KR20220028798A - Pedestrian guidance system and method for the visually impaired on diagonal crosswalk - Google Patents

Abstract

The present invention relates to a system and a method for guiding a walk on a diagonal crosswalk for the visually impaired. A walk guidance method in a user terminal for guiding a walk according to the present invention comprises the steps of: calculating distances corresponding to strength of beacon signals from beacon terminals installed on a plurality of walk signals, respectively; calculating a position of the user terminal using a least square algorithm with respect to the positions of the beacon terminals and the distances corresponding to the positions thereof, respectively; determining a position of a destination beacon terminal of the user with respect to a position of a departure beacon terminal of the user by tracking a route on which the position of the user terminal moves, and determining whether the position of the user terminal leaves a predetermined crosswalk region; and generating an alarm signal if the position of the user terminal leaves the crosswalk region. The present invention can guide a walk safely and rapidly without leaving the crosswalk region.

Description

Pedestrian guidance system and method for the visually impaired on diagonal crosswalk

The present invention relates to a gait guidance system and method for the visually impaired, and more particularly, to a gait guidance system and method for guiding the visually impaired to walk safely even in a diagonal crosswalk.

The conventional crosswalk walking guidance system provided a service to the extent that a beacon terminal function was built into a walking signal (traffic light or sound guidance) to determine whether the visually impaired approached or the starting and ending time of the crosswalk. In addition, the conventional crosswalk walking guidance system provides a technique for walking in a simple crosswalk, and does not provide adequate guidance so that the visually impaired can safely and quickly walk diagonally in a diagonal crosswalk, etc. am.

As a conventional related document, Patent Registration No. 10-2075646 (2020.02.10) identifies and guides the end time of the crossing service for the visually impaired, but guides the location of the visually impaired and the walking path in the diagonal direction In Patent Registration No. 10-1480958 (2015.01.09), the traffic light controller uses the location information (average speed) of the visually impaired through GPS to start a technology to control when the green light of the traffic light turns on However, it is not about the accurate location information of the visually impaired on the crosswalk and the guidance of the walking path through it, and Patent Publication No. 10-2019-0139716 (2019.12.18) does not provide accurate information about the walking path of the visually impaired. Disclosed is a technology for detecting and communicating a traffic light located on a walking path.

Therefore, the present invention has been devised to solve the above problems, and an object of the present invention is to determine the walking path through accurate movement position calculation when a visually impaired person moves at a crosswalk, so that even at a diagonal crosswalk, etc., do not deviate from the crosswalk area An object of the present invention is to provide a gait guidance system and method for the visually impaired that can guide them to walk safely and quickly.

First, to summarize the features of the present invention, the method for guiding a walk in a user terminal for guiding a walk according to an aspect of the present invention for achieving the above object is each beacon from each beacon terminal installed in a plurality of walk signals. calculating each distance corresponding to the signal strength; calculating a location of the user terminal using a least-squares algorithm for each location of the beacon terminal and each distance corresponding to each location; Determine the location of the user's destination beacon terminal with respect to the location of the user's source beacon terminal by tracking the path along which the location of the user terminal moves, and determine whether the location of the user terminal deviates from a predetermined crosswalk area to do; and generating an alarm signal when the location of the user terminal deviates from the crosswalk area.

In the step of calculating each distance, the intensity of each beacon signal received from the beacon terminal is calculated, and a Kalman filter is applied to the calculated intensity to remove noise from each of the respective beacon signals corresponding to the intensity. Calculate the distance of

According to the generation of the alarm signal, the user terminal is recognized by the user as a warning sound, warning message, or vibration.

The beacon terminal and the user terminal may communicate using a short-range wireless communication method (eg, Bluetooth, Zigbee, Wi-Fi, etc.).

을 이용해, 상기 각 비콘 신호의 강도(RSSI)에 대응되는 상기 각각의 거리(d)를 산출하는 단계를 포함하고, 여기서, n은 전파손실도를 반영하는 계수, A는 소정의 오프셋값이다.The step of calculating each distance is in real time,

calculating each distance d corresponding to the intensity (RSSI) of each beacon signal using

The calculating of the respective distances may include, within a service coverage defined by each beacon terminal installed in the plurality of walking signals, the strength of each beacon signal from each of the beacon terminals at a plurality of measurement locations. The method may include storing the corresponding distances in a lookup-table in advance, and determining the respective distances mapped to the strengths of the respective beacon signals by referring to the lookup-table.

From among a plurality of entries most similar to the strength of each beacon signal from the lookup-table, an entry for a measurement location closest to a location received from the GPS module may be selected to determine the respective distances.

The calculating of each distance may include, within a service coverage defined by each beacon terminal installed in the plurality of walking signals, strengths of beacon signals at a plurality of locations and neural network learning for corresponding distances. , maintain in advance a learning model database storing a learning model having a parameter for calculating a corresponding distance to the intensity of an arbitrary beacon signal, refer to the learning model database, and refer to the intensity of each beacon signal input in real time and calculating the respective distances by applying to the corresponding learning model.

In the step of calculating the location of the user terminal, among the location of each of the beacon terminals and the respective distances corresponding to the respective locations, the location determined using a GPS module and the calculated using the least-squares algorithm The location of the user terminal may be calculated using the least-squares algorithm after removing information on one or more corresponding locations and distances so that the difference between the locations of the user terminals is minimized.

The position determined using the GPS module may correspond to an initial GPS position at a point in time at which the position of the user terminal can be calculated using the least-squares algorithm by beacon signals from a plurality of beacon terminals.

