JP4935791B2 - Vehicle sensing system - Google Patents

Description

  The present invention relates to a vehicle sensing system.

  A vehicle sensing system that senses the presence or absence of a vehicle on a road is known in order to check traffic volume and vehicle occupancy time. Patent Document 1 discloses such a vehicle sensing system.

The system of Patent Document 1 includes a sensor that detects a vehicle passing through a monitoring area on a road. This sensor has a thermopile element and senses infrared rays emitted from detection objects such as vehicles and roads. This sensing result is given to the system as an input level.
When the temperature of the vehicle is different from the temperature of the road, the amount of infrared rays to be emitted also differs between the vehicle and the road. For this reason, when the vehicle passes through the monitoring area of the sensor, the input level from the sensor changes according to the temperature. It is possible to detect a vehicle passing through the monitoring area by the change in the input level.

More specifically, in Patent Document 1, a value based on a difference between an input level obtained from a sensor and a background level indicating a road temperature is used as a comparison value, and the comparison value is compared with a threshold value. Determine presence or absence.
Patent Document 1 discloses a background level calculation means for changing the background level using the obtained input level according to the determination result of the presence or absence of a vehicle.

Japanese Patent No. 3719438

When the background level is changed according to the determination result of the presence / absence of the vehicle, for example, the background level is not learned when there is a vehicle, and the background level is learned so as to follow the input level when there is no vehicle. By changing the background level not by a constant value but by learning, it is possible to cope with changes in the true value of the background level (background temperature) due to changes in the air temperature or the like.
In addition to such background level learning, it is desirable to take detailed measures so that the background level does not deviate from the true value as much as possible to further improve the accuracy of vehicle detection.

  Therefore, an object of the present invention is to provide a new technique for dealing with a background level deviating from a true value in a vehicle sensing system.

Vehicle sensing system of the present invention the input level obtained from the detecting section for detecting a temperature of the monitoring area on the road, a comparison value based rather value to the difference between the background level based on the temperature level of the road, the a comparison value and compares the threshold value for determining vehicle determining unit for determining the presence or absence of a vehicle, while it is the determination without vehicle, the execution of the learning process of the input level based rather the background level A learning processing unit that performs switching between pause and pause, and execution of the background level learning process by the learning processing unit and switching between pauses are controlled according to the comparison value, and the comparison value is greater than a threshold for background level learning. If the vehicle level is larger, the learning control unit that pauses the background level learning process and the background level learning process is paused while the background level learning process is paused while the background level learning process is paused. Obtained When the difference between the force level and the background level is greater than or equal to a predetermined value, and a background level adjusting unit to execute processing to match the background level to the input level.

According to the present invention, even when it is determined that there is no vehicle, if it is not preferable to execute the background level learning process, the learning control unit can pause the background level learning process. it can.
However, when it is determined that there is no vehicle and the background level learning process is paused, the background level recognized by the vehicle sensing system and the actual road are detected when the road temperature is constantly changing. A difference occurs between the temperature and the temperature.
Therefore, even in this case, if the difference between the background level in the vehicle sensing system and the input level obtained from the detection unit is equal to or greater than a predetermined value, the background level is adjusted by the background level adjustment unit. It is estimated that it is different from the temperature (the true value of the background level), and processing for adjusting the background level to the input level is executed, so that the background level can be adjusted to the actual road temperature. As a result, the vehicle detection accuracy can be increased.

Further, the background level adjustment unit is configured to input the background level when the difference between the input level and the background level is equal to or longer than a predetermined time. It is preferable to execute processing that matches the level.
As described above, when the time during which the difference is equal to or greater than the predetermined value is equal to or longer than the specified time, the background level in the vehicle detection system is more likely to be different from the actual road temperature. By executing the process of adjusting the background level to the input level, the background level can be adjusted to the actual road temperature.

Further, when the background level adjustment unit switches from the determination of the presence of the vehicle after the determination of the absence of the vehicle to the determination of the absence of the vehicle, a process of adjusting the background level to the input level at the time of the change Preferably it is performed.
In this case, since the input level to be matched with the background level is the one when switching to the determination that there is no vehicle, the background level matched with the input level is considered to be based on the temperature of the road. It is possible to obtain an accurate background level.

