JP7073949B2 - Evacuation guidance system, evacuation guidance system, and control program - Google Patents

Description

The present invention relates to evacuation guidance devices, evacuation guidance systems, and control programs.

Conventionally, a detection sensor such as an ultrasonic sensor or an optical sensor that detects the inside of a detection area detects a moving object such as a vehicle or a passerby, and sounds, sounds, lights or blinks light, and displays characters or images. , Or a technique for notifying the entry of a moving object into the detection area by vibration or the like is known.

In Patent Document 1, in order to avoid unnecessary notification by detecting a moving object that is not originally detected, the absolute distance of the moving object is determined by a plurality of Doppler radars using microwaves or the like. Measure the speed and the direction of movement, respectively. Then, a technique is disclosed in which notification is performed only when the measured absolute distance, speed, and moving direction of the moving body are within a preset range.

Japanese Unexamined Patent Publication No. 2004-192097

However, in the technique of Patent Document 1, since the notification is performed depending on the absolute distance, speed, and movement direction of the moving body, the notification may not function effectively. For example, in a dangerous area such as a highway where pedestrians are prohibited from entering, if the cognitive ability of the pedestrian who has entered is not sufficient, the notification may not function effectively even if the notification is given.

The present invention has been made to solve such a problem. That is, the purpose is to appropriately perform the next notification based on the behavior pattern of the moving body after the notification.

The above object of the present invention is achieved by the following means.

(1) An acquisition unit that acquires moving object information that measures moving objects in a predetermined area, and
An analysis unit that analyzes the behavior pattern of the moving object based on the acquired moving object information,
After the first notification is given by the notification unit, the notification content is determined based on the behavior pattern analyzed by the analysis unit, and the notification unit performs the second notification to the moving object with the determined notification content. Judgment unit to control
Equipped with
The acquisition unit acquires distance measurement point cloud data showing the distribution of distance values to the moving body existing in the predetermined region as the moving body information.
The behavior pattern analyzed by the analysis unit includes the movement locus of the moving body, the moving speed of the moving body, the overturned state of the moving body, the position of the moving body, and the set dangerous area, which are obtained from the range-finding point cloud data. Includes at least one of the distances of the moving object to,
Evacuation guidance device.
(2) An acquisition unit that acquires moving object information that measures moving objects in a predetermined area, and
An analysis unit that analyzes the behavior pattern of the moving object based on the acquired moving object information,
After the first notification is given by the notification unit, the notification content is determined based on the behavior pattern analyzed by the analysis unit, and the notification unit performs the second notification to the moving object with the determined notification content. Judgment unit to control
A type analysis unit that analyzes the type of the moving body based on the moving body information is provided.
When the type of the moving object determined by the type analysis unit is a specific type of moving object that is not allowed to enter the predetermined area, the analysis unit analyzes the behavior pattern for the moving object.
Evacuation guidance device.
(3) An acquisition unit that acquires moving object information that measures moving objects in a predetermined area, and
An analysis unit that analyzes the behavior pattern of the moving object based on the acquired moving object information,
After the first notification is given by the notification unit, the notification content is determined based on the behavior pattern analyzed by the analysis unit, and the notification unit performs the second notification to the moving object with the determined notification content. Judgment unit to control
Equipped with
The acquisition unit acquires image data obtained by photographing the predetermined area, and obtains the image data.
Further, an attribute analysis unit for analyzing the attributes of the moving object from the image data acquired by the acquisition unit is provided.
The notification content of the second notification is determined based on the attributes of the moving object analyzed by the attribute analysis unit and the behavior pattern analyzed by the analysis unit.
Evacuation guidance device.

(4) The acquisition unit acquires distance measurement point cloud data indicating the distribution of distance values to the moving body existing in the predetermined region as the moving body information.
The behavior pattern analyzed by the analysis unit includes the movement locus of the moving body, the moving speed of the moving body, the overturned state of the moving body, the position of the moving body, and the set dangerous area, which are obtained from the range-finding point cloud data. The evacuation guidance device according to ( 2 ) or (3) above , which comprises at least one of the distances of the moving object to.

(5) The notification unit is a plurality of notification units of one or more types.
From the above (1) to the above, the determination unit selects the notification unit together with the notification content according to the action pattern, and controls the selected notification unit to perform a second notification to the moving object. The evacuation guidance device according to any one of ( 4 ).
(6) An acquisition unit that acquires moving object information that measures moving objects in a predetermined area, and
An analysis unit that analyzes the behavior pattern of the moving object based on the acquired moving object information,
After the first notification is given by the notification unit, the notification content is determined based on the behavior pattern analyzed by the analysis unit, and the notification unit performs the second notification to the moving object with the determined notification content. Judgment unit to control
Equipped with
The notification unit is a plurality of notification units arranged at one or more different positions.
The determination unit selects the notification unit together with the notification content according to the action pattern, and controls the selected notification unit to perform a second notification to the moving object.
The acquisition unit acquires, as the moving object information, the distance measurement point cloud data showing the distribution of the distance value from the distance measurement unit that measures the predetermined area to the object in the predetermined area.
The determination unit selects the notification unit based on the movement locus of the moving object or the position of the moving object, which is obtained from the AF point cloud data.
Evacuation guidance device.
(7) The determination unit keeps a history of the behavior pattern, and determines the notification content of the second notification based on the behavior pattern before and after the first notification, from the above (1) to the above (6). ) The evacuation guidance device described in any one of.

(8) A moving body information measuring unit that generates moving body information of a moving body within a predetermined area by measuring, and a moving body information measuring unit.
Notification unit and
The evacuation guidance device according to any one of (1) to (7) above, wherein the notification unit notifies the moving body using the moving body information acquired from the moving body information measuring unit.
Evacuation guidance system equipped with.

