Wearable device and pedestrian guidance method using same

Abstract

A pedestrian guidance method according to an embodiment of the present invention comprises the steps of: acquiring a front image from a camera of a wearable device; acquiring a user's gait information from an inertial sensor of the wearable device; configuring a guide area on the basis of at least one of the front image and the gait information; analyzing a risk in the front image; and outputting a warning if the analyzed risk occurs in the guide area.

Description

Wearable device and walking guidance method using the same

[0001] The present invention relates to a wearable device that provides a walking guidance method for a visually impaired person.

[0002] Because visually impaired people have reduced awareness of their surroundings, they are more likely to encounter accidents, such as colliding with obstacles or entering dangerous spaces.

[0003] In particular, a walking assistance device for the visually impaired has been introduced to help the visually impaired avoid obstacles and move along a safe path. However, because the current location is identified and the movement path is guided by relying on GPS signals, there was a problem that the movement path was subject to significant errors and injuries could occur due to contact with surrounding obstacles when walking on narrow sidewalks or when obstacles were scattered around.

[0004] Conventional camera-based walking assistance devices for the visually impaired assume the forward direction of the camera is the forward direction of the walking direction. However, for visually impaired individuals, the direction of their heads is often not forward, resulting in the analysis of images from the wrong direction.

[0005] Additionally, because the camera provides guidance on obstacles in the entire image or a wide range, there was a problem in that a warning was issued even for obstacles that did not actually pose a threat to walking.

[0006] The invention aims to provide a wearable device that provides a method for measuring and guiding the risk of an obstacle that may be a threat in the walking direction.

[0007] In order to achieve the above object, the walking guidance method of the wearable device of the present invention includes the steps of: obtaining a front image from a camera of the wearable device; obtaining walking information of the user from an inertial sensor of the wearable device; setting a guidance area based on at least one of the front image and the walking information; analyzing a risk level within the front image; and outputting a warning when the analyzed risk level occurs within the guidance area.

[0008] According to an embodiment, the method includes: extracting a walking speed of a wearable device user; recognizing a walking direction of the wearable device user; and recognizing a gaze direction of the wearable device user.

[0009] According to an embodiment, the step of setting a guidance area based on at least one of the forward image and walking information includes the step of setting a guidance radius based on the walking speed of the user; and the step of setting a guidance area in an area corresponding to the walking direction among the set guidance radius.

[0010] In an embodiment, the step of setting the guidance radius based on the walking speed of the user includes the step of setting the guidance radius to be smaller when the walking speed of the user slows down; and the step of setting the guidance radius to be larger when the walking speed of the user increases.

[0011] In an embodiment, the step of setting a guidance area based on at least one of the forward image and the walking information further includes the step of determining whether an image corresponding to the walking direction is acquired within the forward image when the walking direction and the viewing direction are different; and the step of correcting the position of the guidance area in the walking direction based on the difference between the walking direction and the viewing direction when an image corresponding to the walking direction is acquired within the forward image.

[0012] In an embodiment, the step of analyzing the risk level within the forward image includes: a step of analyzing the type of road surface present within the forward image; a step of recognizing the type and movement of an object present within the forward image; a step of analyzing the risk level within the guidance area based on the type of the recognized road surface; and a step of analyzing the risk level within the guidance area based on the type of the recognized object.

[0013] According to an embodiment, the step of analyzing the type of road surface existing within the guidance area and analyzing the risk level includes a step of analyzing the road surface as at least one of a safe road surface, a caution road surface, a safe road surface depending on the situation, and an impassable road surface corresponding to the type of road surface.

[0014] According to an embodiment, the method includes: analyzing the level of risk within the guidance area based on the type of the recognized object; determining the level of risk based on the direction of the moving object when the recognized object is a moving object; determining whether the object is approaching the wearable device based on the direction of the moving object; and determining the recognized object as a dangerous object when the object is approaching the wearable device.

[0015] According to an embodiment, when the analyzed risk occurs within the guidance area, the step of providing a warning to the user includes the step of dividing the guidance area into a short-range area, a medium-range area, and a long-range area according to distance; the step of dividing the guidance area into a left area, a center area, and a right area according to direction; and the step of outputting a preset warning corresponding to the divided area.

[0016] The effects of the wearable device according to the present invention are described as follows.

