JP2010152586A - Vehicle detection device and vehicle detection method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To detect a vehicle with high accuracy using a far infrared sensor. <P>SOLUTION: Whether a vehicle exist is detected according to whether a level difference between a sensing signal level and a road surface level is a predetermined level difference threshold ΔV or more. The level difference threshold ΔV is changed according to the sensing environment. Concretely, the level difference threshold ΔV is increased from a reference value α only by an increment β to obtain "α+β" at fine weather, and the level difference threshold ΔV is defined as a reference value α at cloudy weather, and the level difference threshold ΔV is decreased from the reference value α only by a decrement γ to obtain "α-γ" at rainy weather. Also, the sensing environment is determined based on the positive/negative and level of the sensing signal in a period in which a vehicle is detected. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a vehicle detection device and a vehicle detection method.

2. Description of the Related Art Devices that recognize pedestrians based on images taken with a far-infrared camera are known as on-vehicle driving assistance devices. In such an apparatus, a pedestrian is detected by performing a pattern matching process using a plurality of model images prepared in advance for an image captured by a far-infrared camera. At this time, in order to make a precise determination according to changes in the state of pedestrians and environmental conditions, among the plurality of model images, a model image corresponding to the rainfall state, the outside air temperature, and the time zone is used (for example, Patent Document 1). reference).
JP 2007-58805 A

  Further, for example, as a vehicle detection device that detects a vehicle that is installed on the road side and travels on a road, there is a device that uses a far infrared sensor that is a passive sensor from the viewpoint of power saving. In vehicle detection using a far-infrared sensor, the presence or absence of a vehicle is detected from the change in the signal level of the sensing signal by the sensor, utilizing the fact that the road surface and vehicle temperature are different. Specifically, the presence / absence of the vehicle is detected by comparing the level difference between the sensing signal level and the road surface level with a predetermined threshold.

  However, the temperature of the road surface and the vehicle greatly fluctuates depending on the environment such as sunlight and rainfall. That is, since the temperature difference between the road surface and the vehicle varies greatly depending on the environment, the detection accuracy decreases. The present invention has been made in view of such circumstances, and aims to improve detection accuracy in vehicle detection using a far-infrared sensor.

The first invention for solving the above-described problems is
Far-infrared sensor installed toward the road surface,
Vehicle detection means for detecting the presence or absence of a vehicle depending on whether a level difference between a signal level of a sensor detection signal and a predetermined road surface level satisfies a predetermined threshold condition for determining that there is a vehicle;
An environment determination means for determining the sensing environment;
Threshold condition changing means for changing the threshold condition based on the sensing environment;
It is a vehicle detection apparatus provided with.

As another invention,
Depending on whether the level difference between the signal level of the sensing signal of the far-infrared sensor for detecting the vehicle and the predetermined road surface level when the vehicle is absent satisfies a predetermined threshold condition for determining the presence of the vehicle, A vehicle detection step for detecting presence or absence;
An environment determination step for determining a sensing environment;
A threshold condition changing step for changing the threshold condition based on the sensing environment;
A vehicle detection method including the above may be configured.

  According to the first aspect of the invention, whether or not the level difference between the signal level of the sensing signal of the far-infrared sensor and the predetermined road surface level when the vehicle is absent satisfies a predetermined threshold value for determining that there is a vehicle. The presence or absence of a vehicle is detected depending on whether or not the sensing environment is determined, and the threshold condition is changed based on the determined sensing environment. By the way, the temperature of a road surface or a vehicle changes with sensing environments, such as sunlight and rain. In other words, depending on the sensing environment, the level difference between the signal level of the sensing signal when passing the vehicle and the road surface level may change, and as a result, the sensing accuracy may decrease. However, as in the first invention, it is possible to improve the sensing accuracy by changing the threshold condition based on the determined sensing environment.

As a second invention, the vehicle detection device of the first invention,
The environment determination means may constitute a vehicle detection device that determines the sensing environment using the sign of the level difference and the magnitude.

  According to the second aspect of the invention, the sensing environment is determined using the positive / negative and magnitude of the level difference.

Specifically, as in the third invention,
The environment determination means determines that the environment is a clear sky equivalent environment when the signal level when the threshold condition is satisfied is lower than the road surface level and the level difference satisfies a predetermined large difference condition. And
The threshold condition changing means changes the threshold value set in the threshold condition so as to be larger than a predetermined standard value when it is determined that the environment is equivalent to a clear sky.
You may comprise as follows.

