Route calculation device, route calculation method, and program

Abstract

A route calculation device (10) according to the present invention includes: an acquisition unit (11) that acquires people distribution information indicating the distribution state of people in a passageway through which the user is traveling; a calculation unit (12) that calculates, on the basis of the people distribution information, an optimal route in the passageway that is a route in the passageway where the travel position in the width direction of the passageway is indicated and that satisfies conditions defined on the basis of the distance to other people; and an output unit (13) that outputs optimal route information indicating the calculated optimal route.

Description

Technical Field

[0001] The present invention relates to a route calculation device, a route calculation method, and a recording medium.

Background Art

[0002] Technologies related to the present invention are disclosed in Patent Document 1, Patent Document 2, and Non-Patent Document 1.

[0003] Patent Document 1 discloses a technique for searching for and outputting a route that avoids a preset avoidance area.

[0004] Patent Document 2 discloses a technique for calculating feature amounts of a plurality of key points of a human body included in an image, and searching for an image including a human body with a similar posture or a human body with a similar movement based on the calculated feature amounts, or classifying together those with similar postures and movements.

[0005] Non-Patent Document 1 discloses a technique related to human skeleton estimation.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Patent Document 2

Non-Patent Documents

[0007]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0008] Considering virus infection and the like, it is preferable to keep a sufficient distance from the surrounding people when passing. However, it is not easy for the passerby to judge which position on the passage is preferable to pass.

[0009] The technology disclosed in Patent Document 1 is a technology for searching for the optimal passage to go from the starting point to the goal point, and is not a technology for calculating which position on the passage is preferable to pass. In the technology disclosed in such Patent Document 1, there is a problem that the passerby can grasp the optimal passage, but cannot grasp which position on the passage is preferable to pass.

[0010] Also, the technologies disclosed in Patent Document 2 and Non-Patent Document 1 are technologies related to human skeleton estimation, and are not technologies for calculating which position on the passage is preferable to pass. In the technologies disclosed in such Patent Document 2 and Non-Patent Document 1, there is a problem that the passerby cannot grasp which position on the passage is preferable to pass.

[0011] An example of the object of the present invention is to provide a route calculation device, a route calculation method, and a recording medium that solve the problem of enabling a passerby to easily grasp which position on the passage is preferable to pass in view of the above-described problems.

Means for Solving the Problems

[0012] According to one aspect of the present invention, acquisition means for acquiring person distribution information indicating the distribution state of persons in a passage through which a user passes; a route on the passage indicating a passing position in the width direction of the passage, and a preferred route on the passage that satisfies a condition defined based on the distance from other persons, calculated based on the person distribution information; calculating means; output means for outputting preferred route information indicating the calculated preferred route; A route calculation device having the above is provided.

[0013] According to one aspect of the present invention, a computer acquires person distribution information indicating the distribution state of persons in a passage through which a user passes, calculates a route on the passage indicating a passing position in the width direction of the passage, and a preferred route on the passage that satisfies a condition defined based on the distance from other persons, based on the person distribution information, and outputs preferred route information indicating the calculated preferred route, A route calculation method is provided.

[0014] According to one aspect of the present invention, a computer is caused to function as acquisition means for acquiring person distribution information indicating the distribution state of persons in a passage through which a user passes, calculating means for calculating a route on the passage indicating a passing position in the width direction of the passage, and a preferred route on the passage that satisfies a condition defined based on the distance from other persons, based on the person distribution information, output means for outputting preferred route information indicating the calculated preferred route, A recording medium recording a program for causing the above to function is provided.

Effects of the Invention

[0015] According to one aspect of the present invention, there is realized a route calculation device, a route calculation method, and a recording medium that solve the problem of enabling a passerby to easily grasp which position on the passage is preferably passed through.

Brief Description of Drawings

[0016] The above-described object, as well as other objects, features, and advantages, will become more apparent from the following Suitable described embodiments and the accompanying drawings below.

[0017]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Embodiments for Carrying Out the Invention

[0018] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, the same components are denoted by the same reference numerals, and the description thereof will be omitted as appropriate.

[0019] <First Embodiment> FIG. 1 is a functional block diagram showing an overview of a route calculation device 10 according to the first embodiment. The route calculation device 10 includes an acquisition unit 11, a calculation unit 12, and an output unit 13.

[0020] The acquisition unit 11 acquires person distribution information indicating the distribution state of persons on the passage through which the user passes. The calculation unit 12 calculates, based on the person distribution information, a preferable route on the passage that indicates the passing position in the width direction of the passage and satisfies a condition defined based on the distance from other persons. The output unit 13 outputs preferable route information indicating the calculated preferable route.

[0021] According to the route calculation device 10 having such a configuration, the problem of enabling the passerby to grasp which position on the passage is preferably passed is solved.

[0022] <Second Embodiment> "Overview" The route calculation device 10 according to the second embodiment is a more specific implementation of the route calculation device 10 according to the first embodiment. Here, an overview of the route calculation device 10 will be briefly described.

[0023] As shown in FIG. 2, the route calculation device 10 cooperates with a user terminal 20 held by the user and monitoring cameras 30 installed at various locations on the passage to present predetermined information to the user.

[0024] First, the route calculation device 10 analyzes an image (hereinafter, "monitoring camera image") generated by the monitoring camera 30 that captures the position where the user is located, thereby generating person distribution information indicating the distribution state of persons on the passage through which the user passes. The identification of the position where the user is located is based on the current GroundIt may be realized by using a positioning function or by searching for a user in a surveillance camera image using face recognition technology.