In addition, according to another aspect of the present invention, there is provided a method for guiding a walk in a user terminal for guiding a walk of beacon signals at a plurality of locations within the service coverage defined by each beacon terminal installed in a plurality of walk signals. calculating a position of the user terminal through neural network learning with respect to strength and positions of the user terminal; Determine the location of the user's destination beacon terminal with respect to the location of the user's source beacon terminal by tracking the path along which the location of the user terminal moves, and determine whether the location of the user terminal deviates from a predetermined crosswalk area to do; and generating an alarm signal when the location of the user terminal deviates from the crosswalk area.

In addition, the walking guidance system according to another aspect of the present invention, a distance calculator for calculating each distance corresponding to the strength of each beacon signal from each beacon terminal installed in a plurality of walking signal; a location calculator for calculating the location of each of the beacon terminals and the respective distances corresponding to the respective locations, using a least-squares algorithm, for calculating the location of the user terminal equipped with the walking guidance system; Determine the location of the user's destination beacon terminal with respect to the location of the user's source beacon terminal by tracking the path along which the location of the user terminal moves, and determine whether the location of the user terminal deviates from a predetermined crosswalk area a path deviation determination unit; and an alarm unit that generates an alarm signal when the location of the user terminal deviates from the crosswalk area.

The walking guidance system includes a noise filtering unit that calculates the intensity of each beacon signal received from the beacon terminal and outputs the intensity of each beacon signal from which noise is removed by applying a Kalman filter to the calculated intensity to the distance calculator. may include more.

According to the generation of the alarm signal in the alarm unit, the user terminal may be recognized by the user as a warning sound, warning message, or vibration.

을 이용해, 상기 각 비콘 신호의 강도(RSSI)에 대응되는 상기 각각의 거리(d)를 산출하고, 여기서, n은 전파손실도를 반영하는 계수, A는 소정의 오프셋값이다.The distance calculator, in real time,

is used to calculate each distance d corresponding to the intensity (RSSI) of each beacon signal, where n is a coefficient reflecting the degree of propagation loss, and A is a predetermined offset value.

Each distance corresponding to the strength of each beacon signal from each of the beacon terminals in a plurality of locations within the service coverage defined by the respective beacon terminals installed in the plurality of walking signals, the walking guidance system It may further include a lookup-table that is measured and stored in advance, and the distance calculator may determine the respective distances mapped to the strengths of the respective beacon signals with reference to the lookup-table.

The walking guidance system may further include a GPS module, and the position calculator may include, in the lookup-table, a measurement position closest to the position received from the GPS module among a plurality of entries most similar to the strength of each beacon signal. You can determine each distance by selecting an entry for .

The walking guidance system, within the service coverage defined by each of the beacon terminals installed in the plurality of walking signals, through neural network learning for the strengths and corresponding distances of beacon signals at a plurality of locations, any beacon It may further include a learning model database storing a learning model having a parameter for calculating a corresponding distance to the signal strength, wherein the distance calculator refers to the learning model database, and The respective distances may be calculated by applying the intensity to the corresponding learning model.

The walking guidance system may further include a GPS module, and the location calculator may include, among the locations of each of the beacon terminals and the respective distances corresponding to the respective locations, a location positioned using the GPS module and the minimum The location of the user terminal may be calculated using the least squares algorithm after removing information on one or more corresponding locations and distances so that the difference between the locations of the user terminals calculated using the squares algorithm is minimized.

The position determined using the GPS module may correspond to an initial GPS position at a point in time at which the position of the user terminal can be calculated using the least-squares algorithm by beacon signals from a plurality of beacon terminals.

And, in the walking guidance system according to another aspect of the present invention, within the service coverage defined by each beacon terminal installed in a plurality of walking signals, the strength of the beacon signals at a plurality of locations and the locations of the corresponding user terminals a position calculation unit for calculating the position of the user terminal equipped with the walking guidance system through neural network learning; Determine the location of the user's destination beacon terminal relative to the location of the user's source beacon terminal by tracking the path along which the location of the user terminal moves, and determine whether the location of the user terminal deviates from a predetermined crosswalk area a path deviation determination unit; and an alarm unit that generates an alarm signal when the location of the user terminal deviates from the crosswalk area.

According to the gait guidance system and method for the visually impaired according to the present invention, when the visually impaired move at a crosswalk, the walking path is determined through accurate movement position calculation, and guides to walk safely and quickly without departing from the designated crosswalk area even at a diagonal crosswalk can do. In the present invention, the location of the visually impaired walking in a diagonal crosswalk, etc. based on the unique identification code transmitted from the beacons inside a plurality of walking signals installed in the crosswalk through Bluetooth communication from the user terminal (app) and the RSSI strength of the received signal However, by calculating the location more accurately using a lookup-table method or a model through an artificial neural network, it accurately detects the walking path of the visually impaired and makes a warning sound and warning when moving in a diagonal direction and departs from the designated crosswalk area. An alarm can be generated through a comment or vibration to enable safe walking.

BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are included as a part of the detailed description to help the understanding of the present invention, provide embodiments of the present invention and, together with the detailed description, explain the technical spirit of the present invention.
1 is a block diagram of a walking guidance system for the visually impaired according to an embodiment of the present invention.
2 is a flowchart for explaining the operation of the walking guidance system for the visually impaired according to an embodiment of the present invention.
3 is a graph of beacon signal strength (RSSI) over time before and after noise filtering according to an embodiment of the present invention.
4 is a diagram for explaining a first method of calculating a distance between a user terminal and a beacon terminal in the present invention.
5 is a diagram for explaining a second method of calculating a distance between a user terminal and a beacon terminal in the present invention.
6 is a diagram for explaining a third method of calculating a distance between a user terminal and a beacon terminal in the present invention.
7A is an example of positions for beacon terminals B1, B2, ..., Bm with m=8 at an intersection.
7B is a diagram for explaining a relationship between a radio wave directivity of a beacon terminal and a beacon signal strength (RSSI) according to a location of a pedestrian according to an embodiment of the present invention.
7C is a diagram for explaining a method of selecting a radio directional beacon terminal having a small error by calculating a position of a pedestrian using GPS according to the present invention.
8A is a diagram for explaining another embodiment of the calculation of the location of the user terminal in the present invention.
8B is a block diagram of a walking guidance system for the visually impaired according to a second embodiment of the present invention.
9 is a view for explaining a method of determining deviation of the route according to the present invention when a pedestrian passes a crosswalk.
10 is a view for explaining an example of the implementation method of the walking guidance system according to an embodiment of the present invention.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings. In this case, the same components in each drawing are denoted by the same reference numerals as much as possible. In addition, detailed descriptions of already known functions and/or configurations will be omitted. The content disclosed below will focus on parts necessary to understand operations according to various embodiments, and descriptions of elements that may obscure the gist of the description will be omitted. Also, some components in the drawings may be exaggerated, omitted, or schematically illustrated. The size of each component does not fully reflect the actual size, so the contents described herein are not limited by the relative size or spacing of the components drawn in each drawing.

In describing the embodiments of the present invention, if it is determined that the detailed description of the known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted. And, the terms to be described later are terms defined in consideration of functions in the present invention, which may vary according to intentions or customs of users and operators. Therefore, the definition should be made based on the content throughout this specification. The terminology used in the detailed description is for the purpose of describing the embodiments of the present invention only, and should not be limiting in any way. Unless explicitly used otherwise, expressions in the singular include the meaning of the plural. In this description, expressions such as “comprising” or “comprising” are intended to indicate certain features, numbers, steps, acts, elements, some or a combination thereof, one or more other than those described. It should not be construed to exclude the presence or possibility of other features, numbers, steps, acts, elements, or any part or combination thereof.

In addition, terms such as first and second may be used to describe various components, but the components are not limited by the terms, and the terms are for the purpose of distinguishing one component from other components. is used only as

1 is a block diagram of a walking guidance system 100 for the visually impaired according to an embodiment of the present invention.

Referring to FIG. 1 , the walking guidance system 100 for the visually impaired according to an embodiment of the present invention includes a beacon signal receiving unit 110 , a noise filtering unit 120 , a distance calculating unit 130 , a location calculating unit ( 140 ), a path deviation determination unit 150 , and an alarm unit 160 .

Each of the above components of the walking guidance system 100 for the visually impaired according to an embodiment of the present invention that can be mounted on a user terminal is hardware such as a semiconductor processor, software such as an application (app) program, or their It can be implemented as a combination.

The walking guidance system 100 for the visually impaired is mounted on a user terminal for guiding the visually impaired, and the user terminal may be a portable terminal dedicated to walking guidance of the visually impaired, and wireless Internet communication such as WiFi, WiBro, WCDMA, LTE, etc. It may include a wireless terminal such as a smart phone, a wearable device, a tablet PC, and a notebook PC supporting mobile communication.

Hereinafter, the operation of the walking guidance system 100 for the visually impaired according to an embodiment of the present invention will be described in detail with reference to the flowchart of FIG. 2 .

2 is a flowchart for explaining the operation of the walking guidance system 100 for the visually impaired according to an embodiment of the present invention.

Referring to FIG. 2 , first, when a user, such as a visually impaired user, who has a user terminal equipped with the above-mentioned walking guidance system 100 in possession enters around the crosswalk, the beacon signal receiver 110 is a plurality of crosswalks. Receives a beacon signal from each beacon terminal installed in the walking signal (S110).

For example, at an intersection with a crosswalk that allows pedestrians to cross in a diagonal direction, including a crosswalk that allows pedestrians to cross in the opposite direction of the road as shown in FIG. 4, a plurality of pedestrian signals, that is, each crossing of the intersection A pedestrian signal having a controller for informing of whether pedestrians can pass on the sidewalk with a traffic light or sound may be installed. Each walking signal may be provided with a beacon terminal in order to assist the present invention walking guidance. It is preferable that each beacon terminal and the user terminal communicate with a short-range wireless communication method (e.g., Bluetooth, Zigbee, Wi-Fi, etc.), but in some cases, communication with a mobile communication method such as WiBro, WCDMA, LTE is not excluded . Hereinafter, a crosswalk of a four-way intersection as shown in FIG. 4 will be described as an example, but the present invention is not limited thereto. It is possible to operate for guiding walking in the back than when crossing in the .

Each beacon terminal installed in such a plurality of walking signals may transmit a predetermined beacon signal for informing its location including a unique identification code. The beacon signal may include pre-stored information on a corresponding location or location information (GPS information) acquired in real time using a global positioning system (GPS).

When the beacon signal receiving unit 110 receives each beacon signal installed in such walking signals, the noise filtering unit 120 calculates the strength of each beacon signal received from each beacon terminal, and the Kalman filter on the strength Received signal strength indication (RSSI) of each beacon signal from which noise has been removed by applying the same may be output to the distance calculator 130 (S120). Here, the Kalman filter is an example, and other filters such as a band filter for removing noise may be applied.

