JP2001004742A - Device and method for detecting obstacle on road, systems for monitoring road condition and obstacle on road, and record medium storing program for detecting obstacle on road - Google Patents

Abstract

PROBLEM TO BE SOLVED: To detect an obstacle hidden by another object. SOLUTION: The obstacle-detecting device checks to see if there is an obstacle being hidden temporarily by another object according to history information for indicating the detection history of the object (S19). When it is estimated that there is an obstacle hidden by another object, the background data of a specific region including the hidden obstacle is updated, thus storing an obstacle hidden temporarily by another object also in the background data and hence more accurately detecting the obstacle using the background data.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a road obstacle detecting device, a road obstacle detecting method, a road obstacle detecting system, a road condition monitoring system, and a recording medium on which a road obstacle detecting program is recorded.

[0002]

2. Description of the Related Art On an expressway or the like, if an obstacle is present on the road, it is very dangerous for the vehicle to travel. Therefore, it is desired to detect an obstacle on the road and notify the driver of the obstacle. As a road obstacle detection system, it is conceivable to detect an object on the road with a sensor and identify whether the object is an obstacle based on whether it is moving at a certain speed or more or is stationary. Can be

[0003]

For example, when a plurality of sensors are installed along a highway and an obstacle detection system for detecting an obstacle based on measurement data measured by each sensor is constructed, Obstacles are in the shadow of a running vehicle, even if
Alternatively, it is conceivable that an obstacle becomes a shadow of another obstacle and cannot be detected by the sensor. In a system for detecting an obstacle on a road, how to detect an obstacle temporarily hidden by such another object is an important theme.

[0004] It is also considered useful to implement a system for monitoring the road condition by measuring the road condition at regular intervals by using the above-mentioned sensor, in terms of road operation management. In such a case, if the data obtained from the measurement data is updated each time the road condition is measured by the sensor, the data updating process is performed even when the vehicle is flowing smoothly and the road condition hardly changes, and the data is updated. It is conceivable that the data update processing time for displaying the situation increases.

[0005] It is an object of the present invention to be able to detect obstacles hidden by other objects. Another object is to make it possible to change the update timing of data indicating the road condition according to the road condition.

[0006]

According to the first aspect of the present invention,
Detecting means for detecting an obstacle based on measurement data indicating the state of the road measured by the sensor; and detecting other information based on information on the obstacle detected by the detecting means and information on the obstacle detected in the past. Estimating means for estimating whether or not an obstacle hidden by the object exists, and updating means for updating data obtained from the measurement data based on the estimation result of the estimating means.

According to the present invention, when it is estimated that an obstacle hidden by another object exists, the data obtained from the measurement data is used to prevent the obstacle hidden by the other object from being erased. Can be updated, so that an obstacle that is a shadow of another object and cannot be measured by the sensor can be detected. Also, when an obstacle hidden by another object is measured again, the data obtained from the measurement data is continuous because the hidden obstacle is stored as it is, and the obstacle is It will not be measured or not measured.

The estimation of whether or not there is an obstacle hidden by another object is performed by, for example, storing attribute information of an obstacle detected in the past and history information indicating the history of obstacle detection. In the case where an obstacle having the same attribute information is repeatedly detected a predetermined number of times or more at the measurement timing close to the present, but the obstacle is not detected this time, the obstacle is replaced with another object. Presumed to be hidden by

The detection of an obstacle is performed, for example, by taking the difference between the background data obtained from the data obtained by weighting the measurement data and the measurement data. According to a twelfth aspect of the present invention, a sensor for measuring a road condition at regular intervals and measurement data indicating a road condition detected by the sensor or an update timing of data obtained from the measurement data are measured by the sensor. Updating means for changing according to the road condition.

According to the present invention, the update timing of the data indicating the road condition is changed in accordance with the road condition. For example, when there is no change in the road condition, the data update cycle is made longer than the measurement cycle of the sensor. When a change occurs in the situation, by shortening the data update cycle, unnecessary data update is not performed, and the overall processing efficiency can be increased.