[0025] Next, based on the acquired person distribution information, the route calculation device 10 calculates a suitable route on the passage through which the user indicated the passing position in the width direction of the passage, and which satisfies the conditions defined based on the distance from other persons. The route calculation device 10 calculates a suitable route that can ensure a sufficient distance from other persons.

[0026] Then, the route calculation device 10 outputs suitable route information indicating the calculated suitable route and causes it to be displayed on the user terminal 20.

[0027] FIG. 3 shows an example of the suitable route information displayed on the user terminal 20. The passing routes 1 and 2 shown in FIG. 3 are the suitable routes presented to the user. The passage extends in the width direction (left - right direction toward the extending direction of the passage). Therefore, when passing through the passage, there are various options such as "pass through the right end of the passage", "pass through the left end of the passage", "pass through near the middle of the passage", etc. Also, there are options to pass while maintaining the passing position, and options to pass while changing the passing position (that is, while changing the passing position in the left - right direction toward the traveling direction). The suitable route calculated by the route calculation device 10 indicates which position on the passage that extends in the width direction to pass through, as shown in FIG. 3.

[0028] As is clear from FIG. 3 and the above description, the technology for calculating a suitable route by the route calculation device 10 and the technology for searching for the optimal passage to go from the start point to the goal point as disclosed in Patent Document 1 are clearly different in their implementation means and the resulting products (calculation results), etc.

[0029] "Hardware Configuration" Next, an example of the hardware configuration of the route calculation device 10 will be described. Each functional unit of the route calculation device 10 is realized by an arbitrary combination of hardware and software centered around a CPU (Central Processing Unit) of an arbitrary computer, a memory, a program loaded into the memory, a storage unit such as a hard disk that stores the program (in addition to the program stored in advance at the stage of shipping the device, it can also store programs downloaded from a storage medium such as a CD (Compact Disc) or a server on the Internet), and a network connection interface. And it is understood by those skilled in the art that there are various modifications to the realization method and device.

[0030] FIG. 4 is a block diagram illustrating the hardware configuration of the route calculation device 10. As shown in FIG. 4, the route calculation device 10 includes a processor 1A, a memory 2A, an input / output interface 3A, a peripheral circuit 4A, and a bus 5A. The peripheral circuit 4A includes various modules. The route calculation device 10 may not have the peripheral circuit 4A. Note that the route calculation device 10 may be composed of a plurality of physically and / or logically divided devices. In this case, each of the plurality of devices can have the above hardware configuration.

[0031] Bus 5A is a data transmission path for the processor 1A, memory 2A, peripheral circuit 4A, and input / output interface 3A to transmit and receive data with each other. The processor 1A is an arithmetic processing device such as a CPU or a GPU (Graphics Processing Unit). The memory 2A is a memory such as a RAM (Random Access Memory) or a ROM (Read Only Memory). The input / output interface 3A includes an interface for acquiring information from an input device, an external device, an external server, an external sensor, a camera, etc., and an interface for outputting information to an output device, an external device, an external server, etc. The input device is, for example, a keyboard, a mouse, a microphone, a physical button, a touch panel, etc. The output device is, for example, a display, a speaker, a printer, a mailer, etc. The processor 1A can issue commands to each module and perform operations based on their operation results.

[0032] "Functional Configuration" Next, the functional configuration of the route calculation device 10 of the second embodiment will be described in detail. FIG. 1 shows an example of a functional block diagram of the route calculation device 10 of the second embodiment. As shown in the figure, the route calculation device 10 includes an acquisition unit 11, a calculation unit 12, and an output unit 13.

[0033] The acquisition unit 11 acquires person distribution information indicating the distribution state of persons in the passage through which the user passes.

[0034] In the second embodiment, the "passage through which the user passes" is the passage where the user is located. The acquisition unit 11 generates person distribution information indicating the distribution state of persons in the passage through which the user passes by analyzing the surveillance camera image generated by the surveillance camera 30 that captures the position where the user is located. Hereinafter, the process will be described in detail.

[0035] -Identification of the position where the user is located- The identification of the position where the user is located is the current GroundA positioning function (such as a GPS (Global Positioning System) function) may be used. In this case, the acquisition unit 11 receives, from the user terminal 20, position information indicating the current location measured by the user terminal 20, and specifies the position indicated by the position information as the position where the user is located.

[0036] Alternatively, the identification of the position where the user is located may be realized by searching for the user in the surveillance camera image using image analysis technology. In this case, the feature amounts of the user (such as a face image and face feature amounts) are registered in the route calculation device 10 in advance. Then, the acquisition unit 11 searches for the user in the surveillance camera image using the feature amounts. The acquisition unit 11 specifies the shooting position of the surveillance camera 30 that generated the surveillance camera image in which the user was found as the position where the user is located. The search for the user in the surveillance camera image may be realized using the image analysis system 40 described below.

[0037] Note that the above-exemplified technology is merely an example, and the acquisition unit 11 may identify the position where the user is located using other technologies such as beacons.

[0038] -Analysis of Surveillance Camera Images- In advance, information indicating the installation position (shooting position) of each of the plurality of surveillance cameras 30 is registered in the route calculation device 10. The acquisition unit 11 specifies the surveillance camera 30 that shoots the position where the user is located based on the information. Then, the acquisition unit 11 analyzes the surveillance camera image generated by the specified surveillance camera 30 and generates person distribution information.