  According to the third aspect of the invention, when the signal level when the threshold condition is satisfied is lower than the road surface level, and the magnitude of the level difference satisfies the predetermined large difference condition, it is determined that the environment is equivalent to a clear sky environment. When it is determined that the environment is equivalent to a clear sky, the threshold value set in the threshold condition is changed to be larger than a predetermined standard value. In an environment equivalent to sunny weather, the road surface is warmer than the vehicle because the road surface is warmed by sunlight. For this reason, the signal level of the sensing signal when passing through the vehicle tends to be lower than the road surface level.

As in the fourth invention,
The environment determination means determines that the environment is equivalent to cloudy when the signal level when the threshold condition is satisfied is higher than the road surface level and the level difference satisfies a predetermined large difference condition. And
The threshold condition changing means changes the threshold condition to a predetermined standard threshold condition when it is determined that the environment is equivalent to cloudy weather,
You may comprise as follows.

  According to the fourth invention, when the signal level when the threshold condition is satisfied is higher than the road surface level and the magnitude of the level difference satisfies the predetermined large difference condition, it is determined that the environment is equivalent to cloudy weather. When the cloudy sky equivalent environment is determined, the threshold condition is changed to a predetermined standard threshold condition. In an environment equivalent to cloudy weather, there is almost no influence of sunlight, so the temperature of the vehicle is higher than the road surface compared to the environment equivalent to sunny weather. For this reason, the signal level of the sensing signal when passing through the vehicle tends to be higher than the road surface level. The cloudy time equivalent environment is an environment that is not affected by sunlight and includes nighttime and the like.

As in the fifth invention,
The environment determination means determines that the environment corresponding to rainy weather is present when the magnitude of the level difference at each time when the threshold condition is satisfied a predetermined number of times satisfies a predetermined small difference condition,
The threshold condition changing means changes the threshold value set in the threshold condition so as to be smaller than a predetermined standard value when it is determined that the environment corresponds to rainy weather.
You may comprise as follows.

  According to the fifth aspect of the present invention, when the level difference of each time when the threshold condition is satisfied a predetermined number of times continuously satisfies the predetermined small difference condition, it is determined that the environment is equivalent to rainy weather. If it is determined that the environment corresponds to the time, the threshold value set in the threshold condition is changed to be smaller than a predetermined standard value. In an environment equivalent to rain, the temperature difference between the vehicle and the road surface is small because the road surface and the vehicle are cooled by rain and snow. For this reason, there is a tendency that the level difference between the signal level of the sensing signal when the vehicle passes and the road surface level is small.

As a sixth invention, the vehicle detection device according to any one of the first to fifth inventions,
You may comprise the vehicle detection apparatus further provided with the road surface level correction | amendment means which correct | amends the said road surface level based on the said signal level when it is detected by the said vehicle detection means that there is no vehicle.

  According to the sixth aspect of the invention, the road surface level is corrected based on the signal level when it is detected that there is no vehicle. The temperature of the road surface changes depending on the sensing environment. For this reason, the road surface level is corrected to an appropriate value, and more accurate vehicle detection is realized.

  Preferred embodiments of the present invention will be described below with reference to the drawings.

[System configuration]
FIG. 1 is a diagram illustrating an installation example of the vehicle sensing system 1 of the present embodiment. As shown in FIG. 1, the vehicle sensing system 1 includes one or more sensors (sensors) 10 and a control device 20. Each of the sensors 10 and the control device 20 can communicate with each other by wire / wireless.

  The sensor 10 is provided above a pillar installed on the road side so as to overlook a lane to be detected from above. The sensor 10 is a far-infrared type using, for example, a thermopile element, and outputs a sensing signal having a level corresponding to the temperature of an object to be sensed to the control device 20 as needed. The control device 20 is installed below the pillar, and detects the presence or absence of a vehicle in the corresponding lane based on the sensing signal from each of the sensors 10. The detection result is sent to a centralized management center or the like connected via a predetermined communication line.

[principle]
The principle of vehicle detection based on the sensing signal from the sensor 10 will be described. The presence / absence of the vehicle is detected based on whether a level difference between the signal level of the sensing signal and the road surface level satisfies a predetermined threshold condition. The threshold condition is “the level difference between the sensing signal level and the road surface level exceeds a predetermined level difference threshold ΔV”.