3 is a graph of beacon signal strength (RSSI) according to time before and after noise filtering in the noise filtering unit 120 according to an embodiment of the present invention.

As shown in (a) of Figure 3, the raw data before applying the Kalman filter to the intensity (RSSI) of each beacon signal (A, B, C, D) received from each beacon terminal contains noise and is stable Since processing is difficult, it is desirable to ensure stable and accurate distance measurement by using the intensity (RSSI) of each beacon signal from which noise is removed by applying a Kalman filter, as shown in FIG. 3B .

The distance calculator 130 calculates each distance corresponding to the strength (RSSI) of each beacon signal from each beacon terminal installed in a plurality of walking signals around the crosswalk (S130).

4 is a view for explaining a first method of calculating the distance between the user terminal 200 and the beacon terminals (B1, B2, B3, B4) in the present invention. Figure 4 is a user terminal 200 equipped with a walking guidance system 100 of the present invention when a user such as a visually impaired user walks a crosswalk in a diagonal direction of a four-way intersection, the user terminal 200 is a plurality of An example of receiving each beacon signal from each of the beacon terminals B1, B2, B3, and B4 installed in the walking signal is shown.

Referring to FIG. 4 , the distance calculator 130 corresponds to the intensity (RSSI) of each beacon signal from each of the beacon terminals B1, B2, B3, and B4 using [Equation 1] in real time. Each distance d (d1, d2, d3, d4) can be calculated. Here, n is a coefficient reflecting the degree of propagation loss that varies according to mountain or urban environments, and A is a predetermined offset value (eg, RSSI value at a distance of 1 m, etc.). In the example of FIG. 4, a point where circles having a radius of each distance d (d1, d2, d3, d4) from each of the beacon terminals B1, B2, B3, and B4 overlap and meet the user terminal 200 ) can be the location of

[Equation 1]

5 is a view for explaining a second method of calculating the distance between the user terminal 200 and the beacon terminals (B1, B2, B3, B4) in the present invention.

5, the walking guidance system 100 of the present invention, each of the beacon terminals (B1, B2, B3, B4) from each distance (d) (d1, d2, d3, d4) to determine It may further include a lookup-table 500 referenced by the distance calculator 130 .

The lookup-table 500 is a service coverage defined by each beacon terminal (B1, B2, B3, B4) installed in a plurality of walking signals such as a crosswalk (area in which beacon signals of all beacon terminals are received) ( 300), each beacon signal from each beacon terminal B1, B2, B3, B4 at a plurality of measurement positions P11,..Pij,..Pmn (eg, several tens cm to several m intervals). It may be information stored in a memory or the like by measuring each distance corresponding to the intensity in advance. 5, each beacon from the user terminal 200 for the case where the strength of the beacon signals respectively received by the beacon terminals B1, B2, B3, and B4 at the measurement location Pij is R1ij, R2ij, R3ij, and R4ij An example of measuring distances d1ij, d2ij, d3ij, and d4ij to the terminals B1, B2, B3, and B4 is shown.

The distance calculator 130 refers to such a lookup-table 500, and each of the distances d1ij, d2ij, d3ij,. .) can be determined. In FIG. 5, although an example of four beacon terminals B1, B2, B3, .. is illustrated, a larger number may be installed. However, the distance calculating unit 130, such a lookup-table 500 of the strength (R1ij, R2ij, R3ij, ..) of each beacon signal of the beacon signals of the beacon terminals giving unnecessary or inaccurate information to the calculation. We can remove the influence to determine the respective distances (d1ij, d2ij, d3ij,..). For example, as shown in FIG. 7B , the beacon terminals B may transmit a beacon signal or the like with radio wave directivity by a directional antenna. Due to such directivity or even if an omni-directional beacon terminal is used, a received RSSI value may be reduced even if a pedestrian is near the beacon terminal B due to a prop installed with a traffic light or a walking signal. Due to this, an error may occur in the calculation of the pedestrian's position, that is, the distances d1ij, d2ij, d3ij, ..) or the position X(x,y) of the user terminal 200 . To this end, if necessary, the walking guidance system 100 of the present invention may further include a GPS module for positioning GPS location information.

For example, when a beacon signal is received from a plurality of beacon terminals B, the distance calculator 130 selectively uses beacon signals of the beacon terminal in which the beacon signal strength (RSSI) value is not disturbed to determine the location. can be calculated For example, in the example of FIG. 7c, when a pedestrian approaches around the beacon terminals B5 and B6, the beacon terminals B3, B5, B6, and B8 of the beacon terminals B3, B5, B6, B8 are obscured by the respective props due to the RSSI The influence is removed.

To this end, the distance calculator 130 refers to the lookup-table 500 as above and refers to the intensity of each beacon signal (R1ij, R2ij, R3ij, ..) and any one (entry) of the plurality of entries most similar to to determine the distance. That is, the distance calculator 130 receives the GPS location information (latitude, longitude, altitude, etc.) of the user terminal 200 from the GPS module, and the corresponding location is the measurement locations P11 in the lookup-table 500 . ,..Pij,..Pmn), the corresponding distance value can be determined by selecting the entry corresponding to the nearest position. The entry contains the information of each row in the drawing, that is, the measurement location (P11,..Pij,..Pmn), the strength of the corresponding beacon signal (R1ij, R2ij, R3ij,..), the corresponding distance (d1ij, d2ij, d3ij, ..) is included.