[0039] The analysis of the surveillance camera image is performed by a pre-prepared image analysis system 40. As shown in FIG. 5, the acquisition unit 11 inputs the surveillance camera image into the image analysis system 40. Then, the acquisition unit 11 acquires the analysis result of the surveillance camera image from the image analysis system 40. The image analysis system 40 may be a part of the route calculation device 10, or may be an external device physically and / or logically independent from the route calculation device 10.

[0040] Here, the image analysis system 40 will be described. The image analysis system 40 includes at least one of a face recognition function, a humanoid recognition function, a posture recognition function, a motion recognition function, an appearance attribute recognition function, an image gradient feature detection function, an image color feature detection function, an object recognition function, and a character recognition function.

[0041] The face recognition function extracts the face feature amounts of a person. Further, the similarity between the face feature amounts may be compared and calculated (such as determining whether they are the same person). Also, the extracted face feature amounts may be compared with the face feature amounts of a plurality of users registered in advance in the database to identify which user the person shown in the image is. Note that the comparison between the extracted face feature amounts and the face feature amounts registered in advance in the database may be performed by the image analysis system 40 or by the acquisition unit 11.

[0042] The humanoid recognition function extracts the human body feature amounts of a person (for example, referring to overall features such as the fatness or thinness of the body shape, height, and clothing). Further, the similarity between the human body feature amounts may be compared and calculated (such as determining whether they are the same person). Also, the extracted human body feature amounts may be compared with the human body feature amounts of a plurality of users registered in advance in the database to identify which person the person shown in the image is. Note that the comparison between the extracted human body feature amounts and the human body feature amounts registered in advance in the database may be performed by the image analysis system 40 or by the acquisition unit 11.

[0043] In the posture recognition function and movement recognition function, the joint points of a person are detected, and the joint points are connected to form a stick figure model. Then, based on the stick figure model, a person is detected, the height of the person is estimated, the feature quantities of the posture are extracted, and the movement is specified based on the change in the posture. Further, the similarity between the feature quantities of the postures and the similarity between the feature quantities of the movements may be collated and calculated (such as determining whether they are in the same posture or the same movement). Also, the estimated height may be collated with the heights of a plurality of users registered in advance in the database to identify which user the person shown in the image is. Note that the collation of the estimated height with the heights registered in advance in the database may be performed by the image analysis system 40 or by the acquisition unit 11. The posture recognition function and the movement recognition function may be realized by the techniques disclosed in Patent Document 2 and Non-Patent Document 1 mentioned above.

[0044] In the appearance attribute recognition function, the appearance attributes associated with a person (for example, clothing color, shoe color, hairstyle, wearing of hats, neckties, etc., there are, for example, more than 100 types of appearance attributes in total) are recognized. Further, the similarity of the recognized appearance attributes may be collated and calculated (it is possible to determine whether they are the same attribute). Also, the recognized appearance attributes may be collated with the appearance attributes of a plurality of users registered in advance in the database to identify which user the person shown in the image is. Note that the collation of the recognized appearance attributes with the appearance attributes registered in advance in the database may be performed by the image analysis system 40 or by the acquisition unit 11.

[0045] The gradient feature detection function of the image is SIFT, SURF, RIFF, ORB, BRISK, CARD, HOG, etc. According to this function, the gradient features of each frame image are detected.

[0046] In the color feature detection function of the image, data indicating the color features of the image, such as a color histogram, is generated. According to this function, the color features of each frame image are detected.

[0047] The object recognition function is realized by using an engine such as YOLO (which can extract general objects [e.g., tools, equipment, etc. used in sports and other performances] and people). By using the object recognition function, various objects can be detected from an image.

[0048] In the character recognition function, numbers, characters, etc. are recognized.

[0049] The acquisition unit 11 acquires, as an analysis result from the image analysis system 40 as described above, the detection result of a person in the surveillance camera image. In the analysis result, the position of each person detected in the surveillance camera image within the surveillance camera image is shown.

[0050] - Generation of person distribution information - The acquisition unit 11 generates person distribution information based on the above analysis result. Note that the image analysis system 40 may generate person distribution information.

[0051] The person distribution information indicates the distribution state of people on the passage where the user passes. That is, the person distribution information indicates at which position on the passage where the user passes there are people. In the person distribution information, the position of a person may be indicated by coordinates (coordinates on the image) in the coordinate system set in the surveillance camera image. Alternatively, the position of a person may be indicated by coordinates (coordinates in the real space) in the coordinate system set in the real space. The conversion from coordinates on the image to coordinates in the real space can be realized by using any technology.

[0052] Returning to FIG. 1, the calculation unit 12 calculates a preferred route that satisfies a condition (hereinafter sometimes referred to as a "route condition") defined based on the distance from other people, which is a route on the passage where the user passes and indicates the passing position in the width direction of the passage, based on the person distribution information acquired by the acquisition unit 11.

[0053] The passageway extends in the width direction (left - right direction along the extending direction of the passageway). Therefore, when passing through the passageway, there are various options such as "passing through the right end of the passageway", "passing through the left end of the passageway", "passing through near the middle of the passageway", etc. Also, there are options to maintain the passing position while passing, and options to change the passing position (changing the passing position in the left - right direction along the traveling direction) while passing. The preferred route is the route on the passageway through which the user passes, indicating which position in the passageway that extends in the width direction to pass through. The preferred route can also be said to be a route indicating the passing position in the width direction of the passageway at each of a plurality of points along the traveling direction of the passageway.