  FIG. 2 is a diagram for explaining the principle of vehicle detection based on the sensing signal from the sensor 10. In the figure, the upper side shows a sensing signal when passing through the vehicle, and the lower side shows a detection result. As shown in the figure, when no vehicle is present on the road, the sensing signal level substantially matches the road surface level. When the vehicle passes, the sensing signal level fluctuates because the road surface and the vehicle temperature are different.

In order to detect the fluctuation of the sensing signal level when the vehicle passes, the upper threshold value V _{TH + which} is larger (higher) by a predetermined level difference threshold value ΔV than the road surface level Vb, and the lower threshold value V _{TH which is} smaller (lower) by the level difference threshold value ΔV. _- is determined. If “the sensing signal level is not less than the lower threshold V _{TH− and not} more than the upper threshold V _{TH +} ”, it is detected that the threshold condition is not satisfied, that is, “no vehicle”, and “the sensing signal level is lower threshold V _{TH If it is} less than _TH− or exceeds the upper threshold V _{TH +} ”, it is detected that the threshold condition is satisfied, that is,“ there is a vehicle ”.

  Note that the detection signal level when passing through the vehicle largely fluctuates in a short period due to a transient phenomenon. For this reason, when the detection signal level no longer satisfies the threshold condition, it is not determined as “no vehicle” immediately, but “no vehicle” is detected when a state that does not satisfy the threshold condition continues for a predetermined time. Specifically, a holding period Tk is set that starts when the sensing signal level no longer satisfies the threshold condition. If the sensing signal level does not satisfy the threshold condition even after the holding period Tk has elapsed, “No vehicle” at the time.

  By the way, the temperature difference between the road surface and the vehicle changes depending on the environment such as time zone and weather (hereinafter referred to as “sensing environment”), and the detection accuracy of the presence / absence of the vehicle changes due to the change of the temperature difference. Specifically, when the temperature difference between the road surface and the vehicle is large, the vehicle presence / absence detection accuracy is improved, and conversely, when the temperature difference is small, the detection accuracy is deteriorated.

  The sensing environment that affects the temperature difference between the road surface and the vehicle is roughly divided into three categories: (1) clear weather, (2) cloudy weather (including nighttime), and (3) rainy weather (including snowfall). it can. In general, on sunny days, the road surface tends to be hotter than the vehicle. Also, when it is cloudy, the temperature of the vehicle tends to be higher than that of the road surface, as opposed to when it is fine. And when it is raining, the temperature difference between the road surface and the vehicle tends to be smaller than when it is sunny or cloudy. For this reason, in this embodiment, in order to cope with a change in detection accuracy, the threshold condition is changed according to the sensing environment. The sensing environment is determined from the characteristics of the sensing signal.

FIG. 3 is a diagram illustrating an example of a sensing signal when passing through the vehicle in fine weather. In the figure, the upper side shows a sensing signal, and the lower side shows a detection result. When the weather is fine, the road surface is warmed by sunlight, and the road surface tends to have a higher temperature than the vehicle. For this reason, as a characteristic of the sensing signal when passing through the vehicle in fine weather, the sensing signal level is a “negative” waveform that is lower than the road surface level, and the level difference between the sensing signal level and the road surface level is a level difference. It can be said that it is larger than the threshold value ΔV. Accordingly, during fine weather, the level difference threshold ΔV is increased from the reference value α by a predetermined change amount (increase amount) β to “α + β”. That is, the upper threshold value V _{TH +} is “Vb + (α + β)”, and the lower threshold value V _TH− is “Vb− (α + β) = Vb−α−β”.

FIG. 4 is a diagram illustrating an example of a sensing signal when the vehicle passes during cloudy weather. In the figure, the upper side shows a sensing signal, and the lower side shows a detection result. In addition, the cloudy time is an environment that is hardly affected by sunlight, and includes, for example, nighttime. During cloudy weather, there is almost no influence of sunlight, so the vehicle tends to have a higher temperature than the road surface. For this reason, as a characteristic of the sensing signal when the vehicle passes during cloudy weather, the sensing signal level is a “positive” waveform higher than the road surface level, and the level difference between the road surface level and the sensing signal level is a level difference threshold ΔV. It can be said that it is big. Accordingly, the level difference threshold value ΔV is set as the reference value α during cloudy weather. That is, the upper threshold value V _{Th +} is “Vb + α”, and the lower threshold value V _TH− is “Vb−α”.

