 configured as described above detects targets in the image 21 captured by the imaging unit 20. The walking speed calculation unit 40b calculates the walking speed based on the amount of change per cycle (unit time: 1 second) in the number of guide blocks 30a located closer to the user than a predetermined stationary target (electric pole 31) serving as a reference in the image 21 captured by the imaging unit 20. In this manner, the mobility support device 1 of this embodiment can calculate the user's walking speed based on the image 21 captured by the imaging unit 20. Therefore, when providing mobility support, such as notifying the user of the presence of an obstacle, the mobility support device 1 of this embodiment can perform the support at a timing according to the user's running speed. Furthermore, since the mobility support device 1 of this embodiment calculates the user's walking speed using the image 21 captured by the imaging unit 20, there is no need to provide a separate sensor or the like for calculating the walking speed. Therefore, the mobility support device 1 of this embodiment can be realized with an inexpensive configuration. Furthermore, the user's walking speed changes depending on the road surface conditions (slope, etc.), but the mobility assistance device of the present invention can provide mobility assistance at an appropriate time even when the user's walking speed changes in this way.

[0057] (b) The target detection unit 40a includes a bounding box detection unit 40a1 that detects a predetermined stationary target (utility pole 31) in the image 21 as a bounding box X2 with sides in the horizontal and vertical directions, and the number of guide blocks 30a can be determined as the number of guide blocks 30a that are located vertically below (on the +Y side of) the reference line, which is a virtual straight line CL that overlaps with the horizontal side (one of the sides parallel to the X direction in FIG. 3 ) of the bounding box X2 of the predetermined stationary target (utility pole 31) in the image 21 and is located below (on the +Y side of) the vertical direction (the direction parallel to the Y direction in FIG. 3 ).

[0058] In this way, the mobility assistance device 1 of this embodiment can easily calculate the walking speed of the user based on the bounding box X2 that detects the predetermined stationary target (the utility pole 31).

[0059] (c) Furthermore, the mobility support device 1 of this embodiment is equipped with a reference point derivation unit 40a2 that derives a reference point S for grasping the installation position of the guide block 30a, and the number of guide blocks 30a that are located closer to the user than a predetermined stationary landmark (utility pole 31) can also be the number of reference points S of the guide blocks 30a that are located closer to the user than the reference line (virtual straight line CL) in the image 21.

[0060] In this way, the movement support device 1 of this embodiment can easily find the number of the guide blocks 30a from the number of reference points S that are closer to the user than the reference line (imaginary straight line CL).

[0061] (d) The mobility support device 1 of this embodiment includes a mobility support control unit 40c that, when an obstacle is detected by the target detection unit 40a, executes mobility support control including notification control to notify the user that an obstacle has been detected. Here, when the user's walking speed calculated by the walking speed calculation unit 40b is faster than a predetermined value, the mobility support control unit 40c executes notification control at an earlier timing than when the user's walking speed is slower than the predetermined value.

[0062] In this way, when the traveling speed is faster than a predetermined value, the mobility support device 1 of this embodiment notifies the user of the presence of an obstacle at an early timing, allowing the user to respond to the obstacle with ample time to react. On the other hand, when the traveling speed is slower than a predetermined value, the mobility support device 1 of this embodiment notifies the user of the presence of an obstacle at a late timing, preventing the user from feeling anxious because the user is unable to reach the obstacle despite the notification. In other words, by doing this, the mobility support device 1 of this embodiment can perform notification control at an appropriate timing according to the user's walking speed.

[0063] (e) Furthermore, if the walking speed calculation unit 40b becomes unable to calculate the user's walking speed midway, the movement assistance control unit 40c can determine the timing of notification control based on the average value of the walking speed calculated up until the walking speed calculation unit 40b becomes unable to calculate the walking speed.

[0064] In this way, even if the movement assistance device 1 of this embodiment becomes unable to calculate the walking speed midway, it can determine the timing of notification control by referring to the walking speed up to that point.

[0065] (f) Furthermore, the movement assistance control unit 40c can also execute notification control at a predetermined timing (timing for executing notification control based on the first threshold value) on the condition that the walking speed calculation unit 40b is unable to calculate the user's walking speed midway.