[0054] The calculation unit 12 calculates the preferred route on the passageway shown in the surveillance camera image. In the second embodiment, the calculation unit 12 cannot grasp the distribution state of people in the passageway not shown in the surveillance camera image. Therefore, the calculation unit 12 cannot calculate the preferred route on the passageway not shown in the surveillance camera image.

[0055] Also, in the second embodiment, the calculation unit 12 calculates the distance between the user and other people on the premise that the position of the people on the passageway is fixed at the position indicated by the people distribution information, and performs various processes. In the following embodiments, an example of calculating the distance between the user and other people in consideration of the change in the position of the people on the passageway and performing various processes will be described.

[0056] The process of calculating the preferred route that satisfies the route conditions is various, and may be realized by using technologies such as machine learning, for example. Hereinafter, an example of the process of calculating the preferred route that satisfies the route conditions will be described.

[0057] As an example, the calculation unit 12 may calculate a plurality of routes on the passageway according to a predetermined rule. Then, the calculation unit 12 may determine the route that satisfies the route conditions among the calculated routes as the preferred route.

[0058] First, an example of a process for calculating a route on a path according to a predetermined rule will be described. As shown in FIG. 6, the calculation unit 12 may determine which point of the path widened in the width direction to pass through at an arbitrary target position on the path. Then, the calculation unit 12 may determine which point of the path widened in the width direction to pass through at each of a plurality of target positions while shifting the target position in the extending direction of the path. Then, the calculation unit 12 may connect the passing points determined at each of the plurality of target positions to determine a route.

[0059] The calculation unit 12 determines, as the passing point at the target position, "a point where the distance from another person can be ensured to be equal to or greater than a threshold value". For example, the calculation unit 12 may determine, as the passing point at the target position, "the point with the smallest distance from the passing point of the adjacent target position" among "points where the distance from another person can be ensured to be equal to or greater than a threshold value".

[0060] By the way, if the right end of the path is set as the passing point at a certain target position and the left end of the path is set as the passing point at the immediately subsequent target position, the amount of movement in the width direction of the path between a certain target position and the immediately subsequent target position becomes large, and an unnatural route will be determined. Therefore, the calculation unit 12 may determine the passing point at each target position so as to satisfy the condition that "the distance in the width direction of the path from the passing point of the adjacent target position is equal to or less than a lower limit value". The lower limit value is determined based on the size of the path in the width direction, the distance from the adjacent target position, and the like.

[0061] If there is no "point where the distance from another person can be ensured to be equal to or greater than a threshold value" at the target position, the calculation unit 12 may determine, as the passing point at that target position, "the point with the largest distance from another person", or "the point with the smallest distance from the passing point of the adjacent target position", or may determine it based on other criteria.

[0062] The distance (interval) between adjacent target positions is a design matter. By making the distance between adjacent target positions smaller, it becomes possible to calculate a more accurate and preferable route, but the processing load on the computer increases.

[0063] In addition, the "other persons" considered in determining the above route may be "all persons detected in the surveillance camera image", or may be "persons present on the path among the persons detected in the surveillance camera image", or may be "persons detected in the surveillance camera image who are present on the path and whose direction of travel is opposite to the direction of travel of the user". The direction of travel may be specified based on the orientation of the body or face specified from the surveillance camera image (e.g., the orientation of the body or face is the direction of travel), or in the case where the surveillance camera image is a moving image, it may be specified based on the movement trajectory in the moving image.

[0064] Next, the "route conditions" that the preferred route satisfies will be described. The route conditions are "being able to maintain a reference level or higher of a reference holding state where the distance from other persons is equal to or greater than a threshold value".

[0065] The "other persons" in the route conditions have the same definition as the "other persons" considered in determining the above route.

[0066] More specifically, the route conditions are "the ratio of the number of other persons in a reference holding state where the distance from the user is equal to or greater than a threshold value to the number of other persons passing by the user", "the ratio of the distance of a location where a reference holding state where the distance from other persons is equal to or greater than a threshold value is maintained to the moving distance", or "the ratio of the time of a reference holding state where the distance from other persons is equal to or greater than a threshold value is maintained to the moving time", and the reference holding rate, which is this, is equal to or higher than the reference level.

[0067] The "number of other persons passing by the user" may be, for example, the number of other persons defined as described above.

[0068] "The number of other persons in a reference holding state where the distance from the user is equal to or greater than the threshold" is the number of persons among other persons for whom the reference holding state where the distance from the user is equal to or greater than the threshold is continuously maintained when the user moves along the determined route (persons for whom the distance from the user never becomes less than the threshold).

[0069] "Moving distance" is the moving distance of the determined route. The length of the route on the surveillance camera image may be calculated as the moving distance, or the length of the route in the real space may be calculated as the moving distance.

[0070] "Distance of the portion where the reference holding state where the distance from another person is equal to or greater than the threshold is maintained" is the distance of the portion where the reference holding state where the distance from another person is equal to or greater than the threshold is maintained when the user moves along the determined route. The length of the portion on the surveillance camera image may be calculated, or the length of the portion in the real space may be calculated.