(9) A control program that controls an evacuation guidance device that guides evacuation to moving objects in a predetermined area.
Step (a) of acquiring moving object information obtained by measuring a moving object in a predetermined area, and
The step (b) of analyzing the behavior pattern of the moving body based on the acquired moving body information, and
The step (c) in which the notification unit first notifies the moving object, and
After step (c), a step (d) of determining the notification content based on the behavior pattern analyzed in the step (b), and
In the step (e) of performing the second notification to the moving object with the determined notification content,
Including
In the step (a), as the moving object information, the ranging point cloud data showing the distribution of the distance value to the moving object existing in the predetermined region is acquired.
In the action pattern analyzed in the step (b), the movement locus of the moving object, the moving speed of the moving object, the overturned state of the moving object, the position of the moving object, and the position of the moving object, which were obtained from the range-finding point cloud data, were set. Includes at least one of the moving objects' distances to the danger zone,
A control program that lets a computer perform processing.
(10) A control program that controls an evacuation guidance device that guides evacuation to moving objects in a predetermined area.
Step (a) of acquiring moving object information obtained by measuring a moving object in a predetermined area, and
The step (b) of analyzing the behavior pattern of the moving body based on the acquired moving body information, and
The step (c) in which the notification unit first notifies the moving object, and
After step (c), a step (d) of determining the notification content based on the behavior pattern analyzed in the step (b), and
In the step (e) of performing the second notification to the moving object with the determined notification content,
Including
Further, the step (f) for analyzing the type of the moving body based on the moving body information acquired in the above (a) is included.
When the type of the moving body determined in the step (f) is a specific type of moving body that is not allowed to enter the predetermined area, the analysis of the behavior pattern for the moving body in the step (b) is performed. conduct,
A control program that lets a computer perform processing.
(11) A control program that controls an evacuation guidance device that guides evacuation to moving objects in a predetermined area.
Step (a) of acquiring moving object information obtained by measuring a moving object in a predetermined area, and
The step (b) of analyzing the behavior pattern of the moving body based on the acquired moving body information, and
The step (c) in which the notification unit first notifies the moving object, and
After step (c), a step (d) of determining the notification content based on the behavior pattern analyzed in the step (b), and
In the step (e) of performing the second notification to the moving object with the determined notification content,
Including
In the step (a), further, image data captured in the predetermined area is acquired, and the image data is acquired.
Further, the step (f) for analyzing the attributes of the moving object from the image data acquired in the step (a) is included.
In the step (d), the notification content of the second notification is determined based on the attributes of the moving object analyzed in the step (f) and the behavior pattern analyzed in the step (b).
A control program that lets a computer perform processing.
(12) A control program that controls an evacuation guidance device that guides evacuation to moving objects in a predetermined area.
Step (a) of acquiring moving object information obtained by measuring a moving object in a predetermined area, and
The step (b) of analyzing the behavior pattern of the moving body based on the acquired moving body information, and
The step (c) in which the notification unit first notifies the moving object, and
After step (c), a step (d) of determining the notification content based on the behavior pattern analyzed in the step (b), and
In the step (e) of performing the second notification to the moving object with the determined notification content,
Including
The notification unit is a plurality of notification units arranged at one or more different positions.
In the step (a), as the moving object information, the ranging point cloud data showing the distribution of the distance value from the ranging unit for measuring in the predetermined region to the object in the predetermined region is acquired.
In the step (d), the notification content is determined and the notification unit is selected according to the action pattern.
In the step (e), the notification unit selected in the step (d) performs a second notification to the moving body.
In the step (d), the notification unit is selected based on the movement locus of the moving body or the position of the moving body obtained from the AF point cloud data.
A control program that lets a computer perform processing.

The evacuation guidance device according to the present invention determines the notification content based on the behavior pattern of the moving object in the predetermined region analyzed by the analysis unit after the first notification is performed by the notification unit, and the determined notification content is used for notification. A second notification is given to the moving body by the unit. As a result, the next notification can be appropriately performed based on the behavior pattern of the moving body after the notification.

It is a block diagram which shows the structure of the evacuation guidance system which concerns on this embodiment. It is sectional drawing which shows the schematic structure of a rider. It is a schematic diagram which shows the state which scans in the monitoring area by a rider. This is an example of the position information data of the moving object detected by the AF point cloud data at each time. It is a figure which shows the area around the highway entrance to which the monitoring area is applied. It is a schematic diagram which shows the monitoring area at the entrance of a highway. It is a flowchart which shows the notification processing in 1st Embodiment. It is a figure which shows the example of the pedestrian attribute discriminated from the image data of a camera. It is a figure which shows the example of the movement locus of pedestrians A to D in a monitoring area. It is a figure which shows the change of the moving speed of the pedestrians A to D corresponding to FIG. 9A. It is a figure which shows the example of the effect determination result of the 1st notification to pedestrians A to D. It is a figure which shows the example of the notification content in the second notification to pedestrians A to D. It is a figure which shows the example of the effect determination result of the 2nd notification to pedestrians A to D, and the example of the notification content in the 3rd notification. It is a figure which shows the example which arranged a plurality of notification units in the monitoring area of a highway entrance. It is a flowchart which shows the notification processing in 2nd Embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the description of the drawings, the same elements are designated by the same reference numerals, and duplicate description will be omitted. In addition, the dimensional ratios in the drawings are exaggerated for convenience of explanation and may differ from the actual ratios.

FIG. 1 is a block diagram showing the configuration of the evacuation guidance system 10. The evacuation guidance system 10 has an input unit 100, an evacuation guidance device 200, and a notification unit 300. The evacuation guidance device 200 is, for example, a computer, and is a CPU (Central Processing Unit), a memory (semiconductor memory, magnetic recording medium (hard disk, etc.)), an input / output unit (display, keyboard, etc.), and a communication I / F (interface). ) Etc. are provided. The communication I / F is an interface for communicating with an external device. For communication, a network interface according to a standard such as Ethernet (registered trademark), SATA, PCI Express, USB, or IEEE 1394 may be used. Further, a wireless communication interface such as Bluetooth (registered trademark), 802.11, or 4G may be used for communication.

(Input unit 100)
The input unit 100 includes a lidar (LiDAR: Light Detection and Ringing) 110 and a camera 120. The input unit 100 may be configured only by the rider 110. The camera 120 is composed of, for example, a visible light camera. The camera 120 may be configured by a thermal camera. Hereinafter, the input unit 100 will be described as being composed of the rider 110 and the camera 120.

The input unit 100 measures the distance to the object (moving object) in the monitoring area (predetermined area) by the rider 110 as the distance measuring unit, and obtains the distance measuring point cloud data showing the distribution of the distance value in the monitoring area. Generate. The rider 110 functions as a "moving object information measuring unit", and the generated range-finding point cloud data corresponds to the moving object information obtained by measuring the moving object in a predetermined area. The inside of the surveillance area is photographed by the camera 120 to generate visible light image data.