[0066] In this way, even if the movement assistance device 1 of this embodiment becomes unable to calculate the walking speed midway, it can determine the timing of notification control by referring to the walking speed up to that point.

[0067] (g) Furthermore, the travel assistance device 1 of this embodiment selects the utility pole 31 as the predetermined stationary target that serves as a reference.

[0068] The utility pole 31 is a stationary target that is likely to be included in the image 21 in which the guide block 30a is captured. Therefore, by doing so, the mobility support device 1 of this embodiment can stably calculate the walking speed of the user based on the stationary target that is stably present in the image 21.

[0069] The mobility support device 1 of this embodiment has all of the characteristic configurations (a) to (g) described above, but the present invention is not limited to this. For example, the mobility support device 1 may not have some or all of the configurations (b) to (g) described above, or may have other configurations in addition to the configurations related to (a) to (g). Furthermore, the mobility support device 1 may be modified in such a way that the configurations related to (a) to (g) described above are changed to different ones, without departing from the spirit of the present invention.

[0070] <<Variation>> Hereinafter, a movement support device 1 according to a modification of the above-described embodiment of the present invention will be described in detail with reference to Figures 6 to 8. Figures 6 and 7 each show an example of an image 22 captured by the imaging unit 20 of the movement support device 1 according to this example, and are diagrams for explaining a method of calculating the walking speed of a user when the warning block 30b is used as a reference.

[0071] The mobility support device 1 according to this embodiment differs from the mobility support device 1 described with reference to Figures 1 to 5 in that the method of selecting a predetermined target that serves as a reference when calculating the number of guide blocks 30a is different. The other configurations are the same as those in the above-described embodiment, and therefore the same reference numerals are used and the description thereof will be omitted.

[0072] In the above embodiment, the case where the predetermined target serving as a reference is a utility pole 31 has been described, but as shown in Fig. 3, there are cases where the image captured by the imaging unit 20 includes multiple stationary targets. In such cases, the mobility support device 1 according to this example selects one of the stationary targets based on a predetermined criterion, calculates the number of guide blocks 30a located closest to the user using the selected stationary target as a reference, and calculates the user's walking speed.

[0073] In the mobility support device 1 according to the present example, the order of stationary targets to be used as a reference with priority among a plurality of targets detected by the target detection unit 40a is determined as a predetermined criterion. Here, the stationary target with the first priority as a reference is the warning block 30b (see FIG. 6). The stationary target with the second priority as a reference is the utility pole 31 (see FIG. 3, etc.). The stationary target with the third priority as a reference is the other targets. Below, a method for calculating the user's walking speed when the warning block 30b is used as a reference will be described with reference to FIGS. 6 and 7.

[0074] 6 shows an image 22 captured by the imaging unit 20. Here, there are multiple guide blocks 30a arranged in a row ahead of the user (in the direction of travel), and multiple warning blocks 30b are placed close to the front ends of the guide blocks 30a. On the right side (+X side) of the row formed by the group of multiple guide blocks 30a, there are multiple stationary targets 34 and 35, and on the front side (-Y side) of the warning blocks 30b, there are multiple vehicles 36.

[0075] When the target detection unit 40a recognizes the guide block 30a and the warning block 30b based on the image 22 captured by the imaging unit 20, it sets bounding boxes X1 and X3 with sides in the horizontal and vertical directions for each target (e.g., targets 30a and 30b). Note that only the bounding boxes X1 and X3 of the guide block 30a and the warning block 30b are shown in Figs. 6 and 7.

[0076] The bounding box detection unit 40a1 detects the set bounding boxes X1 and X3, and obtains the coordinates of each vertex of each of the bounding boxes X1 and X3.

[0077] The walking speed calculation unit 40b calculates the user's walking speed based on the warning blocks 30b. Specifically, in the image 22 shown in FIG. 6, there are ten guide blocks 30a located closer to the user than the warning blocks 30b. Therefore, the walking speed calculation unit 40b performs image processing (image analysis) on the image 22 to derive "10" as the number of guide blocks 30a located closer to the user than the reference stationary target (warning block 30b). At this time, the walking speed calculation unit 40b stores the derived number in the guide block number storage area 40d of the RAM. The number of guide blocks 30a can be derived, for example, based on the XY coordinates of each vertex of the bounding box X3 of each warning block 30b and the XY coordinates of each vertex of the bounding box X1 of each guide block 30a.

