JPH03209599A - Detector for abnormal traffic flow - Google Patents

Abstract

PURPOSE:To detect abnormal traffic flow by deciding the traffic flow is abnormal when a real traffic state amount detected after the lapse of prescribed time is out of a range between upper and lower set threshold values. CONSTITUTION:Based on the forecasted value of a traffic state amount forecasting means D to forecast the traffic state amount after the lapse of prescribed time from a current time point based on current traffic state amount data detected by a traffic state amount detecting means B, a threshold value setting means E sets the upper and lower threshold values for abnormal traffic flow after the lapse of prescribed time. Based on these set threshold values, a traffic flow abnormality deciding means F decides whether the real traffic state amount detected by the traffic state amount detecting means B is out of the range between the upper and lower threshold values after the lapse of prescribed time or not, and when the traffic state amount is out of the range, it is decided that the traffic flow is abnormal. Thus, the abnormal traffic flow which lower traffic capacity by an unexpected accident can be detected.

Description

[Detailed description of the invention] <Industrial application field> The present invention relates to an abnormal traffic flow detection device.

<Conventional technology> Conventional traffic flow monitoring methods employ a threshold-based determination method using traffic flow speed calculated based on vehicle detection data from vehicle detectors installed along the road. There is.

That is, a vehicle is detected by an ultrasonic vehicle detector installed along the road, and the vehicle detection time and the number of vehicles within a predetermined time are determined based on the output from the vehicle detector. From these data, we can calculate that the vehicle detection time ratio per unit time at one point on the road (hereinafter referred to as occupancy rate) is 0 and the number of vehicles per unit time at one point on the road (hereinafter referred to as traffic volume). Calculate Q. Furthermore, the occupancy rate ○
is assumed to be the density (the number of vehicles existing within a unit distance of the road) K, and the speed of the vehicle at that point is estimated from the following equation.

Q=K ・■ And, as shown in the seventh section, the threshold value V for determining whether there is a traffic jam or not in advance. , the calculated current speed ■ and the threshold value V. Compare with V<V.

If so, it would have been determined that there was a traffic jam.

<Problem to be solved by the invention> However, such conventional methods can only determine whether there is a traffic jam or not, but cannot detect abnormal traffic flows (traffic flows whose traffic capacity has decreased due to sudden events such as accidents). There wasn't.

For example, in Fig. 7, even if an unexpected event occurs at point only detected extinction.

The present invention has been made in view of the above circumstances, and it is an object of the present invention to provide an abnormal traffic flow detection device that can detect abnormal traffic flows that could not be handled conventionally. Another object of the present invention is to provide an abnormal traffic flow detection device that can determine the location and time of occurrence of an unexpected event that causes abnormal traffic flow.

Means for Solving the Problems> Therefore, as shown in FIG. A traffic state amount detection means B that detects a traffic state amount, and a traffic jam that determines whether or not there is a traffic jam by comparing the traffic state amount detected by the traffic state amount detection means B with a preset threshold for determining a traffic jam. a determining means C; a traffic state quantity prediction means for predicting a traffic state quantity after a predetermined time from the present time based on the traffic state quantity data detected by the traffic state quantity detection means B; and the traffic state quantity. Threshold value setting means E for setting upper and lower thresholds for abnormal traffic flow determination after the predetermined time based on predicted values of the prediction means; and actual traffic conditions detected by the traffic state amount detection means B after the predetermined time. The traffic flow abnormality determination means F determines that the traffic flow is abnormal when the amount is outside the range between the upper and lower threshold values set by the threshold value setting means E.

Further, as shown by the broken line in FIG. 1, the vehicle detection means A
, traffic state amount detection means B, traffic jam determination means C2, traffic state amount prediction means, threshold value setting means E, and traffic flow abnormality determination means F
At least two sets of vehicle detection means A are installed at intervals along the road, and the determination results of the traffic flow abnormality determination means F of the adjacent sets of G are compared. The device is configured to include means H.

Function> In the above configuration, the traffic state quantity detection means B detects the traffic state quantity at regular intervals based on the output of the vehicle detection means A that detects vehicles on the road.

The traffic jam determining means C compares the traffic state quantity detected by the traffic state quantity detecting means B with a preset congestion determination threshold value in the same manner as in the past to determine whether or not there is a traffic jam.

Further, a threshold value is set based on a predicted value of a traffic state amount prediction means that predicts a traffic state amount after a predetermined time from the present time based on the traffic state amount data detected by the traffic state amount detection means B up to the present time. The means sets upper and lower thresholds for abnormal traffic flow determination after the predetermined time, and based on the set thresholds, the traffic flow abnormality determination means F determines whether the traffic flow abnormality is detected by the traffic state quantity detection means B after the predetermined time. determining whether the actual traffic state quantity is outside the range between the upper and lower thresholds;
It is determined that the traffic flow is abnormal when it is outside the range.

