JP7165110B2 - road information distribution system, road information distribution device, road information distribution program - Google Patents

Description

The present invention relates to technology for distributing road information.

Conventionally, there is a system that acquires image data and position information from a plurality of vehicles and distributes road information to each vehicle based on the acquired image data and position information. By referring to the distributed road information, each vehicle can grasp, for example, the state of congestion on the road.

JP 2014-191578 A JP 2007-071579 A

Provided is a road information distribution system that collects detection information from a plurality of vehicles and distributes road information indicating road conditions to each vehicle based on the detection information.

A road information distribution system according to an embodiment is a road information distribution system that includes an in-vehicle terminal that acquires detection information and a management device that can communicate with the in-vehicle terminal and distributes road information based on the detection information. The in-vehicle terminal includes a first sensor device that acquires an image by photographing the front and/or rear of the vehicle on which the in-vehicle terminal is mounted, and a second sensor device that acquires first position information indicating the position of the vehicle. and a detection information acquiring unit that acquires detection information that associates an image acquired at a predetermined time with the first position information acquired at the predetermined time. The management device indicates a position within a predetermined range regarding the position of the vehicle to which the road information is to be distributed, based on the storage unit that stores the detection information in advance and the second position information that indicates the position of the vehicle to which the road information is to be distributed. An image recognition unit that executes image recognition processing on an image associated with the first position information, and a judgment unit that generates road information about a predetermined range based on judgment based on the result of the image recognition processing. The image recognition unit recognizes a pedestrian included in the image and also recognizes the face of the pedestrian. The determination unit estimates the positions and number of pedestrians, estimates the characteristics of the pedestrians based on the faces of the pedestrians, and generates road information indicating the positions and the number of pedestrians and the characteristics of the pedestrians.

1 is a network configuration diagram of a road information distribution system according to a first embodiment; FIG. 1 is a functional block diagram of a road information distribution system according to a first embodiment; FIG.

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

(First embodiment)
FIG. 1 is a network configuration diagram of the road information distribution system of this embodiment. The road information distribution system includes an in-vehicle terminal 100 and a management device 200 (corresponding to a road information distribution device). The in-vehicle terminal 100 and the management device 200 are wirelessly connected via a network such as an IP network. The in-vehicle terminal 100 is mounted in a vehicle such as an automobile or a motorized bicycle. The management device 200 is provided, for example, in a road traffic control center that manages road traffic conditions. The in-vehicle terminal 100 acquires detection information regarding a vehicle in which the in-vehicle terminal 100 is mounted (hereinafter referred to as a mounted vehicle), and transmits the detected information to the management device 200 . The detection information includes vehicle position information, image data captured by a camera mounted on the vehicle, and the like, as will be described later.

Detection information acquired by the in-vehicle terminal 100 is transmitted to the management device 200 from a plurality of vehicles. The management device 200 can accumulate detection information received from each on-board vehicle. The management device 200 executes analysis processing based on the detection information received from each mounted vehicle, and generates road information for grasping the conditions (traffic conditions) of the roads on which each mounted vehicle travels. The management device 200 distributes road information to each mounted vehicle. In other words, the equipped vehicle is a probe car that functions as a sensor that acquires detection information for generating road information.

FIG. 2 is a functional block diagram of the road information distribution system. The in-vehicle terminal 100 includes a control section 110 , a sensor unit 120 , a storage section 130 , a communication section 140 and an output section 150 . The storage unit 130 stores various information. The communication unit 140 controls communication with the management device 200 .

The control unit 110 has a detection information acquisition unit 111 . The detection information acquisition unit 111 acquires detection information related to the equipped vehicle according to acquisition setting information described later. The detection information acquisition unit 111 collects information output from the sensor unit 120 as detection information. The detection information acquisition unit 111 can also collect information detected by devices already installed in the vehicle as detection information. For example, the detection information acquisition unit 111 collects, as detection information, information regarding ON/OFF of the brake pedal, information regarding ON/OFF of the wiper, information regarding temperature detected by an outside air temperature sensor, information regarding traveling speed, and the like.