  According to the present invention, when it is determined that there is no vehicle and the learning process of the background level is suspended, if the road temperature changes, the background level recognized by the vehicle sensing system and the actual road Although there is a difference between the temperature and the temperature, the background level adjustment unit can adjust the background level to the actual road temperature, and the vehicle detection accuracy can be improved.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
[Overall configuration of vehicle sensing system]
1 and 2 show a vehicle sensing system 1. The vehicle sensing system 1 senses the vehicle V when the predetermined area on the road is the monitoring area A and the vehicle V exists in the monitoring area A.

  The vehicle sensing system 1 includes a detection unit 2 that detects the temperature of the monitoring area A in order to detect the vehicle V. The input level (input voltage value corresponding to the average temperature of the monitoring area A) obtained by the detection unit 2 is given to the sensing processing unit 3. The sensing processing unit 3 determines the presence or absence of the vehicle V in the monitoring area A, and outputs a signal indicating whether there is a vehicle (sensing ON) or no vehicle (sensing OFF) as a sensing result.

  The sensing result is transmitted to a traffic signal controller or a traffic control center. The traffic signal controller is installed in the vicinity of the vehicle sensing system 1. In a traffic control center or the like, the detection results from a plurality of vehicle detection systems are totaled to calculate traffic volume and vehicle occupancy time, and traffic congestion judgment and vehicle average speed calculation are performed.

The detection unit 2 includes a thermopile element that detects the temperature of the monitoring area A by sensing infrared rays emitted from a vehicle or a road. As shown in FIG. 1, the detection unit 2 is attached to a roadside column 4 in order to set the monitoring area A on the road R.
The detecting unit 2 is connected to the sensing processing unit 3, and the input level obtained by the detecting unit 2 is transmitted to the sensing processing unit 3.
The sensing processing unit 3 is disposed in a housing 5 attached to the support column 4. The sensing processing unit 3 may be configured to be housed in the same housing as the detecting unit 2, and the arrangement of the detecting unit 2 and the sensing processing unit 3 is not particularly limited to the configuration illustrated in the drawing.

[Determination of presence / absence of sensing processing unit 3 and vehicle V]
The detection processing unit 3 is configured by hardware including a computer having a CPU, a storage unit, and the like, and performs various processes for vehicle detection by executing a computer program stored in the storage unit. .

  As a basic principle for the detection processing unit 3 to determine the presence or absence of the vehicle V in the monitoring area A (sensing determination), the detection processing unit 3 stores the temperature of the road R when the vehicle V is not present as a background level. If there is a difference between the input level obtained from the detection unit 2 and the background level, it is determined that there is a vehicle (sensing ON), and if there is no difference between the input level and the background level, it is determined that there is no vehicle (sensing OFF). .

  In the present embodiment, the sensing processing unit 3 determines a value based on the difference between the input level and the background level in order to perform the sensing determination more accurately rather than simply comparing the input level and the background level. Is calculated as a comparison value, and the comparison value is compared with a threshold value (threshold value for sensing determination) to obtain a sensing result (sensing ON / sensing OFF).

  For this purpose, the sensing processing unit 3 has a function as a comparison value calculation unit 31 that calculates a value based on the difference between the input level and the background level as a comparison value (see FIG. 3A). Furthermore, the sensing processing unit 3 has a function as a determination unit 32 that compares the comparison value and a threshold for vehicle determination to determine the presence or absence of the vehicle (see FIG. 3B).

  The comparison value calculation unit 31 calculates a sum of products of differences between the input level and the background level as a value (comparison value) indicating a difference between the input level and the background level. This sum of micro products makes it easy to compare with the threshold value by reducing the influence of noise from the simple difference between the input level and the background level and emphasizing the change of the simple difference.