[0011]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a diagram showing a configuration of a system for monitoring a road condition according to an embodiment of the present invention.
This system includes a millimeter-wave sensor 11 attached to a drive unit capable of swinging and rotating to measure a certain range of road conditions, and measurement data (distance, speed, angle data) measured by the millimeter-wave sensor 11. ), An obstacle detection device 12 that creates display data indicating the road condition, and a message etc. sent from the obstacle detection device 12 to notify the presence of an obstacle. And an information display plate 13.

The information display panel 13 is installed along or near a nearby road such as a curved road on which a road with poor visibility is ahead, so that the driver of the vehicle has an obstacle ahead. It is to inform.

A number of millimeter wave sensors 11 are located along the road.
Is installed, and the measurement data of each millimeter wave sensor 11 is transmitted from the obstacle detection device 12 to the central monitoring center that monitors the road condition by wire or wirelessly, and the display device of the central monitoring center displays the obstacle at each point on the road. May be displayed, and the central monitoring center may display a message or the like on the information display board 13 to notify the presence of the obstacle.

Next, an obstacle detection process in the road condition monitoring system having the above configuration will be described with reference to a flowchart of FIG. The obstacle detection device 12 acquires measurement data indicating the state of the road from the millimeter wave sensor 11 (S11 in FIG. 2), and executes generation / update processing of background data based on the measurement data. The background data generation / update processing is related to the occlusion check and the like in step S19 described later, and will be described in detail after the description thereof is completed.

Next, an object moving at a speed higher than a certain speed is excluded from the measured data (S13). This allows
It is possible to obtain measurement data including a vehicle having an extremely low speed, a fixedly installed object such as a guardrail and a speed sign, and a stationary obstacle.

FIGS. 3A and 3B are diagrams showing the road conditions at the time of background data acquisition and measurement data acquisition, respectively. FIGS. 4A and 4B show background data and measurement data. FIG. 4 is an explanatory diagram of data.

FIG. 3A shows the state of the road when no vehicle or obstacle exists, and FIG. 3B shows the state of the road when a vehicle or obstacle exists. FIG.
When the state of the road where no vehicle is present in (A) is measured by the millimeter wave sensor 11, the measured data is that in which only the guardrail exists, and FIG.
Is generated as shown in FIG.

Assuming that the range indicated by the broken line in FIG. 4A is the scan range of the millimeter wave sensor 11, since no obstacle exists in this case, the millimeter wave sensor 11 at the intersection between the left broken line and the guardrail 31 is assumed. Dot data obtained from measurement data in a range from a point represented by an angle and a distance viewed from the point to a point represented by an angle and a distance viewed from the millimeter wave sensor 11 at an intersection of the right broken line and the guardrail 31. It is stored as matrix data of background data.

When the state of the road when the vehicle or the obstacle A in FIG. 3B is present is measured by the millimeter wave sensor 11, the measured data is a part of the guard rail as shown in black in FIG. 4B. And the vehicle or obstacle A. In this case, the center of the guardrail 31 is the obstacle A
Is not measured by the millimeter-wave sensor 11.

FIG. 5 is a diagram showing a data matrix of the background data, and FIG. 5 shows a state in which the background data of FIG. 4A is stored. The measurement data detected by the millimeter wave sensor 11 is obtained as angle and distance data with the position of the millimeter wave sensor 11 as the origin, and the number of dots of the measurement data is determined by the resolution of the millimeter wave sensor 11,
The data matrix of the background data shown in FIG. 5 is generated from the angle and distance data of each dot of the measurement data. In FIG. 5, the vertical axis shows the angle and the horizontal axis shows the distance, but this does not mean that the vertical axis and the horizontal axis show the angle and the distance, respectively. It is obtained as data represented by

Returning to FIG. 2, the difference between the measurement data obtained by removing the moving object having a speed equal to or higher than the predetermined speed and the background data is obtained (S1).
4). When the obstacle A is present, the measurement data includes an image (L-shaped) of the obstacle A viewed from the millimeter wave sensor 11 and the guardrail 31 as shown in black in FIG. Then, assuming that the background data before the existence of the obstacle is as shown in FIG. 4 (A), by taking the difference between them, the central part of the guardrail 31, 31a and the obstacle A are extracted. However, since the guardrail 31 is a part existing in the background data from the beginning, it is excluded from obstacles, and only L-shaped data as shown in FIG. 6 is extracted as difference data.