The sensor unit 120 has a camera 121 (corresponding to first sensor equipment) and a GPS (Global Positioning System) sensor 122 (corresponding to second sensor equipment). The camera 121 is provided so as to be able to photograph the front and/or rear of the mounted vehicle. A plurality of cameras 121 can be provided. The camera 121 generates image data by photographing. For example, the camera 121 is a visible light camera, a near-infrared camera, an infrared camera, or the like. The GPS sensor 122 acquires vehicle position information (corresponding to first position information). Image data and position information are output to the detection information acquisition unit 111 as detection information.

The output unit 150 transmits the road information provided from the management device 200 to the occupants of the mounted vehicle through each output device. The output unit 150 has, for example, a display (display unit) and a speaker, and displays road information provided from the management device 200 and outputs audio based on the road information.

Acquisition setting information for the detection information acquisition unit 111 to acquire predetermined detection information is stored in the storage unit 130 . The acquisition setting information includes acquisition condition information and designation information corresponding to the acquisition condition information. Acquisition condition information is information that defines conditions for acquiring detection information. The designation information is information that defines detection information to be acquired. Acquisition condition information and designation information are each defined in detection information.

A process of acquiring detection information by the in-vehicle terminal 100 will be described. When the detection information specified in the acquisition condition information is detected, the detection information acquisition unit 111 acquires the detection information and also acquires the detection information specified in the designation information. The detection information acquisition unit 111 acquires at least image data at a predetermined time (detection time described later) and position information at a predetermined time based on the acquisition setting information.

For example, when "position information [XXX (position coordinates indicating position information)]" is set as a condition in the acquisition condition information, "image data" and "time" are set in the designation information. In this case, when the GPS sensor 122 acquires the position information [XXX], the camera 121 shoots and generates image data. At this time, a timer (not shown) measures the time, and can grasp the time when the GPS sensor 122 acquires the position information [XXX], in other words, the time when the camera 121 captures the image. Here, the time when the position information is acquired and the shooting time are referred to as detection time. Also, the position information indicates the shooting location of the image. In this manner, the detection information acquisition unit 111 can acquire the position information of the predetermined point, the image data, and the detection time in association with each other when the vehicle equipped with the vehicle has arrived at the predetermined point.

Note that a geographic range using position information may be set in the acquisition condition information. For example, in the acquisition condition information, the range can be set using the location information of the A point, the location information of the B point, and the location information of the C point. At this time, when the mounted vehicle enters the range surrounded by points A to C, the detection information acquisition unit 111 can acquire various detection information by the method described above.

For the location information to be set as the acquisition condition information, for example, if you set location information such as intersections and junctions where traffic is heavy (easily congested), accident locations, and accident-prone locations, the acquired detection information , it becomes easier for the management device 200 to provide information that the vehicle occupants should pay attention to.

Further, when "time [X hour X minute]" is set as a condition in the acquisition condition information, "image data" and "position information" are set in the designation information. In this case, when the time ascertained by the timer reaches X:X:00, the camera 121 takes a picture and generates image data, and the GPS 122 acquires position information. In this manner, the detection information acquisition unit 111 can associate and acquire the time (that is, the detection time), the position information, and the image data at a predetermined time. By setting a time in the acquisition condition information every predetermined time, the detection information acquisition unit 111 can acquire the position information, the image data, and the detection time every predetermined time.

The information acquired by the detection information acquiring unit 111 is transmitted to the management device 200 and accumulated in a storage device 230 (described later) of the management device 200 .

Acquisition setting information is set in advance in the management device 200 and distributed to the in-vehicle terminal 100 . Also, the acquired setting information can be set in advance on the in-vehicle terminal 100 side. Acquisition setting information can be arbitrarily added or changed. The acquired detection information is transmitted to the management device 200 via the communication unit 140 and accumulated in the storage device 230, which will be described later. In other words, the management device 200 collects detection information output from the in-vehicle terminal 100 .