As shown in FIG. 3A, in the comparison value calculation unit 31, first, the difference calculation unit 31a calculates the difference between the input level and the background level in order to calculate the product sum. Further, an integral value of the absolute value of the difference is obtained by the integral calculation unit 31b.
This integral value corresponds to the time average value of the difference, and a value obtained by reducing the influence of noise from the difference can be obtained. Further, a calculation for obtaining a differential value of the absolute value of the difference is performed by the differential calculation unit 31c. The differential value indicates the amount of change in the difference.

  The integrated value and the differentiated value are added by the adding unit 31d, and this added value becomes a sum of products (comparison value). The micro product sum is obtained by adding a differential value indicating a change to an integral value in which noise is reduced, and therefore, the influence of noise is reduced and the change is emphasized.

  Since the determination unit 32 performs determination using this sum of products, it is possible to perform detection determination more accurately. However, the comparison value is not limited to the sum of products as long as it is based on the difference between the input level and the background level. The comparison value calculation unit 31 also outputs the integral value. This integral value is also a value based on the difference between the input level and the background level, and is used for threshold learning described later.

As illustrated in FIG. 3B, the determination unit 32 uses the comparison value (sum of products) calculated by the comparison value calculation unit 31 to perform a detection determination that outputs a detection result (sensing ON / sensing OFF). Do.
If the comparison value is larger than the vehicle determination threshold value (comparison value> the vehicle determination threshold value), it is determined that the sensing is ON (there is a vehicle), and the comparison value is the vehicle determination threshold value. If it is smaller than the threshold (comparison value <threshold for vehicle determination), it is determined that sensing is OFF (no vehicle).

  However, in this embodiment, in order to prevent chattering of the sensing result immediately after switching from sensing ON to sensing OFF or immediately after switching from sensing OFF to sensing ON, “threshold Lo” (first vehicle) is used as the threshold for sensing determination. Two thresholds are introduced: a determination threshold value) and a “threshold value Hi” (second vehicle determination threshold value).

  The threshold Lo is used to determine the absence of the vehicle (sensing OFF) while the determination that the vehicle is present (sensing ON). The threshold Hi is determined to be the absence of the vehicle (sensing OFF). The vehicle is used to determine whether the vehicle is present (sensing ON). The threshold value Lo is set to a value that is a predetermined value less than the threshold value Hi, thereby preventing chattering at the time of sensing ON / OFF switching.

As shown in FIG. 4, the sensing processing unit 3 further has a function as a background level learning processing unit 33 that learns the background level. In addition, the sensing processing unit 3 preferably has a function as a threshold learning processing unit 34 for learning thresholds for vehicle determination (threshold Lo and threshold Hi).
The sensing processing unit 34 also has a function as a learning control unit 35 for controlling the learning processing of one or both of the background level learning processing unit 33 and the threshold learning processing unit 34.
Further, the detection processing unit 34 also functions as a background level adjustment unit 40 for eliminating the difference between the background level recognized by the vehicle detection system 1 and the true value of the background level indicating the actual road temperature. Have.

[Background level learning processing unit 33 and learning control unit 35]
The background level (road surface temperature) varies greatly depending on the environment, such as when the road becomes sunny or shaded by sunlight. If a constant value is used as the background level, it will be true (actual road temperature). Deviation occurs. Therefore, it is conceivable to learn the background level as shown in FIG. 5A (first background level learning).

In this learning method, when the sensing is OFF when the vehicle V does not exist in the monitoring area A, the input level should indicate the temperature of the road R. Therefore, the background level learning processing unit 33 follows the input level so as to follow the input level. Do level learning.
Also, in this learning method, when the vehicle V is present in the monitoring area A, when the sensing is ON, the input level should mainly indicate the temperature of the vehicle V. Therefore, the background level learning processing unit 33 learns the background level. The background level when switching from sensing OFF to sensing ON is maintained.

  As described above, in the first background level learning, the presence / absence of learning is switched based only on the sensing result (sensing ON / sensing OFF). This learning switching is performed by the learning control unit 35. The learning control unit 35 can perform switching control of presence / absence of learning in the background level learning processing unit 33 by acquiring only the sensing result.

