JP4052299B2 - Exposure control method and apparatus for camera-type vehicle detector - Google Patents

Description

  The present invention relates to a camera-type vehicle sensor capable of detecting a vehicle on a road by photographing a road with a camera and processing the image, and more particularly to an exposure control method and apparatus obtained by the camera-type vehicle sensor. Is.

As a vehicle detector for detecting a vehicle on a road, an ultrasonic type is well known. This ultrasonic type measures the vehicle by emitting ultrasonic waves from the top to the bottom of the road and detecting the arrival time of the reflected wave, but detects the characteristics of each vehicle. I can't do that.
Therefore, a camera-type vehicle detector is known that detects the characteristics of a vehicle and identifies a vehicle license plate by photographing a road with a camera and processing the image.
Japanese Patent Laid-Open No. 2001-021958

In the EE (Electric Eye camera) control (control that automatically adjusts the exposure according to the intensity of light hitting the subject) performed by this camera-type vehicle detector, the range of the road to be photographed (shooting target range) And the exposure time and aperture amount are adjusted so that the average value becomes the target luminance.
However, when the sun and shade are mixed in the shooting target range, if the above control is performed, the vehicle in the sun is reflected brightly by the reflection of sunlight, the contrast with the bright road cannot be taken, and vehicle identification becomes difficult. There is a risk of hindering post-processing for detecting vehicle characteristics such as reading a license plate. The same problem arises that the shaded vehicle appears dark due to the shade of sunlight, making it difficult to distinguish the vehicle from the dark road and making it difficult to identify the vehicle.

This is because the average value of the brightness of the sunlit and shaded roads is obtained and the exposure control is performed so that it approaches the target brightness, so that it is difficult to detect both the sunlit and shaded vehicles. .
Accordingly, an object of the present invention is to provide an exposure control method and apparatus for a camera-type vehicle detector that can easily identify as many vehicles as possible even on a screen in which the sun and shade are mixed.

  An exposure control method for a camera-type vehicle sensor according to the present invention is based on an image captured by a camera-type vehicle sensor, a vehicle existing portion is cut out from the range to be imaged, and luminance data of the input image is used. Then, divide the shooting range into either the sun or shade, calculate the contrast between the brightness of the vehicle existing in the sun and the surrounding brightness, and the brightness of the vehicle existing in the shade Then, the contrast with the surrounding brightness is calculated, the number of vehicles A in which the contrast is less than or equal to the threshold in the sun, and the number of vehicles B in which the contrast is less than or equal to the threshold in the shade, and the number of vehicles A> the number of vehicles B For example, the exposure condition is changed to reduce the exposure amount, and if the number of vehicles A <the number of vehicles B, the exposure condition is changed to increase the exposure amount.

According to this exposure control method, the contrast between the vehicle included in the sun and the surrounding road is calculated, the contrast between the vehicle included in the shade and the surrounding road is calculated, and the number of vehicles with low contrast is larger. The exposure conditions are corrected in accordance with the categories.
Therefore, when the screen includes the sun and shade, if there are many vehicles with poor contrast in the sun, the exposure conditions can be changed in a direction that allows them to be detected with proper exposure. If there are many bad ones, it is possible to change the exposure conditions in such a direction that they can be detected with appropriate exposure.

In this way, as many vehicles as possible appearing on the screen can be detected.
In the exposure control method, if the contrast with the surrounding brightness is calculated using the maximum value of the brightness of the vehicle presence range included in the sun (Claim 2), the contrast is calculated lower. . This is because the brightness of surrounding roads is high in the sun, so that the difference in brightness between a bright part of the vehicle (for example, a lighted part of the vehicle body, a roof of the vehicle body for a white car) and the surrounding roads is reduced. Accordingly, the contrast is calculated to be low, the number of vehicles A in which the contrast is equal to or less than the threshold in the sun increases, and the exposure conditions can be changed so that these vehicles can be easily detected.