[0071] "Moving time" is the time required for the user to move along the determined route. For example, the moving time may be calculated on the premise that the user moves at a general walking speed.

[0072] "Time during which the reference holding state where the distance from another person is equal to or greater than the threshold is maintained" is the time during which the reference holding state where the distance from another person is equal to or greater than the threshold is maintained when the user moves along the determined route. For example, the time may be calculated on the premise that the user moves at a general walking speed.

[0073] The output unit 13 outputs suitable route information indicating the suitable route calculated by the calculation unit 12. The suitable route information output by the output unit 13 is transmitted to the user terminal 20 and displayed on the display of the user terminal 20. For example, the calculation unit 12 can generate the suitable route information.

[0074] As shown in FIG. 3, the output unit 13 may output suitable route information with information indicating a suitable route superimposed on the surveillance camera image. The passage routes 1 and 2 in FIG. 3 are suitable routes. The calculation unit 12 generates suitable route information by superimposing information indicating a suitable route at a predetermined position on the surveillance camera image.

[0075] Alternatively, as shown in FIG. 7, the output unit 13 may output suitable route information with information indicating a suitable route superimposed on a map. The passage routes 1 and 2 in FIG. 7 are suitable routes. The calculation unit 12 generates suitable route information by superimposing information indicating a suitable route at a predetermined position on the map data held in advance.

[0076] Alternatively, as shown in FIG. 8, the output unit 13 may output suitable route information with information indicating the positions of persons indicated by the person distribution information further superimposed on the map of FIG. 7. The passage routes 1 and 2 in FIG. 8 are suitable routes, and the positions of the persons are indicated by marks with crosses inside circles. The calculation unit 12 generates suitable route information by superimposing information indicating a suitable route at a predetermined position on the map data held in advance and information indicating the positions of the persons indicated by the person distribution information.

[0077] Alternatively, as shown in FIG. 9, the output unit 13 may output suitable route information further indicating the reference retention rate of the suitable route. The definition of the reference retention rate is as described above. In FIG. 9, the reference retention rate of the suitable route is shown in the suitable route information of FIG. 3, but the reference retention rate of the suitable route may also be shown in the suitable route information of FIG. 7 or FIG. 8.

[0078] Next, an example of the processing flow of the route calculation device 10 will be described using the flowchart of FIG. 10.

[0079] First, the acquisition unit 11 acquires person distribution information in the passage through which the user passes (S10). For example, the acquisition unit 11 is currently installed in the user terminal 20 possessed by the user. GroundUsing the positioning function, the current position of the user is identified. Next, the acquisition unit 11 identifies the surveillance camera 30 that captures the current position of the identified user, analyzes the surveillance camera image generated by the identified surveillance camera 30, and generates person distribution information.

[0080] Next, the calculation unit 12 calculates a preferred route that is a route on the passage where the user indicating the passage position in the width direction of the passage travels and satisfies the route conditions defined based on the distance from other persons, based on the person distribution information acquired in S10 (S11). The route conditions are, for example, "the ratio of the number of other persons in a reference holding state where the distance from the user to the number of other persons passing by the user is equal to or greater than a threshold value", "the ratio of the distance of a portion in a reference holding state where the distance from other persons to the moving distance is equal to or greater than a threshold value", or "the ratio of the time in a reference holding state where the distance from other persons to the moving time is equal to or greater than a threshold value", and the reference holding rate is equal to or higher than the reference level.

[0081] Then, the output unit 13 outputs preferred route information indicating the preferred route calculated in S11 (S12). The output unit 13 outputs preferred route information as shown in, for example, FIGS. 3, 7, 8, or 9. The preferred route information output by the output unit 13 is transmitted to the user terminal 20 and displayed on the display of the user terminal 20.

[0082] Note that the route calculation device 10 can repeatedly perform the processes of S10 to S12 above. When the current position of the user changes as the user moves, the route calculation device 10 newly identifies the surveillance camera 30 that captures the current position of the user after the movement, analyzes the surveillance camera image generated by the newly identified surveillance camera 30, and newly generates person distribution information (S10). Thereafter, the route calculation device 10 performs the processes of S11 and S12 described above.

[0083] "Function and effect" According to the route calculation device 10 of the second embodiment, it is possible to analyze a surveillance camera image to generate person distribution information indicating the distribution state of persons on the passage through which the user passes, and based on this information, calculate a suitable route on the passage. Generally, since the surveillance camera captures the passage from above, it is possible to generate an image showing the overall situation of the passage. By grasping the distribution state of persons on the passage based on such a surveillance camera image and calculating a suitable route on the passage, it is possible to calculate a highly accurate suitable route.

[0084] In addition, by calculating a suitable route that satisfies the route condition that the reference holding rate, which is "the ratio of the number of other persons in a reference holding state where the distance from the user to the number of other persons to be passed by the user is equal to or greater than a threshold value", "the ratio of the distance of a location where a reference holding state where the distance from other persons to the moving distance is equal to or greater than a threshold value is maintained", or "the ratio of the time of a reference holding state where the distance from other persons to the moving time is equal to or greater than a threshold value" is equal to or greater than a reference level, it is possible to calculate a suitable route that sufficiently maintains the distance from other persons.