(Rider 110)
Hereinafter, the configuration of the rider 110 will be described with reference to FIGS. 2 and 3. FIG. 2 is a cross-sectional view showing a schematic configuration of the rider 110. FIG. 3 is a schematic diagram showing a state in which the lidar 110 scans the inside of the monitoring area. The rider 110 includes a light emitting / receiving unit 111 and a AF point cloud data generation unit 112. The light emitting / receiving unit 111 includes a semiconductor laser 51, a collimating lens 52, a mirror unit 53, a lens 54, a photodiode 55, a motor 56, and a housing 57 that houses each of these components. The light emitting / receiving unit 111 outputs a light receiving signal of each pixel obtained by scanning the monitoring space of the lidar 110 with the laser spot light 500. The AF point cloud data generation unit 112 generates the AF point cloud data based on the received light signal. This range-finding point cloud data is also called a distance image or a distance map.

The semiconductor laser 51 emits a pulsed laser light beam. The collimating lens 52 converts the divergent light from the semiconductor laser 51 into parallel light. The mirror unit 53 scans and casts the laser beam parallel to the collimating lens 52 toward the monitoring area by the rotating mirror surface, and reflects the reflected light from the object. The lens 54 collects the reflected light from the object reflected by the mirror unit 53. The photodiode 55 receives the light collected by the lens 54 and has a plurality of pixels arranged in the Z direction. The motor 56 rotates and drives the mirror unit 53.

The AF point cloud data generation unit 112 obtains distance information (distance value) according to the time difference between the emission timing of these semiconductor lasers 51 and the light reception timing of the photodiode 55. The AF point group data generation unit 112 is composed of a CPU (Central Processing Unit) and a memory, and obtains the AF point group data by executing various processes by executing a program stored in the memory. , A dedicated hardware circuit for generating AF point group data may be provided. Further, the AF point cloud data generation unit 112 may be integrated into the analysis unit 220 (described later) as one function of the above-mentioned evacuation guidance device 200.

In the present embodiment, the semiconductor laser 51 and the collimating lens 52 form an emitting unit 501, and the lens 54 and the photodiode 55 form a light receiving unit 502. It is preferable that the optical axes of the light emitting unit 501 and the light receiving unit 502 are orthogonal to the rotation axis 530 of the mirror unit 53.

The box-shaped housing 57 fixed to a rigid wall 91 or the like has an upper wall 57a, a lower wall 57b facing the upper wall 57a, and a side wall 57c connecting the upper wall 57a and the lower wall 57b. Have. An opening 57d is formed in a part of the side wall 57c, and a transparent plate 58 is attached to the opening 57d.

The mirror unit 53 has a shape in which two quadrangular pyramids are joined in opposite directions and integrated, that is, four pairs (but not limited to four pairs) of mirror surfaces 531a and 531b tilted in pairs facing each other. ) Have. The mirror surfaces 531a and 531b are preferably formed by depositing a reflective film on the surface of a resin material (for example, PC (polycarbonate)) in the shape of a mirror unit.

The mirror unit 53 is connected to a shaft 56a of a motor 56 fixed to a housing 57 and is rotationally driven. In the present embodiment, for example, in a state of being installed on the wall 91, the axis (rotational axis) of the axis 56a extends in the Z direction which is the vertical direction, and is formed by the X direction and the Y direction orthogonal to the Z direction. Although the XY plane is a horizontal plane, the axis of the axis 56a may be tilted with respect to the vertical direction.

Next, the object detection principle of the rider 110 will be described. In FIG. 2, the divergent light emitted intermittently in a pulse shape from the semiconductor laser 51 is converted into a parallel light flux by the collimating lens 52 and incident on the first mirror surface 531a of the rotating mirror unit 53. After that, it is reflected by the first mirror surface 531a, further reflected by the second mirror surface 531b, and then transmitted through the transparent plate 58 and directed toward the external measurement space, for example, as a laser spot light having a vertically long rectangular cross section. Be lit. The direction in which the laser spot light is emitted and the direction in which the emitted laser spot light is reflected by the object and returned as reflected light overlap, and these two overlapping directions are referred to as light emitting and receiving directions. Laser spot light traveling in the same light emitting / receiving direction is detected by the same pixel.

FIG. 3 is a diagram showing a state in which the laser spot light 500 (indicated by hatching) emitted in response to the rotation of the mirror unit 53 scans the inside of the monitoring area. Here, in the combination of the pair of mirrors (first mirror surface 531a and second mirror surface 531b) of the mirror unit 53, the four pairs have different crossing angles. The laser beam is sequentially reflected by the rotating first mirror surface 531a and the second mirror surface 531b. First, the laser light reflected by the first pair of the first mirror surface 531a and the second mirror surface 531b horizontally moves from left to right in the uppermost region Ln1 of the measurement space according to the rotation of the mirror unit 53. Is scanned. Next, the laser light reflected by the second pair of the first mirror surface 531a and the second mirror surface 531b horizontally covers the second region Ln2 from the top of the measurement space from the left in accordance with the rotation of the mirror unit 53. Scanned to the right. Next, the laser light reflected by the third pair of the first mirror surface 531a and the second mirror surface 531b horizontally covers the third region Ln3 from the top of the measurement space from the left in accordance with the rotation of the mirror unit 53. Scanned to the right. Next, the laser light reflected by the 4th pair of the first mirror surface 531a and the second mirror surface horizontally moves horizontally from left to right in the lowest region Ln4 of the measurement space according to the rotation of the mirror unit 53. It is scanned. This completes one scan of the entire measurement space that the rider 110 can measure. The images obtained by scanning the regions Ln1 to Ln4 are combined to obtain one frame 900. Then, after the mirror unit 53 makes one rotation, it returns to the first pair of first mirror surface 531a and the second mirror surface 531b again, and thereafter, scanning from the uppermost region Ln1 to the lowermost region Ln4 in the measurement space. Is repeated to obtain the next frame 900.