In the above explanation, the image data, the position information, and the detection time are used. can be obtained under the following conditions: The acquisition setting information described above is just an example, and the detection information acquisition unit 111 only needs to be able to acquire predetermined detection information specified under predetermined conditions.

The management device 200 includes a communication device 210 , a control device 220 and a storage device 230 . The communication device 210 controls communication with the in-vehicle terminal 100 . The storage device 230 stores detection information received from the in-vehicle terminal 100 . The control device 220 has a determination section 221 and a road information distribution section 222 . The determination unit 221 executes various types of determination processing, which will be described later, and generates road information as a result of the determination processing. The road information distribution unit 222 distributes the generated road information.

The determination unit 221 has an image recognition unit 2211 and a determination unit 2212 . The image recognition unit 2211 performs image recognition processing on image data accumulated in the storage device 230 as detection information. The determination unit 2212 executes determination processing based on the result of image recognition processing and generates various types of road information. The determination unit 221 executes lane congestion degree determination processing, road surface state determination processing, and pedestrian determination processing (to be described later). Road information includes lane congestion degree information, road surface condition information, and pedestrian information.

The lane congestion degree determination processing will be described. The lane congestion level determination process is a process for determining the vehicle congestion level for each lane. The lane congestion degree determination processing includes congestion degree determination processing and lane recognition processing.

First, the congestion degree determination process will be described. The image recognition unit 2211 performs image recognition processing on image data collected as detection information. For example, the image recognition unit 2211 executes image recognition processing based on a vehicle detection dictionary (hereinafter referred to as a vehicle detection dictionary) for recognizing forward vehicles. For example, the vehicle detection dictionary includes feature quantities that describe features of the vehicle such as the outline of the vehicle, window frames, bumpers, and tires. A vehicle detection dictionary is stored, for example, in the storage device 230 .

The image recognition unit 2211 performs image recognition processing by matching a feature amount image obtained by performing feature amount extraction processing on an image collected from a mounted vehicle and a vehicle detection dictionary. Thereby, the image recognition unit 2211 recognizes the area occupied by the characteristic portion of the forward vehicle in the image. Based on the size of the area occupied by the characteristic portion of the forward vehicle in the image or the position where the vehicle touches the road surface, the determination unit 2212 estimates the distance between the equipped vehicle and the vehicle ahead of the equipped vehicle, that is, the inter-vehicle distance. do. It should be noted that the inter-vehicle distance between the mounted vehicle and the vehicle behind the mounted vehicle can be similarly estimated. Note that other existing methods may be used to estimate the inter-vehicle distance.

For example, the determination unit 2212 can determine that the shorter the estimated inter-vehicle distance, the higher the degree of congestion. The determination unit 2212 can determine that the longer the estimated inter-vehicle distance, the lower the degree of congestion.

Next, lane recognition processing will be described. The image recognition unit 2211 performs image recognition processing on image data collected as detection information. For example, the image recognition unit 2211 performs line segment detection processing for recognizing lanes, conditions such as the width and color of lane boundary lines, conditions related to the width of lanes, and a template image (hereinafter referred to as a lane template image). Execute the recognition process. The lane boundary conditions are stored in the storage device 230, for example.

Here, lane boundary lines that define boundaries between lanes are drawn on the road. Therefore, the position of the lane boundary line in the image captured by the camera 121 differs according to the lane in which the mounted vehicle is located. For example, when the mounted vehicle is positioned in the left lane, the lane boundary line is positioned on the right side in the image taken in front of the vehicle. For example, when the mounted vehicle is positioned in the right lane, the lane boundary line is positioned on the left side in the image taken in front of the vehicle. For example, when the on-board vehicle is positioned in the center lane, the lane boundary lines are positioned on both the left and right sides in the image taken in front of the vehicle. Therefore, lane boundary line conditions are prepared for each of the images described above.