[0017] According to at least one embodiment of the present invention, a wearable device provides the minimum necessary warnings and guidance using information about the road surface and objects in the walking direction recognized by the wearable device. This has the advantage of preventing accidents while walking by visually impaired people in advance, thereby enabling them to move more safely.

[0018] The effects that can be obtained from the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by a person having ordinary skill in the art to which the present invention belongs from the description below.

[0019] FIG. 1 is a block diagram illustrating a wearable device according to one embodiment of the present invention.

[0020] FIG. 2 is a drawing for explaining a method for setting a guidance area according to one embodiment of the present invention.

[0021] FIG. 3 and FIG. 4 are drawings for explaining a method for correcting a guidance area according to a line of sight direction according to one embodiment of the present invention.

[0022] Figure 5 is a drawing for explaining road surface risk according to one embodiment of the present invention.

[0023] Figure 6 is a drawing for explaining the object risk according to one embodiment of the present invention.

[0024] FIG. 7 is a drawing for explaining provision of a warning according to a guidance area according to one embodiment of the present invention.

[0025] FIG. 8 is a flowchart illustrating a walking guidance method of a wearable device according to one embodiment of the present invention.

[0026] Hereinafter, the embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Regardless of the drawing numbers, identical or similar components will be given the same reference numbers, and redundant descriptions thereof will be omitted. The suffixes "module" and "part" used for components in the following description are assigned or used interchangeably only for the convenience of writing the specification, and do not in themselves have distinct meanings or roles. In addition, when describing the embodiments disclosed in this specification, if it is determined that a specific description of a related known technology may obscure the gist of the embodiments disclosed in this specification, a detailed description thereof will be omitted. In addition, the attached drawings are only intended to facilitate easy understanding of the embodiments disclosed in this specification, and the technical ideas disclosed in this specification are not limited by the attached drawings, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and technical scope of the present invention.

[0027] The following examples of the present invention are intended only to illustrate the invention and are not intended to limit or restrict the scope of the invention. Anything readily inferred by a specialist in the technical field of the invention from the detailed description and examples of the invention is construed as falling within the scope of the invention.

[0028] The above detailed description should not be construed as limiting in any respect, but rather as illustrative. The scope of the present invention should be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present invention are intended to be included within the scope of the present invention.

[0029] ESG stands for Environmental, Social, and Governance. "Environmental" refers to a company's impact on the environment during its business operations. "Social" refers to whether a company is fulfilling its social responsibilities. It's often associated with human rights and community contributions. It encompasses worker treatment, respect for diversity, and the company's impact on the local communities and institutions it engages with. Finally, "Governance" can be seen as a measure of management transparency. It determines whether decision-making processes, corporate structure, personnel, and management policies are democratically and responsibly managed.

[0030] The wearable device of the present invention and the walking guidance method using the same can, in particular, provide psychological stability to visually impaired people who walk independently by informing them of the road surface and obstacles, thereby eliminating their fear of the unseen ahead, improving safety, and providing accessibility, thereby performing a social role.

[0031] FIG. 1 is a block diagram illustrating a wearable device according to one embodiment of the present invention.

[0032] Referring to FIG. 1, a wearable device (100) according to an embodiment of the present invention may include a camera (110), an inertial sensor (120), a walking direction recognition unit (130), a walking speed extraction unit (140), a guidance area setting unit (150), a road surface analysis unit (160), an object analysis unit (170), a risk analysis unit (180), and an output unit (190).

[0033] The camera (110) may be a wide-angle camera facing forward. The camera (110) can capture a front image of the user.

[0034] The inertial sensor (120) can measure movement in real time using a 9-axis sensor (Accel, Gyro, Magnetic) built into the wearable device. Through this, the inertial sensor (120) can obtain gait information of the wearable device user.

[0035] The walking direction recognition unit (130) can recognize the user's walking direction and gaze direction using an image or inertial sensor (120). The walking direction recognition unit (130) can calculate the difference between the walking direction and the gaze direction. In this case, the gaze direction may be the direction of the wearable device (100), and specifically, the direction of the camera (110) placed on the wearable device.

[0036] The walking speed extraction unit (140) can estimate the user's walking speed using the inertial sensor (120). That is, the walking speed extraction unit (140) can extract the walking speed of the wearable device user.