In FIG. 2, a part of the laser beam reflected by hitting the object among the light rays projected by scanning is transmitted through the transparent plate 58 again and incident on the second mirror surface 531b of the mirror unit 53 in the housing 57. Here, it is reflected, further reflected by the first mirror surface 531a, condensed by the lens 54, and detected for each pixel on the light receiving surface of the photodiode 55. Further, the AF point cloud data generation unit 112 obtains distance information according to the time difference between the emission timing of the semiconductor laser 51 and the light reception timing of the photodiode 55. As a result, it is possible to detect an object in the entire area in the monitoring space and obtain a frame 900 (see FIG. 3) as distance measurement point cloud data having distance information for each pixel. Further, according to the user's instruction, the obtained AF point cloud data may be stored as background image data in the memory in the AF point cloud data generation unit 112 or in the memory of the evacuation guidance device 200.

(Evacuation guidance device 200)
The configuration of the evacuation guidance device 200 will be described with reference to FIG. 1 again. The evacuation guidance device 200 includes an acquisition unit 210, an analysis unit 220, a database 230, and a determination unit 240. Mainly, the CPU of the above-mentioned evacuation guidance device 200 functions as the analysis unit 220 and the determination unit 240, the memory functions as the database 230, and the communication I / F functions as the acquisition unit 210.

(Acquisition unit 210)
The acquisition unit 210 acquires the range-finding point cloud data (also referred to as “moving object information”) arranged in time series generated by the rider 110 from the input unit 100, and sends the acquired range-finding point cloud data to the analysis unit 220. Further, the acquisition unit 210 acquires the image data generated by the camera 120 from the input unit 100 and sends it to the analysis unit 220.

(Analysis unit 220)
The analysis unit 220 includes a moving body type analysis unit 221, a walking characteristic analysis unit 222, and a pedestrian attribute analysis unit 223.

Here, a detection algorithm for an object to be measured by the rider 110 using the background subtraction method will be described. In this embodiment, for example, the background subtraction method is adopted. In this background subtraction method, a background image (also referred to as a reference image) that has been generated and saved in advance is used. Specifically, as a pre-measurement (pre-processing), the laser spot light 500 is scanned from the rider 110 in the absence of a moving object such as a human or an animal according to a user's instruction. As a result, a background image can be obtained based on the reflected light obtained from the background object 92. At the time of actual measurement, when, for example, a pedestrian 93 appears as an object to be an object of behavior analysis in front of the background object 92, the reflected light from the pedestrian 93 is newly generated.

The moving body type analysis unit 221 has a function of detecting a moving body. The moving object type analysis unit 221 compares the background image data held in the memory with the current range-finding point cloud data, and if a difference occurs, some moving object (object) such as a pedestrian enters the monitoring space. You can recognize that it has appeared. For example, foreground data is extracted by comparing the background data with the current range-finding point cloud data (distance image data) using the background subtraction method. Then, the pixels (pixel group) of the extracted foreground data are divided into clusters according to, for example, the distance value of the pixels. Then, the size of each cluster is calculated. For example, the vertical dimension, the horizontal dimension, the total area, and the like are calculated. The "size" here is an actual size, and is different from the apparent size (angle of view, that is, the spread of pixels), and a mass of pixel groups is determined according to the distance to the object. For example, the moving object type analysis unit 221 determines whether or not the calculated size is equal to or less than a predetermined size threshold value for specifying the moving object to be analyzed to be extracted. The size threshold can be arbitrarily set depending on the measurement location, the behavior analysis target, and the like. If pedestrians are tracked and their behavior is analyzed, the minimum size of a normal person may be used as the size threshold value for clustering. Conversely, the size threshold may be smaller than this if all moving objects are to be tracked.

The moving body type analysis unit 221 functions as a "type analysis unit" and determines the type of moving body by comparing the size, aspect ratio, etc. of the clustered moving body with the reference data in the memory stored in advance. do. The types of moving objects to be discriminated include people (pedestrians) and vehicles (four-wheeled and two-wheeled vehicles). Further, in the case of an object that is difficult to discriminate only by the size at this time, the moving speed may be further calculated and the moving speed may be combined to discriminate the type of the moving body. For example, a two-wheeled motorcycle that can pass on a highway and a bicycle that is prohibited from passing are discriminated by size and moving speed.

The walking characteristic analysis unit 222 analyzes the behavior pattern (movement characteristic) of the moving body. FIG. 4 is an example of position information data of a moving object detected by the AF point cloud data at each time. Each detected moving object is managed by a moving object ID (pedestrian ID). The walking characteristic analysis unit 222 analyzes the behavior pattern by analyzing the position information of each moving body in the time series. The behavior pattern includes at least one of the moving locus of the moving body, the moving speed of the moving body, the falling state of the moving body, the position of the moving body, and the distance of the moving body to the set dangerous area, which are obtained from the AF point cloud data. .. As the position of the moving body used in this analysis, the center value or the center of gravity value of the clustered moving body may be used, and if the moving body is clustered by a rectangle, the center of the rectangle may be used as the position of the moving body. .. The fallen state of the moving body is used when the moving body is determined to be a pedestrian, and when the height of the center position of the moving body from the ground drops sharply, or the aspect ratio (ratio of height to width) suddenly decreases. If it decreases or if the condition is maintained, it is judged to be in a fallen condition. The setting of the dangerous area is set in advance, for example, the highway main line is set as the dangerous area.

In the present embodiment, particularly when the moving body type analysis unit 221 determines that the type of the moving body is the pedestrian 93, the moving speed (walking speed) and the locus of the pedestrian 93 are analyzed as an action pattern.

The pedestrian attribute analysis unit 223 functions as an "attribute analysis unit" and mainly analyzes the attributes of a moving object from the image data acquired from the camera 120. Specifically, by analyzing two-dimensional image data, pedestrians are extracted and attributes of pedestrians are analyzed. Analysis items include gender, age, and race. Further, as an attribute of the pedestrian, a portable item such as a cane, a wheelchair, or a carry bag may be further identified. The determination of the portable item can be made by registering the shape and size of the object that can be the portable item in the pedestrian attribute analysis unit 223 in advance and matching it with the registered data.