  In the exposure control method, if the contrast with the surrounding brightness is calculated using the minimum value of the brightness of the vehicle existing range included in the shade (Claim 3), the contrast is calculated lower. . This is because in the shade, the brightness of the surrounding road is low, so the difference in brightness between the dark part of the vehicle (for example, the lower part of the vehicle body, the front window, tires, etc.) and the surrounding road is reduced. Accordingly, the contrast is calculated to be low, the number of vehicles B in which the contrast is equal to or less than the threshold value in the shade increases, and the exposure conditions can be changed so that these vehicles can be easily detected.

  An exposure control apparatus for a camera-type vehicle detector according to the present invention is an apparatus according to the same invention as the exposure control method according to claim 1 (claim 4).

  As described above, according to the present invention, when the screen includes the sun and shade, if there are many low-contrast vehicles included in the sun, the exposure conditions can be changed in the direction in which they can be detected, and are included in the shade. If there are many low-contrast vehicles, the exposure conditions can be changed in such a direction that they can be detected. In this way, it is possible to easily identify as many vehicles as possible even on a screen in which the sun and shade are mixed.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
FIG. 1 is a schematic block diagram of a camera type vehicle sensing system to which an exposure control apparatus of the present invention is applied.
A camera-type vehicle sensor 1 is attached to an upper portion of a pole 2 installed in the vicinity of the road. A communication line 5 is connected from the camera-type vehicle sensor 1 to a computer 4 of a traffic information center 3 that collects traffic conditions on the road. The communication line 5 may be either wired / wireless or a combination thereof, and may be a dedicated line or a public communication line.

FIG. 2 is a block diagram showing the internal configuration of the camera-type vehicle detector 1. The camera-type vehicle detector 1 includes a camera 11, a camera DSP (Digital Signal Processor) 12 that controls the operation of the camera 11, an image processing device 13, and a communication interface 14.
The camera 11 includes a lens system 15 and an image sensor 16. The aperture stop amount in the lens system 15 is adjusted based on the stop control signal from the camera DSP 12. The field of view of the camera 11 is directed to a road (not shown), and the camera 11 captures a road state and forms a captured image on the image sensor 16. Data of the image formed on the image sensor 16 is output to the camera DSP 12. The exposure time (corresponding to the shutter speed) of the image sensor 16 is adjusted based on the exposure time control signal from the camera DSP 12.

  The image processing device 13 generates image data of the road surface area. This image is referred to as a “reference image”. The reference image data is transmitted to the traffic information center 3 through the communication interface 14 and the communication line 5. Based on the reference image data, the computer 4 performs vehicle detection, license plate reading, vehicle speed detection, traffic jam length detection, and the like to obtain various types of information for grasping the traffic flow.

Further, the image processing apparatus 13 performs exposure control of the camera 11 based on the reference image data. The result of exposure control is used for exposure time control of the image sensor 16 and aperture control of the lens system 15 through the camera DSP 12.
FIG. 3 is a graph for explaining an outline of exposure control performed by the image processing apparatus 13. The horizontal axis represents time, and the vertical axis represents luminance and exposure time. The exposure control is executed for each night, morning, daytime, and evening. At night, the purpose is to shoot a headlight, and as shown in FIG. 3, the exposure time is fixedly controlled. In the daytime, the purpose is to photograph the vehicle body and the license plate, and control is performed to match the luminance of the reference image to the reference luminance. This reference luminance is called “target luminance”. In FIG. 3, the target brightness is fixed at daytime. However, this may mean that the target brightness is fixed, and the target brightness is not always fixed at daytime. The target brightness may be changed for each time zone of the day, or the target brightness may be changed according to the change in the weather of the day.

  In the morning, control is performed to increase the exposure time in order to connect from night control to daytime control. The purpose of increasing the exposure time is to shoot a headlight at night, so the exposure time may be relatively short. However, in the morning, it is necessary to increase the exposure amount of the image sensor 16 to shoot a vehicle body or the like. This is because it is necessary to gradually increase the exposure time for this purpose. In the evening, control is performed to shorten the exposure time in order to connect from daytime control to nighttime control.