The image recognition unit 2211 performs image recognition processing by matching the image collected from the mounted vehicle, the result of performing the line segment detection processing on the image, and the condition of the lane boundary line. Thereby, the determination unit 2212 grasps the position of the lane boundary line in the image collected from the equipped vehicle. Then, the determination unit 2212 can determine the lane in which the mounted vehicle is located, among the plurality of lanes, based on the position of the lane boundary line. Note that other existing methods may be used to recognize lanes.

By grasping the lane along with the degree of congestion as described above, the degree of congestion for each lane can be determined. The degree of congestion for each lane is distributed to the vehicle-mounted terminal 100 according to request information transmitted from the vehicle-mounted terminal 100 as described later. In addition, in the congestion degree determination process, the traveling speed may be taken into consideration. For example, when information about the travel speed of the vehicle equipped with the image data is stored as the detection information in the storage device 230, the determination unit 2212 can determine the degree of congestion in consideration of the travel speed. As a result, the degree of congestion can be determined based on both the inter-vehicle distance and the traveling speed, such as when the inter-vehicle distance is short but the traveling speed is fast, or when the inter-vehicle distance is long but the traveling speed is slow. Similarly, when information about ON/OFF of the brake pedal is accumulated in the storage device 230 as detection information, the determination unit 2212 can determine the degree of congestion in consideration of ON/OFF of the brake pedal. For example, when the brake pedal is ON for a long time or when the brake pedal is ON many times, it can be determined that the degree of congestion is high.

Road surface condition determination processing will be described. The road surface condition determination process is a process for determining the condition of the road surface. Examples of road surface conditions include a snow-covered condition and a frozen road surface condition. The road surface state determination process includes a snow state determination process and a frozen state determination process.

First, the snow cover state determination processing will be described. The image recognition unit 2211 performs image recognition processing on image data collected as detection information. For example, the image recognition unit 2211 executes image recognition processing based on a template image for recognizing the road surface condition (hereinafter referred to as a road surface condition template image). The road surface condition template image is stored in the storage device 230, for example.

Here, the snow-covered road has an increased percentage of white due to the snow compared to the non-snow-covered road (not covered with snow). Therefore, when comparing an image of a road with snow and an image of a road without snow, the image of the road with snow has more white pixels (white areas). Therefore, an image of a road without snow is prepared for the road surface condition template image.

The image recognition unit 2211 executes image recognition processing by searching and comparing images collected from the vehicle equipped with the road surface template image. Thereby, the determination unit 2212 can grasp the area that has changed to white due to snow accumulation from the difference between the image collected from the vehicle equipped with the road surface template image and the road surface template image. The determination unit 2212 can determine the presence or absence of snow cover based on the area that has changed to white.

Here, since snow accumulates upward (in the direction away from the road surface) from the road surface, there is a space where snow is not covered above the snow-covered area on the road surface. A space without snow is not white because it is not colored by snow. Therefore, the determination unit 2212 can estimate the depth of snow cover (for example, the depth of snow cover) based on the white areas sequentially detected from below in the image captured during snow cover. Here, the snow depth can represent the depth of snow in units such as cm. In the above description, it is assumed that the snow is colored white. By presetting the color that is colored by the snow, an area of the preset color is detected as an area covered with snow, and the area is covered with snow. Depth can be determined. In this manner, the determination unit 211 generates snow cover information as a result of the snow cover state determination process. Note that other existing methods may be used to estimate the depth of snow cover.

Next, the frozen state determination processing will be described. Frozen road surfaces develop a darker color than non-frozen road surfaces. Therefore, an image of a non-frozen road surface is prepared as the road surface template image.