[0078] FIG. 7 shows an image 22 captured by the imaging unit 20 in the next cycle (one second after) of FIG. 6. Similar to FIG. 6, the image 22 includes multiple warning blocks 30b. However, due to the user's movement, the number of guide blocks 30a closer to the user than the warning blocks 30b has decreased to seven. Therefore, the walking speed calculation unit 40b derives "7" as the number of guide blocks 30a closer to the user than the reference stationary target (warning block 30b). Here, the walking speed calculation unit 40b calculates the user's walking speed using the same method as described in the above embodiment, based on the change (3) between the number of guide blocks 30a (7) and the previously derived number of guide blocks 30a (10).

[0079] The above is the method for calculating the walking speed of the user based on the warning block 30b. Next, the calculation process for the walking speed of the user when there are multiple stationary targets in the image captured by the imaging unit 20 will be described with reference to Fig. 8. Fig. 8 is a flowchart showing an example of the walking speed calculation process of the movement support device 1 according to this example.

[0080] In step S10, the imaging unit 20 captures an image of the area in front of the user wearing the mobility assistance device 1. Image data representing the image is sent to the control unit .

[0081] Next, in step S11, the target detection unit 40a performs image processing on the image data acquired by the imaging unit 20 to detect the targets 30a, 30b, 34-36 in the image 22. At this time, the target detection unit 40a sets bounding boxes X1 and X3 for the targets 30a, 30b, 34-36, respectively.

[0082] Next, in step S12, the target detection unit 40a determines whether or not the warning block 30b exists among the detected targets 30a, 30b, 34 to 36.

[0083] In step S12, if the target detection unit 40a determines that the warning block 30b exists (YES in step S12), the walking speed calculation unit 40b calculates the user's walking speed and ends the process (step S13). At this time, the walking speed calculation unit 40b can calculate the user's walking speed by the above-mentioned method, using the warning block 30b as the reference stationary target.

[0084] In step S12, if it is determined that the warning block 30b does not exist (NO in step S12), the target detection unit 40a determines whether or not a utility pole 31 (see FIG. 3) exists among the detected targets 30a, 30b, 34 to 36 (step S14).

[0085] In step S14, if it is determined that the utility pole 31 (see FIG. 3) is present among the targets 30a, 30b, 34 to 36 detected by the target detection unit 40a (YES in step S14), the walking speed calculation unit 40b calculates the user's walking speed and ends the process (step S15). At this time, the walking speed calculation unit 40b can calculate the user's walking speed in the same manner as the process shown in FIG.

[0086] In step S14, if it is determined that the utility pole 31 does not exist (NO in step S14), the target detection unit 40a determines whether or not there is another target among the detected targets 30a, 30b, 34 to 36 (step S16). The target at this time may be not only a stationary target but also a person, a vehicle, etc.

[0087] In step S16, if the target detection unit 40a determines that there is no other target (NO in step S16), the process ends without detecting the user's walking speed.

[0088] In step S16, if it is determined that another target exists among the targets detected by the target detection unit 40a (YES in step S16), the target detection unit 40a determines whether the target is stationary or not (step S17).

[0089] In step S17, if the target detection unit 40a determines that the other target is not stationary (NO in step S17), the process ends without calculating the user's walking speed.

[0090] In step S17, if the target detection unit 40a determines that the other target is stationary (YES in step S17), the walking speed calculation unit 40b calculates the user's walking speed using the other target as a reference, and ends the process (step S18). Note that in step S16, if there are multiple other targets, one target may be set as a reference from among these multiple targets based on a predetermined priority order.

[0091] The above is the movement support device 1 according to the modified example of this embodiment. Next, the effects achieved by the movement support device 1 of this example will be described below.