6 is a view for explaining a third method of calculating the distance between the user terminal 200 and the beacon terminals (B1, B2, ..., Bn) in the present invention.

6, the walking guidance system 100 of the present invention, each of the beacon terminals (B1, B2, ..., Bn) to determine each distance (d1, d2, ..., dn) For this purpose, it may further include a learning model database 600 referenced by the distance calculator 130 .

The learning model database 600 is, within the service coverage 300, the strength (RSSI1, RSSI2, ..., RSSIn) of each beacon signal at a plurality of locations (eg, several tens cm to several m intervals) in advance and each of them Parameter(s) (W1, W2,. .Wn) to save the learning model.

The learning model may include a function associated with one or more parameters (W1, W2, ..Wn) for calculating the corresponding distance (Y) for the strength (R) of any beacon signal, for example, each beacon The regression coefficients of the deep neural network learning process to obtain a logistic function to satisfy the signal strength (RSSI1, RSSI2,..., RSSIn) and their respective distances (d1, d2,..., dn) are shown above. can have the same parameters.

If necessary, the walking guidance system 100 of the present invention may further include a machine learning device for performing such a deep neural network learning process.

The distance calculator 130 refers to this learning model database 600, and applies the strength R of each beacon signal input in real time to the corresponding learning model stored in the learning model database 600 to each Each distance d1, d2, ..., dn may be calculated from the beacon terminals B1, B2, ..., Bn.

In this way, when the respective distances d1, d2, d3,..) from each of the beacon terminals B1, B2, B3,.. For the location of B3, ..) and each distance (d1, d2, d3, ..) corresponding to each location, using the least squares algorithm, the walking guidance system of the present invention ( 100), the position X(x,y) of the mounted user terminal 200 is calculated ( S140 ).

In the example of FIG. 4, a point where circles having respective distances d1, d2, d3, and d4 as radiuses from each of the beacon terminals B1, B2, B3, and B4 overlap and meet is the location of the user terminal 200 It can be X(x,y), but it can be computed using a least squares algorithm.

For example, it is assumed that the positions of m beacon terminals are (x1, y1), (x2, y2), ..., (xm, ym). Also, suppose that the distance from the user terminal 200 to each of the beacon terminals B1, B2, ..., Bm is (d1, d2, ..., dm). 7A illustrates the positions of eight beacon terminals with m=8 at the intersection. The positions (x1, y1), (x2, y2), ..., (xm, ym) of the beacon terminal may be information stored in the memory of the walking guidance system 100 of the present invention, and the walking guidance system ( 100) or the location calculator 140 may be information received from each beacon terminal. Each beacon terminal may transmit a predetermined beacon signal to inform its location including a unique identification code, and the beacon signal includes pre-stored information on the corresponding location, or location information obtained in real time using GPS (GPS information) and the like may be included.

The position X(x,y) of the user terminal 200 is obtained by calculating (x,y) in [Equation 2] according to the least-squares algorithm. [Equation 2] may be converted into an equation for calculating X(x,y) as in [Equation 3], and the position X(x,y) of the user terminal 200 may be obtained using this. .

[Equation 2]

[Equation 3]

However, as shown in FIG. 7B , the beacon terminals B may transmit a beacon signal or the like with radio wave directivity by a directional antenna. Due to such directivity or even if an omni-directional beacon terminal is used, a received RSSI value may be reduced even if a pedestrian is near the beacon terminal B due to a prop installed with a traffic light or a walking signal. Due to this, an error may occur in the calculation of the position of the pedestrian, that is, the position X(x,y) of the user terminal 200 .

In order to overcome this, if necessary, the walking guidance system 100 of the present invention may further include a GPS module for positioning GPS location information.

For example, when a beacon signal is received from a plurality of beacon terminals (B), the position calculator 140 receives the GPS position information (latitude, longitude, It is possible to receive the initial GPS position (x _int , y _int ) of the user terminal 200 consisting of altitude, etc.), and the beacon signal strength (RSSI) value is not disturbed by using the initial GPS position (x _int , y _int ). The location can be calculated by selectively using beacon signals of non-beacon terminals. Here, the initial GPS position (x _int , y _int ) corresponds to when beacon signals are received from a plurality of beacon terminals B (a time point at which position X(x,y) can be calculated using a least-squares algorithm), but , may be any one of the positions where the position calculator 140 can calculate the position X(x, y) by using the least-squares algorithm by the beacon signals.

That is, the position calculator 140 calculates the position X(x,y) by the least-squares algorithm method as described above, but using the position (x _int , y _int ) positioned using the GPS module and the least-squares algorithm. Optimization algorithm, genetic algorithm, etc. so that the calculated difference between the positions X(x,y) of the user terminal 200 becomes the minimum value, that is, the minimum value Min|(x _int -x) ² +(y _int -y) ² | By applying , the location X(x,y) may be calculated, excluding data related to the location and distance information of one or more beacon terminals. Accordingly, it is possible to accurately calculate the position X(x,y) by removing the influence of beacon signals of beacon terminals that give unnecessary or inaccurate information to the calculation of the position X(x,y). For example, in the example of FIG. 7c, when a pedestrian approaches around the beacon terminals B5 and B6, the beacon terminals B3, B5, B6, and B8 of the beacon terminals B3, B5, B6, B8 are obscured by the respective props due to the RSSI influence is removed.