The image recognition unit 2211 performs image recognition processing by matching the image collected from the equipped vehicle and the road surface template image. Accordingly, the determination unit 2212 can grasp the area where the color has changed to dark due to freezing from the difference between the image collected from the vehicle equipped with the road surface template image. At this time, the determination unit 2212 determines (estimates) that the road surface is frozen when the pixel value changes by a predetermined value or more in the area where the color has changed to dark. Accordingly, the image recognition unit 2211 can determine whether or not the road surface is frozen. Thus, the determination unit 211 generates frozen information as a result of the frozen state determination process. Note that other existing methods may be used to determine whether or not there is freezing.

The road surface template image is an image taken at a point indicated by predetermined position information in advance, such as when the weather is clear and the road surface is not affected by snow or ice. The road surface template image is associated with position information indicating the shooting location. For example, the image recognition unit 2211 can execute the road surface condition determination process when the position information associated with the road surface template image matches the position information associated with the image data obtained from the vehicle equipped with the road surface template image. For example, the road surface template image and the position information linked to the road surface template image may be collected in advance from the vehicle equipped with the road surface template image. The road surface template image and the position information associated with the road surface template image are stored in the storage device 230, for example.

In addition, in the road surface state determination processing, information regarding the temperature detected by the outside air temperature sensor (temperature information) and information regarding ON/OFF of the wiper may be taken into consideration. When temperature information is accumulated in the storage device 230 as detection information together with image data, the judgment unit 2212 can make a judgment considering the temperature in addition to the result of image recognition. For example, when the air temperature is equal to or lower than a predetermined value, the determination unit 2212 additionally determines that the road surface is frozen based on the result of image recognition. Similarly, the determination unit 2212 can additionally determine that there is snow cover. In addition, when information about ON/OFF of the wiper is accumulated in the storage device 230 as detection information together with the image data, the determination unit 2212 makes a determination considering the ON/OFF of the wiper in addition to the result of the image recognition. can be done. For example, when the wiper is ON, the determination unit 2212 may determine that it is snowing, and additionally determine that there is snow based on the image recognition result.

Pedestrian determination processing will be described. The image recognition unit 2211 executes processing for recognizing a person (hereinafter referred to as a pedestrian) present around the vehicle based on image data collected as detection information. For example, the image recognition unit 2211 uses a person detection dictionary (referred to as a person detection dictionary) that includes pre-learned feature points and patterns to recognize a pedestrian area included in the captured image. Thereby, the determination unit 2212 estimates (determines) the positions and the number of pedestrians. Similarly, the image recognition unit 2211 can perform face recognition processing on the recognized pedestrian's face using a face detection dictionary (referred to as a face detection dictionary). Thereby, the determination unit 2212 estimates (determines) characteristics of the photographed pedestrian, such as sex, age group, facial expression, and the like. An existing method can be applied to the processing for grasping the number of pedestrians photographed in the image described above and the face recognition processing.

The determination unit 2212 can determine the degree of congestion of pedestrians present around the vehicle by grasping the number of pedestrians present around the vehicle (which may include the positions of the pedestrians). can. For example, when the number of persons present around the mounted vehicle exceeds a predetermined value, it is determined that the degree of pedestrian congestion is high. As the number of pedestrians increases, the determination unit 2212 determines that the congestion degree of pedestrians is high. The smaller the number of pedestrians, the lower the determination unit 2212 determines that the degree of pedestrian congestion is low.

Moreover, in addition to the degree of crowding of pedestrians, determination can also be made using the results of face recognition processing. For example, when it is determined that the ratio of women among pedestrians is high as a result of face recognition processing, and that the degree of pedestrian congestion is high, it is possible that an event for women is being held near the equipped vehicle. , you can predict that there are tourist destinations for women. Similarly, when it is determined that the ratio of male pedestrians is high as a result of face recognition processing, and the degree of crowding of pedestrians is high, it means that an event geared towards men is being held in the vicinity of the equipped vehicle. Or you can predict that there will be tourist destinations for men. Information determined about pedestrians existing around the vehicle is distributed to the vehicle-mounted terminal 100 in response to request information transmitted from the vehicle-mounted terminal 100 as described later.

