JP4506576B2 - In-vehicle fog condition determination device and auto fog lamp system - Google Patents

Description

  The present invention relates to an apparatus for determining a fog state from an image captured by an in-vehicle camera, and an auto fog lamp system including the apparatus.

An apparatus that processes an image captured by an in-vehicle camera and determines a fog state is known (for example, Patent Document 1). The fog determination method in Patent Document 1 is based on the degree of image blur. In the case of fog, the image is blurred. Therefore, the fog state is determined by estimating the degree of blur of the image. To estimate the degree of blur of an image, first, the edge strength of the luminance (the amount of change in luminance) is calculated for each pixel by a differential operation for the entire image, and the degree of blur of the image is estimated based on the edge strength. ing. As the image is blurred, the edge strength is reduced as a whole. Therefore, the degree of blurring of the image can be estimated based on the edge strength.
Japanese Patent No. 344192

  However, since the image is often blurred not only in the case of fog but also in the case of rain, it is difficult for the device that determines the fog state based on the degree of blur of the image to reliably distinguish between fog and rain. There was also. In particular, as in Patent Document 1, when calculating the edge strength indicating the amount of change in the brightness of the image and performing fog determination based on the edge strength, the edge strength is either foggy or rainy. Since the values are often similar, it was difficult to reliably distinguish between fog and rain.

  The present invention has been made on the basis of this circumstance, and an object thereof is to make it possible to reliably distinguish between fog and rain in an apparatus for determining a fog state based on an image. .

The invention according to claim 1 for achieving the object is an in-vehicle fog state determination device that determines whether or not it is a fog state from an image captured by an in-vehicle camera mounted on a vehicle,
Image blur degree value calculating means for calculating a blur degree value of an image captured by the in-vehicle camera, and a predetermined image blur determination range in which the image blur degree value calculated by the image blur degree value calculating means is preset. is the value of the inner and on the basis of the wiper is not driven, it saw including a mist state determining means for determining that it is a fog,
The fog state determination means is a value within a predetermined image blur determination range that is set in advance, and the image blur degree value calculated by the image blur degree value calculation means, but when the wiper is driven, It is determined that it is raining .

  As described above, it is difficult to distinguish between fog and rain only from the degree of blur of the image. However, according to the first aspect of the present invention, the blur degree value of the image is within a predetermined image blur determination range. Since it is determined that it is fog based on the fact that the wiper is not driven, it is possible to reliably distinguish fog from rain.

  Here, for example, the blur degree value can be calculated based on a distribution diagram of edge intensity of image luminance. That is, the invention according to claim 2 further includes an edge strength distribution diagram creating means for creating an edge strength distribution diagram showing a distribution of edge strength, which is a change amount of luminance of an image captured by the in-vehicle camera. The blur degree value calculating means calculates the blur degree value based on the edge intensity distribution map created by the edge intensity distribution chart creating means.

  When the blur degree value is calculated based on the edge intensity distribution chart as described above, the blur degree value is often a relatively similar value between fog and rain as described above. Therefore, as in the present invention, the effect of determining the fog state using the wiper driving state as a determination factor is further great.

Moreover, an auto fog lamp system can be comprised like the claim 4 using the said vehicle-mounted fog state determination apparatus. That is, the auto fog lamp system includes a vehicle fog state determining apparatus according to claim 1 or 2, wherein, when it is determined that the mist by the vehicle fog state determining device, and a fog lamp lighting control means for lighting the fog lamp It is characterized by this.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing a configuration of an auto fog lamp system 10 of the present invention.

  The auto fog lamp system 10 includes an in-vehicle camera 12, an image processing ECU 14, a wiper switch 16, a light control ECU 18, a fog lamp 20, and an in-vehicle LAN 22. The image processing ECU 14, the wiper switch 16, and the light control ECU 18 are connected to the in-vehicle LAN 22.

  The in-vehicle camera 12 is constituted by a CCD camera, and its mounting position is the interior of the vehicle, for example, the ceiling near the driver's seat. The vehicle-mounted camera 12 continuously captures images in front of the vehicle, and the captured image data is processed in the image processing ECU 14.

  The image processing ECU 14 is a computer having a CPU, a ROM, a RAM, and the like inside (not shown), and the RAM temporarily stores image data for a predetermined time continuously captured by the in-vehicle camera 12. The The CPU determines fog or rain by executing the processing shown in FIG. 2 on the image data stored in the RAM in accordance with the program stored in the ROM. Therefore, this image processing ECU 14 functions as an in-vehicle fog state determination device. The processing of this CPU will be described later.

  The wiper switch 16 controls driving and stopping of a wiper (not shown) and is operated by a driver.

  The light control ECU 18 functions as a fog lamp lighting control unit. When the image processing ECU 14 determines that it is fog, the light control ECU 18 turns on the fog lamp lamp 20 while the image processing ECU 14 determines that it is raining. If it is not determined to be fog or rain, the fog lamp 20 is turned off. The fog lamp 20 is attached to a predetermined part in the front part of the vehicle, and irradiates the front of the vehicle.

  FIG. 2 is a flowchart showing a main part of the control function of the image processing ECU 14. The control shown in FIG. 2 is executed at a predetermined cycle during traveling.