[0037] The guidance area setting unit (150) can set the guidance radius and guidance area using the information generated by the walking direction recognition unit (130) and walking speed extraction unit (140) described above. The guidance area setting unit (150) can set the guidance area based on at least one of the front image and walking information. That is, the guidance area setting unit (150) sets the guidance radius to be smaller when the user's walking speed slows down, and sets the guidance radius to be larger when the user's walking speed increases. This will be described later with reference to FIG. 2.

[0038] The guidance area setting unit (150) determines whether an image corresponding to the walking direction is acquired within the forward image when the walking direction and the viewing direction are different, and when an image corresponding to the walking direction is acquired within the forward image, the position of the guidance area can be corrected in the walking direction based on the difference between the walking direction and the viewing direction. This will be described later with reference to FIGS. 3 and 4.

[0039] The road surface analysis unit (160) can estimate the type of road surface using information received from the video.

[0040] The object analysis unit (170) can estimate the type of object based on information received from the image. The object analysis unit (170) can estimate whether the object is moving, and if so, in what direction and at what speed.

[0041] The risk analysis unit (180) can analyze the risk within the guidance area based on the type of road surface recognized by the road surface analysis unit (160). The risk analysis unit (180) can analyze the risk within the guidance area based on the type of object recognized by the object analysis unit (170). The risk analysis unit (180) analyzes the risk within the guidance area by comprehensively considering whether the current road surface is walkable and whether there is an object ahead or an object is approaching. This will be described later with reference to FIGS. 5 to 7.

[0042] The output unit (190) can provide a warning to the user based on the risk level analyzed by the risk analysis unit (180). The output unit (190) can output a warning if the analyzed risk level occurs within the guidance area. The output unit (190) can provide a warning to the user through at least one of sound and vibration. This will be described later in FIG. 8.

[0043] FIG. 2 is a drawing for explaining a method for setting a guidance area according to one embodiment of the present invention.

[0044] Referring to FIG. 2, the wearable device (100) can set the guidance distance (d) and guidance area (210) based on the body information of the user (200).

[0045] As illustrated in FIG. 2(a), the wearable device (100) can determine a height (h) lowered by a preset height from the height of the user (200) as the height at which the camera of the wearable device (100) is positioned. In addition, the wearable device (100) can set a guidance distance (d) based on the determined position of the camera and the angle (θ) formed between the camera and the road surface.

[0046] Referring to FIG. 2(b), the wearable device (100) can set a guidance radius (220) based on the guidance distance (d). At this time, the wearable device (100) can detect the walking speed of the user (200) through a location tracking device such as GPS or dead reckoning. In addition, the wearable device (100) can set the guidance radius (220) according to the walking speed of the user (200).

[0047] The wearable device (100) can set a short guidance radius (220) when the user's (200) walking speed is slow, and can set a long guidance radius (220) when the user's (200) walking speed is fast.

[0048] For example, the guidance radius (220) may be set to a distance that can be traveled in 5 seconds based on the speed of the user (200). Accordingly, if the user (200) walks slowly and moves at 3 km / h, the guidance radius (220) may be set to 4 m. If the user (200) walks quickly and moves at 5 km / h, the guidance radius (220) may be set to 7 m.

[0049] Referring to Fig. 2(c), in order to prevent the phenomenon of near and far distances being distorted due to the vanishing point effect when the wearable device (100) acquires data through a camera, a guidance area (210) can be set by assuming a certain road width.

[0050] The guidance area (210) captured by the camera of the wearable device (100) may appear to be longer in the shape of an isosceles rectangle at a distance (dx1) from the user (200) than at a distance (dx2) from the user (200) due to the law of circular motion. However, the wearable device (100) may set the guidance area (210) in the shape of an isosceles rectangle in the direction of travel of the user (200) within the guidance radius (220) by taking into account the characteristics of a road that generally has a constant width within the front image.

[0051] FIG. 3 and FIG. 4 are drawings for explaining a method for correcting a guidance area according to a line of sight direction according to one embodiment of the present invention.

[0052] Referring to FIGS. 3 and 4, the wearable device (100) can set a guidance area (210) within a walking path (310) when the walking direction and the gaze direction of the user (200) are identical.

[0053] In addition, the wearable device (100) can calculate the difference between the walking direction and the viewing direction when the walking direction and the viewing direction of the user (200) do not match. To this end, the wearable device (100) can obtain the difference between the walking direction and the viewing direction using techniques such as dead reckoning or image analysis.