This makes it possible to detect abnormal traffic flows where traffic capacity is reduced due to unexpected events that could not be detected conventionally, regardless of whether the traffic is congested or not.

Further, the comparison means H compares the determination results from the respective traffic flow abnormality determination means F corresponding to the mutually adjacent vehicle detection means A installed at intervals along the road.

This makes it possible to know the location and time when abnormal traffic flow occurs.

<Example> Hereinafter, one embodiment of the present invention will be described based on the drawings.

In FIG. 2 showing the configuration of this embodiment, ultrasonic vehicle detectors 2.3 as vehicle detection means are installed at predetermined intervals along a road 1.

The vehicle detectors 2 and 3 are equipped with a transmitter/receiver 2 installed above the road l.
Consisting of A, 3A and sensor bodies 2B, 3B, the transmitter/receiver 2
Ultrasonic waves are emitted toward the road 1 from A and 3A, and the presence or absence of a vehicle is detected by utilizing the time difference that occurs in the reception of the reflected waves depending on whether or not a vehicle has passed through that point. When a vehicle is detected, the sensor body 2B,
3B generates a sensing output of, for example, Hl/Bell.

The control unit 4 uses a built-in microcomputer to detect traffic jams and abnormal traffic flows and determines traffic flow abnormalities according to the flowcharts shown in FIGS. 3 and 4 based on the input data from the vehicle detectors 2 and 3. Set the threshold for

In this embodiment, the traffic state quantity detection means.

The functions of a traffic jam determination means, a traffic state amount prediction means, a threshold value setting means, a traffic flow abnormality determination means, and a comparison means are provided in the form of software, as shown in the flowcharts of FIGS. 3 and 4.

The operation for detecting congestion and abnormal traffic flow in this embodiment will be explained with reference to the flowchart in FIG.

In step 1 (denoted as 31 in the figure; the same applies hereinafter), data from the vehicle sensors 2 and 3 at fixed time intervals (for example, 5 minutes) are input.

In step 2, the traffic state quantity, in this embodiment, the speed V, is calculated in the same way as in the conventional method based on the input data.

That is, the occupancy rate O and the traffic volume Q are calculated from the input data, the occupancy rate 0 is replaced by the density K, and the speed ■ is calculated using the relational expression Q=K·■.

In step 3, the current traffic state quantity, that is, the speed calculated in step 2 is changed to the traffic flow abnormality judgment set based on the previous input speed ■predicted speed predicted from the data according to the flowchart in Figure 4. Upper threshold for ■2+
It is determined whether the traffic flow is abnormal or not depending on whether the traffic flow is within the range between α and the lower limit threshold value ■2α.

Then, the error e between the measured value V and the predicted value V2 (=V-V
, ) is -α≦e≦α, it is determined that there is no traffic flow abnormality (
No) L Proceed to step 11. On the other hand, when e>±α, it is determined that there is an abnormality in traffic flow (YES) and the process proceeds to step 4.

In step 4, it is determined whether or not there is a traffic jam by comparing the actual measurement value ■ with a preset threshold value V0 for traffic congestion determination. Here, V
If it is <Vo, it will be determined that there is a traffic jam and proceed to Ste Nobu 5, ■
≧■. If so, proceed to step 9.

In step 5, a comparison is made with the traffic flow abnormality determination result based on data from an adjacent vehicle sensor to confirm the location and time of occurrence of the abnormal traffic flow.

For example, the abnormality determination results based on the input data from the vehicle sensor 3.2 are shown in FIG. 5(A).

Assuming (B), when comparing both points, the speed at the point on the vehicle detector 2 side has decreased during the period T in the figure, but the speed at the point on the vehicle sensor 3 side has decreased. I haven't. As a result, it can be seen that on the vehicle detector 3 side, vehicles are flowing in the same manner as before, but on the vehicle sensor 2 side, the flow of vehicles is different from before. It can be seen that abnormalities in traffic flow are occurring.

In step 6, the current speed data is stored in advance and compared with past data showing normal traffic flow trends at this location to examine whether the congestion is natural or caused by an unexpected event.

Here, as the past data, for example, an hourly database for each day of the week is used. At this time, if the same day of the week in the previous week is a holiday, data on the same day in the previous week is used. Note that other databases may include a database for weekdays excluding festival days, May 10th, and the like.

Then, if the trend is similar to past data, it is determined that the traffic jam is natural, and if the trend is different, it is determined that the traffic jam is due to the occurrence of an unexpected event, and the process proceeds to step 7 or step 8, respectively. A display output is generated to notify the driver of the traffic jam caused by the occurrence of the traffic jam.

If it is determined in step 4 that there is no traffic jam and the process proceeds to step 9, the location and time at which the abnormal traffic flow occurs is confirmed in the same manner as in step 5.

In step 10, a traffic jam warning message is generated to notify the driver that there is a risk of traffic congestion.