  In FIG. 2, first, in step S10, the luminance value is continuously differentiated in the X direction and the Y direction with respect to the entire image supplied from the in-vehicle camera 12, so that the edge intensity, which is the amount of change in luminance, is obtained. Create a two-dimensional distribution chart. This step S10 corresponds to an edge intensity distribution diagram creating means.

  In step S20, a strong edge amount is calculated, which means a ratio of the edge strength exceeding a preset reference edge strength in the two-dimensional distribution chart created in step S10. It means that the larger the amount of strong edges, that is, the greater the proportion of the edge strength that exceeds the reference edge strength in the two-dimensional distribution diagram of the edge strength, the clearer the image. In other words, the smaller the amount of strong edges, that is, the smaller the proportion exceeding the reference edge strength in the two-dimensional distribution diagram of edge strength, the more blurred the image. Accordingly, this strong edge amount corresponds to the blur degree value, and step S20 corresponds to the image blur degree value calculating means.

  Subsequently, steps S30 to S80 corresponding to fog state determination means are executed. First, in step S30, it is determined whether or not the strong edge amount calculated in step S20 is a value within a preset image blur determination range. As described above, the smaller the strong edge amount, the more blurred the image is. Therefore, the image blur determination range is a range where the lower limit value is zero.

  If the determination in step S30 is affirmative, the weather is considered to be foggy or rainy, so that the subsequent step S40 is executed in order to determine which is the case. On the other hand, if the determination in step S30 is negative, the weather is not foggy or rainy, so step S80 described later is directly executed.

  In step S40, it is determined whether or not a wiper (not shown) is driven by determining whether or not the wiper switch 16 is on. When this determination is negative, that is, when it is determined that the wiper is not driven, it is determined in the following step S50 that the weather is fog, and in the subsequent step S60, a lighting command signal is sent to the light control ECU 18. Output. When the light control ECU 18 receives the lighting command signal, the light control ECU 18 lights the fog lamp 20.

  On the other hand, if the determination in step S40 is affirmative, that is, if it is determined that the wiper is driving, it is determined in the subsequent step S70 that the weather is rain.

  If it is determined in step S70 that it is raining, or if the determination in step S30 is negative, a turn-off command signal is output to the light control ECU 18 in step S80. When receiving the turn-off command signal, the light control ECU 18 turns off the fog lamp 20.

  As described above, according to the present embodiment described above, the strong edge amount representing the degree of image blur is a value within a predetermined image blur determination range set in advance, and fog is generated when the wiper is not driven. Since it judges, fog and rain can be distinguished reliably.

  As mentioned above, although embodiment of this invention was described, this invention is not limited to the above-mentioned embodiment, The following embodiment is also contained in the technical scope of this invention, and also the summary other than the following is also included. Various modifications can be made without departing from the scope.

  For example, in the above-described embodiment, the fog lamp lighting control is performed based on the determination result by the fog state determination unit. However, the optical axis adjustment of the headlight may be performed based on the determination result. In this case, when it is determined to be fog, the optical axis is lowered as compared to the case where it is determined not to be fog.

  In the above-described embodiment, the range in which the two-dimensional distribution diagram of the edge intensity is created is the entire image captured by the in-vehicle camera 12, but the edge intensity is determined for a part of the image captured by the in-vehicle camera 12. A two-dimensional distribution map may be created.

  In the above-described embodiment, the amount of change in image brightness, that is, the edge strength is used as the blur degree value. However, for example, an average value of image brightness may be used as the blur degree value. This is because the brightness of the image tends to increase when the image is totally blurred due to fog.

1 is a block diagram showing a configuration of an auto fog lamp system 10 of the present invention. It is a flowchart which shows the principal part of the control function of image processing ECU14 of FIG.

Explanation of symbols

10: Auto fog lamp system 12: In-vehicle camera 14: Image processing ECU (in-vehicle fog state determination device)
16: Wiper switch 18: Light control ECU (fog lamp lighting control means)
20: Fog lamp 22: In-vehicle LAN

Claims (3)

An in-vehicle fog state determination device that determines whether a fog state is detected from an image captured by an in-vehicle camera mounted on a vehicle,
Image blur degree value calculating means for calculating a blur degree value of an image captured by the in-vehicle camera;
Based on the fact that the image blur degree value calculated by the image blur degree value calculating means is a value within a predetermined image blur determination range set in advance and the wiper is not driven, it is fog. and determining fog state decision means only including,
The fog state determination means is a value within a predetermined image blur determination range that is set in advance, and the image blur degree value calculated by the image blur degree value calculation means, but when the wiper is driven, An on-vehicle fog state determination device characterized by determining that it is raining . An edge strength distribution diagram creating means for creating an edge strength distribution diagram showing a distribution of edge strength which is a change amount of luminance of an image captured by the in-vehicle camera;
2. The vehicle-mounted fog according to claim 1, wherein the image blur degree value calculating unit calculates the blur degree value based on the edge intensity distribution map created by the edge intensity distribution map creating unit. State determination device. The in-vehicle fog state determination device according to claim 1 or 2 ,
An auto fog lamp system comprising: fog lamp lighting control means for lighting a fog lamp when it is determined to be fog by the in-vehicle fog state determination device.

Images