JP2020042859A - Determination method, computer, output device and system - Google Patents

Abstract

To provide a risk determination method which can accurately determine a degree of risk.SOLUTION: A risk determination method includes steps of: acquiring moving body information in which accompanying information showing a present point of a moving body 105 is associated with a present point image showing a surrounding situation of the moving body 105 at the present point; and determining a degree of risk corresponding to the present point based on similarity between the present point image included in the moving body information and a risky point image included in one or more pieces of risk occurrence information stored in a risk occurrence information management part 202 when risk occurrence information corresponding to the present point shown by the accompanying information included in the moving body information is not stored in the risk occurrence information management part 202 and risk occurrence information corresponding to a point except the present point is stored in the risk occurrence information management part 202.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a danger determination method, a danger determination device, a danger output device, and a danger determination system.

  When a user is moving on a moving object (for example, a vehicle), the user is notified or warned in advance of a point where a danger event such as an accident or near-miss event is highly likely to occur, so that the danger event There is known a danger determination system for preventing occurrence of the danger. In such a danger determination system, a point where a danger event is likely to occur (that is, a point with a high degree of danger) is specified based on detection results of the position, behavior, driving operation, and the like of the moving object, and the specified point is specified. Is stored in association with the map data.

  For example, in the danger determination system of Patent Document 1, the danger at each registration point is analyzed by analyzing an image around the moving object acquired by a camera and a position sensor mounted on the moving object and position information at which the image was taken. Register the event in the database. When a user passes through a registration point on a moving object, the danger level corresponding to the registration point is determined based on the danger event at the registration point registered in the database, and the danger is notified to the user or Warning.

JP 2014-154004 A

  However, in the danger determination system of Patent Literature 1, when a user passes a point other than a registered point registered in the database with a mobile object, the danger degree corresponding to the point cannot be determined. To inform or warn the danger to the person.

  Therefore, the present invention provides a danger determination method, a danger determination device, a danger output device, and a danger determination system that can accurately determine the degree of danger.

  A danger determination method according to an aspect of the present invention is a danger determination method used for a danger determination system that manages a degree of danger corresponding to a point where a moving object is located, wherein the danger determination system has a danger event. A danger point information indicating a danger point, and a danger occurrence information management unit storing one or more danger occurrence information in which first sensor information indicating a state of occurrence of the danger event at the danger point is stored. Acquiring the moving object information in which current position information indicating a current position of the moving object and second sensor information indicating a surrounding situation of the moving object at the current position are associated with each other. And the danger occurrence information corresponding to the current location indicated by the current location information included in the moving body information is not stored in the danger occurrence information management unit, and the current location When the danger occurrence information corresponding to an outside point is stored in the danger occurrence information management unit, the danger occurrence information is stored in the danger occurrence information management unit and the second sensor information included in the moving body information. Determining the degree of risk corresponding to the current location based on similarity to the first sensor information included in one or more of the danger occurrence information.

  Note that these comprehensive or specific aspects may be realized by a recording medium such as a system, a method, an integrated circuit, a computer program or a computer-readable CD-ROM, and the system, the method, the integrated circuit, and the computer program. And any combination of recording media.

  According to the danger determination method according to one embodiment of the present invention, the degree of danger can be accurately determined.

FIG. 2 is a block diagram illustrating a configuration of a danger determination system according to Embodiment 1. FIG. 2 is a block diagram illustrating a configuration of a server device according to Embodiment 1. 6 is a diagram illustrating an example of mobile object information according to Embodiment 1. FIG. FIG. 6 is a diagram showing an example of danger occurrence information according to the first embodiment. FIG. 2 is a block diagram illustrating a configuration of a mobile device according to Embodiment 1. FIG. 4 is a sequence diagram illustrating a flow of an operation of the danger determination system according to the first embodiment. FIG. 3 is a diagram for explaining an example of a service to which the danger determination system according to the first embodiment is applied. FIG. 9 is a block diagram illustrating a configuration of a danger determination system according to a second embodiment. FIG. 9 is a block diagram illustrating a configuration of a server device according to Embodiment 2. FIG. 14 is a diagram illustrating an example of danger determination information according to Embodiment 2. FIG. 13 is a sequence diagram illustrating a flow of an operation of the danger determination system according to the second embodiment.

  A danger determination method according to an aspect of the present invention is a danger determination method used for a danger determination system that manages a degree of danger corresponding to a point where a moving object is located, wherein the danger determination system has a danger event. A danger point information indicating a danger point, and a danger occurrence information management unit storing one or more danger occurrence information in which first sensor information indicating a state of occurrence of the danger event at the danger point is stored. Acquiring the moving object information in which current position information indicating a current position of the moving object and second sensor information indicating a surrounding situation of the moving object at the current position are associated with each other. And the danger occurrence information corresponding to the current location indicated by the current location information included in the moving body information is not stored in the danger occurrence information management unit, and the current location When the danger occurrence information corresponding to an outside point is stored in the danger occurrence information management unit, the danger occurrence information is stored in the danger occurrence information management unit and the second sensor information included in the moving body information. Determining the degree of risk corresponding to the current location based on similarity to the first sensor information included in one or more of the danger occurrence information.

  According to this aspect, even if the danger occurrence information corresponding to the current location indicated by the current location information included in the mobile body information is not stored in the danger occurrence information management unit, the second information included in the mobile body information is not included. And the first sensor information included in the danger occurrence information corresponding to a point other than the current point. Thereby, even when the moving body passes through a point other than the danger point corresponding to the danger occurrence information stored in the danger occurrence information management unit, the degree of danger can be accurately determined. The user can be informed or warned of danger.

  For example, in the determining step, the danger occurrence information corresponding to the current location indicated by the current location information included in the moving body information and the danger occurrence information corresponding to a point other than the current location are determined by the danger When stored in the occurrence information management unit, the second sensor information included in the moving body information and the first sensor information included in the danger occurrence information corresponding to a point other than the current location It may be configured to determine the degree of risk corresponding to the current location based on the similarity.

  According to this aspect, the risk occurrence information corresponding to the current location and the risk occurrence information corresponding to a point other than the current location are stored in the risk occurrence information management unit, and the danger information included in the mobile body information is included. If the similarity between the second sensor information and the first sensor information included in the danger occurrence information corresponding to a point other than the current point is the highest, for example, the danger occurrence information corresponding to a point other than the current point is used. To determine the degree of risk. This makes it possible to determine the degree of risk even more accurately.

  For example, the danger occurrence information further includes the severity of the danger event associated with the danger point information and the first sensor information, and in the determining step, the danger information includes the danger point information and the danger point information. The similarity between the second sensor information and the first sensor information included in one or more of the risk occurrence information stored in the risk occurrence information management unit is determined, and the similarity and the first sensor information are determined. The risk level corresponding to the current location may be determined based on the severity level associated with the sensor information.

  According to this aspect, since the risk is determined based on the similarity and the severity associated with the first sensor information, the risk can be determined with higher accuracy.

  For example, the first sensor information is a first image of the occurrence of the dangerous event at the dangerous point, and the second sensor information is an image of the surroundings of the moving body at the current point. The second image, and in the determining step, the risk level corresponding to the current location is determined based on the similarity between the first image and the second image. Is also good.

  According to this aspect, when the similarity between the first image and the second image is high, it can be estimated that the similarity between the occurrence situation of the dangerous event and the surrounding situation of the moving object at the current location is high. Therefore, the risk can be determined with high accuracy by determining the risk based on the similarity between the first image and the second image.

  For example, the danger determination method further analyzes a first traffic condition at the danger point when the danger event occurs based on the first image, and based on the second image. Analyzing the second traffic situation at the current location, wherein in the determining step, based on the similarity between the analyzed first traffic situation and the second traffic situation, It may be configured to determine the corresponding risk level.

  According to this aspect, when the similarity between the first traffic situation and the second traffic situation is high, it can be estimated that the possibility of occurrence of a dangerous event at the current location is high. Therefore, the risk can be determined with high accuracy by determining the risk based on the similarity between the first traffic situation and the second traffic situation.

  For example, the danger determination method, further, when the degree of risk corresponding to the determined current location is within a predetermined range, the current location information included in the mobile information as the danger location information, and Generating the danger occurrence information using the second sensor information included in the moving object information as the first sensor information, and adding the generated danger occurrence information to the danger occurrence information management unit May be included.

  According to this aspect, when the degree of danger is within the predetermined range, the moving body information is added to the danger occurrence information management unit as danger occurrence information, so that the accumulation amount of danger occurrence information in the danger occurrence information management unit is increased. Can be done.

  For example, in the acquiring step, the mobile body information transmitted from a mobile device mounted on the mobile body is received via a network, and the danger determination method further includes a process corresponding to the determined current location. When the risk is within a predetermined range, the method may include a step of transmitting risk information relating to the risk to the mobile device that has transmitted the mobile information.

  According to this aspect, when the risk is within the predetermined range, the risk information is transmitted to the mobile device that has transmitted the mobile information, so that the user of the mobile that is passing the current point is A danger can be notified or warned.

  For example, in the acquiring step, the mobile body information transmitted from a mobile device mounted on the mobile body is received via a network, and the danger determination method further includes a process corresponding to the determined current location. The risk is within a predetermined range, and within a predetermined time after receiving the moving object information, another moving object is included in the moving object information and the current position information indicated by the current position information is included in the current position information. When it is determined that the vehicle passes through a point, the method may include a step of transmitting risk information on the risk to a mobile device mounted on the another mobile body.