[0085] In addition, by outputting suitable route information in which information indicating a suitable route is superimposed on a surveillance camera image as shown in FIGS. 3, 7, 8, or 9, or on a map, the user can intuitively grasp the suitable route. Furthermore, by further showing the persons on the passage as shown in FIGS. 3, 8, or 9, the user can determine the validity of the calculated suitable route. Furthermore, by further showing the reference holding rate of each suitable route as shown in FIG. 9, the user can determine which of the plurality of suitable routes is preferable.

[0086] <Third Embodiment> In the second embodiment, the calculation unit 12 calculated the distance between the user and other persons on the premise that the positions of the persons on the passage were fixed at the positions indicated by the person distribution information, and performed various processes. In the third embodiment, the calculation unit 12 calculates the distance between the user and other persons in consideration of the change in the positions of the persons on the passage, and performs various processes. This will be described in detail below.

[0087] The acquisition unit 11 analyzes a surveillance camera image that has captured a passage, and based on the analysis result, generates person distribution information indicating the distribution state of persons in the passage after a predetermined time has elapsed (after several frames from that surveillance camera image) since the timing when that surveillance camera image was captured. Then, the calculation unit 12 calculates a suitable route based on the person distribution information. The predetermined time is, for example, about several seconds.

[0088] The position of each of a plurality of persons on the passage after a predetermined time has elapsed since the timing when that surveillance camera image was captured is calculated based on the position of each of the plurality of persons at the timing when that surveillance camera image was captured, the traveling direction of each of the plurality of persons, and the passing speed of each of the plurality of persons. For example, the position of a certain person after a predetermined time has elapsed since the timing when that surveillance camera image was captured can be set as the position reached after moving from the position of that person at the timing when that surveillance camera image was captured in the traveling direction of that person at the passing speed of that person for the predetermined time.

[0089] Note that a general walking speed may be used as the passing speed of each of the plurality of persons, or the actual passing speed of each of the plurality of persons may be calculated by analyzing the surveillance camera image (moving image). Also, the traveling direction of each of the plurality of persons may be calculated assuming that it is the extending direction of the passage (that is, assuming that they move straight along the passage and do not move diagonally across the passage or in the width direction). Note that, among the extending directions of the passage, the direction in which the body or face of each of the plurality of persons identified from the surveillance camera image faces can be set as the traveling direction of the user. Additionally, the moving trajectory of each of the plurality of persons may be calculated by analyzing the surveillance camera image (moving image), and the traveling direction at the timing when that surveillance camera image was captured may be calculated.

[0090] The calculation unit 12 further calculates a suitable route using the person distribution information indicating the distribution state of persons in the passage after a predetermined time has elapsed since the timing when the above-mentioned surveillance camera image was captured.

[0091] For example, as described with reference to FIG. 6, the calculation unit 12 determines, at each of a plurality of target positions while shifting the target position in the extending direction of the passage, which point in the passage that spreads in the width direction is to be passed through, and can determine a route by connecting the passing points determined at each of the plurality of target positions. In this case, the calculation unit 12 specifies the timing at which the user reaches each of the plurality of target positions, and uses the person distribution information corresponding to each specified timing to determine, at each target position, which point in the passage that spreads in the width direction is to be passed through.

[0092] The "timing at which the user reaches each of the plurality of target positions" is expressed in the form of a predetermined time elapsing after the timing at which the surveillance camera image is taken. The value of the predetermined time is calculated based on the position of the user at the timing at which the surveillance camera image is taken, the distance between the position and each of the plurality of target positions, and the passing speed of the user.

[0093] A general walking speed may be used as the passing speed of the user, or the actual passing speed of the user may be calculated by analyzing the surveillance camera image (moving image). Also, the traveling direction of the user may be calculated assuming that it is the extending direction of the passage (that is, assuming that the user travels straight along the passage and does not travel diagonally or in the width direction of the passage). Note that, among the extending direction of the passage, the direction in which the body or face of the user specified from the surveillance camera image faces can be set as the traveling direction of the user.

[0094] Also, in the process of determining whether the determined route satisfies the route conditions, the calculation unit 12 also uses the person distribution information corresponding to each timing generated by the acquisition unit 11. Specifically, the calculation unit 12 specifies the timing at which the user reaches each point on the route, and specifies the person distribution state on the passage at each timing based on the person distribution information corresponding to each timing generated by the acquisition unit 11. Then, it is determined whether the distance from other persons is equal to or greater than a threshold value when the user passes through each point on the route.

[0095] The other configurations of the route calculation device 10 are the same as those in the first and second embodiments.

[0096] According to the route calculation device 10 of the third embodiment, the same operational effects as those of the first and second embodiments are realized. Further, according to the route calculation device 10 of the third embodiment that calculates the distance between the user and other persons in consideration of the change in the position of the persons on the passage and performs various processes, it is possible to calculate a more accurate and suitable route.

[0097] <Fourth Embodiment> In the second and third embodiments, the "passage through which the user passes" was the "passage where the user is located". In the fourth embodiment, the "passage through which the user passes" is the "optimal passage to go from the start point searched by the passage search technique to the goal point".

[0098] And in the second and third embodiments, the "person distribution information" was the "real-time information generated by analyzing the surveillance camera image of the passage where the user is located". In the fourth embodiment, the "person distribution information" is the "information indicating the past trend generated by analyzing the past surveillance camera image of the passage through which the user passes".

[0099] The route calculation device 10 of the fourth embodiment is different from the route calculation devices 10 of the second and third embodiments in the above points. This will be described in detail below.