FIG. 5 is a diagram illustrating an example of a waveform of a sensing signal when the vehicle passes during rainy weather. In the figure, the upper side shows a sensing signal, and the lower side shows a detection result. When it rains, water drops and snow adhere to the road surface and the surface of the vehicle, so that the temperature difference between the road surface and the vehicle tends to be small. For this reason, it can be said that the level difference between the detection signal level and the road surface level is smaller than the level difference threshold ΔV as a feature of the detection signal waveform when the vehicle passes in the rainy weather. Accordingly, during rainy weather, the level difference threshold Δ is reduced from the reference value α by a change amount (decrease amount) γ to “α−γ”. That is, the upper threshold value V _{TH +} is “Vb + (α−γ)”, and the lower threshold value V _TH− is “Vb− (α−γ) = Vb−α + γ”.

  Further, the road surface temperature also changes depending on the environment. However, the change in the road surface temperature is a very slow change compared to the change in the sensing signal level when passing through the vehicle. For this reason, when the detection result of the vehicle is “no vehicle”, the road surface level is corrected following the sensing signal. For example, the sensing signal level during a period in which “no vehicle” is detected is sampled at predetermined time intervals, and the average value is used as the road surface level.

Here, “positive / negative” of the sensing signal is determined as follows. That is, for example, as shown in FIGS. 3 and 4, the length of the upper period T ₊ in which the sensing signal level is equal to or higher than the upper threshold and the lower period T ₋ that is equal to or lower than the lower threshold among the periods detected as having a vehicle. Compare If T ₊ > T ₋ , the sensing signal is determined as a “positive” waveform, and if T ₋ > T ₊ , the sensing signal is determined as a “negative” waveform.

Further, whether the level difference between the sensing signal level and the road surface level is “large / small” with respect to the level difference threshold ΔV is determined as follows. That is, as shown in FIG. 3, for example, when the sensing signal has a “negative” waveform, the level difference Vm between the minimum value Vp of the sensing signal level and the lower threshold value V _TH− is calculated. Then, the level difference Vm is compared with a predetermined value Vt. If Vm ≧ Vt, the level difference is determined to be “large” with respect to the level difference threshold ΔV, and if Vm <Vt, it is determined to be “small”. .

For example, as shown in FIG. 4, when the sense signal has a “positive” waveform, the level difference Vm between the maximum value Vp of the sense signal level and the upper threshold value V _{TH +} is calculated. Similarly, Vm ≧ Vt If so, it is determined that the level difference is “large” with respect to the level difference threshold ΔV, and if Vm <Vt, it is determined that it is “small”.

  Note that Vt1 and Vt2 (where Vt1 ≧ Vt2) are determined as the predetermined value Vt. If Vm ≧ Vt1, it is determined that the level difference is “large” with respect to the level difference threshold ΔV, and if Vm <Vt2, “ It may be determined that “small”.

[Function configuration]
FIG. 6 is a block diagram illustrating a functional configuration of the control device 20. According to the figure, the control device 20 is functionally configured to include a processing unit 100, a communication unit 200, and a storage unit 300.

  The processing unit 100 is realized by a CPU, for example, and performs overall control of the control device 20. Further, the processing unit 100 performs vehicle detection processing according to the vehicle detection program 310 and performs vehicle detection based on the detection signal from the sensor 10.

  Specifically, the presence or absence of a vehicle is detected depending on whether the sense signal satisfies a threshold condition. That is, the level difference between the sensing signal level and the road surface level is compared with the level difference threshold Δ, and a period in which the level difference is equal to or greater than the level difference threshold ΔV is detected as “vehicle present”. At this time, during the predetermined holding period Tk from when the level difference becomes less than the level difference threshold value ΔV, “there is a vehicle” continues as a detection result, and the period during which the level difference is less than the level difference threshold value ΔV is the holding period. When Tk is reached, the detection result is “no vehicle”. The period during which “there is a vehicle” as the detection result corresponds to the detection of “one vehicle passing”.

  Here, the data regarding the threshold condition is stored in the threshold condition data 323. FIG. 7 is a diagram illustrating an example of a data configuration of the threshold condition data 323. According to the figure, the threshold condition data 323 stores a current road surface level 323a, a level difference threshold 323b, an upper threshold 323c, and a lower threshold 323d.

  The sensing signal from the sensor 10 is accumulated and stored as sensing signal accumulation data 324, and the detection result is accumulated and stored as detection result data 326.