  According to this aspect, when the risk is within the predetermined range, the risk information is transmitted to a mobile device different from the mobile device that transmitted the mobile information, so that, for example, the The danger can be notified or warned.

  For example, the danger determination method further includes the step of storing danger determination information in which the danger degree corresponding to the determined current location and the current location information are associated with each other in a danger determination information management unit, In the step, when the danger determination information corresponding to the current location indicated by the current location information included in the moving body information is stored in the danger determination information management unit, the danger included in the danger determination information is included. It may be configured to use degrees.

  According to this aspect, when the danger determination information corresponding to the current location is stored in the danger determination information management unit, the danger included in the danger determination information is used. Can be done with

  For example, the moving body information further includes third sensor information indicating a traveling state of the moving body, which is associated with the current location information and the second sensor information, and in the determining step, Determine the similarity between the second sensor information included in the moving object information and the first sensor information included in one or more of the risk occurrence information stored in the risk occurrence information management unit, The risk level corresponding to the current location may be determined based on the similarity and the third sensor information.

  According to this aspect, the risk is determined based on the similarity and the third sensor information, so that the risk can be determined with higher accuracy.

  Further, the danger determination device according to one aspect of the present invention is a danger determination device that manages a danger degree corresponding to a point where a moving object is located, wherein danger point information indicating a danger point where a danger event has occurred, A danger occurrence information management unit that stores at least one danger occurrence information associated with first sensor information indicating a situation of occurrence of the danger event at the danger point, and a current position indicating a current position of the moving body Information, a receiving unit that receives moving body information associated with second sensor information indicating the surrounding state of the moving body at the current location, and a receiving unit that indicates the current location information included in the moving body information. The danger occurrence information corresponding to the current location is not stored in the danger occurrence information management unit, and the danger occurrence information corresponding to a point other than the current location is stored in the danger occurrence information management unit. The similarity between the second sensor information included in the mobile object information and the first sensor information included in one or more of the risk occurrence information stored in the risk occurrence information management unit. And a determination unit that determines the degree of risk corresponding to the current location based on the information.

  According to this aspect, even if the danger occurrence information corresponding to the current location indicated by the current location information included in the mobile body information is not stored in the danger occurrence information management unit, the second information included in the mobile body information is not included. And the first sensor information included in the danger occurrence information corresponding to a point other than the current point. Thereby, even when the moving body passes through a point other than the danger point corresponding to the danger occurrence information stored in the danger occurrence information management unit, the degree of danger can be accurately determined. The user can be informed or warned of danger.

  Further, a danger determination system according to one aspect of the present invention is a danger determination system that includes a danger determination device and a danger output device mounted on a moving body, and manages a danger degree corresponding to a point where the moving body is located. The danger determination device may generate danger point information indicating a danger point at which the danger event has occurred, and danger occurrence information in which first sensor information indicating the occurrence state of the danger event at the danger point is associated. One or more danger occurrence information management units, current position information indicating the current position of the moving object, and second sensor information indicating the surrounding state of the moving object at the current position are associated with each other. A first receiving unit that receives mobile body information, and the danger occurrence information corresponding to the current location indicated by the current location information included in the mobile body information is not stored in the danger occurrence information management unit. When the danger occurrence information corresponding to a point other than the current point is stored in the danger occurrence information management unit, the danger occurrence information management unit includes the second sensor information included in the moving body information. A determination unit that determines the degree of risk corresponding to the current location based on the similarity to the first sensor information included in one or more pieces of the risk occurrence information stored in the determination unit; A danger output device, the danger output device comprising: a first transmission unit that transmits danger information to the danger output device; the danger output device transmits the mobile body information to the danger determination device; A second receiving unit that receives the risk information transmitted from the user, and an output that outputs, based on the received risk information, alert information for alerting a user of the mobile object And a unit

  According to this aspect, even if the danger occurrence information corresponding to the current location indicated by the current location information included in the mobile body information is not stored in the danger occurrence information management unit, the second information included in the mobile body information is not included. And the first sensor information included in the danger occurrence information corresponding to a point other than the current point. Thereby, even when the moving body passes through a point other than the danger point corresponding to the danger occurrence information stored in the danger occurrence information management unit, the degree of danger can be accurately determined. The user can be informed or warned of danger.

  Further, a danger output device according to an aspect of the present invention is a danger output device used in the above-described danger determination system, wherein current position information indicating a current position of the moving object, and a vicinity of the moving object at the current position. A second transmission unit that transmits to the danger determination device mobile object information associated with the second sensor information indicating the situation, and a second reception unit that receives the danger information transmitted from the danger determination device And an output unit that outputs alert information for alerting the user of the mobile object based on the received risk degree information.

  Note that these comprehensive or specific aspects may be realized by a recording medium such as a system, a method, an integrated circuit, a computer program or a computer-readable CD-ROM, and the system, the method, the integrated circuit, and the computer program. Alternatively, it may be realized by an arbitrary combination of recording media.

  Hereinafter, embodiments will be specifically described with reference to the drawings.

  Each of the embodiments described below shows a comprehensive or specific example. Numerical values, shapes, materials, constituent elements, arrangement positions and connection forms of constituent elements, steps, order of steps, and the like shown in the following embodiments are merely examples, and do not limit the present disclosure. In addition, among the components in the following embodiments, components not described in the independent claims indicating the highest concept are described as arbitrary components.

(Embodiment 1)
[1-1. Overall configuration of danger judgment system]
The overall configuration of the danger determination system 10 according to the first embodiment will be described with reference to FIG. FIG. 1 is a block diagram illustrating a configuration of the danger determination system 10 according to the first embodiment.

  As shown in FIG. 1, the danger determination system 10 includes a server device 101 (an example of a danger determination device) and a plurality of mobile devices 102 (an example of a danger output device).

  The server device 101 includes an image database 103 (an example of an image management unit). The image database 103 manages (stores) one or more pieces of danger occurrence information. The danger occurrence information is a danger point image (the first sensor information and the first sensor information) which is an image of a situation around the moving object 105 that has encountered a danger event such as an accident or a near-miss incident at the danger point. 1 example) and accompanying information such as the shooting date and time, shooting position, and shooting direction (that is, the traveling direction of the moving object 105 that has encountered the dangerous event) of the dangerous point image (an example of the dangerous point information indicating the dangerous point) ) Is associated data. It should be noted that i) a method of photographing an image with various cameras, ii) a method of acquiring a photographing date and time, a photographing position, a photographing direction, and the like, and iii) a method of uploading a photographed image to the server apparatus 101 are disclosed in general. And the description thereof is omitted here.

  Each of the plurality of mobile devices 102 is communicatively connected to the server device 101 via the network 104, and is mounted on the corresponding mobile device 105. The moving body 105 is, for example, a vehicle driven by a user. The mobile device 102 transmits the mobile information to the server device 101 via the network 104. The moving object information includes a current position image (an example of the second sensor information and the second image), which is an image obtained by photographing the surrounding situation of the moving object 105 at the current position, and accompanying information (the moving object 105) related to the current position image. Is an example of current position information indicating the current position of the current position).

  The server device 101 analyzes the traffic situation (an example of the second traffic situation) at the current location at the time of capturing the current location image based on the received current location image and the accompanying information, and furthermore, the image database 103 The traffic condition (an example of a first traffic condition) at the danger point at the time of occurrence of the danger event is analyzed based on the danger point image and the accompanying information managed therein. The server apparatus 101 determines the risk of the situation where the moving object 105 is placed at the time of capturing the current location image based on the similarity between the two analyzed traffic conditions, and moves the risk information related to the determined risk. The data is transmitted to the body device 102 via the network 104. Note that the risk level is an index indicating a possibility that a dangerous event will occur at the current location where the moving object 105 is located at the time of capturing the current location image.

  The mobile device 102 outputs alert information for calling the user of the mobile 105 (or the mobile device 102) based on the received risk information.

[1-2. Configuration of server device]
[1-2-1. Overall configuration of server device]
Next, the overall configuration of the server device 101 will be described in detail with reference to FIGS. FIG. 2 is a block diagram showing a configuration of the server device 101 according to the first embodiment. FIG. 3 is a diagram illustrating an example of the moving object information according to the first embodiment. FIG. 4 is a diagram illustrating an example of danger occurrence information according to the first embodiment.

  As shown in FIG. 2, the server apparatus 101 includes a transmission / reception unit 201 (an example of a first transmission unit and a first reception unit), a danger occurrence information management unit 202, an image analysis unit 203, a danger determination unit 204, and a control unit. A unit 205 is provided.

  The server apparatus 101 includes a microprocessor (not shown), a random access memory (RAM), a read only memory (ROM), a hard disk, and the like. A computer program is stored in these RAM, ROM, and hard disk. When the microprocessor operates according to the computer program, the server device 101 fulfills its function.

  Note that each functional block of the transmission / reception unit 201, the danger occurrence information management unit 202, the image analysis unit 203, the danger determination unit 204, the control unit 205, and the like of the server apparatus 101 is typically an LSI (Large Scale) which is an integrated circuit. (Integration). These may be individually integrated into one chip, or may be integrated into one chip so as to include one or more functional blocks or a part of each functional block. Although an LSI is used here, it may also be called an IC (Integrated Circuit), a system LSI, a super LSI, or an ultra LSI depending on the degree of integration. The method of circuit integration is not limited to LSI, and may be realized by a dedicated circuit or a general-purpose processor. An FPGA (Field Programmable Gate Array) that can be programmed after manufacturing the LSI, or a reconfigurable processor that can reconfigure the connection and setting of circuit cells inside the LSI may be used. Furthermore, if an integrated circuit technology that replaces the LSI appears due to the progress of the semiconductor technology or another technology derived therefrom, the functional blocks may be naturally integrated using the technology. The application of biotechnology is possible. Finally, each functional block of the server device 101 may be realized by software, or may be realized by a combination of an LSI and software. Further, the software may be tamper-resistant.