[0100] The acquisition unit 11 acquires person distribution information indicating the tendency of the past distribution state of persons in the passage through which the user passes.

[0101] In the fourth embodiment, the "passage through which the user passes" is the "optimal passage to go from the start point searched by the passage search technology to the goal point". Using a well-known passage search technology, the optimal passage to go from the start point to the goal point set by the user is searched. Then, the acquisition unit 11 acquires information indicating the searched passage. Note that the start point may be set by the user, or the current location of the user may be the start point. The current location of the user is specified by any well-known technology. The optimal passage search may be performed by the route calculation device 10, or may be performed by an external device physically and / or logically separated from the route calculation device 10.

[0102] The acquisition unit 11 generates, in advance, person distribution information indicating the tendency of the distribution state of past persons in each of a plurality of passages, and registers it in the storage device. Then, the acquisition unit 11 acquires, from the storage device, person distribution information indicating the tendency of the distribution state of past persons in the passage through which the user passes. FIG. 11 shows an example of the person distribution state generated by the acquisition unit 11. In the illustrated example, the areas on the passage are classified into (1) an area with a high congestion level, (2) an area with a low congestion level, and (3) an area with a medium congestion level. Note that the method of classifying into three levels of congestion in this way is merely an example and is not limited thereto.

[0103] The acquisition unit 11 inputs the past surveillance camera images generated by the surveillance camera 30 into the image analysis system 40, and generates information indicating the positions of the persons on the passage at each past time point. Then, the acquisition unit 11 statistically processes the information corresponding to a plurality of past time points, and generates person distribution information indicating the tendency of the distribution state of past persons in each of the plurality of passages as shown in FIG. 11.

[0104] Note that the acquisition unit 11 may perform case-by-case classification based on factors that can affect the person distribution state, such as for each day of the week, each month, each time zone, each weather condition, etc., and generate person distribution information corresponding to each case.

[0105] The calculation unit 12 calculates a preferred route on the passage through which the user passes based on the person distribution information of the fourth embodiment as described above. The calculation unit 12 calculates a preferred route passing through a place with a lower degree of congestion. When the acquisition unit 11 makes a case-by-case division based on factors that can affect the distribution state of people, such as for each day of the week, each month, each time zone, each weather condition, etc., and generates person distribution information corresponding to each case, the calculation unit 12 identifies the case corresponding to the timing when the user passes through the passage, and determines a preferred route based on the person distribution information corresponding to the identified case.

[0106] The acquisition unit 11 may identify the current time as the "timing when the user passes through the passage". Alternatively, the user may specify the timing when passing through the passage. For example, when performing a passage search, the user may specify the departure date and time and the arrival date and time in addition to the destination point. Then, the acquisition unit 11 may identify the "timing when the user passes through the passage" based on the departure date and time and the arrival date and time specified by the user.

[0107] Other configurations of the route calculation device 10 are the same as those in the first to third embodiments.

[0108] According to the route calculation device 10 of the fourth embodiment, the same operational effects as those in the first to third embodiments are realized. Further, according to the route calculation device 10 of the fourth embodiment that calculates a preferred route based on person distribution information indicating the tendency of the past person distribution state on the passage, it is possible to notify the user in advance, rather than when the user is on the spot, of which position on the passage is preferably passed through when passing through each passage. Since the user is notified in advance, the user can make preparations for passage in advance.

[0109] <Modification Example> Hereinafter, modification examples applicable to the route calculation device 10 of the first to fourth embodiments will be described.

[0110] The acquisition unit 11 may analyze the surveillance camera image and identify the position of an obstacle on the passage. Then, the acquisition unit 11 may calculate a preferred route that bypasses the obstacle.

[0111] When applying this modification to the fourth embodiment, objects that do not move, such as benches and posts, and that always exist on the passage are registered in advance as obstacles, Monitoring and may be detected from within the camera image.

[0112] On the other hand, when applying this modification to the second and third embodiments, in addition to objects that do not move, such as benches and posts, and that always exist on the passage, objects that temporarily exist on the passage, such as parked automobiles and trucks, are also registered in advance as obstacles, Monitoring and may be detected from within the camera image.

[0113] Also in this modification, the same operational effects as those of the first to fourth embodiments are achieved. Further, according to this modification, a suitable route for passing while avoiding obstacles can be calculated.

[0114] As described above, the embodiments of the present invention have been described with reference to the drawings, but these are examples of the present invention, and various configurations other than the above can also be adopted. The configurations of the above-described embodiments may be combined with each other, or some of the configurations may be replaced with other configurations. Further, the configurations of the above-described embodiments may be variously modified within a range not departing from the gist. Also, the configurations and processes disclosed in the above-described embodiments and modifications may be combined with each other.

[0115] Also, in the flowcharts used in the above description, a plurality of steps (processes) are described in order, but the execution order of the steps executed in each embodiment is not limited to the described order. In each embodiment, the order of the illustrated steps can be changed within a range that does not substantially affect the content. Also, the above-described embodiments can be combined within a range where the contents do not conflict.