  The second background level learning shown in FIG. 5B will be described. In this learning method, a case where learning is not performed is set even when sensing is OFF. In the second background level learning, other than the sensing result is also introduced as a learning execution / pause switching condition.

Specifically, a sum of products (comparison value) is introduced as a learning execution / pause switching condition. When the detection is turned off, the background level learning is not performed immediately (unconditionally), but the background level learning is performed after the sum of products (comparison value) becomes sufficiently small. This switching is performed by the learning control unit 35.
More specifically, a threshold for background level learning (hereinafter referred to as “holding Lo”) is introduced, and if the sum of products (comparison value) is larger than holding Lo, learning is not performed even if sensing is OFF, If the sum of products (comparison value) is smaller than the holding Lo at the time of sensing OFF, the background level is learned.

  As the holding Lo, for example, a value of the sum of products when the sensing is turned on is set every time the sensing is turned on. Specifically, as shown in FIG. 7B, when the detection result changes from detection OFF to detection ON, the threshold Lo when the detection is ON is set (stored) as the retention Lo. . The set holding Lo is used for comparison with the sum of products when sensing is OFF. Note that the value of the holding Lo is maintained while the small product sum exceeds the holding Lo, and is reset when the small product sum falls below the holding Lo.

  In this way, even during the determination that there is no vehicle, the product sum (comparison value) is relatively large (the product sum (comparison value) is greater than the retention Lo). Is likely to exist, the learning process is suspended. Therefore, although it is erroneously determined that there is no vehicle, the learning of the background level can be paused when the vehicle V is actually present in the monitoring area A, and therefore based on the temperature of the vehicle V. The background level is not learned, and the background level can be prevented from deviating from the true value.

  In the first or second background level learning, the learning control unit 35 pauses the learning process for the background level for a long time (for example 5 After the vehicle V exists in the monitoring area A, the vehicle V may leave the monitoring area A. That is, the road temperature temporarily deviates from the normal value due to the influence of the vehicle V stopped in the monitoring area A, but immediately returns to the normal temperature.

  In this case, if the vehicle V leaves the monitoring area A, it is determined that there is no vehicle, and even if the background level learning processing unit 33 immediately starts the background level learning processing so as to follow the input level, this input is performed. The level is based on the temperature of the road temporarily deviating from the normal value, and the learning process may be wasted because the road immediately returns to the normal temperature. Therefore, it may be preferable to pause the background level learning process immediately after the vehicle V is present in the monitoring area A for a long time and immediately after the determination that no vehicle is present (predetermined time).

  As described above, the learning control unit 35 of the present invention performs the background level learning process when it is not preferable to execute the background level learning process even during the determination that the vehicle is not present. You can pause.

[Threshold level learning processing unit 34 and learning control unit 35]
In the present embodiment, as described above, it is preferable to perform learning (adjustment) of not only the background level but also the vehicle determination thresholds (threshold Lo and threshold Hi).
In fact, even when sensing is OFF (when there is no vehicle), the difference (comparison value) between the input level and the background level is not always zero due to factors such as disturbance, but varies with time. Therefore, in order to more accurately determine the sensing ON, as shown in FIGS. 6 and 7B, when sensing is OFF, the threshold learning unit 34 (see FIG. 4) determines the comparison value (small product sum) with respect to the threshold Hi. ) And learning with the goal of adding a certain value.

  The threshold Lo is a value obtained by subtracting a certain value from the threshold Hi. In FIG. 7B, the threshold value is indicated by a single line without distinguishing between the threshold value Hi and the threshold value Lo, and the same applies to FIG. As a result, at the time of sensing OFF, the threshold value Hi and the threshold value Lo follow the change of the comparison value with a value slightly higher than the comparison value (sum of products) while maintaining the interval of the predetermined value. .