This analysis includes discrimination between humans and other objects as the type of object, and discrimination of the discriminated attributes. For example, in recognizing gender, age, and race, a computer extracts a face from the obtained image data and determines a person's attributes from the extracted facial features. This discrimination algorithm can be machine-learned in advance by a known algorithm. This machine learning is performed on another high-performance computer in advance using a huge amount of data to determine parameters. The pedestrian attribute analysis unit 223 can analyze the attributes of pedestrians using the parameters.

Further, the pedestrian attribute analysis unit 223 may receive pedestrian position information from the walking characteristic analysis unit 222 and analyze the pedestrian attribute using the image data and this position information. For example, the optical axes (monitoring areas) of the rider 110 and the camera 120 are aligned, or the alignment is calibrated in advance. Then, the attributes of the pedestrian are analyzed by referring to the size such as the height of the pedestrian, the walking speed, etc. from the image data corresponding to the position information of the pedestrian obtained by the analysis of the AF point group data.

(Database 230)
The database 230 includes a pedestrian data storage unit 231 and a notification content storage unit 232. The pedestrian data storage unit 231 stores the walking characteristics for each pedestrian ID sent from the walking characteristic analysis unit 222 and the pedestrian attributes for each pedestrian ID sent from the pedestrian attribute analysis unit 223. The notification content storage unit 232 stores the notification content (history information regarding the notification content) and the effect for each pedestrian ID. In addition, the history of the notification content and effect is managed. The content and effect of this notification will be described later.

(Judgment unit 240)
The determination unit 240 includes the notification content determination unit 241 and the notification effect determination unit 242, and controls the notification unit 300 so as to determine the notification content and notify with the determined content. The notification content determination unit 241 determines the notification content based on the walking characteristics (walking pattern) stored in the pedestrian data storage unit 231 and the determination result of the notification effect determination unit 242. The notification effect determination unit 242 has the walking characteristics and pedestrian attributes for each pedestrian ID stored in the pedestrian data storage unit 231, and the notification content for each pedestrian ID stored in the notification content storage unit 232 ( The presence or absence of the notification effect is determined based on the history information regarding the notification content) and the effect.

(Notification unit 300)
The notification unit 300 includes two types of notification means, a speaker 310 and a signage 320. Each of the speaker 310 and the signage 320 may be plural. Further, the notification unit 300 may be composed of only one type of the speaker 310 or the signage 320. The speaker 310 emits a voice according to the notification content determined by the notification content determination unit 241. The signage 320 is a digital signage, and displays characters and images according to the content of the notification by a liquid crystal display or a display unit in which a plurality of LEDs are arranged two-dimensionally.

(Application example of evacuation guidance system 10)
FIG. 5 is a diagram showing the vicinity of the highway entrance to which the monitoring area of the evacuation guidance system 10 is applied. FIG. 6 is a schematic diagram showing a monitoring area at the entrance of a highway.

In recent years, pedestrians and bicycles entering the highway have become a social problem. Generally, in dangerous areas such as highways, various measures are taken, such as installing signs near the entrances and exits to alert pedestrians and drivers in order to prevent entry by vehicles other than permitted vehicles. ing. Further, even in the conventional technique as in Known Document 1 (Japanese Unexamined Patent Publication No. 2004-192097), in which the moving direction and the moving speed of the moving body are within the set range, constant notification is performed. When a pedestrian enters the road entrance, the notification for preventing the entry can be similarly performed.

However, with the technique disclosed in the sign installation and the publicly known document 1, a person who accidentally invades the expressway due to the following reasons (1) to (5) cannot evacuate based on appropriate judgment, and others. There was a risk that it would cause a new accident involving people.
(1) There is no evacuation guidance on the highway.
(2) There is a problem in cognitive / thinking ability due to panic, dementia, intoxication, etc., and the evacuation guidance on the highway cannot be recognized / understood, and appropriate evacuation. I can't take action.
(3) The evacuation guidance display is not written and notified in a language that the entrant can understand because the Japanese proficiency of the entrant is insufficient, and the evacuation guidance display cannot be understood.
(4) Although quick evacuation is required on the highway, there is not enough time for security guards and guides to go to the site.
(5) On the highway, the degree of danger varies depending on the area such as the front and back of the tollhouse, the roadway, the shoulder, and the presence or absence of a curve, but in detail whether the person entering the area is approaching or moving away from the more dangerous area. Since it is difficult to grasp, the evacuation guidance content is uniform for each area, and it is not possible to obtain a more appropriate guidance effect.

Therefore, in the present embodiment, as shown in FIG. 6, the input unit 100 (rider 110, camera 120) is arranged as a dangerous area so that the approach road at the entrance of the expressway becomes a monitoring area. Then, by the notification process described below, an evacuation guidance instruction is given from an area dangerous to pedestrians such as a highway entrance. The rider 110 and the camera 120 are arranged so that the monitoring areas (measurement area / photographing area) substantially coincide with each other and the optical axes substantially coincide with each other, and the alignment is performed. Further, when the measurement area of the rider 110 and the shooting area of the camera 120 extend to the outside of the approach road, it may be set in advance so that only the approach road, which is an exclusion zone, is used as the monitoring area. ..

(Notification processing in the first embodiment)
With reference to FIGS. 7 to 12, the notification process executed by the evacuation guidance device 200 according to the first embodiment will be described. FIG. 7 is a flowchart showing the notification process.

(Step S110)
Acquires moving object information in a predetermined area (monitoring area). Specifically, the acquisition unit 210 acquires the AF point cloud group data arranged in the time series in which the monitoring area is measured from the rider 110. Further, the acquisition unit 210 acquires image data (moving image) obtained by photographing the monitoring area from the camera 120.

(Step S120)
The analysis unit 220 analyzes the moving object information acquired in step S110. Here, the moving body type analysis unit 221 analyzes the type of moving body in the monitoring area. Types to be discriminated include pedestrians, bicycles, four-wheeled vehicles, and two-wheeled vehicles.

(Step S130)
The determination unit 240 determines whether or not the type of the moving object is a specific type that is not permitted to enter (invade) the monitoring area. For example, in the case of an approach road as shown in FIGS. 5 and 6, the pedestrian 93 is a specific type of moving object that is not allowed to enter (YES), and the process proceeds to step S140. On the other hand, if it is a four-wheeled vehicle or a two-wheeled vehicle and it is an object of a permitted type (NO), the processing is terminated (end). At this time, the signage 320 of the notification unit 300 may display that the vehicle can pass through.