[1-2-2. Transceiver]
The transmission / reception unit 201 receives the mobile information transmitted from the mobile device 102 via the network 104.

  Here, an example of the mobile object information received by the transmission / reception unit 201 will be described with reference to FIG. FIG. 3A is an example of a current location image included in the moving object information, and FIG. 3B is an example of accompanying information on the current location image included in the moving object information.

  In the example of FIG. 3, the current location image with the file name “98765432.jpg” is captured at “12:12:12 on December 12, 2014”, and the latitude and longitude of the capturing location are “+35.6682343”, respectively. , "+139.773533", indicating that the shooting (progressing) direction is "30 degrees". Here, the latitude / longitude information is obtained by converting the coordinates of a 60-base number (degrees, minutes, and seconds) into a decimal number. The shooting (progressing) direction is 0 degrees in the north direction, 90 degrees in the east direction, and 180 degrees in the south direction. The direction when the west direction is 270 degrees is represented by an angle.

  Further, the current location image whose file name is “98765432.jpg” shown in FIG. 3A is a crossing point ahead when the own vehicle, which is the moving body 105, goes straight through an intersection with a signal with a green light. This is a picture of a situation in which a pedestrian is present nearby and a preceding vehicle is approaching immediately before the pedestrian crossing.

  Further, the transmission / reception unit 201 transmits, via the network 104, the risk information regarding the risk determined by the risk determination unit 204 (described later) to the mobile device 102. The method for determining the degree of danger will be described later in detail.

[1-2-3. Danger occurrence information management department]
The danger occurrence information management unit 202 includes the above-described image database 103, and manages (stores) danger occurrence information. That is, the danger occurrence information management unit 202 accumulates a danger point image, which is an image of the surrounding situation of the moving object 105 that has encountered the danger event, and captures the shooting date and time, shooting position, and shooting (progress) direction of the danger point image. It is managed in association with the accompanying information of.

  Here, an example of danger occurrence information managed by the danger occurrence information management unit 202 will be described with reference to FIG. FIG. 4A is an example of a danger spot image included in the danger occurrence information, and FIG. 4B is an example of accompanying information related to the danger point image included in the danger occurrence information.

  In the example of FIG. 4, the danger point image with the file name “00000123.jpg” is captured at “8:30:30 on December 1, 2014”, and the latitude and longitude of the capturing position are “+35.711283”, respectively. , “+139.704802”, indicating that the shooting (progressing) direction is “30 degrees”. Here, the latitude / longitude information is obtained by converting the coordinates of a 60-base number (degrees, minutes, and seconds) into a decimal number. The shooting (progressing) direction is 0 degrees in the north direction, 90 degrees in the east direction, and 180 degrees in the south direction. The direction when the west direction is 270 degrees is represented by an angle.

  Further, the danger event in each danger point image shown in FIG. The danger event in the danger point image whose file name is “00000123.jpg” is “meeting near the beginning” where the straight-ahead vehicle jumps out from the left when the own vehicle as the moving body 105 goes straight through the intersection without traffic light. . The danger event in the danger point image whose file name is “00445566.jpg” is a pedestrian who crosses the pedestrian crossing ahead with a red light when the own vehicle, which is the moving body 105, goes straight at an intersection with a signal at a green light. This is a "hit-and-miss near-hit" where the preceding vehicle approaching the pedestrian crossing due to injuries suddenly brakes. The danger event in the danger point image whose file name is “77088099.jpg” is that when the own vehicle, which is the mobile unit 105, makes a right turn at an intersection with a signal with a green light, the right turn is completed before the oncoming vehicle approaches the intersection. When I hurried, there was a pedestrian crossing the pedestrian crossing at the right turn.

[1-2-4. Image analysis section]
The image analysis unit 203 analyzes the traffic situation at the current location at the time of capturing the current location image based on the current location image included in the moving object information received by the transmission / reception unit 201. Further, the image analysis unit 203 analyzes traffic information at the danger point at the time of occurrence of the danger event, based on the danger point image included in the danger occurrence information stored in the danger occurrence information management unit 202.

  Here, the traffic condition refers to a condition on road traffic where the moving object 105 on which the mobile device 102 is mounted is placed, and specifically, a condition related to a location including a road shape, a traffic environment, and a vehicle. It is an action. More specifically, the situation relating to a place including a road shape is, for example, an intersection, a single road (straight line), a curve, a narrow road, and the like. The traffic environment includes, for example, the light color of a signal, the presence or absence of a sign, the presence or absence of a pedestrian and an oncoming vehicle, the presence or absence of a preceding vehicle, and the distance between vehicles. The host vehicle behavior is, for example, a straight traveling, a right / left turn, a stop, a retreat, a running speed, an acceleration, and the like.

  Next, an example of a method of analyzing a traffic situation based on a current point image will be described with reference to FIG. As shown in FIG. 3A, when the transmission / reception unit 201 receives the moving body information including the current location image whose file name is “98765432.jpg”, for example, the image analysis unit 203 determines i) the road shape. The traffic condition is an intersection with a traffic light, the traffic environment is a green light, pedestrians are present near the pedestrian crossing, and the preceding vehicle is in front of the pedestrian crossing. It analyzes that the vehicle is approaching, and iii) the vehicle is running straight.

  Here, an example of a method of analyzing a traffic situation based on a current point image will be described more specifically. The situation related to the location including the road shape can be detected by, for example, recognizing a lane marking and a road marking drawn on the road surface from the current location image. The lane marking is, for example, a lane boundary line indicating a traveling lane of the vehicle. The road marking is, for example, a stop line, a "stop" mark, a pedestrian crossing, a rhombic mark indicating the presence of a pedestrian crossing, straight and left / right turning arrows, and a broken line for indicating prohibition of lane change. For example, when these road signs exist, it is possible to detect that the road is an intersection. Further, for example, when these road signs do not exist and the lane markings are straight (or curved), it is possible to detect that the road is a single road (or a curve). Further, for example, it is possible to detect whether or not a road is a narrow road based on the interval between adjacent lane markings.

  Further, the traffic environment can be detected by recognizing an image from a current location image using color characteristics and shape characteristics of an object such as a signal, a sign, a pedestrian, and another vehicle. In addition, for example, by image recognition of the headlight and the taillight, it is possible to detect whether the other vehicle is an oncoming vehicle or a preceding vehicle. In addition, for example, by image recognition of the license plate of the preceding vehicle and characters on the license plate, the inter-vehicle distance can be detected based on the size of the license plate in the image and the known photographing magnification.

  Further, the own-vehicle behavior can be detected by paying attention to the movement of, for example, a road and buildings around the same in a plurality of temporally adjacent current position images. Alternatively, the detection may be performed based on a change in the photographing position of two current position images that are temporally close to each other.

[1-2-5. Risk assessment section]
The danger degree determination unit 204 determines whether or not the moving object 105 has been detected at the time of capturing the current location image based on the similarity between the current location image received by the transmission / reception unit 201 and the dangerous location image stored in the danger occurrence information management unit 202. The degree of danger of the situation where is placed. More specifically, the risk determination unit 204 analyzes the traffic situation at the current location at the time of capturing the current location image, analyzed by the image analysis unit 203, and the traffic situation at the dangerous location when a dangerous event occurs. The above-described risk is determined based on the similarity. Further, the risk determining unit 204 generates risk information regarding the determined risk.

  Next, an example of a risk determination method will be described with reference to FIGS. For example, the danger occurrence information management unit 202 manages the danger point images and their accompanying information shown in FIGS. 4A and 4B, respectively, and the transmission / reception unit 201 sets the file name shown in FIG. 3A to “98765432”. .Jpg ”will be described. In this case, based on the traffic conditions analyzed by the image analysis unit 203, the danger determining unit 204 determines i) that the traffic condition is an intersection with a traffic light related to the location including the road shape, ii) that the traffic environment is a green light, Based on the fact that a pedestrian is present in front of the pedestrian crossing, that a preceding vehicle is approaching immediately before the pedestrian crossing, and iii) that the vehicle is traveling straight ahead, the danger occurrence information management unit The similarity (similarity) between the danger point image whose file name managed by 202 is “00445566.jpg” and the current point image is calculated. If the calculated similarity is, for example, “0.8”, the risk determination unit 204 determines that the moving object 105 is placed at the time of capturing the current location image whose file name is “98765432.jpg”. Is determined to be “0.8”. The risk is, for example, a score from “0” to “1” (grain size in increments of 0.1), where “0” indicates no risk and “1” indicates the highest risk. Is shown.

  Here, an example of a method of calculating the similarity between the dangerous point image and the current point image will be described. For example, the similarity can be calculated by using an image search method called CBIR (Content-Based Image Retrieval) or the like. This CBIR is known as a method of detecting an image similar to a given image from a database based on the similarity of image feature amounts such as color, object shape, and texture (texture and pattern of the surface of the object). . According to the CBIR, it is possible to obtain a highly similar danger spot image by searching the danger occurrence information management unit 202 based on the similarity of the image feature amount of the traffic situation analyzed by the image analysis unit 203. Become.