Further, when sensing is ON (when a vehicle is present), it is conceivable to maintain a threshold value when switching from sensing OFF to sensing ON.
However, the threshold learning unit 34 learns (adjusts) the threshold while sensing is ON because the following problem cannot be dealt with simply by holding the threshold while sensing is ON.
That is, when the vehicle V stops in the monitoring area A for a long time, such as when waiting for a signal, there may be a difference in road surface temperature before and after passing the vehicle. That is, since the road surface temperature changes under the influence of the vehicle V being stopped for a long time, as shown in FIG. 7A, the vehicle V enters the monitoring region A immediately before the detection is turned on from the detection OFF. There is a difference between the road surface temperature immediately before (time t0) and the road surface temperature immediately after the sensing ON is changed from sensing ON (immediately after the vehicle V passes through the monitoring area A: time t1), and the vehicle sensing system 1 recognizes the difference. The background level is different from the true value.

  Even in such a case, the background level learning processing unit 33 holds the background level when the detection is turned on from the detection OFF (time t0) because the background level learning cannot be performed while the detection is turned on. As a result, when the vehicle V exits the monitoring area A and changes from sensing ON to sensing OFF (time t1), the value of the background level is affected by the true value (the vehicle V stopped in the monitoring area A). The road surface temperature changed).

In this way, while the sensing is ON (while the vehicle V is in the monitoring area A), the background level gradually deviates from the true value as time passes. This divergence between the background level and the true value affects the comparison value (sum of products) indicating the difference between the input level and the background level.
In other words, the comparison value increases as the time lapses while sensing is ON.
Therefore, considering the occurrence of a deviation from the true value of the background level, during detection ON, the “sensitivity” for determining detection OFF is increased over time, and detection is performed even if the degree of decrease in the comparison value is small. It is necessary to be able to determine OFF.

Therefore, at the time of sensing ON, as shown in FIG. 6, learning for gradually increasing the threshold value Hi is performed with the target of 90% of the integral value (value based on the difference between the input level and the background level), and the threshold value Lo is determined. Is a value obtained by subtracting a certain value from the threshold value Hi. Here, this learning is referred to as “normal learning”.
This normal learning is not intended to set the threshold to 90% of the integral value itself, but reflects the deviation of the background level included in the integral value in the threshold and responds to the gradual increase of the deviation. This is for gradually increasing the threshold value. Therefore, in this normal learning, the increase degree of the threshold is relatively gradual.

Furthermore, in the present embodiment, the threshold learning unit 34 performs not only normal threshold learning but also rapid threshold increase processing when sensing is ON.
As shown in FIG. 6, this rapid increase process is a process that is executed when a predetermined time (200 msec) has passed since the detection is turned on, and the increase rate is larger than the moderate increase rate of the normal learning process. Increase the threshold significantly.

This rapid increase process is a process for preventing the sensing ON time from becoming longer than the time during which the vehicle is actually present in the monitoring area A even when there is snow on the road surface or when it is raining.
That is, when there is snow on the road surface or when it is raining, the input level obtained from the detection unit 2 is gentle even if the vehicle is in the monitoring area A and the vehicle has passed. The phenomenon that it falls and does not return easily to the background level occurs.

The reason why such a phenomenon occurs is unknown, but when this phenomenon occurs, the comparison value (sum of products) indicating the difference between the input level and the background level is actually relatively large even after the vehicle has passed. Value. In other words, since the input level is increased even if the vehicle is not actually present, the comparison value (sum of products) indicates a value as if the vehicle is present.
As a result, the comparison value (small sum of products) falls below the threshold value at a time later than the time when the vehicle actually passes. For this reason, the sensing ON time is originally longer than the time when the sensing should be ON.

  Therefore, as shown in FIG. 7B, the threshold learning unit 34 is in the normal learning mode and increases the threshold by the normal learning process until a predetermined time (200 msec) elapses after the sensing is turned ON. However, when a predetermined time (200 msec) elapses, the threshold learning processing unit 34 shifts to a rapid increase mode in which the threshold Lo is greatly increased, and performs a rapid increase process of the threshold.

As a result of this rapid increase processing, as soon as the comparison value (sum of products) slightly decreases from the maximum value, the comparison value falls below the threshold value Lo, and the sensing ON time is shortened. As a result, the sensing ON time can be prevented from becoming too long.
Then, after the threshold value Lo is rapidly increased by the rapid increase process, the threshold value is maintained at the value after the rapid increase as long as the sensing ON continues. After the rapid increase process, the normal learning process may be performed again. However, since the threshold value Lo is increased by the rapid increase process, the necessity of performing the normal learning process after the rapid increase process is low.