[0092] The above-described mobility support device 1 has the following characteristic configuration: Therefore, the mobility support device 1 can achieve the following unique effects that cannot be achieved by conventional techniques.

[0093] In this example, the mobility support device 1 selects one of the stationary targets based on a predetermined criterion, provided that there are multiple stationary targets in the image 22, and calculates the walking speed based on the change per unit time in the number of guide blocks 30a located closest to the user, using the stationary target as a reference.

[0094] In this way, when there are multiple stationary targets, the mobility support device 1 of this example can calculate the user's walking speed based on the change per unit time in the number of guide blocks 30a located closest to the user, using one stationary target selected based on a predetermined criterion as the reference.

[0095] Furthermore, the travel assistance device 1 of this example employs the alarm block 30b as one of the stationary targets that serve as a reference.

[0096] The warning blocks 30b, together with the guide blocks 30a, form the braille blocks and are stationary targets that are likely to be included in the captured image. Therefore, by doing so, the mobility support device 1 of this example can stably calculate the user's walking speed based on the stationary targets that stably exist in the image.

[0097] Furthermore, in the travel assistance device 1 of this example, on the condition that the target detection unit 40a detects a plurality of targets including the warning block 30b, the warning block 30b is selected as the reference stationary target (the stationary target of highest priority).

[0098] The warning blocks 30b, together with the guide blocks 30a, form a braille block and are provided close to the guide blocks 30a. Therefore, by using the warning blocks 30b as a predetermined stationary target serving as a reference, the mobility support device 1 of this example can easily derive the number of guide blocks 30a that are located closer to the user than the stationary target serving as the reference.

[0099] The mobility support device 1 according to this example may also have the same characteristic configuration as the mobility support device 1 according to the above-described embodiment. Specifically, the mobility support device 1 may have some or all of the characteristic configurations according to (b) to (g) above. By adopting such a configuration, the mobility support device 1 can achieve the same effects as those described in (b) to (g) above.

[0100] The above are the effects of the mobility support device 1 according to the embodiment of the present invention and the mobility support device 1 according to its modified examples. However, the mobility support device 1 of the present invention is not limited to the above-described embodiment and modified examples, and various modifications can be made.

[0101] For example, the method for deriving the number of guide blocks 30a located closer to the user than the reference stationary target is not limited to the above-described embodiment or modification. For example, the mobility support device 1 of the present invention can use a virtual line passing through a predetermined location of a predetermined stationary target serving as a reference and a specific location of the guide block 30a closest to the predetermined stationary target in an image captured by the imaging unit 20 as a reference, and derive the number of guide blocks 30a as the number of guide blocks 30a located closer to the user than the virtual line. In this case, the specific location of the guide block 30a can be, for example, the reference point S derived by the reference point derivation unit 40a2. Similarly, the predetermined location of the reference stationary target can be determined based on a bounding box surrounding the stationary target.

[0102] In this way, even if the guide blocks 30a are arranged at a distance from a predetermined stationary target serving as a reference, the mobility support device 1 of the present invention can easily derive the number of guide blocks 30a (the number of guide blocks 30a that are located closer to the user than the predetermined stationary target) based on the virtual straight line. That is, even if the guide blocks 30a are arranged at a distance from a predetermined stationary target serving as a reference, the mobility support device 1 of the present invention can easily calculate the walking speed of the user based on the virtual straight line.

[0103] Furthermore, in the mobility support device 1 of the present invention, if there are multiple stationary targets in the image, it is also possible to determine the number of guide blocks 30a by using each of the multiple stationary targets as a specific stationary target that serves as a reference when calculating walking speed.

[0104] With this configuration, the mobility support device 1 of the present invention performs a process for determining the number of guide blocks that are closer to the user than the stationary target for each stationary target, and can calculate the user's running speed based on the results of this process. For example, the mobility support device 1 of the present invention performs a process for determining the number of guide blocks 30a that are closer to the user than the stationary target separately for each detected stationary target, derives the average of the numbers thus obtained as the number of guide blocks 30a, and can calculate the user's running speed based on the results of this process.

