KR20170120149A - Method and system for detecting ambient light - Google Patents

Abstract

The present invention discloses a method and system for detecting ambient light. The method includes capturing one or more visible images by an image capture device, converting each of the captured images to gray color, determining a histogram of each of the images captured in gray color Calculating an average frequency average value and a data average value of the determined histogram and comparing the average frequency average value FM with a predetermined FM threshold value to detect ambient light and comparing the average data value DM with a predetermined DM Comparing the threshold value with a threshold value.

Description

Method and system for detecting ambient light

The present invention relates to the detection of ambient light, and more particularly to the detection of ambient light for a vehicle.

Existing vehicles utilize multiple sensors for various functions, such as for detecting ambient light, position, distance, speed, and the like. These multiple sensors, apart from increasing the complexity and structure of the solution, add to the overall cost of the system for ambient light detection.

Ambient light sensing is needed in a variety of applications where ambient light needs to be detected. For example, for automotive applications, a sensor of ambient light is used to adjust the backlight intensity of the instrument panel in a high-end car or the LCD backlight of a GPS device or DVD screen. Also, the ambient light needs to be detected in a variety of situations, for example, when the vehicle enters a tunnel, a bridge bottom, a canopy bottom of a tree, or the like. In addition, detection of ambient light is necessary to automatically adjust the camera mode from daylight to nighttime on the basis of ambient light sensed.

Existing systems for the detection of ambient light utilize optical / photo sensors, typically used for photo-detection, such as photo-diodes or photo-transistors. Conventional methods for tunnel detection typically use two peripheral sensors. The first sensor has a wide-angle clock, while the other sensor has a narrow-angle clock. This senses the ambient light conditions in front of the vehicle. The sensor responds rapidly to abrupt changes in light. The combination of the two sensors detects the amount of light level in the surrounding environment and automatically actuates and / or blocks the headlights of the vehicle.

 Currently, sensors for ambient light detection are mounted on high-end vehicle models. These sensors are basically optical sensors and are usually mounted on a windscreen inside the vehicle. The sensors track various light levels in the ambient environment and automatically activate and / or shut off the vehicle headlamps.

However, existing systems require a large number of sensors to detect ambient light. This increases the cost and complexity of the system. Thus, there is a need to reduce the number of sensors needed to detect ambient light and provide a cost effective and simple solution.

Various embodiments of the present invention disclose methods and systems for detecting ambient light. The method includes capturing one or more visible images, converting the captured image to a gray color image, determining a histogram of each of the gray color images, Calculating an average frequency mean value (FM) and a data mean value (DM) of the determined histogram; And a) comparing the FM with a predetermined FM threshold and detecting the ambient light as optimal light when the compared FM is greater than the predetermined FM threshold, b) Comparing the FM to a predetermined FM threshold, comparing the DM to a predetermined DM threshold, and when the compared FM is less than the predetermined FM threshold and the compared DM is greater than the predetermined DM threshold, C) comparing the FM with a predetermined FM threshold and also comparing the DM with a predetermined DM threshold, and if the FM is less than the predetermined FM threshold and the DM Compares the FM of the identified ROI with a predetermined FM threshold and if the compared FM of the ROI is less than the predetermined DM threshold, And when it is smaller than the predetermined FM threshold, detecting ambient light as being smaller than the optimal light.

According to one embodiment herein, the method further comprises the steps of: determining an FM of the identified ROI; identifying a region of interest in the captured image; and determining whether the FM is greater than the predetermined FM threshold And determining the FM of the identified ROI when the DM is less than the predetermined DM threshold.

According to one embodiment herein, calculating the FM of the determined histogram comprises: determining a frequency average value of the determined histogram for a predefined number of frames; and determining the predefined number of frames And determining the FM for the mobile station.

According to one embodiment herein, the method further comprises detecting a daytime when the detected ambient light is greater than optimal light, and when the detected ambient light is less than the optimal light, And detecting the possibility of entry into and from the database.

According to one embodiment herein, the method further comprises performing a predefined control function based on detection of one or more states of the ambient light.

According to yet another embodiment of the present invention, a system for detecting ambient light is disclosed, the system comprising: an image capture device configured to capture one or more images; and a processor coupled to the image capture device, The system comprising: converting each of the captured images into a gray color image; determining a histogram of each of the images captured in gray color; determining an average of the determined histograms Calculating a frequency average value (FM) and a data average value (DM), comprising the steps of: a) comparing the FM with a predetermined FM threshold and comparing the compared FM with the predetermined FM threshold B) comparing the FM with a predetermined FM threshold; and b) comparing the FM with a predetermined FM threshold, Determining the ambient light as optimal light when the compared FM is less than the predetermined FM threshold and the compared DM is greater than the predetermined DM threshold, c) comparing the FM with the FM Comparing the DM to a predetermined DM threshold and if the FM is less than the predetermined FM threshold and the DM is less than the predetermined DM threshold, Comparing the FM of the ROI to a predetermined predetermined FM threshold and detecting ambient light as being less than the optimal light when the compared FM of the ROI is less than the predetermined FM threshold .