Next, the extracted difference data is grouped (segmented) (FIG. 2, S15). Grouping refers to classifying black dots for each set when the difference data includes a plurality of obstacle candidates.
After the grouping, data of isolated black dots that do not belong to the group are removed (S16). This is because isolated data is considered to be noise or the like measured by the millimeter wave sensor 11.

Next, attribute information of each obstacle candidate divided into groups is generated (S17). The attribute information means that the position of the center of gravity is calculated from the angle and distance data of each detection point of an obstacle (including an obstacle candidate) measured by the millimeter wave sensor 11, and the position (angle, distance) and speed of the center of gravity is calculated. And the size of the obstacle. This attribute information is stored in association with information for identifying an obstacle (for example, a label name). The attribute information is not limited to the center of gravity, and may be any information that can specify the position of the obstacle, and may be, for example, the center coordinates of a circumcircle of the obstacle, the coordinates of a plurality of points on the outer periphery of the obstacle, or the like.

Next, history information of the detected obstacle candidate is generated (S18). The history information generation process compares the attribute information of the obstacle detected this time with the obstacle detected in the past, and if there is an obstacle with the same attribute information in the past, the obstacle is defined as The recorded label name is recorded as history information at the time of the current measurement. If there is no obstacle having the same attribute information, a new label name is defined for the obstacle candidate, and the label name is recorded as history information. Here, the history information indicates the detection history of the obstacle, and is obtained by sequentially recording the label names defined for the obstacle in correspondence with each scan timing.

FIG. 7 is a diagram showing an example of the configuration of the history information. The history information includes the number of scans indicating the number of scans performed by the millimeter wave sensor 11 and the label name of the obstacle detected at that time. It is configured in pairs.

In the example of FIG. 7, it is stored that two obstacle candidates are detected at the time of the (t-2) th scan, and their label names are L1 and L2. At the time of the next (t-1) -th scan, only the obstacle candidate corresponding to the label name L2 is detected, and no obstacle candidate corresponding to the label name L1 is detected. However, this obstacle candidate is temporarily detected by another object. Is stored in the column of the label name L1 indicating the possibility of occlusion. Next t
At the time of the second scan, since a new obstacle candidate is detected in addition to the obstacle candidates with the label names L1 and L2, the label name L3 is stored.

Returning to FIG. 2, it is checked whether or not there is an obstacle (occlusion) temporarily hidden by another object by referring to the above-mentioned history information and attribute information (S19).
The occlusion check is a process of comparing measured data with history information to check whether there is a traveling vehicle or the like in front of the vehicle that has not been measured. If the obstacle is not measured in this measurement, it is estimated that the obstacle is temporarily hidden by another object.

Next, the presence or absence of an obstacle is detected (S2).
0). The detection of the obstacle is performed by referring to the history information based on whether or not the obstacle candidate having the same label name, that is, the same attribute information is repeatedly detected for a certain number of times or more. If the same obstacle candidate is detected a certain number of times or more (two or more times in the present embodiment), it is determined that the obstacle is detected.

If an obstacle is detected in step S20 (S20, YES), the position of the center of gravity of the obstacle is calculated, and the angle and distance of the center of gravity are calculated (S21). Further, the speed of the obstacle is calculated from the speed at the position of the center of gravity (S22).
Further, the size of the obstacle is calculated from the angle and distance data of each detection point of the obstacle (S23).

When the detection of the position, speed and size of the obstacle is completed, a message notifying that the obstacle is present is displayed on the information display board 13 (S24). Further, when a display device is connected to the obstacle detection device 12, the condition of the road including the obstacle is displayed on the display device.

The position of the detected obstacle and the size of the obstacle are output to an external device via the external I / F of the obstacle detection device 12 (S25). For example, the obstacle detection device 1
The monitoring center that monitors the road condition receives data about the obstacle output via the external I / F 2 and includes the obstacle on the display device of the monitoring center based on the data about the obstacle at each point on the road. Road conditions can be displayed. As a result, the monitoring center can grasp the presence or absence of an obstacle at each point on the road, and can notify the driver of the existence of the obstacle in advance by using an information display board or the like provided along the road.