[0054] When a walking path (310) is located within the camera's FoV (320), the wearable device (100) can perform correction so that the guidance area (210) matches the walking direction. To this end, the wearable device (100) can perform correction equal to the difference between the walking direction and the camera direction in the front image.

[0055] Referring to FIG. 4(a), the wearable device (100) can set the area in front of the camera in the front image as a guidance area (210) when the walking direction and the viewing direction of the user (200) do not match. However, when the walking direction and the viewing direction do not match, the guidance area (210) in front of the camera includes an area other than the walking path (310).

[0056] As shown in Fig. 4(b), the wearable device (100) can perform correction so that the guidance area (210) matches the walking path (310). The wearable device (100) can correct the gaze direction so that the guidance area (210) is located in the walking path (310) within the front image.

[0057] Meanwhile, if the difference between the walking direction and the viewing direction is greater than a preset value, and if the walking path (310) corresponding to the walking direction cannot be acquired within the forward image, the wearable device (100) may stop providing the guidance area (210) to the user (200). Thereafter, the wearable device (100) may output a warning regarding the inability to provide forward guidance to the user (200).

[0058] Figure 5 is a drawing for explaining road surface risk according to one embodiment of the present invention.

[0059] Referring to FIGS. 5(a) to 5(c), the wearable device (100) can determine the type of road surface from the forward image. The wearable device (100) can provide guidance according to the level of risk corresponding to the determined type of road surface.

[0060] For example, if the road surface recognized in the front image is a sidewalk (510) or a Braille block (520), the wearable device (100) can determine the type of road surface as a safe road surface.

[0061] If the road surface recognized in the front image is a bicycle road or a back road, the wearable device (100) can determine the type of road surface as a road surface requiring caution.

[0062] If the road surface recognized in the front image is a crosswalk (530), the wearable device (100) may determine that the road surface is safe depending on the situation, as additional judgment is required depending on the traffic light.

[0063] If the road surface recognized in the front image is a road (540), the wearable device (100) can determine the type of road surface as a dangerous road surface.

[0064] If the road surface recognized in the front image is a flower bed (550), the wearable device (100) can determine the type of road surface as an unwalkable road surface.

[0065] The wearable device (100) can determine the type of road surface by paying attention to changes in the road surface when the road surface recognized in the front image is a transition (start / end) of stairs, escalators, etc.

[0066] The wearable device (100) can determine that an area that is not recognized as a road surface is an area where walking is impossible.

[0067] Meanwhile, the wearable device (100) can recognize an object recognized through deep learning and determine it as an obstacle. For example, if the object recognized in the front image is a motorcycle (560), the wearable device (100) can determine it as an obstacle.

[0068] Figure 6 is a drawing for explaining the object risk according to one embodiment of the present invention.

[0069] Referring to FIG. 6, the wearable device (100) can analyze the direction and speed information of a moving object (610) recognized through deep learning to determine the risk of each obstacle. To this end, the wearable device (100) can monitor a range wider than the guidance radius (220).

[0070] The wearable device (100) may generate a warning when a fast-moving object (bicycle, motorcycle, vehicle, etc.) approaches, even if the moving object is outside the guidance radius (220).

[0071] The wearable device (100) may determine that the object is a dangerous object and generate a warning if the direction of movement of the object is the direction in which the user (200) is approaching the location.

[0072] The wearable device (100) can determine that an object is not dangerous if the direction of movement of the object is away from the location of the user (200).

[0073] FIG. 7 is a drawing for explaining provision of a warning according to a guidance area according to one embodiment of the present invention.

[0074] Referring to FIG. 7, when there is an obstacle, the wearable device (100) can output a warning using a beep sound or vibration haptic, etc.

[0075] The wearable device (100) can output a warning by dividing the distance and direction in response to the location of the obstacle. At this time, the distance of the obstacle can be divided into areas corresponding to short distance, medium distance, and long distance in order of proximity within the guidance area (210). In addition, the direction of the obstacle can be divided into areas corresponding to the left, center, and right of the guidance area (210). The wearable device (100) can divide the location of the obstacle into nine areas within the guidance area (210).

[0076] The wearable device (100) can output a beep sound at a high frequency and at a short interval when the distance to the obstacle is short.