The foregoing aspects and other features of the invention will be apparent from the following description taken in conjunction with the accompanying drawings.
1 illustrates a block diagram of a system for detecting ambient light in accordance with an embodiment of the present invention.
2 is a schematic diagram illustrating an input image and a corresponding histogram according to an embodiment of the present invention.
3 is a flow chart illustrating a method for detecting ambient light conditions in accordance with an embodiment of the present invention.
4 is a schematic diagram illustrating different ambient light conditions and corresponding histograms in accordance with an embodiment of the present invention.
5A and 5B are schematic diagrams illustrating a day time condition with a low contrast image and a good contrast image, according to an embodiment of the present invention.
6A and 6B are schematic diagrams illustrating daytime conditions when the average frequency average value FM is low but the data average value DM is high, according to an embodiment of the present invention.
7A and 7B are schematic diagrams illustrating tunnelability conditions, in accordance with an embodiment of the present invention.
8A is a schematic diagram illustrating a tunnel entering tunnel according to an embodiment of the present invention.
8B is a schematic diagram illustrating in-tunnel conditions according to an embodiment of the present invention.
FIG. 9A is a schematic view illustrating an exiting tunnel condition according to an embodiment of the present invention. FIG.
9B is a schematic diagram illustrating a final exit tunnel condition according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. The present invention may be modified into various forms. Accordingly, embodiments of the present invention are provided solely for the purpose of more clearly illustrating the invention to those skilled in the art. In the accompanying drawings, like reference symbols are used to denote like elements.

The specification may refer to "one", "one", or "some" embodiment (s) in various places. This does not necessarily imply that each such statement is for the same embodiment (s), or that the features apply only to one embodiment. The single features of the different embodiments may be combined to provide other embodiments.

As used herein, the singular forms "a", "an", and "the" are intended to also include the plural forms, unless expressly stated otherwise. It is also to be understood that the expressions " includes / comprising " and / or " including / comprising " when used in this specification are used interchangeably with the terms, / Or the presence of components, but does not preclude the presence or addition of one or more other features, entities, processes, steps, components, components, and / or groups thereof. As used herein, the term " and / or " is intended to encompass any and all combinations and arrangements of one or more of the above listed and listed items.

Unless defined otherwise, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. Terms such as commonly used definitions in the dictionary should be construed to have meanings consistent with their meanings in the context of the relevant art and, unless expressly so defined herein, are intended to mean ideal or overly formal Quot; will not be construed as < / RTI > In one embodiment, the average frequency mean value is referred to interchangeably as FM and FM _avg .

The present invention describes a method and system for detecting ambient light conditions that change in certain circumstances.

1 illustrates a block diagram of a system for detecting ambient light in accordance with an embodiment of the present invention. The system includes an image capturing device 101, a processing device 102, and a display device 103. The image sharing device 101 is configured to capture one or more images. The processing device 102 is connected to the capture device 101 and processes the captured image. The method of claim 1, wherein the processing device (102) is further configured to: convert the color of each of the captured images to a gray color; determine a histogram of each of the converted gray color images; (DM) and an average frequency average value (FM), and comparing the average frequency average value to a predetermined FM threshold to detect ambient light. Additionally, the processing device 102 compares the data average value to a predetermined DM threshold when the average frequency average value is less than the predetermined FM threshold to detect ambient light. When ambient light is detected to be less than optimal, the system sends an alarm to the user. In one embodiment, a visual alert is displayed on the display device 103.

In one embodiment, the method and system are used to detect ambient light using an installed front-facing image capture device 101, such as a camera 101 of a vehicle. The camera facing forward of the vehicle may be an existing camera of a driver assistance system or may be retrofitted.

In this embodiment, the method of the present invention detects ambient light in a variety of road situations including, but not limited to, the following:

* Normal weekly light

* Entry into / out of tunnel

* Entering inside tunnel / parking lot / garage / closed area

* Shady places due to under the bridge / canopy of trees.

When the vehicle is running, the camera 101 facing the front of the vehicle captures an image of the periphery of the front of the vehicle. The captured image is then processed by the processing device 102, wherein the ambient light and conditions of the road scene are detected by the control logic of the processing device. Once the ambient light is detected to be less than the optimal light, the processing device sends an alert to the user. In one embodiment, the alert is in the form of a message displayed on the display device 103. In yet another embodiment, an electronic control unit (ECU) 104 performs a predefined control function based on the detected ambient light. The processing device sends a signal to an optoelectronic control unit (ECU) 104, which in turn controls one or more vehicle functions, such as a headlamp 105. The predefined control functions include, but are not limited to, adjusting the amount of light of the headlamps, the instrument panel, and the orientation of the light automatically according to road conditions.