  Then, the processing unit 100 determines the sensing environment according to the sensing environment table 321 based on the sensing signal during the period when “the vehicle is present” is detected.

  FIG. 8 is a diagram illustrating an example of a data configuration of the sensing environment table 321. According to the figure, the sensing environment table 321 is a data table that defines sensing environment judgment conditions based on sensing signals. For each sensing environment 321a, a judgment object 321b and a judgment condition 321c are stored in association with each other. ing. The determination target 321b is a part of the sensing signal to be determined, and stores the number of times during which “the vehicle is present” is detected. The determination condition 321c includes the positive / negative of the sense signal and the signal level.

  In other words, the processing unit 100 determines whether it is “at the time of fine weather” or “at the time of cloudy weather” from the positive / negative of the sense signal and the magnitude of the signal level in the period when the most recent “vehicle present” is detected. In addition, it is determined whether it is “rainy” from the magnitude of the signal level of each sensing signal during the period in which it is detected that “the vehicle is present” continuously for a predetermined number of times (for example, 5 times). Here, the determined sensing environment is stored as sensing environment data 325.

  When the sensing environment is determined, the upper / lower thresholds corresponding to the determined sensing environment are subsequently changed according to the threshold change table 322.

  FIG. 9 is a diagram illustrating an example of a data configuration of the threshold change table 322. As illustrated in FIG. According to the figure, the threshold change table 322 stores a level difference threshold 322b in association with each sensing environment 322a.

That is, the processing unit 100 changes the level difference threshold value ΔV to a value corresponding to the sensing environment, and changes the upper threshold value V _{TH +} and the lower threshold value V _TH− along with this change.

  If it is not possible to determine any sensing environment, the level difference threshold value ΔV is not changed.

  Further, the processing unit 100 corrects the road surface level based on the sensing signal during the period in which “no vehicle” is detected. In other words, an average value of values obtained by sampling the sensing signal level during the period when “no vehicle” is detected at predetermined time intervals is set as the road surface level.

  Returning to FIG. 6, the communication unit 200 is realized by a communication device such as a wireless communication module, a router, a wired communication cable jack or a control circuit, and performs data communication with an external device (for example, a central management server). I do.

  The storage unit 300 is realized by, for example, an IC memory or a hard disk, and stores a system program for causing the processing unit 100 to control the control device 20 in an integrated manner, a program and data for realizing various functions, and the like. Used as a work area of the processing unit 100. In the present embodiment, the storage unit 300 stores a vehicle detection program 310 as a program, and as data, a sensing environment table 321, a threshold change table 322, threshold condition data 323, and sensing signal accumulation data 324. Sensing environment data 325 and detection result data 326 are stored.

[Process flow]
FIG. 10 is a flowchart for explaining the flow of the vehicle detection process. According to the figure, first, as an initial setting, for example, the processing unit 100 sets the level difference threshold value ΔV to “reference value α”, sets the detection result to “no vehicle”, and sets the current sensing environment to “cloudy”. (Step A1).

  Next, it is determined whether the sensing signal satisfies a threshold condition. That is, the level difference between the sensing signal level and the road surface level is compared with the level difference threshold ΔV. If the level difference is equal to or greater than the level difference threshold ΔV (step A3: YES), the detection result is “vehicle present” (step A5). ). Subsequently, the level difference between the sensing signal level and the road surface level is monitored, and if the level difference becomes less than the level difference threshold ΔV (step A7: YES), a holding period Tk starting from that point is set ( Step A9). Then, the level difference remains below the level difference threshold ΔV (step A11: NO), and when the holding period Tk elapses (step A13: YES), the detection result is “no vehicle” (step A15).

  Subsequently, the sensing environment is determined based on the sensing signal during the period in which “the vehicle is present” is detected (step A17). That is, according to the sensing environment table 321, the sensing environment that satisfies the judgment condition is determined based on the positive / negative level and level of the sensing signal during the most recently determined period of “vehicle present”. Then, the threshold condition is changed according to the determined sensing environment (step A19). That is, the level difference threshold value ΔV is changed to a value corresponding to the sensing environment according to the threshold value change table 322, and the upper / lower threshold values are changed in accordance with this change.

  If the sensing signal does not satisfy the threshold condition (step A3: NO), the road surface level is changed based on the sensing signal during the period determined as “no vehicle” (step A21). If the above process is performed, it will return to step A3 and the same process will be repeated.