Also, when it is determined in step 3 that the traffic flow is not abnormal and the process proceeds to step 11, it is determined whether or not there is a traffic jam in the same way as in step 4. If there is no traffic jam, the process returns to step 1 and it is determined that there is a traffic jam. At this time, there is no abnormality in the traffic flow and a traffic jam has occurred, so the process proceeds to step 7 and a display output of a natural traffic jam is generated.

Next, the setting operation of the threshold value for traffic flow abnormality determination used in the above-mentioned congestion and abnormality detection operation will be explained according to the flowchart of FIG.

In step 21, a predicted speed (2) after a predetermined time (for example, 5 minutes) is set based on the data of the current speed (2) inputted from the vehicle sensor at regular intervals (for example, 5 minutes). This prediction method may be, for example, the average of speed data up to the present or the moving unit uniformity.

In step 22, the predicted speed obtained in step 21 is
2 based on the above-mentioned upper limit threshold for traffic flow abnormality determination ■2+
Set α and lower limit threshold ■2−α.

The threshold value ■2±α set here is used to detect an abnormality in the traffic flow in the flowchart of FIG. 3.

By doing the above, it is possible to detect abnormalities in traffic flow at points X and Y in FIG. 6, which could not be detected conventionally. Then, before a traffic jam occurs, a traffic jam warning can be issued.

Furthermore, by comparing data from adjacent vehicle detectors, it is possible to automatically confirm the location and time when abnormal traffic flow occurs. Furthermore, when abnormal traffic flow is detected during a traffic jam, by comparing it with past data, it is possible to distinguish whether the abnormal traffic flow is normal or not. It will be possible to notify drivers if there is a traffic jam due to traffic jams.

In this example, the speed ■ is used as the traffic state quantity for detecting congestion and abnormal traffic flow, but the speed is not limited to this, and density and traffic volume Q can also be used. It is also possible to detect congestion and abnormal traffic flow by combining these methods.

<Effects of the Invention> As explained above, according to the present invention, it is possible to detect abnormal traffic flows caused by sudden events such as accidents and construction work that could not be detected conventionally, and to issue warnings of traffic congestion. It becomes possible to take it out. In addition, the location and time of occurrence of abnormal traffic flow can be immediately known. Therefore, the accuracy of traffic information can be improved, and more detailed traffic information than before can be provided to drivers, which is extremely effective in alleviating road traffic.

[Brief explanation of drawings]

Fig. 1 is a block diagram explaining the present invention in detail, Fig. 2 is a configuration diagram showing an embodiment of the present invention, Fig. 3 is a flowchart for detecting congestion and abnormal traffic flow of the same embodiment, and Fig. 4 is a block diagram showing a detailed explanation of the present invention. A flowchart for setting the threshold for traffic flow abnormality detection in the above embodiment, Fig. 5 is a diagram showing a comparative example of traffic flow abnormality determination results by adjacent vehicle detectors, and Fig. 6 explains the traffic flow detection operation in the above embodiment. FIG. 7 is a diagram illustrating the detection operation of the conventional example. ■...Road 2 3...Vehicle detector 4...Control unit

Claims (2)

[Claims] (1) A vehicle detection means for detecting a vehicle on the road; a traffic state amount detection means for detecting a traffic state amount at regular intervals based on the output of the vehicle detection means; traffic condition determining means for determining whether or not there is a traffic jam by comparing the traffic condition amount with a preset traffic condition determination threshold; and based on the traffic condition amount data up to the present detected by the traffic condition amount detection means a traffic state amount prediction means for predicting a traffic state amount after a predetermined time from the present time; and a threshold value setting means for setting upper and lower thresholds for abnormal traffic flow determination after the predetermined time based on the predicted value of the traffic state amount prediction means. , a traffic flow in which the traffic flow is determined to be abnormal when the actual traffic state quantity detected by the traffic state quantity detection means after the predetermined time is outside the range between the upper and lower threshold values set by the threshold value setting means; What is claimed is: 1. An abnormal traffic flow detection device comprising: abnormality determination means. (2) a vehicle detection means for detecting a vehicle on the road; a traffic state amount detection means for detecting a traffic state amount at regular intervals based on the output of the vehicle detection means; traffic condition determining means for determining whether or not there is a traffic jam by comparing the traffic condition amount with a preset traffic condition determination threshold; and based on the traffic condition amount data up to the present detected by the traffic condition amount detection means a traffic state amount prediction means for predicting a traffic state amount after a predetermined time from the present time; and a threshold value setting means for setting upper and lower thresholds for abnormal traffic flow determination after the predetermined time based on the predicted value of the traffic state amount prediction means. , a traffic flow in which the traffic flow is determined to be abnormal when the actual traffic state quantity detected by the traffic state quantity detection means after the predetermined time is outside the range between the upper and lower threshold values set by the threshold value setting means; At least two sets of the vehicle detecting means are installed at intervals along the road, and the determination results of the respective traffic flow abnormality determining means of the adjacent sets are compared. What is claimed is: 1. An abnormal traffic flow detection device comprising: means.