The contents of exposure control for automatically adjusting the target luminance during the daytime and maintaining the luminance of the reference image at the target luminance will be described below with reference to FIG. FIG. 4 is an overall flowchart for explaining the exposure time control contents of the camera-type vehicle detector 1.
The image processing device 13 inputs the reference image data (step S1), and calculates an average value of luminance over the entire screen of the reference image data for the reference image data. At this time, a moving average may be taken in consideration of the reference image data captured a certain number of times in the past. Then, the difference between the average luminance value and the target luminance is calculated (steps S2 and S3), and the exposure time and the aperture are increased / decreased so as to reduce the difference (step S4).

FIG. 5 is a flowchart for explaining an exposure correction method for increasing / decreasing the exposure amount according to the number of low contrast vehicles according to the present invention. FIG. 6 is a diagram illustrating an example of a reference image. The screen shows a road with 3 lanes on one side, and there is an elevated road girder on the left side of the screen. The shade of this elevated road is the shaded area, and the rest is the sunny area.
In FIG. 5, first, the reference image is divided into a plurality of sections (step T1). This is performed in order to distinguish the sunny part and the shaded part in units of sections. An example of the divided sections is shown in FIG. In the figure, the reference image is divided into 3 × 4.

Next, the sun and shade are determined for each divided section (step T2). The determination method is performed based on whether the luminance average value of the section is higher or lower than the threshold value.
Next, the vehicle existing portion in each section is cut out. A method of cutting out the vehicle existing portion is known and is described in, for example, Japanese Patent Laid-Open No. 63-174199. Corresponding to the four vehicles shown in FIG. 6, the portions where the vehicles are cut out are represented by a1, a2, b1, and c1. Then, the section to which the vehicle belongs is determined. The vehicle presence portion a2 belongs to the upper right section, but the vehicle presence portions a1, b1, and c1 extend over a plurality of sections. In such a case, the section to which the largest area portion of the vehicle existing portion belongs is determined as the section to which the vehicle belongs. As a result, it is possible to distinguish between the sun and the shade for each vehicle. Furthermore, the part for calculating | requiring the brightness | luminance of a road surface is specified near the vehicle presence part. For example, the sections r1 to r8 are specified road surface portions.

Next, the brightness difference contrast of each vehicle defined by the following equation is obtained (step T3).
Brightness difference contrast = absolute value of (vehicle brightness-road surface brightness) / (road surface brightness)
Here, the vehicle luminance is the maximum value of the luminance of the vehicle existing portion in the case of the sunny vehicle, and the minimum value of the luminance of the vehicle existing portion in the case of the shaded vehicle. The road surface luminance is the luminance of the road surface portion near the vehicle, which is also the maximum value of the luminance of the road surface portion in the case of a sunny vehicle, and the minimum value of the luminance of the road surface portion in the case of a shaded vehicle.

  The number of vehicles A having a luminance difference contrast equal to or less than the contrast threshold in the sun is calculated (step T4), and the number of vehicles B having the luminance difference contrast equal to or less than the contrast threshold in the shade is calculated (step T5). The contrast threshold is based on whether the computer 4 can easily or after-process post-processing such as vehicle detection, license plate reading, vehicle speed detection, and congestion length detection based on the reference image data. It is good to decide.

  Next, the vehicle numbers A and B are compared (step T6), and if A> B, that is, if there are many vehicles with low contrast in the sun, control is performed to shorten the exposure time of the entire screen (step T7). Thereby, the brightness difference contrast can be increased in the sun, and the number of vehicles A having a contrast threshold value or less can be reduced. This process may slightly increase the number of vehicles B whose luminance difference contrast is below the contrast threshold in the shade, but since the decrease in the number of vehicles A is more significant than the increase in the number of vehicles B, The brightness difference contrast of the vehicle can be adjusted in the increasing direction.