[0116] Some or all of the above embodiments may be described as follows in the appended claims, but are not limited thereto. 1. Acquisition means for acquiring person distribution information indicating the distribution state of persons in a passage through which a user passes, A route on the passage indicating a passage position in the width direction of the passage, and a calculation means for calculating a preferred route on the passage that satisfies a condition defined based on the distance from other persons, based on the person distribution information; An output means for outputting preferred route information indicating the calculated preferred route; A route calculation device having the above. 2. The route calculation device according to 1, wherein the acquisition means analyzes an image obtained by photographing the passage and generates the person distribution information based on the analysis result. 3. The route calculation device according to 1 or 2, wherein the acquisition means analyzes an image obtained by photographing the passage and generates the person distribution information indicating the distribution state of persons on the passage after a lapse of a predetermined time from the timing of photographing the image based on the analysis result. 4. The route calculation device according to any one of 1 to 3, wherein the acquisition means acquires the person distribution information indicating a tendency of a past person distribution state on the passage. 5. The route calculation device according to any one of 1 to 4, wherein the condition is that a reference holding state in which the distance from other persons is equal to or greater than a threshold can be maintained at a reference level or higher. 6. The condition is The ratio of the number of other persons maintained in the reference holding state in which the distance from the user is equal to or greater than a threshold with respect to the number of other persons passing by the user, The ratio of the distance of a portion where the reference holding state in which the distance from other persons is equal to or greater than a threshold is maintained with respect to the moving distance, or The ratio of the time in which the reference holding state in which the distance from other persons is equal to or greater than a threshold is maintained with respect to the moving time, The route calculation device according to 5, wherein a reference holding rate, which is the above, is equal to or greater than the reference level. 7. The route calculation device according to 6, wherein the output means outputs the preferred route information further indicating the reference holding rate of the preferred route. 8. The route calculation device according to any one of 1 to 7, wherein the preferred route is a route indicating a passage position in the width direction of the passage at each of a plurality of points along the traveling direction of the passage. 9. A computer Obtain person distribution information indicating the distribution state of persons in the passage through which the user passes, Based on the person distribution information, calculate a preferred route on the passage that is a route on the passage indicating the passing position in the width direction of the passage and satisfies a condition defined based on the distance from other persons, Output preferred route information indicating the calculated preferred route. Route calculation method. 10. Cause a computer to Have an acquisition means for acquiring person distribution information indicating the distribution state of persons in the passage through which the user passes, Have a calculation means for calculating, based on the person distribution information, a preferred route on the passage that is a route on the passage indicating the passing position in the width direction of the passage and satisfies a condition defined based on the distance from other persons, Have an output means for outputting preferred route information indicating the calculated preferred route. A recording medium recording a program for causing it to function as such.

Explanation of Signs

[0117] 10 Route calculation device 11 Acquisition unit 12 Calculation unit 13 Output unit 20 User terminal 30 Surveillance camera 40 Image analysis system 1A Processor 2A Memory 3A Input / output I / F 4A Peripheral circuit 5A Bus

Claims

1. An acquisition means for acquiring person distribution information indicating the distribution state of persons in a passage through which a user passes; A calculation means for calculating, based on the person distribution information, a preferred route on the passage that is a route on the passage indicating a passing position in the width direction of the passage and satisfies a condition defined based on the distance from other persons; An output means for outputting preferred route information indicating the calculated preferred route; comprising; The condition is that a reference holding state in which the distance from other persons is equal to or greater than a threshold can be maintained at a reference level or higher. A route calculation device.

2. The route calculation device according to claim 1, wherein the acquisition means analyzes an image of the passage and generates the person distribution information based on the analysis result.

3. The route calculation device according to claim 1 or 2, wherein the acquisition means analyzes an image of the passage and generates the person distribution information indicating the distribution state of persons in the passage after a lapse of a predetermined time from the timing when the image of the passage was taken based on the analysis result.

4. The route calculation device according to any one of claims 1 to 3, wherein the acquisition means acquires the person distribution information indicating a tendency of the past distribution state of persons in the passage.

5. The condition is The ratio of the number of other persons maintaining the reference holding state in which the distance from the user is equal to or greater than a threshold to the number of other persons passing by the user, The ratio of the distance of a portion maintaining the reference holding state in which the distance from other persons is equal to or greater than a threshold to the moving distance, or The ratio of the time of a portion maintaining the reference holding state in which the distance from other persons is equal to or greater than a threshold to the moving time, The route calculation device according to any one of claims 1 to 4, wherein a reference holding rate that is is equal to or greater than the reference level.

6. The route calculation device according to claim 5, wherein the output means outputs the preferred route information further indicating the reference holding rate of the preferred route.

7. The route calculation device according to any one of claims 1 to 6, wherein the preferred route is a route indicating a passing position in the width direction of the passage at each of a plurality of points along the traveling direction of the passage.

8. A computer acquires person distribution information indicating the distribution state of persons in a passage through which a user passes, calculates, based on the person distribution information, a preferred route on the passage that is a route on the passage indicating a passing position in the width direction of the passage and satisfies a condition defined based on the distance from other persons, Output suitable route information indicating the calculated suitable route. The condition is that a reference holding state in which the distance from other persons is equal to or greater than a threshold can be maintained at a reference level or higher. This is a route calculation method. **Claim 9** A computer An acquisition means for acquiring person distribution information indicating the distribution state of persons on a passage through which a user passes; A calculation means for calculating a suitable route on the passage, which is a route on the passage indicating a passage position in the width direction of the passage and satisfies a condition defined based on the distance from other persons, based on the person distribution information; An output means for outputting suitable route information indicating the calculated suitable route; Function as The condition is that a reference holding state in which the distance from other persons is equal to or greater than a threshold can be maintained at a reference level or higher. This is a program.

Images