The image recognition unit 2211 can execute the above-described various determination processes (lane congestion degree determination process, road surface state determination process, pedestrian determination process) for each image data obtained from a plurality of in-vehicle terminals 100 . The management device 200 distributes the results of various determination processes as road information. When the request information is input, the management device 200 executes various determination processes. A determination process to be executed according to the request information is set in advance.

Here, the request information is information for requesting road information, and is transmitted from the vehicle-mounted terminal 100 . At this time, the vehicle-mounted terminal 100 transmits position information (corresponding to second position information) to the management device 200 together with the request information. For example, the position information is output from the GPS sensor 122 and transmitted to the management device 200 when the vehicle equipped with the vehicle reaches a predetermined position. The management device 200 executes various determination processes based on the position information acquired (inputted) together with the request information.

For example, the determination unit 221 executes lane congestion degree determination processing based on the position information acquired together with the request information. The determination unit 221 executes lane congestion degree determination processing based on image data captured in advance within a predetermined road range based on the position information acquired together with the request information. Specifically, the determination unit 221 reads out from the storage device 230 image data linked with position information within a predetermined road range based on the acquired position information, and executes lane congestion degree determination processing. The road information distribution unit 222 distributes the result of the lane congestion degree determination process (lane congestion degree information) to the vehicle-mounted terminal 100 as road information.

The distributed lane congestion degree information is transmitted by the output unit 150 of the in-vehicle terminal 100 to the occupants (users) of the equipped vehicle. For example, when the in-vehicle terminal 100 has a display for displaying a map, lane congestion degree information for a predetermined road range can be reflected and displayed on the map by color coding according to the degree of congestion. Also, when the in-vehicle terminal 100 has a speaker, the lane congestion degree information can be output by voice. Thereby, the user can grasp the degree of congestion for each lane in a predetermined range and select a lane with a low degree of congestion.

For example, the determination unit 221 executes road surface state determination processing based on the position information acquired together with the request information. The determination unit 221 executes road surface state determination processing based on image data captured in advance within a predetermined road range based on the position information acquired together with the request information. Specifically, the determination unit 221 reads out from the storage device 230 image data associated with position information within a predetermined road range based on the acquired position information, and executes road surface state determination processing. The road information distribution unit 222 distributes the road surface condition determination result (road surface condition information) to the in-vehicle terminal 100 as road information. It should be noted that it is also possible to execute only the snow-covered state determination process, or to execute only the frozen state determination process.

The distributed road surface condition information is transmitted by the output unit 150 of the in-vehicle terminal 100 to the occupants (users) of the equipped vehicle. For example, when the in-vehicle terminal 100 has a display for displaying a map, road surface condition information for a predetermined road range can be reflected and displayed on the map. Further, when the in-vehicle terminal 100 has a speaker, the road surface condition information may be output by voice. As a result, the user can grasp the depth of snow on the road surface and the presence or absence of frozen road surface in a predetermined road range, and can avoid roads with road surface conditions that adversely affect driving.

For example, the determination unit 221 executes pedestrian determination processing based on the position information acquired together with the request information. The determination unit 221 executes pedestrian determination processing based on image data captured in advance within a predetermined road range based on the position information acquired together with the request information. Specifically, the determining unit 221 reads out from the storage device 230 image data linked with position information within a predetermined road range based on the acquired position information, and executes pedestrian determination processing. The road information distribution unit 222 distributes the result of pedestrian determination processing (pedestrian information) to the in-vehicle terminal 100 as road information.

The distributed pedestrian information is transmitted by the output unit 150 of the in-vehicle terminal 100 to the occupants (users) of the equipped vehicle. For example, when the in-vehicle terminal 100 has a display for displaying a map, it is possible to reflect the pedestrian information of a predetermined road range on the map and display it. Moreover, when the in-vehicle terminal 100 has a speaker, the pedestrian information may be output by voice. By referring to information about pedestrians within a predetermined road range, the user can grasp the degree of congestion of pedestrians and the characteristics of pedestrians. As a result, the user can predict sightseeing spots located near a predetermined road range, events held near a predetermined road range, etc., based on the characteristics of pedestrians at points where the degree of pedestrian congestion is high. can do. In addition, the user can reduce the risk of an accident resulting in injury or death by avoiding places where the degree of congestion of pedestrians is high.