[0077] The wearable device (100) can output a beep sound at a medium frequency and medium interval when the distance to the obstacle is medium.

[0078] The wearable device (100) can output a beep sound at a low frequency and at a long interval when the distance to the obstacle is long.

[0079] The wearable device (100) can output a beep sound through a speaker located on the left side when the direction of the obstacle is to the left.

[0080] The wearable device (100) can output a beep sound through a speaker located on the right side when the direction of the obstacle is to the right.

[0081] The wearable device (100) can output a beep sound simultaneously through speakers located on the left and right sides when the direction of the obstacle is central.

[0082] FIG. 8 is a flowchart illustrating a walking guidance method of a wearable device according to one embodiment of the present invention.

[0083] Referring to FIG. 8, the wearable device (100) can receive a front image from a camera (S810). Thereafter, the wearable device (110) can acquire the user's walking information. The user's walking information may include the wearable device user's walking speed, walking direction, and gaze direction.

[0084] The wearable device (100) can calculate the difference between the walking direction and the viewing direction (S820).

[0085] The wearable device (100) can determine whether correction is possible within the camera's FoV (320) (S830). That is, if the walking direction and the viewing direction are different, the wearable device (100) can determine whether an image corresponding to the walking direction is acquired within the forward image.

[0086] The wearable device (100) can set a guidance area (210) corrected in the walking direction if correction is possible within the camera's FoV (320) (S840). Accordingly, when the wearable device acquires an image corresponding to the walking direction within the front image, the position of the guidance area can be corrected in the walking direction based on the difference between the walking direction and the viewing direction.

[0087] If the wearable device (100) is capable of correction within the camera's FoV (320), a warning may be output (S845) that the guidance area (210) cannot be provided.

[0088] Meanwhile, when the guidance area (210) is set, the wearable device (100) can perform road surface risk analysis within the guidance area (210) (S850).

[0089] After analyzing the road surface risk, the wearable device (100) can perform an analysis of the risk of objects in the input image (S860).

[0090] The wearable device (100) can determine whether a dangerous situation has occurred within the guidance area (210) based on the road surface risk level and object risk level (S870). To this end, the wearable device (100) can analyze the risk level within the guidance area based on the type of recognized road surface, and can analyze the risk level within the guidance area based on the type of recognized object.

[0091] The wearable device (100) can output a warning / guidance when a dangerous situation occurs within the guidance area (210) (S880). At this time, the wearable device (100) can divide the guidance area into a short-range area, a medium-range area, and a long-range area according to distance, and can divide the guidance area into a left area, a center area, and a right area according to direction, and output a preset warning corresponding to the divided area.

[0092] The embodiments have been described in terms of methods and / or devices, and the descriptions of methods and devices may be applied complementarily.

[0093] For the convenience of explanation, each drawing has been described separately, but it is also possible to design a new embodiment by combining the embodiments described in each drawing. In addition, designing a computer-readable recording medium having a program recorded thereon for executing the previously described embodiments, as needed by a person skilled in the art, also falls within the scope of the embodiments. The devices and methods according to the embodiments are not limited to the configurations and methods of the embodiments described above, but the embodiments may be configured by selectively combining all or part of the embodiments so that various modifications can be made. Although preferred embodiments of the embodiments have been illustrated and described, the embodiments are not limited to the specific embodiments described above, and various modifications can be made by a person skilled in the art to which the present invention pertains without departing from the gist of the embodiments claimed in the claims, and such modifications should not be understood individually from the technical idea or prospect of the embodiments.

[0094] The various components of the devices of the embodiments may be implemented by hardware, software, firmware, or a combination thereof. The various components of the embodiments may be implemented by a single chip, for example, a single hardware circuit. According to embodiments, the components according to the embodiments may be implemented by separate chips. According to embodiments, at least one of the components of the devices of the embodiments may be configured with one or more processors capable of executing one or more programs, and the one or more programs may perform, or include instructions for performing, one or more of the operations / methods according to the embodiments. The executable instructions for performing the methods / operations of the devices of the embodiments may be stored in non-transitory CRMs or other computer program products configured to be executed by one or more processors, or may be stored in temporary CRMs or other computer program products configured to be executed by one or more processors. In addition, the memory according to the embodiments may be used as a concept including not only volatile memory (e.g., RAM, etc.), but also non-volatile memory, flash memory, PROM, etc. Additionally, it may include implementations in the form of carrier waves, such as transmissions via the Internet. Furthermore, processor-readable recording media may be distributed across network-connected computer systems, allowing processor-readable code to be stored and executed in a distributed manner.