[0105] Furthermore, the mobility support device 1 of the present invention can derive the number of guide blocks 30a by using the stationary target located farthest from the user as the predetermined stationary target that serves as the basis for calculating the user's walking speed, provided that there are multiple stationary targets in the image.

[0106] In this way, the mobility assistance device 1 of the present invention can reduce the frequency of switching between predetermined stationary targets that are used as a reference for calculating the user's walking speed.

[0107] In addition, the mobility assistance control unit 40c of the present invention can also determine the timing of notification control based on the user's walking speed calculated by the walking speed calculation unit 40b and the arrangement of the braille blocks formed by the guide blocks 30a and the warning blocks 30b.

[0108] Examples of the arrangement of tactile paving blocks include those that form forks, crossroads, and T-junctions. These correspond to locations with heavy pedestrian traffic. Therefore, with this configuration, the mobility support device 1 of the present invention can determine the timing of notification control according to not only the running speed but also the arrangement of the tactile paving blocks. As an example of determining the timing of notification control based on the arrangement of the tactile paving blocks, for example, when the arrangement of the tactile paving blocks corresponds to a location with heavy pedestrian traffic, even if the walking speed is slower than the predetermined value, the timing of executing notification control can be advanced by setting the threshold value (second threshold: 5 [m]) for when the walking speed is equal to or greater than the predetermined value.

[0109] The travel assistance control unit 40c can also correct the timing of executing notification control based on the amount of change in the walking speed calculated by the walking speed calculation unit 40b over a predetermined period of time.

[0110] If the calculated walking speed increases in a short period of time, it can be assumed that the user has entered a downward slope. On the other hand, if the calculated walking speed decreases in a short period of time, it can be assumed that the user has entered an upward slope. Therefore, with this configuration, the mobility assistance device 1 of the present invention can correct the notification control at a timing appropriate to the situation depending on the amount of change in walking speed. For example, the timing of executing the notification control can be corrected as follows. That is, when the user enters an upward slope, suppose there is a pedestrian traveling on the upward slope in the opposite direction. In this case, the traveling speed of the oncoming pedestrian, who acts as an obstacle, is considered to be increasing in contrast to the user's traveling speed. Therefore, in such a case, even if the user's running speed is slower than a predetermined value, it is advisable to correct the notification control so that it is executed at the same timing (second threshold) as when the user's running speed is fast (when the walking speed is equal to or greater than a predetermined value).

[0111] The above are embodiments and variations of the mobility support device 1 according to the present invention, but the present invention is not limited to the examples given in the above-mentioned embodiments and variations, and it will be readily apparent to those skilled in the art that other embodiments are possible within the scope of the claims in accordance with the teachings and spirit of the present invention. [Industrial Applicability]

[0112] The present invention can be suitably used in all types of mobility assistance devices that assist users in moving around. [Explanation of symbols]

[0113] 1:Mobility support device 20: Imaging unit 30a: Guidance block 30b: Warning block (prescribed stationary target) 31: Telephone pole (prescribed stationary target) 40a: Target detection unit 40b: Walking speed calculation unit 40c: Mobility support control unit

Claims

1. A mobility assistance device worn on at least one of the user's shoulders and neck, an imaging unit that images a front side of the user; a target detection unit that detects a target in an image captured by the imaging unit based on the image; a walking speed calculation unit that calculates a walking speed of the user based on a guide block among the targets detected by the target detection unit and a predetermined stationary target, The walking speed calculation unit calculates the walking speed based on a change per unit time in the number of guide blocks that are located closer to the user than the predetermined stationary target that serves as a reference in the image.

2. The mobility support device according to claim 1, characterized in that the number of guide blocks is determined as the number of guide blocks that are located closer to the user than a virtual line that passes through a predetermined location of the predetermined stationary target and a specific location of the guide block that is closest to the predetermined stationary target in the image.

3. a travel assistance control unit that executes travel assistance control including notification control that notifies the driver that an obstacle has been detected when the target detection unit detects the obstacle; 3. The mobility assistance device according to claim 1, wherein the mobility assistance control unit executes the notification control at an earlier timing when the walking speed calculated by the walking speed calculation unit is faster than a predetermined value than when the walking speed is slower than the predetermined value.

Images