[Background level adjustment unit 40]
As described above, according to the learning control unit 35, the background level learning processing by the background level learning processing unit 33 is suspended when it is not preferable to perform the background level learning processing even during sensing OFF. Can be made.
However, when the detection OFF determination is made and the background level learning process is paused in this way, the vehicle does not actually exist and the road temperature is constantly changing due to sunlight or the like. There may be a difference between the background level recognized by the vehicle sensing system 1 and the true value of the background level (actual road temperature). In this case, an erroneous determination may occur in subsequent vehicle sensing.

  Therefore, the detection processing unit 3 has a function as a background level adjustment unit 40 for eliminating the difference (see FIG. 4). That is, the background level adjustment unit 40 determines the input level obtained from the detection unit 2 while the background level learning process is suspended and the background level recognized by the detection processing unit 3 is determined. A calculation unit 41 that compares the difference value with a predetermined value stored in advance, and the difference value is equal to or greater than the predetermined value, and the difference value is abnormal. A shift canceling unit 42 is provided for executing a process for adjusting the background level to the input level when doubt is determined.

The function of the background level adjustment unit 40 will be described.
As described above, the background level learning processing unit 33 does not learn the background level when sensing is ON, and also learns the background level when the sum of products is larger than the retained Lo even when sensing is OFF. Is not performed (see FIG. 5B).
Therefore, as shown in FIG. 10A showing the conventional example, the true value of the background level (the temperature of the road surface) changes before and after the vehicle V passes through the monitoring area A (time t0, t1). Thus, the background level recognized by the sensing processing unit 3 deviates from this true value.

  Then, when the detection level is changed from ON to OFF (time t1 in FIG. 10A), if the background level is deviated from the true value, even if the input level is lowered to the true value of the background level, A difference occurs between the level and the background level recognized by the detection processing unit 3, and as shown in FIG. 10B, a small product sum (comparison value) indicating the difference becomes relatively large. . As a result, even if the vehicle V finishes passing through the monitoring area A, the state where the sum of products exceeds the retention Lo continues. For this reason, even if the vehicle V does not exist in the monitoring area A, the background level learning processing unit 33 cannot learn the background level and cannot eliminate the background level shift.

Even in such a state, if the change in the input level when the vehicle subsequently passes is sufficiently large (time t2), the sensing determination can be performed normally as shown in FIG.
However, when the vehicle V having a small change in input level passes through the monitoring area A in an environment where the temperature difference between the road surface and the vehicle V is small, such as in rainy weather, for example (time t4), The sum of products cannot exceed the threshold value (see FIG. 10B), and “sensing omission” that does not turn on sensing occurs when sensing should be turned on (see FIG. 10C). Alternatively, it is not desirable that the state in which the background level is erroneously recognized continues even if no sense loss occurs.

  Therefore, in the present invention, the difference between the input level obtained from the detection unit 2 while the background level learning process is paused and the background level recognized by the system is determined. If it is equal to or greater than the predetermined value, the background level adjustment unit 40 estimates that the recognized background level is different from the true value, and executes the process of matching the background level to the input level, thereby reducing the background level deviation. Eliminate and ensure vehicle detection accuracy.

  Specifically, in FIG. 8, when the determination by the determination unit 32 is in a sensing OFF state (step S11), and the learning control unit 35 is in a state where the background level learning process is suspended (step S12). The calculation unit 41 (see FIG. 4) of the background level adjustment unit 40 obtains a difference between the input level obtained during that time and the background level recognized by the system (the sensing processing unit 3) (step S13). This difference is obtained every time the input level is sampled.