  Further, an example of a method of generating risk information regarding the determined risk will be described. For example, the determined degree of risk (“0.8” in the example of the above-described method of determining the degree of risk) can be directly used as the degree of risk information. Any information that can be output to call attention to the driver) may be used. For example, any character information or voice may be used. It is not necessary to generate the risk information every time the risk is determined, and any character information or voice or the like may be selected as the risk information from the character information or voice or the like registered in advance. . Here, for example, when any character information or voice is used as the risk information, it is desirable to use character information or voice that allows the user of the moving object 105 to understand the risk.

[1-2-6. Control section]
The control unit 205 implements the function of the server device 101 by managing and controlling the above-described transmission / reception unit 201, danger occurrence information management unit 202, image analysis unit 203, and danger determination unit 204.

[1-3. Configuration of mobile device]
[1-3-1. Overall Configuration of Mobile Device]
Next, the overall configuration of the mobile device 102 will be described in detail with reference to FIG. FIG. 5 is a block diagram showing a configuration of the mobile device 102 according to the first embodiment.

  As shown in FIG. 5, the mobile device 102 includes a transmission / reception unit 501 (an example of a second transmission unit and a second reception unit), an input reception unit 502, an output unit 503, and a control unit 504.

  The mobile device 102 includes a microprocessor, a RAM, a ROM, a hard disk, and the like (not shown). A computer program is stored in these RAM, ROM, and hard disk. When the microprocessor operates according to the computer program, the mobile device 102 performs its function.

  Each functional block such as the transmission / reception unit 501, the input reception unit 502, the output unit 503, and the control unit 504 is typically realized as an LSI which is an integrated circuit. These may be individually integrated into one chip, or may be integrated into one chip so as to include one or more functional blocks or a part of each functional block. Although an LSI is used here, it may be called an IC, a system LSI, a super LSI, or an ultra LSI depending on the degree of integration. The method of circuit integration is not limited to LSI, and may be realized by a dedicated circuit or a general-purpose processor. After the LSI is manufactured, a programmable FPGA or a reconfigurable processor capable of reconfiguring connection and setting of circuit cells inside the LSI may be used. Furthermore, if an integrated circuit technology that replaces the LSI appears due to the progress of the semiconductor technology or another technology derived therefrom, the functional blocks may be naturally integrated using the technology. The application of biotechnology is possible. Finally, each functional block of the mobile device 102 may be realized by software, or may be realized by a combination of an LSI and software. Further, the software may be tamper-resistant.

[1-3-2. Transceiver]
The transmission / reception unit 501 transmits the mobile body information received by the input reception unit 502 to the server device 101 via the network 104.

  In addition, the transmission / reception unit 501 receives the risk level information transmitted from the server device 101 via the network 104.

[1-3-3. Input reception unit]
The input receiving unit 502 receives mobile object information as input. More specifically, the input receiving unit 502 receives, as inputs, a current location image, which is an image of the surroundings of the moving object 105 at the current location, and accompanying information related to the current location image.

  The current location image is an image captured by, for example, a vehicle-mounted camera, a drive recorder, or a camera of a smartphone. It should be noted that i) a method of photographing an image with various cameras, and ii) a method of acquiring a photographing date and time, a photographing position, a photographing (progressing) direction, and the like may be any method that is generally disclosed. Omitted.

[1-3-4. Output section]
The output unit 503 outputs alert information for alerting the user of the mobile object 105 (or the mobile device 102) based on the risk information received by the transmitting / receiving unit 501. For example, when the alert information is text information, the alert information is output to a display or the like (not shown) mounted on the moving object 105 to output the alert information to the user. (For example, a character string stating that “the risk of occurrence of a rear-end collision is 0.8”) is displayed on the display. Further, for example, when the alert information is a voice, the alert information is output to a speaker or the like (not shown) mounted on the moving body 105, so that a voice for alerting the user is provided. (For example, a voice uttering “the risk of occurrence of a rear-end collision is 0.8”) is output from the speaker.

[1-3-5. Control section]
The control unit 504 implements the function of the mobile device 102 by managing and controlling the transmission / reception unit 501, the input reception unit 502, and the output unit 503 described above.

[1-4. Operation of the danger judgment system]
Next, the operation of the danger determination system 10 (danger determination method) will be described with reference to FIG. FIG. 6 is a sequence diagram illustrating a flow of the operation of the danger determination system 10 according to the first embodiment.

  First, the mobile device 102 receives the input of the current location image of the surroundings of the mobile device 105 on which the mobile device 102 is mounted and the accompanying information related to the current location image by the input receiving unit 502 (S601). . Thereafter, the mobile device 102 transmits the received current location image and the accompanying information to the server device 101 via the transmission / reception unit 501 (S602).

  The server device 101 receives the current location image and the accompanying information from the mobile device 102 via the transmission / reception unit 201 (S603). After that, the image analysis unit 203 of the server device 101 analyzes the traffic situation at the current point at the time of capturing the current point image based on the received current point image and the accompanying information (S604). Thereafter, based on the traffic condition analyzed by the danger degree determination unit 204, the server apparatus 101 determines the similarity between the danger point image managed by the danger occurrence information management unit 202 and the current point image, based on the similarity of the received current point image. The degree of danger of the situation where the moving object 105 is placed at the time of shooting is determined, and danger level information relating to the determined degree of danger is generated (S605).

  At this time, the danger spot image corresponding to the current location (for example, the intersection A shown in the current location image whose file name is “98765432.jpg” shown in FIG. 3A) is managed by the danger occurrence information management unit 202. The danger point image corresponding to a point other than the current point (for example, the intersection B represented in the danger point image whose file name is “00445566.jpg” shown in FIG. When managed by the occurrence information management unit 202, the risk determination unit 204 determines based on the similarity between the danger point image corresponding to a point other than the current point (for example, the intersection B) and the current point image. Determine the degree of risk.

  Further, when the danger point image corresponding to the current point (for example, the intersection A) and the danger point image corresponding to a point other than the current point (for example, the intersection B) are managed by the danger occurrence information management unit 202, For example, the danger determination unit 204 searches for a danger point image having the highest similarity with the current point image from among danger point images corresponding to the current point and danger point images corresponding to points other than the current point. As a result, when the similarity between the danger point image corresponding to a point other than the current point (for example, the intersection B) and the current point image is the highest, the risk degree determination unit 204 corresponds to a point other than the current point. The degree of danger is determined based on the similarity between the danger point image and the current point image. If the similarity between the dangerous spot image corresponding to the current location and the current location image is the highest, the risk determination unit 204 determines based on the similarity between the dangerous location image corresponding to the current location and the current location image. The risk may be determined by using

  After that, when the risk level is within the predetermined range, the server apparatus 101 transmits the generated risk level information to the mobile device 102 via the transmission / reception unit 201 (S606). The predetermined range is, for example, a case where the risk exceeds a preset threshold (for example, “0.5”). The mobile device 102 that is the destination of the risk information is, for example, the mobile device 102 that is the source of the mobile information received by the server device 101.

  The mobile device 102 receives the risk information on the risk determined by the server device 101 from the server device 101 via the transmission / reception unit 501 (S607). Thereafter, the mobile device 102 outputs, on the output unit 503, alert information for calling the user of the mobile 105 (or the mobile device 102) based on the received risk information. (S608).

[1-5. Application example of danger judgment system]
Next, an example of a service to which the danger determination system 10 according to the first embodiment is applied will be described with reference to FIG. FIG. 7 is a diagram for explaining an example of a service to which the danger determination system 10 according to the first embodiment is applied.

  A group 700 shown in FIG. 7A is, for example, a company, an organization, a home, or the like, and its size does not matter. The group 700 includes a plurality of mobile devices 102 and communication devices 703. Each of the plurality of mobile devices 102 is a device directly connectable to the Internet (for example, a car navigation system with a communication module, a smartphone, a tablet or a personal computer, or the like), or a device not directly connectable to the Internet by itself (for example, , A car navigation system without a communication module, etc.). When each of the plurality of mobile devices 102 is a device that cannot directly connect to the Internet by itself, the mobile device 102 may be a device that can connect to the Internet via the communication device 703. The group 700 includes a user 701 who uses a plurality of mobile devices 102.

  The server apparatus 101 described above exists in the data center operating company 710 shown in FIG. The server apparatus 101 is a virtual server that cooperates with various devices via the Internet, and mainly manages huge data (big data) that is difficult to handle with a normal database management tool or the like. The data center operating company 710 performs data management, management of the server device 101, and operation of a data center that performs these operations. The services performed by the data center operating company 710 will be described later in detail.

  Here, the data center operating company 710 is not limited to a company that performs only data management and operation of the server device 101. As shown in FIG. 7B, for example, a device maker that develops and manufactures one of the plurality of mobile devices 102 performs data management, management of the server device 101, and the like. In this case, the device maker corresponds to the data center operating company 710.

  Further, the data center operating company 710 is not limited to one company. As shown in FIG. 7C, for example, when the device maker and another management company jointly or share the data management and the operation of the server device 101, both or one of the data management and the management is performed. This corresponds to the center operating company 710.

  The service provider 720 shown in FIG. 7A has a server device 721. The server device 721 may be, for example, a memory in a personal computer, regardless of its size. Note that the service provider 720 may not have the server device 721 in some cases.

  Next, an information flow in a service to which the danger determination system 10 is applied will be described with reference to FIG.