Here, the contents of the background data generation / update processing in step S12 in FIG. 2 will be described with reference to the flowchart in FIG. First, in step S31, it is determined whether or not an object (including an obstacle) is within a blur range. The blurring range is a predetermined area surrounding the object (the area surrounding the obstacle in FIG. 10). If it is determined that the measured data is within the blurred range (S31, YES), the process proceeds to step S32, where the background data is updated. If step S31 is NO, the process proceeds to step S33 to determine whether or not the data is the measurement data behind the object and whether or not the occlusion exists in the rear area. If occlusion does not exist in the measurement data behind the object (S3
3, YES), the background data is not updated, and the process ends there. On the other hand, if occlusion exists even in the measurement data behind the object (S33, NO), the process of updating the background data in step S32 is executed.

Here, the updating process of the background data will be described. In the present embodiment, even if the road condition suddenly changes, the background data serving as the reference for detecting the obstacle is not affected by the sudden change in the road condition. For this purpose, the background data is updated using data obtained by weighting a plurality of measurement data measured at different measurement timings. In particular,
The background data is obtained from the following equation.

[0034] ^{M t = (1-α)} M t-1 + αW t-1 ··· (1) M; background data W; blurring data α; 0 ≦ α ≦ 1 t ; number of scans of the millimeter wave sensor 11 still , Blur data W is obtained from W = f (D). "
“D” is measurement data, and “f (D)” is an arithmetic expression for weighting a plurality of measurement data.

By calculating the background data from the above equation (1), it is possible to obtain background data in which the influence of sudden measurement data is suppressed. Here, the above-described step S
The contents of the occlusion check 19 and the background data generation / update processing in step S12 will be described with reference to FIGS. 9 and 10.

FIG. 9A is a diagram showing an object such as a vehicle and obstacles actually existing on the road, and FIG. 9B is a diagram showing measurement data measured by the millimeter wave sensor 11 at that time. FIG. In FIG. 9, the vertical axis represents angle and the horizontal axis represents distance, but this does not mean that the vertical axis and horizontal axis directly indicate the angle and distance, respectively, and the measured data indicates the angle and the distance. It is obtained as data represented by distance.

In a region which is not measured by the millimeter wave sensor 11 and becomes a shadow of an object, it is not usually necessary to update the background data. However, if there is a possibility that part or all of the obstacle may be included in the shadow area of the object, unless the background data of the area is updated, the obstacle that actually exists in that area will There is a problem that the data is not included.

Therefore, in the present embodiment, when it is estimated that an obstacle (occlusion) hidden as a shadow of an object exists, the background data of a predetermined area surrounding the hidden obstacle is obtained. Update processing is performed. As a result, an obstacle which is a shadow of the object and is not measured by the millimeter wave sensor 11 is stored as background data, and display data or the like for displaying the obstacle can be created using the background data.

An object A such as a vehicle, a stationary obstacle B, and a stationary obstacle C are placed on the road in a positional relationship as shown in FIG.
Is present, the object A and the obstacle B near the millimeter wave sensor 11 are measured by the millimeter wave sensor 11, but the obstacle C behind the obstacle B is It is not measured as a shadow.

Since part of the obstacle B is a shadow of the object A,
As shown in FIG. 9B, the millimeter wave sensor 11 measures an obstacle in which a part of the obstacle B is missing (this is called an obstacle B ′). Then, in the occlusion check in step S19 in FIG.
The attribute information of obstacles measured in the past is compared, and it is estimated whether or not occlusion hidden by another object exists. In this case, there is no obstacle whose attribute information completely matches, but the obstacle B measured at the time of the last and previous scans is not measured this time from the history information, and the obstacle B ′ and the obstacle B are determined based on the attribute information. Since it can be seen that the obstacle B 'is at substantially the same position, the obstacle B' is estimated to be a part of the obstacle B hidden.