(Step S140)
Here, the notification content determination unit 241 of the determination unit 240 causes the notification unit 300 to perform notification with the notification content preset or the notification content determined in step S170 described later. If the pedestrian 93 that is approaching has not been notified in the past, the first (first time) notification is performed with the preset notification content.

For example, the preset notification content for the first notification is "Please return" (Japanese), which is uniformly determined according to the type of moving object (person: pedestrian). The first notification (evacuation instruction) is performed immediately according to the determination that the pedestrian exists in the monitoring area without waiting for the result of the pedestrian behavior pattern determination performed below. This is because prompt evacuation instructions and evacuation start are important for accident prevention on the approach road of the expressway. It should be noted that the notification performed here continues until it is determined that the notification is not necessary or the notification is performed with a new notification content. For example, in the case of the speaker 310, the voice of the notification content is repeated and output, and in the case of the signage 320, the sound is continuously displayed.

(Step S150)
After performing the first notification, the analysis unit 220 continues to acquire the moving body information and determines the behavior pattern of the moving body. Here, the walking characteristic analysis unit 222 analyzes the walking speed and the locus. Further, the pedestrian attribute analysis unit 223 analyzes the pedestrian attribute.

In the following, a case where pedestrians A to D are assumed as an example of the pedestrian 93 will be described. It is assumed that these pedestrians A to D enter the highway entrance at different timings. However, it may be assumed that a plurality of people enter the monitoring area at the same time. In that case, each pedestrian 93 is individually tracked in parallel by the moving object ID (see FIG. 4). FIG. 8 is a diagram showing an example of pedestrian attributes of pedestrians A to D determined by the pedestrian attribute analysis unit 223 from the image data of the camera 120. 9A and 9B are diagrams showing changes in the movement loci and movement speeds of the same pedestrians A to D, respectively. FIG. 9A is a bird's-eye view (X, Y coordinates), showing that the lower side is the highway entrance, the upper side is the highway main line side, and the vehicle has proceeded in the direction of the arrow. Further, in FIG. 9A, the position of the pedestrian at the time of the first notification is indicated by a black circle. The position of this black circle corresponds to time t1 in FIG. 9B. The walking speed, the locus, and the behavior pattern composed of the classification of the behavior pattern described later are stored in the database 230 in a state of history management before and after the notification is performed.

FIG. 8 is a diagram showing the determination results of gender, age (classification), portable goods, and race for pedestrians A to D, which were performed by the pedestrian attribute analysis unit 223. Regarding gender, the certainty (%) of the judgment calculated by the pedestrian attribute analysis unit 223 is shown on the right side of the judgment result of male / female.

In the example shown in FIGS. 9A and 9B, since the pedestrian A is traveling straight, the behavior pattern is classified as "straight ahead". Since pedestrian B is returning toward the entrance, the behavior pattern is classified as "U-turn". Since pedestrian C is moving at a relatively slow speed while swaying from side to side, the behavior pattern is classified as "staggering". Since the pedestrian D is stopped from the middle, the behavior pattern is classified as "retention". These classifications are performed by the gait characteristic analysis unit 222.

(Step S160)
Here, the notification effect determination unit 242 determines the effect from the notification in step S140 and the action pattern determined in step S150. In particular, the effect is judged from the history of behavior patterns before and after the notification.

FIG. 10 is a diagram showing an example of the effect determination result of the notification (first notification (first notification)) of step S140. The figure shows the cognitive level, comprehension level, evacuation achievement rate level, and state prediction result of each of pedestrians A to D. Each level is displayed in 5 stages from 1 to 5 (1 is the lowest and 5 is the highest).

The notification effect determination unit 242 determines that the pedestrian B is "evacuated completed" because it can be seen from the behavior pattern that the first notification has effectively functioned. The notification effect determination unit 242 determines (estimates) that the pedestrian A is "language difference" and the pedestrian C is "intoxicated or cognitive impairment" from the behavior pattern and the pedestrian attribute. In addition, since the pedestrian D is stopped after the first notification, it is determined as "panic or language difference" from the history before and after.

(Step S170)
The notification content determination unit 241 determines the necessity of the next notification and the notification content. FIG. 11 is a diagram showing an example of the notification content in the second notification determined based on the effect determination result of FIG. 10 for the first notification, or together with the behavior pattern, and the pedestrian attribute. These notification contents are stored in the database 230 in advance and are selected from them, but the notification content determination unit 241 may automatically create them. For pedestrian A, the achievement level is low, and it is determined that the language is different. Therefore, it is determined that the second notification is necessary, and the notification content is determined to be "Stop and U-Turn". For pedestrian B, since the achievement level is sufficiently high, it is determined that the second notification is unnecessary. For pedestrian C, the achievement level is low, and it is determined that "drunkenness or cognitive impairment" is required, so it is determined that a second notification is necessary, and the content of the notification is determined to be "grandmother, please return". For pedestrian C, the achievement level was low, and it was judged as "panic or language difference", so it was judged that a second notification was necessary, and the content of the notification was "calm, check left and right, and the wall side." Please drop in. "

(Step S180)
The determination unit 240 determines whether or not the next notification is necessary by the determination in step S170. As shown in FIG. 11, if it is a pedestrian B, the notification is not necessary (NO), the notification up to that point is stopped, and the process is terminated. On the other hand, if it is a pedestrian A, C, or D, notification is necessary (YES), the process is returned to step S140, and the notification process is performed with the second notification content shown in FIG. Then, the processes after step S150 are repeated.

FIG. 12 is a diagram showing an example of the effect determination result of the second notification to the pedestrians A to D, and an example of the notification content in the third notification. 12 (a) and 12 (b) correspond to FIGS. 10 and 11, respectively.

As shown in FIG. 12, even after the second notification is performed, the history of the behavior pattern of the pedestrian before and after the previous notification (first notification) and the pedestrian's behavior pattern are the same as in the above judgment. From the pedestrian attribute, the necessity of the next notification (second notification) and the content of the notification are determined.

As described above, in the present embodiment, the determination unit 240 performs the next notification (second notification) based on the pedestrian behavior pattern analyzed by the analysis unit 220 after the previous notification (first notification). The necessity of notification) and the content of the notification are determined. Then, if notification is necessary, the notification unit 300 is controlled to notify the pedestrian with the determined notification content.