  First, the mobile device 102 of the group 700 transmits the current location image obtained by capturing the surrounding situation of the mobile device 105 (see FIG. 1) on which the mobile device 102 is mounted, and the accompanying information on the current location image to the data center operation. The data is transmitted to the server device 101 of the company 710. Thereby, the server device 101 accumulates the current location image and the accompanying information transmitted from the mobile device 102 ((A) shown in FIG. 7). The current location image and the accompanying information may be provided directly from the plurality of mobile devices 102 to the server device 101 via the Internet. Further, the current location image and the accompanying information may be provided from a plurality of mobile devices 102 to the server device 101 via the communication device 703.

  Next, the server device 101 of the data center operating company 710 provides the accumulated current location image and the accompanying information to the service provider 720 in fixed units. Here, the unit of the information provided by the data center operating company 710 may be a unit capable of organizing the accumulated current location image and the accompanying information and providing the same to the service provider 720, or the unit provided by the service provider 720. You can also use a unit. Also, the unit of information provided by the data center operating company 710 may not be constant, and the amount of information provided may vary depending on the situation.

  The current point image and the accompanying information are stored in the server device 721 owned by the service provider 720 as necessary ((B) shown in FIG. 7). After that, the service provider 720 arranges the current location image and the accompanying information into information (risk level information or alert information output based on the risk level information) suitable for the service provided to the user, and provides the information to the user. The user to be provided may be a user 701 using a plurality of mobile devices 102 or an external user 702.

  The current point image and the accompanying information may be provided directly from the service provider 720 to the user 702 (or the user 701) ((E) or (F) shown in FIG. 7), or the data center operation. It may be provided to the user 701 via the server device 101 of the company 710 again ((C) and (D) shown in FIG. 7). Further, the server device 101 of the data center operating company 710 may arrange the current location image and the accompanying information into information suitable for a service provided to the user, and provide the information to the service provider 720. Note that the user 701 and the user 702 may be different users or the same user.

[1-6. effect]
Next, effects obtained by the danger determination system 10 according to the first embodiment will be described. As described above, the risk determination unit 204 determines that the danger occurrence information corresponding to the current location (for example, the intersection A) indicated by the accompanying information related to the current location image is not stored in the danger occurrence information management unit 202. Also, the degree of danger is determined based on the similarity between the danger point image included in the danger occurrence information corresponding to a point other than the current point (for example, the intersection B) and the current point image. Thereby, even when the moving object 105 passes through a point other than the danger point corresponding to the danger occurrence information managed by the danger occurrence information management unit 202 (for example, the intersection A), the degree of danger is accurately determined. For example, it is possible to notify or warn the user of the mobile object 105 of danger.

[1-7. Modification of First Embodiment]
[1-7-1. Modification 1]
The danger spot image managed by the danger occurrence information management unit 202 of the server apparatus 101 does not need to be the photographed image itself, and is processed into an image in which the degree of similarity with the current location image can be easily calculated by the danger determination unit 204. Alternatively, one or more dangerous spot images processed in this way may be newly managed in association with the original dangerous spot image.

  Specifically, for example, image features related to traffic conditions such as a situation related to a place including a road shape, a traffic environment, and own vehicle behavior may be processed into a binary image in which the image features are raised, or the binarized image may be processed. The image may be managed in association with the original danger point image.

  Furthermore, the image feature amount relating to the traffic situation may be managed in association with the original dangerous spot image as a plurality of binarized images corresponding to the situation relating to the location including the road shape, the traffic environment, the own vehicle behavior, and the like. good. In this case, the risk determination unit 204 calculates not the similarity between the original dangerous point image and the current point image but, for example, the similarity between the dangerous point image processed into the binarized image and the current point image. Is desirable.

[1-7-2. Modification 2]
The accompanying information of the danger point image managed by the danger occurrence information management unit 202 by the server apparatus 101 does not need to be the value itself acquired at the time of shooting, and the danger determination unit 204 determines the similarity between the current point image and the danger point image. May be replaced with a granularity that has a meaning (or similarity can be easily calculated) in calculating the, or additional information of the granularity may be newly added.

  More specifically, the meaningful (or easy to calculate similarity) granularity of the shooting date and time is, for example, 24 time zones every hour from 0:00, am / pm, monday, day of the week, season, holiday And so-called Goto days (5 days, 10 days, 15 days, 20 days, 25 days, 30 days) and the like. Further, the meaningful (or easy to calculate similarity) granularity of the photographing position is, for example, an area in which map information is divided into a rectangular shape having a uniform size, a road section in which a road is divided by a predetermined distance, or the like. It is. Further, the granularity that is meaningful (or easy to calculate the similarity) with respect to the shooting (progressing) direction is, for example, four directions of east, west, north, and south, eight directions in which northeast / southeast / northwest / southwest is added, or road up / Such as going down.

  Further, the accompanying information of the danger spot image managed by the danger occurrence information management unit 202 by the server apparatus 101 does not need to be limited to the traffic situation at the time of shooting, and includes the mobile device 102 that has acquired the current spot image. Various attribute information on the moving object 105 may be included. In this case, it is desirable that the risk determination unit 204 calculates not only the similarity between the dangerous point image and the current point image but also the similarity including these various pieces of attribute information. Here, the various types of attribute information include, for example, the weight, displacement, and vehicle type of the vehicle that is the moving body 105. The vehicle type is, for example, a sedan, a wagon or a truck. These pieces of attribute information are fixed for each moving object 105, and can be acquired by a method such as presetting in the mobile device 102 according to the moving object 105, for example.

[1-7-3. Modification 3]
The accompanying information of the danger point image managed by the danger occurrence information management unit 202 by the server apparatus 101 may include information describing the content of a danger event such as an accident or a near-miss incident shown in the danger point image. Furthermore, the risk information generated by the risk determining unit 204 of the server apparatus 101 may include part or all of the information describing the contents of the dangerous event.

  Here, an example of information describing the content of the dangerous event will be described with reference to FIG. As shown in FIG. 4A, the information describing the content of the danger event with respect to the danger point image whose file name is “00000123.jpg” is, for example, “a near-miss incident”. Further, the information describing the content of the danger event with respect to the danger point image whose file name is “00445566.jpg” is, for example, “back-end near-miss”. In addition, information that describes the contents of a dangerous event with respect to a dangerous spot image whose file name is “77088099.jpg” is, for example, “a near-missing crossing with an oncoming pedestrian”.

  An example of a method of generating risk information in this case will be described. For example, in the server apparatus 101, the transmission / reception unit 201 receives the current location image whose file name is “98765432.jpg” shown in FIG. 3A, and the risk determination unit 204 shows the current location image shown in FIG. If it is determined that the danger is “0.8” based on the similarity between the danger spot image whose file name is “00445566.jpg” and the current location image, the danger determination unit 204 generates the danger. The risk information is, for example, "the risk of a rear-end collision is 0.8."

[1-7-4. Modification 4]
The accompanying information of the current location image received by the server apparatus 101 from the mobile apparatus 102 does not need to be limited to information related to capturing of the current location image, and may include moving information acquired from sensors separately mounted on the mobile body 105. Various sensor information indicating the traveling state of the body 105 (an example of third sensor information) may be included. In this case, it is desirable that the risk determination unit 204 calculates not only the similarity between the dangerous point image and the current point image but also the similarity including these various types of sensor information.

  Here, the various types of sensor information include, for example, the traveling speed, acceleration, and angular velocity of the moving body 105 obtained from a position sensor such as a GPS (Global Positioning System), an acceleration sensor, and an angular velocity sensor such as a gyro. Further, the sensor information is not limited to the above, and may include, for example, any information necessary for analyzing the traffic condition by the image analysis unit 203. For example, when the moving body 105 is a vehicle, the sensor information may include a steering operation, a brake operation, an accelerator operation, a wiper operation, and the like, and these may include, for example, a CAN (Control Area Network) in the vehicle. Can be obtained from the network.

  Further, the accompanying information of the current location image received by the server apparatus 101 from the mobile apparatus 102 may include various types of attribute information on the mobile body 105 having the mobile apparatus 102 that has acquired the current location image. In this case, it is desirable that the risk determination unit 204 calculates not only the similarity between the dangerous point image and the current point image but also the similarity including these various pieces of attribute information. Here, the various types of attribute information include, for example, the weight, displacement, and vehicle type of the vehicle that is the moving body 105. The vehicle type is, for example, a sedan, a wagon or a truck. These pieces of attribute information are fixed for each moving object 105, and can be acquired by, for example, a method of presetting the moving object device 102 according to the moving object 105.

[1-7-5. Modification 5]
The server apparatus 101 does not always need to individually and sequentially execute the traffic condition analysis processing in the image analysis unit 203 and the similarity calculation processing between the danger point image and the current point image in the danger degree determination unit 204. For example, by using a machine learning method called deep learning (deep learning) or the like, the traffic condition analysis processing and the similarity calculation processing may be performed in parallel.

[1-7-6. Modification 6]
In the danger occurrence information management unit 202, the server apparatus 101 may also manage the severity of the danger event encountered by the moving object 105 in association with each danger point image as accompanying information. In this case, the risk determining unit 204 multiplies, for example, the similarity between the dangerous point image having the highest similarity and the current point image by the severity managed in association with the dangerous point image. Alternatively, the risk of the situation where the moving object 105 is placed at the time of capturing the current location image may be determined.