When it is estimated that the obstacle B 'is a part of the obstacle B hidden, a predetermined area surrounding the obstacle B is determined in step S12 of FIG. Update the background data for the area.

Hereinafter, the contents of the background data updating process at this time will be described with reference to FIG. Areas a and b surrounded by squares around the object A and the obstacle B in FIG. 10 indicate areas where background data is updated in the present embodiment. Areas d and e indicated by oblique lines behind the object A and the obstacle B are areas behind the object A and the obstacle B, and are areas in which background data is not normally updated.

If the obstacle B is estimated to be occlusion, in the background data generation / update processing in step S12, a predetermined area b surrounding the obstacle B is determined based on the original size of the obstacle B and the position of the center of gravity. Is calculated, and the background data in the area b is updated. The update of the background data is obtained from the measurement data at the time t and the previous background data from the above-described equation (1). At this time, since the measurement data at time t is data in which a part of the obstacle B is missing, for example, the measurement data is corrected based on the attribute information of the obstacle B indicating the original size of the obstacle B ′. The background data including the entire obstacle B is updated by calculating the background data using the corrected measurement data.

Thus, even if a part of an obstacle is hidden by another object, the background data includes the entirety of the obstacle that actually exists, so that the obstacle can be detected more accurately. It becomes possible.

Next, an occlusion check on the obstacle C and updating of the background data will be described with reference to FIG. In this case, the occlusion check in step S19 in FIG. 2 indicates that the obstacle C has been repeatedly measured in the previous measurement from the history information, and that the obstacle C was not measured in the current measurement data. The object C is presumed to be occlusion temporarily hidden by another object.

When the obstacle C is estimated to be occlusion, the size and the size of the obstacle C are determined based on the attribute information of the obstacle C in the background data generation / update processing in step S12 in FIG.
The position of the center of gravity is acquired, and background data in a predetermined area c surrounding the obstacle C is updated.

The update of the occlusion background data is performed, for example, by using the data generated from the attribute information of the obstacle C in place of the data of the obstacle C in the current measurement data, and using the above-described equation (1) to update the background data. It may be performed by generating, or may be realized by another method.

Thus, even if the obstacle C is hidden by another object, the history information indicates that the obstacle C actually exists.
And the obstacle C is not removed from the history information,
Obstacles that are likely to actually exist can be reliably detected.

In the above-described first embodiment, when some or all of the obstacles that have been measured until then are not measured, those obstacles are temporarily hidden by other objects. And updating the background data of a predetermined area around the position where the obstacles exist based on the attribute information of the obstacles, thereby enabling the obstacles hidden by other objects to Can be saved as part of the data. As a result, it is possible to obtain accurate background data including obstacles that are likely to actually exist.Using the background data, an obstacle that is not measured as a shadow of another object can be accurately detected. It can be detected and displayed.

Next, a second embodiment of the present invention will be described with reference to FIG.
This will be described with reference to FIG. The second embodiment is realized in the above-mentioned road condition monitoring system. The millimeter wave sensor 11 detects the condition of the road at regular intervals, and the road condition is determined in accordance with the detected condition of the road. The timing of updating the data for displaying the status is changed.

Road conditions can be classified into two types: a state in which cars are flowing smoothly and a state in which traffic is congested. Then, in consideration of a change in the state, road conditions can be classified into the following four types.

While the state where the car flows smoothly continues,
There are four types of transition: a state in which the vehicle is flowing smoothly, a state in which the flow gradually deteriorates, a transition to a congested state, a state in which the vehicle is gradually transited from a congested state to a state in which the vehicle flows smoothly, and a state in which the traffic continues.

Then, based on the speed of the vehicle detected by the millimeter wave sensor 11, a vehicle having a speed equal to or higher than a certain speed is extracted from the measurement data, and a change in the number of vehicles having a speed equal to or higher than the certain speed and a change in the average speed are monitored. It is determined which of the four states it is in.