  When A <B, that is, when there are many vehicles with low contrast in the shade (step T8), control is performed to increase the exposure time of the entire screen (step T7). Thereby, the brightness difference contrast can be increased in the shade, and the number B of vehicles having a contrast threshold value or less can be reduced. Note that this process may slightly increase the number A of vehicles whose luminance difference contrast is below the contrast threshold in the sun, but the decrease in the number B of vehicles is more significant than the increase in the number A of vehicles. The brightness difference contrast of the vehicle can be adjusted in the increasing direction.

If A = B, the exposure time is not changed (step T10).
In steps T7 and T9, the aperture amount may be changed in addition to the process of changing the exposure time. In this case, increasing the exposure time corresponds to increasing the aperture amount, and decreasing the exposure time corresponds to decreasing the aperture amount. In addition, the target brightness may be changed. Increasing the exposure time corresponds to increasing the target luminance, and decreasing the exposure time corresponds to decreasing the target luminance.

In this way, it is possible to reduce the number of vehicles having a low luminance difference contrast in the sun or in the shade, and to reduce the number of vehicles having a low luminance difference contrast in the entire screen.
Therefore, when performing post-processing such as vehicle detection, license plate reading, vehicle speed detection, and congestion length detection, the certainty of processing can be improved.

  Although the embodiments of the present invention have been described above, the embodiments of the present invention are not limited to the above-described embodiments. For example, in the camera-type vehicle detection system, the image processing device 13 is provided in the camera-type vehicle detector 1, but is not limited thereto, and is connected to the camera-type vehicle detector 1 through the communication line 5. It may be provided in the personal computer 4. In addition, various modifications can be made within the scope of the present invention.

(1) The range to be photographed in FIG. 6 was selected, and the screen was brightly photographed with the aperture wide open in fine weather. The number of pixels of the image data is 640 × 480, and the luminance is represented by 0 to 255 gradations. Actually, this screen is too bright to allow the contrast of the sunny vehicle to be taken, and this is an example in which the sunny vehicle cannot be post-processed.
The luminance of the vehicle part a1 in FIG. 7 and the surrounding road surface part r3 was measured.
The average luminance of the road surface portion r3 was 250, the maximum value was 252 and the minimum value was 246. The average luminance of the vehicle part a1 was 214, the maximum value was 255, and the minimum value was 26. Using the average luminance of the vehicle portion a1 and the average luminance of the road surface portion r3, the brightness difference contrast (average luminance) of the vehicle portion a1 is calculated, and the maximum value of the vehicle portion a1 and the maximum value of the road surface portion r3 are used. The luminance difference contrast (maximum value) of the portion a1 was calculated, and the luminance difference contrast (minimum value) of the vehicle portion a1 was calculated using the minimum value of the vehicle portion a1 and the minimum value of the road surface portion r3. as a result,
Brightness difference contrast (average brightness) = 0.144
Brightness difference contrast (maximum value) = 0.012
Brightness difference contrast (minimum value) = 0.894
Thus, the brightness difference contrast (maximum value) is the lowest value. It can be said that the brightness difference contrast (maximum value) most appropriately represents the contrast of the vehicle. Therefore, it is preferable to use this brightness difference contrast (maximum value) to determine whether the vehicle has low contrast in the sun. Thereby, the exposure condition of the whole screen can be changed in a direction in which the contrast of the sunny vehicle is clear. Although the contrast of a shaded vehicle is a little worse, even if it gets worse, it will not hinder post-processing.