In addition, in step S140, the location calculator 140 refers to a predetermined location learning model database, and the user corresponding to the strength (RSSI) of each beacon signal from each beacon terminal installed in a plurality of walking signals around the crosswalk. The position X(x,y) of the terminal 200 may be estimated.

8A is a diagram for explaining another embodiment of the calculation of the location of the user terminal 200 in the present invention.

Referring to FIG. 8A , the walking guidance system 100 of the present invention is a location learning model database 700 referenced by the location calculator 140 to determine the location X(x,y) of the user terminal 200 . ) may be further included. Here, the location learning model database 700, within the service coverage 300, in advance of a plurality of positions (eg, several tens cm to several m intervals) of the strength of a plurality of beacon signals (RSSI1, RSSI2, ..., RSSIn) ) through neural network learning for the position X(x,y) of the user terminal 200 corresponding to the corresponding position X( Store the learning model with parameter(s) (W1, W2, ..Wn) for calculating x,y).

The learning model is one or more parameters (W1', W2) for calculating the position X (x, y) of the user terminal 200 with respect to the strengths (RSSI1, RSSI2, ..., RSSIn) of a plurality of beacon signals that are arbitrarily input ',..Wn') and related functions, for example, a logistic function for satisfying the strength of the beacon signal (RSSI1, RSSI2,..., RSSIn) and the corresponding position X(x,y). A regression coefficient of a deep neural network learning process for obtaining . If necessary, the walking guidance system 100 of the present invention may further include a machine learning device for performing such a deep neural network learning process. The location calculation unit 140 refers to the location learning model database 700 as such, and the corresponding learning stored in the location learning model database with respect to the intensity (RSSI1, RSSI2, ..., RSSIn) of the beacon signal input in real time. The position X(x,y) of the user terminal 200 may be calculated by applying the model.

In the case of using such a location learning model database 700, in the walking guidance system 100 of the present invention of FIG. 1, the distance calculator 130 may be omitted. A block diagram of the walking guidance system 190 for the visually impaired according to the second embodiment of the present invention, which corresponds to this case, is shown in FIG. 8B . Referring to FIG. 8B , the walking guidance system 190 for the visually impaired according to the second embodiment of the present invention includes a beacon signal receiving unit 110 , a noise filtering unit 120 , a location calculating unit 140 , and path deviation determination. It may include a unit 150 and an alarm unit 160 .

The position calculator 140 in the walking guidance system 190 for the visually impaired according to the second embodiment of the present invention refers to the position learning model database 700 based on deep neural network learning using a machine learning device, and the user The position X(x,y) of the terminal 200 can be calculated immediately.

In the walking guidance system 100 for the visually impaired according to the first embodiment of the present invention, the location calculator 140 corresponds to the strength of each beacon signal from the beacon terminal in the distance calculator 130 as above. Calculating the position X (x, y) of the user terminal 200 using a least-squares algorithm based on the calculation of each distance, and referring to the position learning model database 700 , the user terminal 200 It is also possible to immediately compute the position X(x,y) of

The functions and operations of the beacon signal receiving unit 110, the noise filtering unit 120, the path deviation determining unit 150, and the alarm unit 160 in addition to the position calculating unit 140 in FIG. The function and operation of the corresponding unit in the walking guidance system 100 for the visually impaired according to the first embodiment are the same.

As the location X (x, y) of the user terminal 200 is acquired in real time according to the movement of the user, the route deviation determination unit 150 tracks the route along which the location of the user terminal 200 moves based on this. to determine the location of the user's destination beacon terminal (B1 in the example of FIG. 4) with respect to the location of the user's origin beacon terminal (B3 in the example of FIG. 4), and the crosswalk area where the location of the user terminal 200 is predetermined It is determined whether or not to depart (S150). For each crosswalk for crossing the road in the horizontal, vertical and diagonal directions, a crosswalk for determining departure from the route between the source beacon terminal (B3 in the example of FIG. 4) and the destination beacon terminal (B1 in the example of FIG. 4) The zone may be predefined and defined. For example, the target walking path (x _ref , y _ref ), which is the center line connecting the source beacon terminal (B3 in the example of FIG. 4) and the destination beacon terminal (B1 in the example of FIG. 4), has a predetermined width ( For example, 3m), etc. may be determined.

The route deviation determination unit 150 can know the movement direction and speed of the user by tracking the movement route through the location X (x, y) of the user terminal 200 as described above, and the origin beacon terminal placed in the movement direction. (B3 in the example of FIG. 4) and the destination beacon terminal (B1 in the example of FIG. 4) may be determined. When the source beacon terminal (B3 in the example of FIG. 4) and the destination beacon terminal (B1 in the example of FIG. 4) are determined, the route departure determination unit 150 tracks the location X(x,y) of the user terminal 200 . While doing so, it is possible to determine in real time whether or not to depart from the crosswalk zone defined in the corresponding direction.

9 is a view for explaining a method of determining deviation of the route according to the present invention when a pedestrian passes a crosswalk.

Referring to FIG. 9 , in the service coverage, which is a beacon signal area in which beacon signals of all beacon terminals are received in the user terminal 200, according to the movement of the user, the real-time location of the user terminal 200 as shown in [Equation 3] If the difference between X(x,y) and the target pedestrian path (x _ref , y _ref ) exceeds a preset threshold value (d _thres ) (eg, 3 m left and right), it may be judged as a departure from the crosswalk area. there is.