Specifically, when the number of vehicles having a speed equal to or higher than a certain value is equal to or more than a certain value and the number does not change much,
It is determined that the state in which the car is flowing smoothly is continuing. When the speed is equal to or higher than a certain value and the number of vehicles is decreasing, and the average speed of the vehicles is also decreasing, it is determined that the flow of the vehicle gradually deteriorates and the vehicle is transitioning to the congestion state. Further, when the number of vehicles at a certain speed or higher is increasing and the average speed is also increasing, it is determined that the vehicle is transitioning from the above-mentioned traffic congestion state to a state where the flow of vehicles gradually improves. Further, when there is almost no number of vehicles whose speed is equal to or higher than a certain value and the number does not change, it is determined that the above-mentioned traffic congestion is continuing.

When the road condition as described above is detected and the road condition is as described above and the state where the vehicle is flowing smoothly continues, the road condition does not change rapidly.
The data indicating the road condition is updated in a cycle longer than the measurement cycle of the millimeter wave sensor 11.

In the example of FIG. 11, one of the millimeter wave line sensors 11
Assuming that the data for the scan is one frame, the background data is updated every three frames, that is, every three scans.

In cases other than the above, that is, when the vehicle flow gradually deteriorates and the vehicle is transitioning to a congested state,
During the transition from the traffic congestion state to the state where the traffic flow gradually improves, and when the traffic congestion state continues, the road condition may change, so the background data is updated for each frame. .

In the second embodiment, the background data is not updated at each measurement timing, but the number of updates is reduced according to the road condition. , The processing time for updating the background data, data for displaying road conditions, and the like can be reduced.

Further, the obstacle detection program according to the present invention or the road condition detection program according to the second embodiment is stored in a floppy disk shown in FIG.
M, etc., is stored in a recording medium 1201, and the recording medium 1201 is read by a medium driving device (floppy disk driver, CDROM driver, etc.) of an information processing device (a personal computer, etc.) 1202, and the read program is stored in a hard disk, etc. Storage device 12
03, and the program may be executed. Alternatively, the program is stored in a storage device 1204 such as a hard disk of the information provider's computer, transferred to the user's information processing device 1202 by communication, stored in the user's storage device 1203, and executed. You may. Also, the recording medium 1201
May have some functions of the program described in the embodiment.

In the above-described first embodiment, background data is generated from measurement data, and an obstacle is detected using the background data. However, an obstacle detection device that does not use background data is also used. The present invention is applicable.

The sensor used is a millimeter wave sensor 11.
The sensor is not limited to this, and any sensor may be used as long as it can detect the speed, position, and the like of the object.

[0062]

According to the present invention, even if there is an obstacle hidden by another object, for example, data can be updated so that the obstacle hidden by another object is not erased. Thus, it is possible to more accurately detect an obstacle that actually exists. Further, by changing the update timing of the measurement data or the data obtained from the measurement data according to the road conditions, the number of update processes can be reduced, and the overall processing load can be reduced.

[Brief description of the drawings]

FIG. 1 is a system configuration diagram of a road condition monitoring system.

FIG. 2 is a flowchart of an obstacle detection process.

FIGS. 3A and 3B are diagrams showing road conditions at the time of background data acquisition and measurement data acquisition.

FIGS. 4A and 4B are explanatory diagrams of background data and measurement data.

FIG. 5 is a diagram showing a data matrix of background data.

FIG. 6 is a diagram showing obstacles extracted from a difference between measurement data and background data.

FIG. 7 is a diagram showing a configuration of history data.

FIG. 8 is a flowchart of background data generation / update processing.

FIGS. 9A and 9B are diagrams showing an actually existing obstacle and an obstacle detected by a sensor.

FIG. 10 is an explanatory diagram of an update range of background data.

FIG. 11 is an explanatory diagram of an update process according to the second embodiment.

FIG. 12 is an explanatory diagram of a recording medium.