[0095] In this document, “ / ” and “,” are interpreted as “and / or”. For example, “A / B” is interpreted as “A and / or B”, and “A, B” is interpreted as “A and / or B”. Additionally, “A / B / C” means “at least one of A, B, and / or C”. Also, “A, B, C” means “at least one of A, B, and / or C”. Additionally, “or” in this document is interpreted as “and / or”. For example, “A or B” can mean 1) “A” only, 2) “B” only, or 3) “A and B”. In other words, “or” in this document can mean “additionally or alternatively”.

[0096] Terms such as "first" and "second" may be used to describe various components of the embodiments. However, the various components according to the embodiments should not be interpreted as limited by these terms. These terms are merely used to distinguish one component from another. For example, a first user input signal may be referred to as a "second user input signal." Similarly, a second user input signal may be referred to as a "first user input signal." The use of these terms should be interpreted as not departing from the scope of the various embodiments. Although "first user input signal" and "second user input signal" are both user input signals, they do not mean the same user input signals unless the context clearly indicates otherwise.

[0097] The terminology used to describe the embodiments is for the purpose of describing particular embodiments and is not intended to be limiting of the embodiments. As used in the description of the embodiments and in the claims, the singular is intended to include the plural unless the context clearly dictates otherwise. The expressions “and / or” are used to mean all possible combinations of terms. The expression “includes” describes the presence of features, numbers, steps, elements, and / or components, but does not mean that additional features, numbers, steps, elements, and / or components are not included. Conditional expressions such as “if” or “when” used to describe the embodiments are not intended to be limited to only optional cases. When a specific condition is satisfied, a related action is performed in response to a specific condition, or a related definition is intended to be interpreted.

[0098] Additionally, the operations according to the embodiments described in this document may be performed by a transceiver device including a memory and / or a processor according to the embodiments. The memory may store programs for processing / controlling the operations according to the embodiments, and the processor may control various operations described in this document. The processor may be referred to as a controller, etc. The operations according to the embodiments may be performed by firmware, software, and / or a combination thereof, and the firmware, software, and / or a combination thereof may be stored in the processor or in the memory.

[0099] Meanwhile, the operations according to the embodiments described above may be performed by a transmitting device and / or a receiving device according to the embodiments. The transmitting / receiving device may include a transmitting / receiving unit for transmitting and receiving media data, a memory for storing instructions (program code, algorithm, flowchart, and / or data) for a process according to the embodiments, and a processor for controlling the operations of the transmitting / receiving device.

[0100] The processor may be referred to as a controller or the like, and may correspond to, for example, hardware, software, and / or a combination thereof. The operations according to the above-described embodiments may be performed by the processor. Furthermore, the processor may be implemented as an encoder / decoder or the like for the operations of the above-described embodiments.

[0101] Various embodiments for implementing the present invention have been described in detail in the previous table of contents.

[0102] The present invention is applicable to technology related to wearable devices, and thus its industrial applicability is recognized.

Claims

1. In a walking guidance method of a wearable device, A step of acquiring a front image from a camera of the wearable device; A step of obtaining user's walking information from the inertial sensor of the wearable device; A step of setting a guidance area based on at least one of the above forward image and walking information; A step of analyzing the risk level within the above forward image; and A pedestrian guidance method including a step of outputting a warning when an analyzed risk level occurs within the above guidance area.

2. In paragraph 1, The step of obtaining the user's walking information from the inertial sensor of the above wearable device is Step of extracting the walking speed of a wearable device user; A step of recognizing the walking direction of the wearable device user; and A walking guidance method comprising a step of recognizing a gaze direction of a user of the wearable device.

3. In paragraph 2, The step of setting a guidance area based on at least one of the above forward image and walking information is A step of setting a guidance radius based on the walking speed of the user; and A walking guidance method including a step of setting a guidance area in an area corresponding to the walking direction within a set guidance radius.

4. In paragraph 3, The step of setting the guidance radius based on the user's walking speed is A step of setting the guidance radius to be smaller when the walking speed of the user slows down; and A walking guidance method including a step of setting the guidance radius to increase as the walking speed of the user increases.