[Equation 3]

(x _ref -x) ² +(y _ref -y) ² > d _thres

The alarm unit 160 generates an alarm signal when the location of the user terminal 200 deviates from the crosswalk area as above (S160). In FIG. 9, the positions at which the alarm signal is generated at positions A, B, and C are shown. As the alarm unit 160 generates an alarm signal, the user terminal 200 recognizes the user with a warning sound (eg, a sound such as 'beep'), a warning message (eg, a message such as 'out of the route') or vibration can make it happen

10 is a view for explaining an example of the implementation method of the walking guidance system 100 for the visually impaired according to an embodiment of the present invention.

The gait guidance system 100 (or user terminal) for processing gait guidance for the visually impaired according to an embodiment of the present invention may be made of hardware, software, or a combination thereof. For example, the walking guidance system 100 of the present invention may be implemented in the form of a computing system 1000 as shown in FIG. 10 having at least one processor for performing the above functions/steps/processes or a server on the Internet. .

The computing system 1000 includes at least one processor 1100 , a memory 1300 , a user interface input device 1400 , a user interface output device 1500 , a storage 1600 connected through a bus 1200 , and a network An interface 1700 may be included. The processor 1100 may be a central processing unit (CPU) or a semiconductor device that processes instructions stored in the memory 1300 and/or the storage 1600 . The memory 1300 and the storage 1600 may include various types of volatile or nonvolatile storage media. For example, the memory 1300 may include a read only memory (ROM) 1310 and a random access memory (RAM) 1320 .

In addition, the network interface 1700 is a communication module such as a modem that supports wireless Internet communication such as WiFi, WiBro, etc., mobile communication such as WCDMA and LTE in a wireless terminal such as a smartphone as described above, or a short-distance wireless communication method (eg, , Bluetooth, Zigbee, Wi-Fi, etc.) may include a communication module such as a modem supporting communication. Accordingly, steps of a method or algorithm described in connection with the embodiments disclosed herein may be directly implemented in hardware, a software module executed by the processor 1100 , or a combination of the two. A software module may be a storage/recording medium (i.e., memory 1300 and/or memory 1300) readable by a device, such as a computer, such as RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, or CD-ROM. Alternatively, it may reside in storage 1600 . An exemplary storage medium is coupled to the processor 1100 , the processor 1100 capable of reading information (code) from, and writing information (code) to, the storage medium. Alternatively, the storage medium may be integrated with the processor 1100 . The processor and storage medium may reside within an application specific integrated circuit (ASIC). The ASIC may reside within the user terminal. Alternatively, the processor and storage medium may reside as separate components within the user terminal.

As described above, according to the walking guidance system 100 for the visually impaired according to the present invention, when a visually impaired person moves at a crosswalk, the walking path is determined through accurate movement position calculation, so that even at a diagonal crosswalk, etc., without departing from the designated crosswalk area It can guide you to walk safely and quickly. In the present invention, the location of the visually impaired walking in a diagonal crosswalk, etc. based on the unique identification code transmitted from the beacons inside a plurality of walking signals installed in the crosswalk through Bluetooth communication from the user terminal (app) and the RSSI strength of the received signal However, by calculating the location more accurately using a lookup-table method or a model through an artificial neural network, it accurately detects the walking path of the visually impaired and makes a warning sound and warning when moving in a diagonal direction and departs from the designated crosswalk area. An alarm can be generated through a comment or vibration to enable safe walking.

As described above, in the present invention, specific matters such as specific components, etc., and limited embodiments and drawings have been described, but these are only provided to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments. , various modifications and variations will be possible without departing from the essential characteristics of the present invention by those of ordinary skill in the art to which the present invention pertains. Therefore, the spirit of the present invention should not be limited to the described embodiments, and all technical ideas with equivalent or equivalent modifications to the claims as well as the claims to be described later are included in the scope of the present invention. should be interpreted as

Beacon signal receiver 110
Noise filtering unit 120
Distance calculator 130
Position calculator 140
Deviation of path determination unit 150
Alarm unit 160

Claims (20)

In the gait guidance method in a user terminal for gait guidance,
calculating each distance corresponding to the strength of each beacon signal from each beacon terminal installed in a plurality of walking signals;
calculating a location of the user terminal using a least-squares algorithm for each location of the beacon terminal and each distance corresponding to each location;
Determine the location of the user's destination beacon terminal with respect to the location of the user's source beacon terminal by tracking the path along which the location of the user terminal moves, and determine whether the location of the user terminal deviates from a predetermined crosswalk area to do; and
generating an alarm signal when the location of the user terminal deviates from the crosswalk area
A walking guidance method comprising a. According to claim 1,
In the step of calculating each distance, the intensity of each beacon signal received from the beacon terminal is calculated, and a Kalman filter is applied to the calculated intensity to remove noise from each of the respective beacon signals corresponding to the intensity. A walking guidance method to calculate the distance of. The method of claim 1,
A walking guidance method in which the user terminal is recognized by the user as a warning sound, warning message, or vibration according to the generation of the alarm signal. According to claim 1,
The step of calculating each distance is,
real-time math