A predetermined road range based on the acquired position information can be set in advance. The predetermined road range based on the acquired position information can be set, for example, to a range in which the mounted vehicle that has transmitted the request information can travel. Further, when transmitting the request information from the in-vehicle terminal 100, it is also possible to transmit the position information indicating the starting point of the mounted vehicle and the position information indicating the destination. In this case, various determination processes can be executed based on image data captured on a route predicted based on the position information indicating the departure point and the position information indicating the destination.

Note that the determination unit 221 can also perform various determination processes in real time based on detection information collected from the vehicle-mounted terminal 100 . In this case, the road information distribution unit 222 distributes the results of various determination processes when the position information is input together with the request information.

According to the road information distribution system of this embodiment, since the management device 200 executes image recognition processing with a large processing load, it is not necessary to install an advanced device for performing image recognition processing for each vehicle. Therefore, the cost can be reduced compared to the case where image recognition processing is performed on the vehicle side.

Furthermore, according to the road information distribution system of the present embodiment, by executing various determination processes based on one type of data called image data, the degree of congestion for each lane, road surface conditions (snow cover, ice), pedestrian It is possible to extract a plurality of different information such as the degree of congestion and characteristics of

The road information distribution system of the embodiment has been described above. means, an output means such as a printer, an auxiliary storage device (such as a hard disk), and the like.

Further, each function of the present invention can be realized by a program, a computer program prepared in advance for realizing each function is stored in an auxiliary storage device, and a control unit such as a CPU is stored in the auxiliary storage device. The program can be read out to the main storage device, and the control unit can execute the program read out to the main storage device to cause the in-vehicle terminal 100 and the management device 200 to operate the functions of the respective units of the present invention. On the other hand, each function of the present invention can be configured by an individual control device, or a plurality of control devices can be connected directly or via a network to configure an IVR device.

The program can also be provided to the computer in a state recorded on a computer-readable recording medium. Examples of computer-readable recording media include optical discs such as CD-ROMs, phase-change optical discs such as DVD-ROMs, magneto-optical discs such as MO (Magnet Optical) and MD (Mini Disk), floppy (registered trademark) discs, and the like. Examples include magnetic disks such as removable hard disks, compact flash (registered trademark), smart media, SD memory cards, memory cards such as memory sticks. Further, a hardware device such as an integrated circuit (IC chip, etc.) specially designed and configured for the purpose of the present invention is also included as a recording medium.

Although embodiments of the present invention have been described, the embodiments are presented as examples and are not intended to limit the scope of the invention. This novel embodiment can be embodied in various other forms, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the scope of the invention described in the claims and equivalents thereof.

100 In-vehicle terminal 110 Control unit 111 Detection information acquisition unit 120 Sensor unit 121 Camera 122 GPS sensor 130 Storage unit 140 Communication unit 150 Output unit 200 Management device 210 Communication device 220 Control device 221 Determination unit 2211 Image recognition unit 2212 Determination unit 222 Road information Distribution unit 230 Storage device

Claims (8)