5. In paragraph 3, The step of setting a guidance area based on at least one of the above forward image and walking information is When the above walking direction and the above viewing direction are different, a step of determining whether an image corresponding to the walking direction is acquired within the front image; and A walking guidance method further comprising a step of correcting the position of the guidance area in the walking direction based on the difference between the walking direction and the gaze direction when acquiring an image corresponding to the walking direction within the forward image.

6. In paragraph 1, The step of analyzing the risk within the above forward image is A step of analyzing the type of road surface existing in the above forward image; A step of recognizing the type and movement of an object existing in the above forward image; A step of analyzing the risk level within the guidance area based on the type of the recognized road surface; and A walking guidance method comprising a step of analyzing the level of risk within the guidance area based on the type of the recognized object.

7. In paragraph 6, The step of analyzing the risk level by analyzing the type of road surface existing within the above guidance area is A pedestrian guidance method including a step of analyzing the road surface as at least one of a safe road surface, a caution road surface, a safe road surface depending on the situation, and an impassable road surface in response to the type of the road surface.

8. In paragraph 6, A step of analyzing the risk level within the guidance area based on the type of the recognized object is included. A step of determining the level of risk based on the direction of the moving object, when the recognized object is a moving object; A step of determining whether to approach the wearable device based on the direction of the moving object; and A walking guidance method including a step of determining the recognized object as a dangerous object when the recognized object approaches the wearable device.

9. In paragraph 1, If the risk analyzed above occurs within the above guidance area, the step of providing a warning to the user is as follows: A step of dividing the above guidance area into a short-range area, a medium-range area, and a long-range area according to distance; A step of dividing the above guidance area into a left area, a center area, and a right area according to direction; and A walking guidance method comprising a step of outputting a preset warning corresponding to the above-described separated area.

10. In wearable devices, A camera that captures forward-facing images; An inertial sensor that obtains walking information of a wearable device user; A guidance area setting unit that sets a guidance area based on at least one of the above-mentioned forward image and walking information; A risk analysis unit that analyzes the risk within the above forward image; and A wearable device including an output section that outputs a warning when an analyzed risk level occurs within the above guidance area.

11. In paragraph 10, A walking speed extraction unit for extracting the walking speed of the wearable device user; and A wearable device further comprising a walking direction recognition unit that recognizes a walking direction of a user of the wearable device and recognizes a gaze direction of the user of the wearable device.

12. In paragraph 10, The above guidance area setting section Set the guidance radius based on the user's walking speed, A wearable device characterized by setting a guidance area in an area corresponding to the walking direction within a set guidance radius.

13. In paragraph 12, The above guidance area setting section If the user's walking speed slows down, the guidance radius is set to be smaller. A wearable device characterized in that the guidance radius is set to increase as the walking speed of the user increases.

14. In paragraph 12, The above guidance area setting section If the above walking direction and the above viewing direction are different, it is determined whether an image corresponding to the walking direction is acquired within the above forward image, A wearable device characterized in that, when an image corresponding to the walking direction is acquired within the above forward image, the position of the guidance area is corrected in the walking direction based on the difference between the walking direction and the gaze direction.

15. In paragraph 9, A road surface analysis unit that analyzes the type of road surface existing in the above forward image; It further includes an object analysis unit that recognizes the type and movement of objects existing in the above front image, The above risk analysis department Based on the type of road surface recognized above, the risk level within the guidance area is analyzed, A wearable device characterized by analyzing the level of risk within the guidance area based on the type of the recognized object.

16. In paragraph 15, The above risk analysis department A wearable device characterized in that it analyzes the road surface as at least one of a safe road surface, a caution road surface, a safe road surface depending on the situation, and an impassable road surface in response to the type of the road surface.

17. In paragraph 15, The above risk analysis department If the above recognized object is a moving object, the level of risk is determined based on the direction of the moving object. Based on the direction of the moving object, determine whether it is approaching the wearable device, A wearable device characterized in that, when the recognized object approaches the wearable device, the recognized object is judged to be a dangerous object.

18. In paragraph 10, The above output section The above guidance area is divided into short-range, medium-range, and long-range areas according to distance. The above guidance area is divided into left area, center area, and right area according to direction. A wearable device characterized by outputting a preset warning corresponding to the above-mentioned distinguished area.

Images