calculating each distance d corresponding to the intensity (RSSI) of each beacon signal using
Here, n is a coefficient reflecting the degree of propagation loss, and A is a predetermined offset value. According to claim 1,
The step of calculating each distance is,
Within the service coverage defined by each of the beacon terminals installed in the plurality of walking signals, each distance corresponding to the strength of each beacon signal from each of the beacon terminals at a plurality of measurement locations is measured and looked-up- Determining the respective distances mapped to the strengths of the respective beacon signals by storing them in a table and referring to the lookup-table
A walking guidance method comprising a. 6. The method of claim 5,
In the lookup-table, from among a plurality of entries most similar to the strength of each beacon signal, an entry for a measurement location closest to a location received from a GPS module is selected to determine the respective distances. According to claim 1,
The step of calculating each distance is,
Within the service coverage defined by each of the beacon terminals installed in the plurality of walking signals, the strength of the beacon signals at a plurality of locations and the corresponding distances for the strength of any beacon signals through neural network learning Maintaining in advance a learning model database storing a learning model having a parameter for calculating the distance, referring to the learning model database, and applying the strength of each beacon signal input in real time to the corresponding learning model Steps to calculate the distance
A walking guidance method comprising a. The method of claim 1,
In the step of calculating the location of the user terminal,
Among the positions of each of the beacon terminals and the respective distances corresponding to the respective positions, the difference between the position determined using the GPS module and the position of the user terminal calculated using the least-squares algorithm is minimized. , a walking guidance method of calculating the location of the user terminal by using the least-squares algorithm after removing information on one or more corresponding locations and distances. 9. The method of claim 8,
The position determined using the GPS module is an initial GPS position at a point in time when the position of the user terminal can be calculated using the least-squares algorithm by beacon signals from a plurality of beacon terminals. In the gait guidance method in a user terminal for gait guidance,
Within the service coverage defined by each beacon terminal installed in a plurality of walking signal devices, the strength of beacon signals at a plurality of locations and the locations of the corresponding user terminals through neural network learning to calculate the location of the user terminal step;
Determine the location of the user's destination beacon terminal with respect to the location of the user's source beacon terminal by tracking the path along which the location of the user terminal moves, and determine whether the location of the user terminal deviates from a predetermined crosswalk area to do; and
generating an alarm signal when the location of the user terminal deviates from the crosswalk area
A walking guidance method comprising a. In the walking guidance system,
a distance calculator for calculating each distance corresponding to the strength of each beacon signal from each beacon terminal installed in a plurality of walking signal devices;
a location calculator for calculating the location of each of the beacon terminals and the respective distances corresponding to the respective locations, using a least-squares algorithm, for calculating the location of the user terminal equipped with the walking guidance system;
Determine the location of the user's destination beacon terminal with respect to the location of the user's source beacon terminal by tracking the path along which the location of the user terminal moves, and determine whether the location of the user terminal deviates from a predetermined crosswalk area a path deviation determination unit; and
An alarm unit that generates an alarm signal when the location of the user terminal deviates from the crosswalk area
A walking guidance system comprising a. 12. The method of claim 11,
A noise filtering unit that calculates the intensity of each beacon signal received from the beacon terminal and outputs the intensity of each beacon signal from which noise is removed by applying a Kalman filter to the calculated intensity to the distance calculator
A walking guidance system further comprising a. 12. The method of claim 11,
A walking guidance system for allowing the user terminal to be recognized by the user as a warning sound, warning message, or vibration according to the generation of the alarm signal in the alarm unit. 12. The method of claim 11,
The distance calculator,
real-time math

Calculate each distance d corresponding to the intensity (RSSI) of each beacon signal using
Here, n is a coefficient reflecting the degree of propagation loss, and A is a predetermined offset value of the walking guidance system. 12. The method of claim 11,
Within the service coverage defined by each beacon terminal installed in the plurality of walking signal devices, each distance corresponding to the strength of each beacon signal from each beacon terminal at a plurality of locations is measured and stored in advance. further comprising a lookup-table;
The distance calculator is configured to determine the respective distances mapped with the strengths of the respective beacon signals by referring to the lookup-table. 16. The method of claim 15,
The walking guidance system further comprises a GPS module,
The location calculator, from among a plurality of entries most similar to the intensity of each beacon signal in the lookup-table, selects an entry for a measurement location closest to the location received from the GPS module to determine the respective distance guidance system. 12. The method of claim 11,
Within the service coverage defined by each of the beacon terminals installed in the plurality of walking signals, the strength of the beacon signals at a plurality of locations and the corresponding distances for the strength of any beacon signals through neural network learning Further comprising a learning model database storing a learning model with parameters for calculating the distance,
The distance calculation unit refers to the learning model database, and applies the strength of each of the beacon signals input in real time to the corresponding learning model to calculate the respective distances. 12. The method of claim 11,
The walking guidance system further comprises a GPS module,
The location calculator, between the location of each of the beacon terminals and the respective distances corresponding to the respective locations, between the location measured using the GPS module and the location of the user terminal calculated using the least-squares algorithm A walking guidance system for calculating the location of the user terminal by using the least-squares algorithm after removing information on one or more corresponding locations and distances so that the difference between the values is minimized. 19. The method of claim 18,
The position determined using the GPS module is an initial GPS position at a point in time at which the position of the user terminal can be calculated using the least-squares algorithm by beacon signals from a plurality of beacon terminals. In the walking guidance system,
Within the service coverage defined by each beacon terminal installed in a plurality of walking signal devices, a user equipped with the walking guidance system through neural network learning about the strength of beacon signals at a plurality of locations and the locations of the corresponding user terminals a location calculator for calculating the location of the terminal;
Determine the location of the user's destination beacon terminal with respect to the location of the user's source beacon terminal by tracking the path along which the location of the user terminal moves, and determine whether the location of the user terminal deviates from a predetermined crosswalk area a path deviation determination unit; and
An alarm unit that generates an alarm signal when the location of the user terminal deviates from the crosswalk area
A walking guidance system comprising a.

Images