The computing unit 41 executes the process shown in FIG. 9 according to the difference value obtained in step S13 (step S14).
That is, when the obtained difference ε is larger than the first threshold σ1 (the predetermined value) (ε> σ1), that is, when the difference ε is relatively large, the time (seconds) during which the difference ε is generated is calculated. Count. When the obtained difference ε is equal to or less than the first threshold value σ1 and equal to or greater than the second threshold value σ2 (σ1 ≧ ε ≧ σ2), that is, when the difference ε is relatively small, the time counted so far is held. When the obtained difference ε is less than the second threshold σ2 (ε <σ2), that is, when the shift is small or not shifted, the count is initialized (0 seconds).
And the calculating part 41 hold | maintains this total time (count) as an adjustment value. That is, the adjustment value is a “deviation time” related to the time during which there is a difference between the input level and the background level. This shift time means a time during which the difference ε between the input level and the background level is equal to or greater than the first threshold σ1 (the predetermined value).

  The process shown in FIG. 9 is continued until the determination by the determination unit 32 is turned ON next. When the sensing is turned on (Yes in step S15), the calculation unit 41 compares the deviation time with the specified time stored in advance by the calculation unit 41, and the deviation time is equal to or longer than the specified time. On the other hand (Yes in step S16), the deviation eliminating unit 42 (see FIG. 4) executes a process of matching the background level in the system with the input level obtained from the detecting unit 2 (step S18).

  On the other hand, if the shift time is less than the specified time as a result of the comparison calculation by the calculation unit 41 (No determination in step S16), the shift cancellation unit 42 executes a process for matching the background level in the system to the input level. The background level is maintained as it is (step S19).

  In steps S14 to S16, a suspicion that the background level is shifted from the true value is predicted based on the magnitude of the difference ε and the shift time. If the deviation time is equal to or longer than the specified time (Yes in step S16), it is predicted that the background level in the system is likely to be different from the true value, and the deviation elimination unit 42 inputs the background level. By executing the process to match the level, the background level can be adjusted to the true value.

In this embodiment, before proceeding to step S18, the deviation canceling unit 42 can obtain information on the determination result of sensing ON / sensing OFF by the determining unit 32, and the deviation canceling unit 42 receives the information in step S11. The timing of switching from the determination of sensing ON after the determination of sensing OFF (determination of Yes in step S15) to the determination of sensing OFF (determination of Yes in step S17) is made. When the determination of Yes in step S17 is made, at that timing, a process of matching the background level in the system with the input level when switching to the detection OFF determination (at the time of switching) is executed.
That is, in this step S17, even if it is suspected that the background level is deviated from the true value by the computing unit 41, the deviation canceling unit 42 performs processing for adjusting the background level to the input level until the detection is switched off next time. Waiting (No determination in step S17).

  As described above, the reason for proceeding to step S18 via step S17 is that the input level when the sensing is switched to the next time (when determining Yes in step S17) is that the vehicle V leaves the monitoring area A. Since the input level is considered to indicate the road temperature, the background level adjusted to this input level is based on the road temperature, and the accurate background level is It is because it becomes possible to obtain.

A specific example of the processing by the background level adjustment unit 40 will be described with reference to FIG.
At time t0, sensing is ON and the background level is not learned, and at time t1, sensing is OFF (step S11 in FIG. 8), and the background level learning process is paused (step S12). The calculation unit 41 of the level adjustment unit 40 obtains the difference between the input level obtained from the detection unit 2 after time t1 and the background level recognized by the system (the sensing processing unit 3). The process for obtaining this difference is continued until the sensing is turned ON at time t2, and the “deviation time” occurring from time t1 to time t2 is obtained (step S13, step S14 and step s15).

  When the sensing is turned on (Yes determination at step S15), the calculation unit 41 determines that the shift time is equal to or longer than the specified time (Yes determination at step S16), and further from the sensing ON state to the time t3. When the detection is switched to OFF (Yes in step S17), the deviation elimination unit 42 of the background level adjustment unit 40 performs a process of adjusting the background level in the system to the input level when the switching is performed (deviation correction). Execute (Step S18). Thereby, the shift of the background level with respect to the true value can be eliminated.

Further, in the shift correction process in step S18, the background level is matched to the input level by substituting the input level at the time of switching to the sensing OFF (the input level at time t3) into the background level in the system. Can do. In this case, the background level shift can be quickly eliminated.
Alternatively, as another method, after the time t3, the system background level may be learned and matched so as to follow the input level after switching to the sensing OFF at the time t3.