[Explanation of symbols]

 11 millimeter wave sensor 12 obstacle detection device 13 information display board

Continued on front page F term (reference) 5H180 AA01 CC12 EE11 JJ09 LL08 LL15 5J070 AA04 AB24 AC01 AC02 AC06 AC11 AE01 AE07 AE20 AF01 AH14 AH19 AH50 AJ05 AJ14 AK04 AK30 BG28

Claims (14)

[Claims] 1. A detecting means for detecting an obstacle based on measurement data indicating a state of a road measured by a sensor, information on the obstacle detected by the detecting means and information on an obstacle detected in the past. Estimating means for estimating whether or not there is an obstacle hidden by another object based on and an updating means for updating data obtained from the measurement data based on the estimation result of the estimating means. An obstacle detection device for a road, comprising: 2. The updating means according to claim 1, wherein said estimating means estimates that an obstacle hidden temporarily exists.
The road obstacle according to claim 1, wherein when updating data obtained from the measurement data, the data is updated so that the temporarily hidden obstacle is not deleted from the data. Detection device. 3. The road fault according to claim 1, wherein the updating means generates data obtained from data obtained by weighting a plurality of measurement data measured at different measurement timings as the data. Object detection device. 4. The apparatus according to claim 1, wherein said updating means generates the next background data from the previously generated background data and data obtained by weighting a plurality of measurement data including the current measurement data. 3. The road obstacle detection device according to claim 3. 5. A storage means for storing history information indicating a detection history of an obstacle and attribute information of the obstacle, wherein the estimating means determines that an obstacle having the same attribute information from the history information is a predetermined number of times or more. 2. The method according to claim 1, wherein when the obstacle is repeatedly detected and the obstacle having the attribute information is not detected in the current measurement, the obstacle is estimated to be temporarily hidden by another object. , 2,
The road obstacle detection device according to 3 or 4. 6. An updating means for updating background data of a predetermined area including the temporarily hidden obstacle when it is estimated that a temporarily hidden obstacle exists. The road obstacle detection device according to claim 4, characterized in that: 7. The road obstacle detecting apparatus according to claim 4, wherein said detecting means detects an obstacle from a difference between background data and measured data. 8. An apparatus according to claim 1, wherein said sensor is a millimeter wave sensor. 9. An obstacle is detected based on measurement data indicating a road condition measured by a sensor, and another object is detected based on information on the detected obstacle and information on an obstacle detected in the past. Estimate whether or not there is an obstacle hidden by, and if it is estimated that there is an obstacle hidden by another object, when updating data obtained from the measurement data, And updating the data so that the detected obstacle is not erased from the data. 10. Stored is history information indicating an obstacle detection history and attribute information of the detected obstacle, and an obstacle having the same attribute information is repeatedly detected from the history information a predetermined number of times or more, and the current measurement is performed. 10. The road obstacle detection method according to claim 9, wherein when no obstacle having the attribute information is detected, it is estimated that the obstacle is temporarily hidden by another object. Method. 11. A sensor for measuring a condition of a road, a detecting means for detecting an obstacle based on measurement data indicating a condition of the road measured by the sensor, and information on the obstacle detected by the detecting means. And estimating means for estimating whether or not there is an obstacle hidden by another object based on information on obstacles detected in the past, and an obstacle hidden by another object by the estimating means. An updating unit that updates the data so that the hidden obstacle is not erased from the data when updating the data obtained from the measurement data when the data is estimated to be present. Road obstacle detection system. 12. A sensor for measuring a road condition at predetermined intervals, and measurement data indicating a road condition measured by the sensor or an update timing of data obtained from the measurement data is obtained from the measurement data. A road condition monitoring system comprising: an updating unit that changes according to a road condition. 13. The updating means calculates the speed of the vehicle from the measurement data measured by the sensor, determines whether or not the vehicle is flowing smoothly, and determines whether the vehicle is flowing smoothly. 13. The road condition monitoring system according to claim 12, wherein when the state in which the sensor is kept on is updated, the measurement data or data obtained from the measurement data is updated in a cycle longer than a measurement cycle of the sensor. . 14. An obstacle is detected based on measurement data indicating a road condition measured by a sensor, and another object is detected based on information on the detected obstacle and information on an obstacle detected in the past. To estimate whether or not there is a hidden obstacle, and if it is estimated that there is an obstacle hidden by another object, obtain from the measurement data so that the hidden obstacle is not erased. And a computer-readable recording medium storing a road obstacle detection program for updating data to be obtained.