By doing so, it is possible to appropriately notify the notification from the evacuation guidance device 200 based on the behavior pattern of the moving body after the notification. Specifically, if there is no change in the behavior of the target pedestrian, is it because the subject is too old to hear and does not notice the voice, or is it impossible to understand the content because the language used for notification cannot be used? It is possible to judge (guess) with high accuracy the reason why notifications such as, etc. do not function effectively. Then, the success rate of evacuation guidance can be increased by selecting an appropriate notification content according to the target person based on the judgment result. Further, in the present embodiment, when used on an expressway, the above-mentioned problems (1) to (5) can be solved.

(Second embodiment)
Hereinafter, the notification process executed by the evacuation guidance device 200 according to the second embodiment will be described with reference to FIGS. 13 and 14. FIG. 13 is a schematic diagram showing a monitoring area at the entrance of the highway. FIG. 14 is a flowchart showing the notification process. In the second embodiment, the notification unit 300 includes a plurality of speakers 310a, 310b, 310c, and a plurality of signage 320a, 320b, 320c, and is used according to the position and behavior pattern of the pedestrian 93. Select 300 (speaker 310 or signage 320). Each position of these notification units 300 is stored in advance in the memory of the evacuation guidance device 200. Further, regarding the signage 320, information on the direction and orientation of the display surface of the display is stored in the memory. The second embodiment is the same as the first embodiment unless otherwise specified.

(Steps S210 to S230)
The same process as in steps S110 to S130 of FIG. 7 is performed, and if the type of moving object is a pedestrian, the process proceeds to step S235.

(Steps S235, S240)
Here, the type (speaker 310 or signage 320) and position of the notification unit 300 used for the next notification are selected according to the current position of the moving object (pedestrian). As shown in FIG. 13, if the pedestrian 93 is moving at a position far from the highway entrance, the speaker 310c and the signage 320c closest to the pedestrian 93 and / or forward in the traveling direction according to the movement locus are selected. , The selected speaker 310c and signage 320c are used for notification.

The notification content at this time is the notification content set in advance or the notification content determined in step S270, as in the first embodiment. Further, at this time, if it is determined that any signage 320 cannot be visually recognized from the position of the pedestrian 93, only the speaker 310 may be selected as the type of the notification unit 300. Further, as another example, when the evacuation guidance device 200 determines that there is no effect as a result of performing the effect determination after the first notification, both the speaker 310 and the signage 320 are selected. May be good. The speaker 310 and the signage 320 selected at this time may be the one closest to the pedestrian 93 and / or the one located forward in the traveling direction.

(Steps S250 to S280)
The following processes are the same as those in steps S150 to S180 of FIG. 7, and the process ends (end).

As described above, the same effect as that of the first embodiment can be obtained in the second embodiment.

The configurations of the evacuation guidance device 200 and the evacuation guidance system 10 described above have described the main configurations in explaining the features of the above-described embodiment, and are not limited to the above configurations and are within the scope of the claims. , Can be modified in various ways. Further, the configuration provided in the general evacuation guidance system 10 is not excluded.

For example, in the above-described embodiment, an example in which a pedestrian is determined to be a specific type of moving object and evacuation guidance is performed has been described, but the present invention is not limited to this, and a bicycle (and a driver) is further used as a specific type of moving object. This may be the target of evacuation guidance. Further, in this case, the first notification content and the second and subsequent notification contents may be configured to be different from the notification contents for pedestrians.

The means and methods for performing various processes in the evacuation guidance device according to the above-described embodiment can be realized by either a dedicated hardware circuit or a programmed computer. The program may be provided by a computer-readable recording medium such as a USB memory or a DVD (Digital Versail Disc) -ROM, or may be provided online via a network such as the Internet. In this case, the program recorded on the computer-readable recording medium is usually transferred to and stored in a storage unit such as a hard disk. Further, the above program may be provided as a single application software, or may be incorporated into the software of the device as a function of the device.

10 Evacuation guidance system 100 Input unit 110 Rider 120 Camera 200 Evacuation guidance device 210 Acquisition unit 220 Analysis unit 221 Moving object type analysis unit 222 Walking characteristic analysis unit 223 Pedestrian attribute analysis unit 230 Database 231 Pedestrian data storage unit 232 Notification content storage unit 240 Judgment unit 241 Notification content determination unit 242 Notification effect determination unit 300 Notification unit 310, 310a to 310c Speaker 320, 320a to 320c Signage

Claims (12)