  Here, the severity may be anything as long as the severity of the dangerous event encountered by the moving object 105 is expressed based on a predetermined criterion. For example, the degree of seriousness indicates whether or not an accident has occurred, the degree of human damage, or the degree of the amount of insurance paid, such as a score from “0” to “1” (0. (Grain size of one step). Note that the degree of seriousness may be obtained by any method from accident or information on the occurrence of near-miss incidents held by the police or transport companies, or accident assessment information held by non-life insurance companies, etc. Here, the description is omitted.

[1-7-7. Modification 7]
The server device 101 stores the current location image received by the transmission / reception unit 201 as a new danger location image in the danger occurrence information management unit 202 when the danger determined by the danger determination unit 204 is within a predetermined range. (Addition) and may be managed in association with the accompanying information of the current location image. Here, the predetermined range is, for example, a case where a value exceeds a preset threshold value (for example, “0.5”).

[1-7-8. Modification 8]
The mobile device 102 to which the risk information related to the risk determined by the server device 101 is transmitted need not be the same as the mobile device 102 from which the current location image received by the server device 101 is transmitted. For example, when the moving object 105 is a vehicle, the risk information on the risk corresponding to the specific point determined based on the current point image transmitted from the preceding vehicle is slightly delayed from the same specific point (for example, moving The information may be transmitted to the mobile device 102 mounted on the following vehicle (another mobile object 105) determined to pass within a predetermined time after receiving the body information. Thereby, it is possible to call attention to the user (driver) of the following vehicle.

(Embodiment 2)
[2-1. Overall configuration of danger judgment system]
The overall configuration of the danger determination system 10A according to the second embodiment will be described with reference to FIG. FIG. 8 is a block diagram illustrating a configuration of a danger determination system 10A according to the second embodiment. Note that, in the present embodiment, the same components as those in Embodiment 1 are denoted by the same reference numerals, and description thereof will be omitted.

  As shown in FIG. 8, the danger determination system 10A includes a server device 101A and a plurality of mobile devices 102. Mobile device 102 is the same as that described in the first embodiment.

  The server device 101A includes an index database 106 (an example of an index management unit) in addition to the image database 103 described in the first embodiment. In the index database 106, a risk index (danger determination information) relating to the danger of a dangerous event such as an accident or a near-miss event that has occurred in the past, the date and time, position and direction of occurrence of the dangerous event (that is, the traveling direction of the moving object 105) ) Is managed (stored) in association with accompanying information such as Here, the risk index is obtained or calculated in advance by any method from, for example, information on the occurrence of accidents or near-miss incidents held by the police or transportation companies, or accident assessment information held by non-life insurance companies. It is sufficient that the description is omitted here.

  The server apparatus 101 </ b> A determines whether the mobile object 105 is located at the time of capturing the current location image based on the similarity between the accompanying information received from the mobile apparatus 102 and the risk index managed in the index database 106. Is determined as the first risk. Further, the server device 101A transmits the first risk information on the determined first risk to the mobile device 102 via the network 104.

  Further, the server apparatus 101A analyzes the traffic situation at the time of capturing the current location image based on the current location image received from the mobile device 102 and the accompanying information, and identifies the dangerous location managed by the image database 103. From the similarity between the image and the current location image, a second risk level, which is the risk level of the situation where the moving object 105 is placed at the time of capturing the current location image, is determined. Further, when the determined second risk is within a predetermined range, the server device 101A stores the second risk information regarding the determined second risk as a new risk index in the index database 106 ( ), And manages the information in association with the accompanying information of the current location image. Here, the predetermined range is, for example, a case where a value exceeds a preset threshold value (for example, “0.5”).

[2-2. Configuration of server device]
[2-2-1. Overall configuration of server device]
Next, the overall configuration of the server device 101A will be described in detail with reference to FIG. FIG. 9 is a block diagram illustrating a configuration of a server device 101A according to the second embodiment.

  As shown in FIG. 9, the server device 101A includes a risk determination information management unit 206 in addition to the transmission / reception unit 201, the risk occurrence information management unit 202, the image analysis unit 203, the risk determination unit 204A, and the control unit 205A. I have.

  The server device 101A includes a microprocessor, a RAM, a ROM, a hard disk, and the like (not shown). A computer program is stored in these RAM, ROM and hard disk. When the microprocessor operates according to the computer program, the server device 101A performs its function.

  In addition, each functional block of the transmission / reception unit 201, the danger occurrence information management unit 202, the image analysis unit 203, the danger determination unit 204A, the control unit 205A, and the danger determination information management unit 206 of the server apparatus 101A is typically integrated. It is realized as an LSI which is a circuit. These may be individually integrated into one chip, or may be integrated into one chip so as to include one or more functional blocks or a part of each functional block. Although an LSI is used here, it may be called an IC, a system LSI, a super LSI, or an ultra LSI depending on the degree of integration. The method of circuit integration is not limited to LSI, and may be realized by a dedicated circuit or a general-purpose processor. After the LSI is manufactured, a programmable FPGA or a reconfigurable processor capable of reconfiguring connection and setting of circuit cells inside the LSI may be used. Furthermore, if an integrated circuit technology that replaces the LSI appears due to the progress of the semiconductor technology or another technology derived therefrom, the functional blocks may be naturally integrated using the technology. The application of biotechnology is possible. Finally, each functional block may be realized by software, or may be realized by a combination of an LSI and software. Further, the software may be tamper-resistant.

[2-2-2. Transceiver]
The transmission / reception unit 201 is the same as that described in the first embodiment, but transmits first risk information on the first risk determined by the risk determination unit 204A to the mobile device 102.

[2-2-3. Danger occurrence information management department]
The danger occurrence information management unit 202 is the same as that described in the first embodiment.

[2-2-4. Image analysis section]
The image analysis unit 203 is the same as that described in the first embodiment.

[2-2-5. Risk assessment section]
The danger determining unit 204 </ b> A determines whether or not the current location image has been captured based on the similarity between the accompanying information on the current location image received by the transmission / reception unit 201 and the danger determination information managed by the danger determination information management unit 206. A first risk, which is a risk in a situation where the moving object 105 is placed, is determined, and first risk information relating to the determined first risk is generated. The method of generating the first degree of risk information is the same as that described in the first embodiment.

  Here, an example of a method of determining the first degree of risk will be described. The danger determination information management unit 206 manages, for example, danger determination information shown in FIG. 10 described later, and the transmission / reception unit 201 shows, for example, the accompanying information of the current location image whose file name is “98765432.jpg” shown in FIG. Is received. In this case, for example, based on the fact that both time zones are on the same 12 o'clock and that their positions (latitude and longitude) and traveling directions are close to each other, the risk degree determination unit 204A determines “December 8, 2014” Based on the similarity between the danger determination information of the danger event that occurred at 12:00:20 on the day and the accompanying information of the current location image, it is determined that the first degree of danger is “0.9”.

  Further, based on the traffic situation analyzed by the image analysis unit 203, the risk determination unit 204A determines whether or not the transmission / reception unit 201 has similarity between the danger point image managed by the danger occurrence information management unit 202 and the current point image. The second danger level, which is the danger level of the situation where the moving object 105 is placed at the time of capturing the received current point image, is determined. Further, the risk determining unit 204A generates second risk information regarding the determined second risk. Here, a method for calculating the similarity between the dangerous point image and the current point image, a second risk degree determining method, and a second risk degree information generating method are the same as those described in the first embodiment. The same is true.

[2-2-6. Danger judgment information management section]
The danger determination information management unit 206 includes the above-described index database 106, and manages (stores) danger determination information. That is, the danger determination information management unit 206 accumulates danger determination information on the danger of a danger event such as an accident or near-miss event that occurred in the past, and links it with accompanying information such as the date and time of occurrence, the location and the direction of occurrence (progress). Manage.

  Here, an example of danger determination information managed by the danger determination information management unit 206 will be described with reference to FIG. FIG. 10 is a diagram illustrating an example of danger determination information according to the second embodiment.

  In the example of FIG. 10, “December 1, 2014, 8:30:30”, “December 5, 2014, 12:45:30”, and “December 8, 2014 12:00:20” The danger determination information of a danger event such as an accident or a near-miss incident that occurred at “14:00:45 on December 10, 2014” is managed in association with each occurrence date and time, occurrence position, and occurrence (progress) direction. Have been. For example, at “8: 30: 00: 00 on December 1, 2014”, while traveling at points with latitude and longitude of “+35.7121283” and “+139.704802” in the traveling direction “30 degrees”, the degree of danger is It indicates that a dangerous event such as an accident or a near miss that is “0.5” has occurred.

  The latitude / longitude information is obtained by converting the coordinates of a 60-base number (degrees, minutes, and seconds) into a decimal number. The shooting (progressing) direction is 0 degrees in the north direction, 90 degrees in the east direction, 180 degrees in the south direction, and west direction. Is 270 degrees, and the direction is represented by an angle. The risk level is, for example, a score from “0” to “1” (grain size in increments of 0.1), where “0” indicates no risk level and “1” indicates the highest risk level. ing. The method of expressing the degree of risk is not limited to this, and for example, the upper limit value and the granularity (for example, only an integer value or in increments of 0.1) representing the highest degree of risk can be arbitrarily determined and adopted.

  When the second risk level determined by the risk level determination unit 204A is within a predetermined range, the risk determination information management unit 206 converts the second risk level information relating to the second risk level into a new risk level. The information is stored (added) as information and managed in association with the accompanying information of the current location image. Here, the predetermined range is, for example, a case where the value exceeds a preset threshold value (for example, “0.5”).

[2-2-7. Control section]
The control unit 205A implements the function of the server device 101A by managing and controlling the above-described transmission / reception unit 201, danger occurrence information management unit 202, image analysis unit 203, danger degree determination unit 204A, and danger determination information management unit 206. I do.