(2) Next, at the same time, the screen was taken dark with the aperture closed. The number of pixels of the image data is 640 × 480, and the luminance is represented by 0 to 255 gradations. In fact, this screen is an example that is too dark to provide contrast for a shaded vehicle and cannot be post-processed for a shaded vehicle.
7 has an average luminance of 43.4, a maximum value of 50, and a minimum value of 38. The average luminance of the vehicle portion c1 was 57.2, the maximum value was 201, and the minimum value was 28. Using the average luminance of the vehicle portion c1 and the average luminance of the road surface portion r8, the luminance difference contrast (average luminance) of the vehicle portion c1 is calculated, and the vehicle portion c1 is calculated using the maximum value of the vehicle portion c1 and the maximum value of the road surface portion r8. The brightness difference contrast (maximum value) of the portion c1 was calculated, and the brightness difference contrast (minimum value) of the vehicle portion c1 was calculated using the minimum value of the vehicle portion c1 and the minimum value of the road surface portion r8. as a result,
Brightness difference contrast (average brightness) = 0.318
Brightness difference contrast (maximum value) = 3.02
Brightness difference contrast (minimum value) = 0.263
Thus, the luminance difference contrast (minimum value) is the lowest value. Therefore, it can be said that this brightness difference contrast (minimum value) most appropriately represents the contrast of the vehicle. Therefore, it is preferable to use this brightness difference contrast (minimum value) to determine whether the vehicle has low contrast in the shade. As a result, the exposure condition of the entire screen can be changed in a direction in which the contrast of the shaded vehicle is clear. In addition, although the contrast of a sunny vehicle becomes a little bad, even if it gets worse, there is no hindrance to the post-processing.

It is a schematic block diagram of the camera type vehicle sensing system to which the exposure control apparatus of this invention is applied. 2 is a block diagram showing an internal configuration of the camera-type vehicle detector 1. FIG. It is a graph for demonstrating the outline | summary of exposure control. It is a whole flowchart for demonstrating the exposure time control content of the camera type vehicle sensor. It is a flowchart for demonstrating the exposure correction method of increasing / decreasing exposure amount according to the number of vehicles with low contrast of this invention. It is a figure which shows the example of the image | photographed screen. It is a figure which shows the example which divided | segmented the screen.

Explanation of symbols

1 camera type vehicle detector 2 pole 3 traffic information center 4 computer 5 communication line 11 camera 12 camera DSP
13 Image Processing Device 14 Communication Interface 15 Lens System 16 Image Sensor

Claims (4)

Enter an image taken with a camera-type vehicle detector,
Cut out the vehicle part from the shooting range,
Based on the brightness data of the input image, the shooting target range is divided into either sun or shade,
Calculate the contrast between the brightness of the vehicle in the sun and the surrounding brightness,
Calculate the contrast between the brightness of the part of the vehicle in the shade and the brightness around it,
Calculate the vehicle number A in which the contrast is less than or equal to the threshold value in the sun and the vehicle number B in which the contrast is less than or equal to the threshold value in the shade,
If the number of vehicles A> the number of vehicles B, the exposure condition is changed to reduce the exposure amount. If the number of vehicles A <the number of vehicles B, the exposure condition is changed to increase the exposure amount. An exposure control method for a vehicle sensor. When calculating the contrast between the brightness of the vehicle existing in the sun and the surrounding brightness,
The exposure control method for a camera-type vehicle sensor according to claim 1, wherein a contrast with a surrounding brightness is calculated using a maximum brightness value of a vehicle existing range included in the sun. When calculating the contrast between the brightness of the vehicle existing in the shade and the surrounding brightness,
2. The exposure control method for a camera-type vehicle sensor according to claim 1, wherein a contrast with a surrounding brightness is calculated using a minimum brightness value of a vehicle existing range included in the shade. Image data input means for inputting data of an image taken by a camera of a camera-type vehicle detector;
Vehicle existence part specifying means for cutting out the vehicle existence part from the shooting target range;
Based on the brightness data of the input image, the shooting target range is divided into either the sun or shade, and the contrast between the brightness of the vehicle's existing part and the surrounding brightness included in the sun section is calculated. Contrast calculation means for calculating the contrast between the brightness of the vehicle existing in the shaded area and the brightness of the surrounding area;
Vehicle number comparison means for calculating and comparing the number of vehicles A in which the contrast is less than or equal to a threshold value in the sun and the number of vehicles B in which the contrast is less than or equal to the threshold value in the shade;
If the number comparison means determines that the number of vehicles A> the number of vehicles B, the exposure condition is changed to reduce the exposure amount. If the number of vehicles A <the number of vehicles B, the exposure condition correction means An apparatus for adjusting the brightness of a screen in a camera-type vehicle sensor.

Images