[Action / Effect]
As described above, according to the present embodiment, the presence or absence of the vehicle is detected based on whether or not the detection signal from the sensor 10 satisfies the threshold condition, and the detection signal of the period when “the vehicle is present” is detected. In addition, the threshold condition is changed. The vehicle detection using the far-infrared sensor 10 utilizes the fact that the temperature of the road surface and the vehicle are different, but the temperature of the road surface and the vehicle changes depending on the sensing environment such as sunlight and rainfall. That is, the level difference between the signal level of the detection signal when the vehicle passes and the road surface level changes depending on the detection environment, and as a result, the detection accuracy may be lowered. Specifically, when the temperature difference between the road surface and the vehicle is large, the vehicle presence / absence detection accuracy is improved, and conversely, when the temperature difference is small, the detection accuracy is deteriorated. However, vehicle detection can be performed with high accuracy by changing the threshold condition according to the sensing environment as in the present embodiment.

[Modification]
It should be noted that embodiments to which the present invention can be applied are not limited to the above-described embodiments, and can of course be changed as appropriate without departing from the spirit of the present invention.

(A) Determination of sensing environment For example, in the above-described embodiment, the sensing environment is determined from the sensing signal. However, a sensor may be separately provided or externally input. For example, it is possible to judge whether the environment is “fine weather” or any other environment based on the measured value from the illuminometer, whether it is “rainy” or otherwise, using a hygrometer, "Or other environment.

Installation example of a vehicle sensing system. An example of a waveform of a sensing signal. Waveform example of the sensing signal in “fine weather”. An example of the waveform of the sensing signal during cloudy weather. An example of the waveform of the sensing signal when it rains. The internal block diagram of a control apparatus. The data structural example of threshold value condition data. The data structural example of a sensing environment table. The data structural example of a threshold value change table. The flowchart of a vehicle detection process.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Vehicle sensing system 10 Sensor 20 Control apparatus 100 Processing part, 200 Communication part 300 Storage part 310 Vehicle detection program 321 Sensing environment table 322 Threshold change table 323 Threshold condition data 324 Sensing signal accumulation data, 325 Sensing environment data 326 Detection result data

Claims (7)

Far-infrared sensor installed toward the road surface,
Vehicle detection means for detecting the presence or absence of a vehicle depending on whether a level difference between a signal level of a sensor detection signal and a predetermined road surface level satisfies a predetermined threshold condition for determining that there is a vehicle;
An environment determination means for determining the sensing environment;
Threshold condition changing means for changing the threshold condition based on the sensing environment;
A vehicle detection apparatus comprising:   The vehicle detection device according to claim 1, wherein the environment determination unit determines a sensing environment by using a sign of the level difference and a magnitude thereof. The environment determination means determines that the environment is a clear sky equivalent environment when the signal level when the threshold condition is satisfied is lower than the road surface level and the level difference satisfies a predetermined large difference condition. And
The threshold condition changing means changes the threshold value set in the threshold condition so as to be larger than a predetermined standard value when it is determined that the environment is equivalent to a clear sky.
The vehicle detection device according to claim 1 or 2. The environment determination means determines that the environment is equivalent to cloudy when the signal level when the threshold condition is satisfied is higher than the road surface level and the level difference satisfies a predetermined large difference condition. And
The threshold condition changing means changes the threshold condition to a predetermined standard threshold condition when it is determined that the environment is equivalent to cloudy weather,
The vehicle detection apparatus as described in any one of Claims 1-3. The environment determination means determines that the environment corresponding to rainy weather is present when the magnitude of the level difference at each time when the threshold condition is satisfied a predetermined number of times satisfies a predetermined small difference condition,
The threshold condition changing means changes the threshold value set in the threshold condition so as to be smaller than a predetermined standard value when it is determined that the environment corresponds to rainy weather.
The vehicle detection apparatus as described in any one of Claims 1-4.   The vehicle detection device according to any one of claims 1 to 5, further comprising a road surface level correction unit that corrects the road surface level based on the signal level when the vehicle detection unit detects that there is no vehicle. . Depending on whether the level difference between the signal level of the sensing signal of the far-infrared sensor for detecting the vehicle and the predetermined road surface level when the vehicle is absent satisfies a predetermined threshold condition for determining the presence of the vehicle, A vehicle detection step for detecting presence or absence;
An environment determination step for determining a sensing environment;
A threshold condition changing step for changing the threshold condition based on the sensing environment;
A vehicle detection method including:

Images