[2-3. Mobile device]
Mobile device 102 is basically the same as that described in the first embodiment. The transmitting / receiving unit 501 (see FIG. 5) of the mobile device 102 transmits the current location image and the accompanying information to the server device 101A, and receives the first risk information from the server device 101A. The output unit 503 (see FIG. 5) of the mobile device 102 outputs the alert information based on the received first risk information.

[2-4. Operation of the danger judgment system]
Next, the operation of the danger determination system 10A (danger determination method) will be described with reference to FIG. FIG. 11 is a sequence diagram illustrating a flow of the operation of the danger determination system 10A according to the second embodiment.

  The mobile device 102 receives, as an input, an input receiving unit 502 (see FIG. 5) of a current location image obtained by capturing a situation around the mobile device 105 on which the mobile device 102 is mounted, and accompanying information relating to the current location image. (S1101). Thereafter, the mobile device 102 transmits the received current location image and the accompanying information to the server device 101A via the transmission / reception unit 501 (S1102).

  The server device 101A receives the current location image and the accompanying information from the mobile device 102 via the transmission / reception unit 201 (S1103). Thereafter, when the danger determination information corresponding to the current location indicated by the accompanying information on the received current location image is managed by the danger determination information management unit 206, the server apparatus 101A causes the danger determination unit 204A to output the danger determination information The first risk is determined based on the similarity with the accompanying information on the current point image, and the first risk information on the determined first risk is generated (S1104). Thereafter, when the first risk level is within the predetermined range, the server apparatus 101A transmits the generated first risk level information to the mobile device 102 via the transmission / reception unit 201 (S1105).

  The mobile device 102 receives the first risk information from the server device 101A via the transmission / reception unit 501 (S1106). Thereafter, the mobile device 102 outputs, on the output unit 503, the alert information for calling the user of the mobile device 105 (or the mobile device 102) based on the received first risk information. Is output (S1107).

  In addition, the server device 101A analyzes the traffic situation at the time of capturing the current location image based on the received current location image and the accompanying information in the image analysis unit 203 (S1108). Thereafter, based on the traffic condition analyzed by the danger degree determination unit 204A, the server device 101A determines the similarity between the danger point image managed by the danger occurrence information management unit 202 and the current point image, and determines whether the received current point image has been received. The second danger level of the situation where the moving object 105 is placed at the time of imaging is determined, and second danger level information relating to the determined second danger level is generated (S1109). Thereafter, the server apparatus 101A stores (adds) the determined second degree of risk information as new danger determination information in the danger determination information management unit 206, and manages it in association with the accompanying information of the current location image (S1110). ).

[2-5. Application example of danger judgment system]
An application example of the danger determination system 10A according to the second embodiment is the same as that described in the first embodiment.

[2-6. effect]
Next, effects obtained by the danger determination system 10A according to the second embodiment will be described. As described above, the risk determination unit 204A determines the first risk based on the similarity between the risk determination information and the accompanying information on the current location image. This first risk determination process can be executed in a shorter time than the similarity calculation process between the danger point image and the current point image, so that the mobile device 105 quickly outputs the alert information. can do.

[2-7. Modification of Second Embodiment]
[2-7-1. Modification 1]
The danger point image managed by the danger occurrence information management unit 202 by the server apparatus 101A does not need to be the photographed image itself, and is processed into an image in which the degree of similarity with the current point image can be easily calculated by the danger degree determination unit 204A. Alternatively, one or more dangerous spot images processed in this way may be newly managed in association with the original dangerous spot image.

  Specifically, for example, it may be processed into a binarized image in which image features related to traffic conditions such as a situation relating to a road shape, a traffic environment and a vehicle behavior such as a vehicle behavior are raised, or the binarized image may be processed. May be managed in association with the original danger point image.

  Furthermore, even if the image feature amount relating to the traffic condition is managed in association with the original dangerous spot image as a plurality of binarized images corresponding to the situation relating to the location including the road shape, the traffic environment, the own vehicle behavior, etc. good. In this case, the danger degree determination unit 204A calculates, for example, the similarity between the danger point image processed into the binarized image and the current point image instead of the similarity between the original danger point image and the current point image. Is desirable.

[2-7-2. Modification 2]
The accompanying information of the danger determination information managed by the server apparatus 101A by the danger determination information management unit 206 does not need to be the value itself acquired in advance, and the danger determination unit 204A calculates the similarity to the accompanying information of the current location image. It may be replaced with a granularity that is meaningful (or the similarity can be easily calculated), or additional information of the granularity may be newly added.

  Specifically, the granularity meaningful (or easy to calculate the similarity) with respect to the occurrence date and time is, for example, 24 hours every hour from 0:00, am / pm, monday, day of the week, season, holiday, So-called Goto days (5 days, 10 days, 15 days, 20 days, 25 days, 30 days) and the like. Further, the granularity that has meaning (or is easy to calculate the similarity) with respect to the occurrence position is, for example, an area in which map information is divided into a rectangular shape having a uniform size, a road section in which a road is divided by a predetermined distance, or the like. It is. Further, the granularity meaningful (or the similarity can be easily calculated) with respect to the generation (progress) direction is, for example, four directions of north, south, east, west, north, eight directions including northeast / southeast / northwest / southwest, or ascending / descending roads. Such as going down.

  Further, the accompanying information of the danger determination information managed by the server device 101A in the danger determination information management unit 206 does not need to be limited to the traffic situation at the time of occurrence, and may include various attributes related to the mobile object 105 that has encountered the danger event. It may include information. The various types of attribute information include, for example, the weight, displacement, and vehicle type of the host vehicle, which is the mobile unit 105. The vehicle type is, for example, a sedan, a wagon or a truck. These attribute information may be obtained by an arbitrary method from, for example, information on the occurrence of accidents or near-miss incidents held by the police or transportation companies, or accident assessment information held by non-life insurance companies, etc. Here, the description is omitted.

[2-7-3. Modification 3]
The accompanying information of the risk determination information managed by the server device 101A by the risk determination information management unit 206 may include information describing the contents of a dangerous event such as an accident or near-miss that occurred in the past. Furthermore, the first risk information generated by the server device 101A in the risk determination unit 204A may include part or all of the information describing the content of the dangerous event.

  Here, an example of information describing the content of the dangerous event will be described with reference to FIG. As shown in FIG. 10, the information that describes the content of the dangerous event that occurred on “December 1, 2014, 8: 30: 00: 00” is, for example, “a near-miss incident”. Further, the information that describes the content of the dangerous event that occurred at “12:45:30 on December 5, 2014” is, for example, “a near-miss collision”. The information describing the content of the dangerous event that occurred at “12:00:20 on December 8, 2014” is, for example, “right-right accident with oncoming vehicle”. Further, the information describing the details of the dangerous event that occurred at “14:00:45 on December 10, 2014” is, for example, “a near-miss incident with an oncoming pedestrian”.

  An example of a method of generating the first risk information in this case will be described. For example, the server device 101A receives the accompanying information of the current location image whose file name is “98765432.jpg” shown in FIG. 3B by the transmission / reception unit 201, and further sends the “Dec. 2014” by the risk determination unit 204A. If it is determined that the first risk level is “0.9” based on the similarity with the risk determination information of the dangerous event that occurred at 12:00:20 on the 8th, the risk level determination unit The first risk information generated in 204A is, for example, “the risk of a right-hand-right accident with an oncoming vehicle is 0.9”.

[2-7-4. Modification 4]
The server apparatus 101A does not necessarily need to individually and sequentially execute the traffic condition analysis processing in the image analysis unit 203 and the similarity calculation processing between the danger point image and the current point image in the danger degree determination unit 204A. For example, by using a machine learning method called deep learning (deep learning) or the like, the traffic condition analysis processing and the similarity calculation processing may be performed in parallel.

[2-7-5. Modification 5]
When the second risk level determined by the risk level determination unit 204A is within a predetermined range, the server apparatus 101A converts the current location image received by the transmission / reception unit 201 into a new risk location in the risk occurrence information management unit 202. It may be stored (added) as an image and managed in association with the accompanying information. Here, the predetermined range is, for example, a case where a value exceeds a preset threshold value (for example, “0.5”).

[2-7-6. Modification 6]
When the second risk level determined by the risk level determination unit 204A is within a predetermined range, the server apparatus 101A may use the risk determination information that the risk level determination unit 204A refers to when determining the first risk level. It may be rewritten or deleted from the danger determination information management unit 206. Here, “within the predetermined range” means, for example, a case where the value falls below a preset threshold value (for example, “0.5”).

[2-7-7. Modification 7]
The mobile device 102 that is the destination of the first risk information related to the first risk determined by the server device 101A is the same as the mobile device 102 that is the source of the current location image received by the server device 101A. No need to be. For example, when the moving object 105 is a vehicle, the first danger level information on the first danger level of the specific point determined based on the current point image transmitted from the preceding vehicle is transmitted slightly after the same specific point. The information may be transmitted to the mobile device 102 mounted on the following vehicle that passes. Thereby, it is possible to call attention to the user (driver) of the following vehicle.

(Other modifications)
As described above, the danger determination method and the like according to one or more aspects have been described based on the first and second embodiments, but the present disclosure is not limited to the first and second embodiments. Unless departing from the gist of the present disclosure, various modifications conceivable by those skilled in the art may be applied to the first and second embodiments, or a configuration constructed by combining components in different embodiments or modifications, or It may be included in the scope of a plurality of aspects. For example, the first and second embodiments may be combined.