An acquisition unit that acquires moving object information that measures moving objects in a predetermined area,
An analysis unit that analyzes the behavior pattern of the moving object based on the acquired moving object information,
After the first notification is given by the notification unit, the notification content is determined based on the behavior pattern analyzed by the analysis unit, and the notification unit performs the second notification to the moving object with the determined notification content. Judgment unit to control
Equipped with
The acquisition unit acquires distance measurement point cloud data showing the distribution of distance values to the moving body existing in the predetermined region as the moving body information.
The behavior pattern analyzed by the analysis unit includes the movement locus of the moving body, the moving speed of the moving body, the overturned state of the moving body, the position of the moving body, and the set dangerous area, which are obtained from the range-finding point cloud data. Includes at least one of the distances of the moving object to,
Evacuation guidance device. An acquisition unit that acquires moving object information that measures moving objects in a predetermined area,
An analysis unit that analyzes the behavior pattern of the moving object based on the acquired moving object information,
After the first notification is given by the notification unit, the notification content is determined based on the behavior pattern analyzed by the analysis unit, and the notification unit performs the second notification to the moving object with the determined notification content. Judgment unit to control
A type analysis unit that analyzes the type of the moving body based on the moving body information is provided .
When the type of the moving object determined by the type analysis unit is a specific type of moving object that is not allowed to enter the predetermined area, the analysis unit analyzes the behavior pattern for the moving object.
Evacuation guidance device. An acquisition unit that acquires moving object information that measures moving objects in a predetermined area,
An analysis unit that analyzes the behavior pattern of the moving object based on the acquired moving object information,
After the first notification is given by the notification unit, the notification content is determined based on the behavior pattern analyzed by the analysis unit, and the notification unit performs the second notification to the moving object with the determined notification content. Judgment unit to control
Equipped with
The acquisition unit acquires image data obtained by photographing the predetermined area, and obtains the image data.
Further, an attribute analysis unit for analyzing the attributes of the moving object from the image data acquired by the acquisition unit is provided.
The notification content of the second notification is determined based on the attributes of the moving object analyzed by the attribute analysis unit and the behavior pattern analyzed by the analysis unit.
Evacuation guidance device. The acquisition unit acquires distance measurement point cloud data showing the distribution of distance values to the moving body existing in the predetermined region as the moving body information.
The behavior pattern analyzed by the analysis unit includes the movement locus of the moving body, the moving speed of the moving body, the overturned state of the moving body, the position of the moving body, and the set dangerous area, which are obtained from the range-finding point cloud data. The evacuation guidance device according to claim 2, wherein the evacuation guidance device according to claim 3 includes at least one of the distances of the moving body up to. The notification unit is a plurality of notification units of one or more types.
Claim 1 to claim 1, wherein the determination unit selects the notification unit together with the notification content according to the action pattern, and controls the selected notification unit to perform a second notification to the moving object. The evacuation guidance device according to any one of 4. An acquisition unit that acquires moving object information that measures moving objects in a predetermined area,
An analysis unit that analyzes the behavior pattern of the moving object based on the acquired moving object information,
After the first notification is given by the notification unit, the notification content is determined based on the behavior pattern analyzed by the analysis unit, and the notification unit performs the second notification to the moving object with the determined notification content. Judgment unit to control
Equipped with
The notification unit is a plurality of notification units arranged at one or more different positions.
The determination unit selects the notification unit together with the notification content according to the action pattern, and controls the selected notification unit to perform a second notification to the moving object.
The acquisition unit acquires, as the moving object information, the distance measurement point cloud data showing the distribution of the distance value from the distance measurement unit that measures the predetermined area to the object in the predetermined area.
The determination unit selects the notification unit based on the movement locus of the moving object or the position of the moving object, which is obtained from the AF point cloud data.
Evacuation guidance device. The determination unit holds the history of the behavior pattern, and determines the notification content of the second notification based on the behavior pattern before and after the first notification, according to any one of claims 1 to 6. The described evacuation guidance device. A moving body information measuring unit that generates moving body information of a moving body within a predetermined area by measuring,
Notification unit and
The evacuation guidance device according to any one of claims 1 to 7, wherein the notification unit notifies the moving body by using the moving body information acquired from the moving body information measuring unit.
Evacuation guidance system equipped with. It is a control program that controls an evacuation guidance device that guides evacuation to moving objects in a predetermined area.
Step (a) of acquiring moving object information obtained by measuring a moving object in a predetermined area, and
The step (b) of analyzing the behavior pattern of the moving body based on the acquired moving body information, and
The step (c) in which the notification unit first notifies the moving object, and
After step (c), a step (d) of determining the notification content based on the behavior pattern analyzed in the step (b), and
In the step (e) of performing the second notification to the moving object with the determined notification content,
Including
In the step (a), as the moving object information, the ranging point cloud data showing the distribution of the distance value to the moving object existing in the predetermined region is acquired.
In the action pattern analyzed in the step (b), the movement locus of the moving object, the moving speed of the moving object, the overturned state of the moving object, the position of the moving object, and the position of the moving object, which were obtained from the range-finding point cloud data, were set. Includes at least one of the moving objects' distances to the danger zone,
A control program that lets a computer perform processing. It is a control program that controls an evacuation guidance device that guides evacuation to moving objects in a predetermined area.
Step (a) of acquiring moving object information obtained by measuring a moving object in a predetermined area, and
The step (b) of analyzing the behavior pattern of the moving body based on the acquired moving body information, and
The step (c) in which the notification unit first notifies the moving object, and
After step (c), a step (d) of determining the notification content based on the behavior pattern analyzed in the step (b), and
In the step (e) of performing the second notification to the moving object with the determined notification content,
Including
Further, the step (f) for analyzing the type of the moving body based on the moving body information acquired in the above (a) is included.
When the type of the moving body determined in the step (f) is a specific type of moving body that is not allowed to enter the predetermined area, the analysis of the behavior pattern for the moving body in the step (b) is performed. conduct,
A control program that lets a computer perform processing. It is a control program that controls an evacuation guidance device that guides evacuation to moving objects in a predetermined area.
Step (a) of acquiring moving object information obtained by measuring a moving object in a predetermined area, and
The step (b) of analyzing the behavior pattern of the moving body based on the acquired moving body information, and
The step (c) in which the notification unit first notifies the moving object, and
After step (c), a step (d) of determining the notification content based on the behavior pattern analyzed in the step (b), and
In the step (e) of performing the second notification to the moving object with the determined notification content,
Including
In the step (a), further, image data captured in the predetermined area is acquired, and the image data is acquired.
Further, the step (f) for analyzing the attributes of the moving object from the image data acquired in the step (a) is included.
In the step (d), the notification content of the second notification is determined based on the attributes of the moving object analyzed in the step (f) and the behavior pattern analyzed in the step (b).
A control program that lets a computer perform processing. It is a control program that controls an evacuation guidance device that guides evacuation to moving objects in a predetermined area.
Step (a) of acquiring moving object information obtained by measuring a moving object in a predetermined area, and
The step (b) of analyzing the behavior pattern of the moving body based on the acquired moving body information, and
The step (c) in which the notification unit first notifies the moving object, and
After step (c), a step (d) of determining the notification content based on the behavior pattern analyzed in the step (b), and
In the step (e) of performing the second notification to the moving object with the determined notification content,
Including
The notification unit is a plurality of notification units arranged at one or more different positions.
In the step (a), as the moving object information, the ranging point cloud data showing the distribution of the distance value from the ranging unit for measuring in the predetermined region to the object in the predetermined region is acquired.
In the step (d), the notification content is determined and the notification unit is selected according to the action pattern.
In the step (e), the notification unit selected in the step (d) performs a second notification to the moving body.
In the step (d), the notification unit is selected based on the movement locus of the moving body or the position of the moving body obtained from the AF point cloud data.
A control program that lets a computer perform processing.

Images