  In this way, by eliminating the background level shift, as shown in FIG. 7B, the sum of products obtained after time t3 becomes smaller (correct), and at time t4, the input level is reduced. Even when a vehicle having a relatively small amount of change passes through the monitoring area A, the sum of micro products exceeds the threshold value and can be turned on (time t4), as in the conventional case (time t4 in FIG. 10). Can be prevented. In addition, according to the present invention, the sum of products obtained thereafter becomes smaller than the retention Lo, so that the background level learning processing unit 33 can learn the background level in the sensing OFF state.

According to the vehicle sensing system configured as described above, the true value of the background level changes before and after the vehicle V passes through the monitoring area A, so that the background level recognized by the system is changed from this true value. Even if a shift occurs, this shift can be eliminated, and the subsequent vehicle detection determination accuracy can be maintained high.
As a result, the traffic signal controller and the traffic control center (see FIG. 2) can normally grasp information relating to traffic volume and occupation time on the road, and the traffic signal device can be effectively used using such information. Can be controlled.

In addition, regarding the vehicle sensing system of the present invention, the embodiment disclosed this time should be considered as illustrative in all points and not restrictive. The scope of the present invention is not intended to include the above-described meanings, but is intended to include meanings equivalent to the claims and all modifications within the scope.
For example, the determination method by the determination unit 32 may be another method. The threshold value Hi and the threshold value Lo may be combined into one without providing the threshold value Hi and the threshold value Lo. Further, the learning method by the background level learning processing unit 33 may be a method other than that shown in FIG.

It is a perspective view which shows the vehicle detection system installed in the road. It is a block diagram of a vehicle sensing system. It is a block diagram which shows a part of function of a sensing process part, (a) shows a comparison value calculation part, (b) shows a determination part. It is a block diagram which shows the function of a sensing process part. It is a table | surface which shows the background level learning method performed by the sensing process part. It is a table | surface which shows the threshold value learning method performed by the sensing process part. It is explanatory drawing at the time of correct | amending the deviation | shift from the true value of a background level, (a) shows the relationship between an input level and a background level, (b) shows the relationship between a sum of small products, and a threshold value, (c ) Indicates the sensing result. It is a figure explaining deviation correction performed by a sensing processing part. It is a figure explaining the function of a background level adjustment part. It is explanatory drawing of a prior art example, (a) shows the relationship between an input level and a background level, (b) shows the relationship between a sum of products, and a threshold value, (c) shows the sensing result.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Vehicle sensing system 2 Detection part 3 Sensing process part 33 Background level learning process part (learning process part)
35 Learning control unit 40 Background level adjustment unit A Monitoring area R Road V Vehicle

Claims (3)

An input level obtained from the detecting section for detecting a temperature of the monitoring area on the road, and a comparison value based rather value to the difference between the background level based on the temperature level of the road, the threshold of the comparison value and the vehicle determination And a determination unit that determines whether or not there is a vehicle by comparing
During the determination without vehicle is, a learning processing unit that performs switching the execution and pause based rather the background level of the learning process on the input level,
Execution of the background level learning process by the learning processing unit and switching between pauses are controlled according to the comparison value, and when the comparison value is larger than a threshold for background level learning, it is determined that there is no vehicle. A learning control unit that pauses the background level learning process ,
A process for adjusting the background level to the input level when the difference between the input level and the background level obtained while the determination that there is no vehicle and the background level learning process is suspended is greater than or equal to a predetermined value. A background level adjustment unit for executing
A vehicle sensing system comprising:   The background level adjustment unit sets the background level to the input level when the difference between the input level and the background level is equal to or longer than a predetermined time. The vehicle sensing system according to claim 1, wherein a matching process is executed.   When the background level adjustment unit switches from the vehicle presence determination after the vehicle absence determination to the vehicle absence determination, the background level adjustment unit executes a process of adjusting the background level to the input level at the time of the switching. The vehicle sensing system according to claim 1 or 2.

Images