  Further, for example, in the above embodiments, the moving body 105 is a vehicle, but the vehicle includes an automobile, a motorcycle, a train, a bicycle, or the like. The moving body 105 is not limited to a vehicle, and may be, for example, a smartphone or a tablet.

  A part or all of the components constituting each of the above devices may be constituted by an IC card detachable to each device or a single module. The IC card or the module is a computer system including a microprocessor, a ROM, a RAM, and the like. The IC card or the module may include the above-mentioned super multifunctional LSI. When the microprocessor operates according to the computer program, the IC card or the module achieves its function. This IC card or this module may have tamper resistance.

  The present invention may be the method described above. Further, these methods may be a computer program that is realized by a computer, or may be a digital signal formed by the computer program. Further, the present invention provides a computer-readable recording medium capable of reading the computer program or the digital signal, for example, a flexible disk, a hard disk, a CD-ROM, an MO, a DVD, a DVD-ROM, a DVD-RAM, a BD (Blu-ray (registered) (Trademark) Disc), and may be recorded on a semiconductor memory or the like. Further, the digital signal may be recorded on these recording media. In the present invention, the computer program or the digital signal may be transmitted via an electric communication line, a wireless or wired communication line, a network represented by the Internet, a data broadcast, or the like. The present invention may be a computer system including a microprocessor and a memory, wherein the memory stores the computer program, and the microprocessor operates according to the computer program. Further, the program or the digital signal is recorded on the recording medium and transferred, or the program or the digital signal is transferred via the network or the like, so that it is implemented by another independent computer system. It is good.

  INDUSTRIAL APPLICABILITY The risk determination method according to the present invention is useful for a risk determination system or the like that manages the degree of risk corresponding to a point where a moving object is located.

10, 10A risk determination system 101, 101A, 721 server device 102 mobile device 103 image database 104 network 105 mobile object 106 index database 201, 501 transmitting / receiving unit 202 risk occurrence information management unit 203 image analysis unit 204, 204A risk determination unit 205, 205A, 504 control unit 206 danger determination information management unit 502 input reception unit 503 output unit 700 group 701, 702 user 703 communication device 710 data center operating company 720 service provider

Claims (11)

A danger determination method used in a danger determination system that manages a degree of risk corresponding to a point where a moving object is located,
The danger determination system includes a danger point information indicating a danger point at which the danger event has occurred, and a first image of the danger point at the danger point, which indicates the occurrence state of the danger event at the danger point. A danger occurrence information management unit that stores at least one danger occurrence information associated with
The danger determination method includes:
Movement in which current position information indicating the current position of the moving object is associated with a second image of the surrounding state of the moving object at the current position, which indicates the surrounding state of the moving object at the current position. Obtaining body information;
The danger occurrence information corresponding to the current location indicated by the current location information included in the moving body information is not stored in the danger occurrence information management unit, and the danger corresponding to a location other than the current location When occurrence information is stored in the danger occurrence information management unit, the second image included in the mobile object information and one or more danger occurrence information stored in the danger occurrence information management unit Judging the degree of risk corresponding to the current location based on the similarity with the first image included,
The danger occurrence information further includes the severity of the danger event associated with the danger point information and the first image,
The severity is the presence or absence of an accident or the degree of the damage of the accident,
In the determining step, the similarity between the second image included in the moving body information and the first image included in one or more of the risk occurrence information stored in the risk occurrence information management unit is determined. A risk determination method for determining the degree of risk corresponding to the current location by calculating the similarity and calculating the similarity and the degree of seriousness associated with the first image. In the determining step, the danger occurrence information corresponding to the current location indicated by the current location information included in the moving body information and the danger occurrence information corresponding to a point other than the current location are the danger occurrence information. When stored in the management unit, based on the similarity between the second image included in the mobile object information and the first image included in the danger occurrence information corresponding to a point other than the current point The risk determination method according to claim 1, wherein the risk degree corresponding to the current location is determined. The danger determination method further includes:
Analyzing a first traffic situation at the danger point when the danger event occurs based on the first image, and analyzing a second traffic situation at the current location based on the second image Analyzing the
The danger determining method according to claim 1, wherein, in the determining step, the degree of risk corresponding to the current location is determined based on a similarity between the analyzed first traffic condition and the second traffic condition. . The danger determination method further includes:
When the degree of risk corresponding to the determined current location is within a predetermined range, the current location information included in the moving body information is set as the dangerous location information, and the second location included in the moving body information is included. Generating the danger occurrence information using the second image as the first image;
The risk determination method according to any one of claims 1 to 3, further comprising: adding the generated risk occurrence information to the risk occurrence information management unit. In the obtaining step, via a network, receiving the mobile body information transmitted from a mobile device mounted on the mobile body,
The danger determination method further includes:
When the risk corresponding to the determined current location is within a predetermined range, the method further includes a step of transmitting risk information regarding the risk to the mobile device that has transmitted the mobile information. 4. The danger determination method according to any one of 4. In the obtaining step, via a network, receiving the mobile body information transmitted from a mobile device mounted on the mobile body,
The danger determination method further includes:
In the case where the degree of risk corresponding to the determined current point is within a predetermined range, and within a predetermined time after receiving the moving body information, another moving body is included in the moving body information. The method according to any one of claims 1 to 4, further comprising a step of, when it is determined that the vehicle passes through the current location indicated by the current location information, transmitting risk information on the risk to a mobile device mounted on the another mobile body. The danger determination method according to item 1. The danger determination method further includes:
Storing the risk determination information associated with the risk degree corresponding to the determined current location and the current location information in a risk determination information management unit,
In the determining step, when the danger determination information corresponding to the current location indicated by the current location information included in the moving body information is stored in the danger determination information management unit, the danger determination information is included in the danger determination information The danger determination method according to any one of claims 1 to 6, wherein the danger level is used. The moving object information further includes sensor information indicating a traveling state of the moving object, which is associated with the current location information and the second image,
In the determining step, the similarity between the second image included in the moving body information and the first image included in one or more of the risk occurrence information stored in the risk occurrence information management unit is determined. The danger determination method according to any one of claims 1 to 7, wherein the danger is determined based on the similarity and the sensor information. A risk determination device that manages a risk corresponding to a point where a moving object is located,
The danger point information indicating the danger point at which the danger event occurred was associated with the first image of the danger point at the danger point, which indicates the occurrence state of the danger event at the danger point. A danger occurrence information management unit that stores one or more danger occurrence information;
Movement in which current position information indicating the current position of the moving object is associated with a second image of the surrounding state of the moving object at the current position, which indicates the surrounding state of the moving object at the current position. A receiving unit for receiving body information;
The danger occurrence information corresponding to the current location indicated by the current location information included in the moving body information is not stored in the danger occurrence information management unit, and the danger corresponding to a location other than the current location When occurrence information is stored in the danger occurrence information management unit, the second image included in the mobile object information and one or more danger occurrence information stored in the danger occurrence information management unit A determination unit configured to determine the degree of risk corresponding to the current location based on the similarity to the included first image,
The danger occurrence information further includes the severity of the danger event associated with the danger point information and the first image,
The severity is the presence or absence of an accident or the degree of the damage of the accident,
The determination unit is configured to determine a similarity between the second image included in the moving body information and the first image included in one or more of the danger occurrence information stored in the danger occurrence information management unit. And determining the degree of danger corresponding to the current location by calculating the similarity and the degree of severity associated with the first image. A danger determination system that includes a danger determination device and a danger output device mounted on the moving body, and manages a danger degree corresponding to a point where the moving body is located,
The danger determination device,
The danger point information indicating the danger point at which the danger event occurred was associated with the first image of the danger point at the danger point, which indicates the occurrence state of the danger event at the danger point. A danger occurrence information management unit that stores one or more danger occurrence information;
Movement in which current position information indicating the current position of the moving object is associated with a second image of the surrounding state of the moving object at the current position, which indicates the surrounding state of the moving object at the current position. A first receiving unit that receives body information;
The danger occurrence information corresponding to the current location indicated by the current location information included in the moving body information is not stored in the danger occurrence information management unit, and the danger corresponding to a location other than the current location When occurrence information is stored in the danger occurrence information management unit, the second image included in the mobile object information and one or more danger occurrence information stored in the danger occurrence information management unit A determining unit that determines the degree of risk corresponding to the current location based on the similarity to the included first image;
A first transmission unit that transmits the risk information on the risk to the risk output device,
The danger output device,
A second transmission unit that transmits the mobile object information to the danger determination device,
A second receiving unit that receives the risk level information transmitted from the risk determination device,
An output unit that outputs alert information for alerting the user of the mobile object based on the received risk information,
The danger occurrence information further includes the severity of the danger event associated with the danger point information and the first image,
The severity is the presence or absence of an accident or the degree of the damage of the accident,
The determination unit is configured to determine a similarity between the second image included in the moving body information and the first image included in one or more of the danger occurrence information stored in the danger occurrence information management unit. And determining the degree of danger corresponding to the current location by calculating the similarity and the degree of severity associated with the first image. A danger output device used in the danger determination system according to claim 10,
A second transmitting unit configured to transmit to the danger determination device current position information indicating a current position of the moving object and moving object information in which a second image indicating a surrounding state of the moving object at the current position is associated with the current position information; ,
A second receiving unit that receives the risk level information transmitted from the risk determination device;
A danger output device, comprising: an output unit configured to output alert information for alerting a user of the mobile object based on the received risk information.

Images