A road information distribution system including an in-vehicle terminal that acquires detection information and a management device that can communicate with the in-vehicle terminal and distributes road information based on the detection information,
The in-vehicle terminal is
a first sensor device that acquires an image by photographing the front and/or rear of the vehicle on which the in-vehicle terminal is mounted;
a second sensor device that acquires first position information indicating the position of the mounted vehicle;
a detection information acquisition unit that acquires the detection information that associates the image acquired at a predetermined time with the first position information acquired at the predetermined time,
The management device
a storage unit that stores the detection information in advance;
The image associated with the first position information indicating a position within a predetermined range regarding the position of the vehicle to which the road information is to be distributed, based on the second position information indicating the position of the vehicle to which the road information is to be distributed. an image recognition unit that executes image recognition processing for
a determination unit that generates the road information related to the predetermined range based on determination based on the result of the image recognition process;
The image recognition unit recognizes a pedestrian included in the image and recognizes the face of the pedestrian,
The determination unit estimates the positions and the number of pedestrians, estimates the characteristics of the pedestrians based on the faces of the pedestrians, and indicates the positions and the number of pedestrians and the characteristics of the pedestrians. A road information distribution system characterized by generating road information. 2. The road information distribution system according to claim 1 , wherein the determining unit estimates the inter-vehicle distance based on the vehicles included in the image, and generates the road information indicating the degree of congestion of the vehicles. The image recognition unit recognizes a vehicle included in the image and a lane boundary line that is a boundary line between lanes,
The determination unit estimates a vehicle-to-vehicle distance based on the vehicles included in the image, and determines a lane in which the mounted vehicle is located, among a plurality of lanes, based on the position of the lane boundary line included in the image. 3. The road information distribution system according to claim 1, wherein the road information indicating the congestion degree of each lane is generated based on the inter-vehicle distance and the lane in which the mounted vehicle is located. The detection information further includes information on either the running speed of the vehicle or ON/OFF of the brake pedal,
3. The determining unit generates the road information indicating the degree of congestion of the vehicles based on the inter-vehicle distance and the traveling speed or the ON/OFF state of the brake pedal. 3. The road information distribution system according to 3. The image recognition unit recognizes snow cover included in the image,
5. The road information distribution system according to claim 1 , wherein the determining unit generates the road information indicating the snow depth by estimating the snow depth of the snow. The image recognition unit recognizes a road surface included in the image,
6. The road information distribution system according to any one of claims 1 to 5 , wherein the judgment unit generates the road information indicating the presence or absence of freezing by judging the presence or absence of freezing on the road surface. A road information distribution device capable of communicating with an in-vehicle terminal, collecting detection information from the in-vehicle terminal, and distributing road information based on the detection information,
Preliminary storage of the detection information linking an image of the front and/or rear of the vehicle on which the in-vehicle terminal is mounted, taken at a predetermined time, with first position information indicating the position of the vehicle at the predetermined time a storage unit for
The image associated with the first position information indicating a position within a predetermined range regarding the position of the vehicle to which the road information is to be distributed, based on the second position information indicating the position of the vehicle to which the road information is to be distributed. an image recognition unit that executes image recognition processing for
a determination unit that generates the road information related to the predetermined range based on determination based on the result of the image recognition process;
The image recognition unit recognizes a pedestrian included in the image and recognizes the face of the pedestrian ,
The determination unit estimates the position and number of pedestrians, estimates the characteristics of the pedestrian based on the face of the pedestrian, and indicates the position and number of pedestrians and the characteristics of the pedestrian. A road information distribution device characterized by generating road information. Road information based on detection information linking an image of the front and/or rear of a vehicle equipped with an in-vehicle terminal at a predetermined time and first position information indicating the position of the vehicle at the predetermined time A program running on a computer that supports distribution,
a first function of pre-accumulating the detection information acquired by the in-vehicle terminal;
The image associated with the first position information indicating a position within a predetermined range regarding the position of the vehicle to which the road information is to be distributed, based on the second position information indicating the position of the vehicle to which the road information is to be distributed. a second function for executing image recognition processing for
causing a computer to implement a third function of generating the road information related to the predetermined range based on determination based on the result of the image recognition process;
The second function recognizes a pedestrian included in the image and performs a first process of recognizing the face of the pedestrian ,
The third function estimates the position and number of pedestrians, estimates the characteristics of the pedestrian based on the face of the pedestrian, and indicates the position and number of pedestrians and the characteristics of the pedestrian. A program for executing a second process for generating the road information.

Images