2 is a schematic diagram illustrating an input image and a corresponding histogram according to an embodiment of the present invention. The image captured by the camera 101 facing the front of the vehicle is a color image as shown in Fig. 2 (a), and the processing device 102 converts the captured color image into a gray image , And subsequently the histogram of the image is determined as shown in FIG. 2 (b).

 3 is a flow chart illustrating a method for detecting ambient light conditions in accordance with an embodiment of the present invention. In step 301, the color image of the surrounding situation in front of the vehicle is captured by the camera 101 facing the front. In step 302, the captured color image is processed by the processing device 102 and converted into a gray image. In step 303, the histogram of the processed image is determined. In step 304, from the determined histogram of the image, the average of the data providing the average brightness of the image (Data Mean / DM) and the average of the frequency values of the histogram are calculated. In step 305, the calculated FM value is compared with the predetermined FM threshold value. In step 306, if the FM value is less than the predetermined FM threshold value, the calculated DM value is compared with a predetermined DM threshold value. In step 307, based on the above comparison, the ambient light conditions are identified and flags and thresholds are defined using it. In step 308, appropriate alarms / warnings are provided / displayed based on the varying values of DM and FM with respect to the predefined thresholds.

According to one embodiment of the present invention, a system for detecting ambient light is considered to be currently booting from day time / sufficient ambient light. An average frequency mean value (FM) is calculated for the current scene and the calculated FM is compared to the predetermined FM threshold. If the FM is greater than the predetermined FM threshold, the scene is confirmed to be daytime, and ambient light is detected as optimal light. If the FM is less than the predetermined FM threshold, the data mean value DM is calculated for the current field, and if the DM is greater than the predetermined DM threshold, the field is identified as being weekly, The ambient light is detected as the optimum light. Also, if the FM is smaller than the predetermined FM threshold and the DM is also less than the predetermined DM threshold, then a small region (ROI) at the center of the image is selected, The FM for the selected ROI is calculated. When the FM of the compared ROI is smaller than the predetermined FM threshold, the ambient light is detected as being smaller than the optimal light.

According to another embodiment of the present invention, a system for detecting ambient light is assumed to be currently booted in a night time / dark area / area where the ambient light is smaller. The average frequency mean value (FM) and the data mean value (DM) are calculated for the current field of view. The FM and DM are compared to the predetermined thresholds described above. If FM is greater than the predetermined FM threshold and DM is also greater than the predetermined DM threshold, the scene is identified as daytime and its ambient light is detected as optimal light. If FM is smaller than the predetermined FM threshold and DM is greater than the predetermined DM threshold, the scene is identified as daytime and its ambient light is detected as optimal light. On the other hand, if FM is smaller than the predetermined FM threshold and DM is also less than the predetermined DM threshold, then a small region (ROI) at the center of the image is selected and then the FM for the selected ROI is calculated do. When the FM of the compared ROI is smaller than the predetermined FM threshold, the ambient light is detected as being smaller than the optimal light.

Herein, the term " optimal light " is meant to include, but is not limited to, light exceeding a predefined threshold, bright light conditions, and day time conditions. The expression " less than optimal light ", as used herein, refers to light below a predefined threshold, low light conditions, night time conditions, tunnels, parking lots, garages, Etc. When a suboptimal light condition is detected, the system displays appropriate warnings to the driver, and the ECU controls the appropriate vehicle functions.

For example, in one of the above embodiments, the method according to the present invention can detect possible tunnel conditions - i.e., entering tunnel, in-tunnel, and exiting tunnel conditions do. A method for detecting possible tunnel conditions is described in detail in the following description. If the FM of the ROI of the selected image is less than the predetermined FM threshold, the system warns that there may be a tunnel in the forward region, and if a predetermined warning message (e.g., " possible tunnel & Of the display device. If this condition continues for a predetermined number of frames ('n'), for example, for 10 frames, the warning message will be changed to "tunnel entry", followed by the flag "In_Tunnel". Once the " in tunnel " flag is set, the vehicle is considered to be in the tunnel area and a warning message " INTERNAL TUNNEL " The FM is monitored for the situation in the tunnel, and if it falls well below the predetermined FM threshold, the system warns that it is a tunnel entry condition. Thus, a " tunnel advance " warning message will be provided and a " Exit_Tunnel " flag will be set. The 'tunnel advance' warning is displayed for, for example, 15 frames. The final departure is monitored after 15 frames of the entry condition until the FM is greater than the predetermined FM threshold. Once FM is greater than the predetermined FM threshold, it represents the optimal light and daytime condition, and thus all the flags are reset.

According to one embodiment of the present invention, the algorithm used to identify possible scenarios (scenario) will include the following:

a. Histogram Computation (Total bins = 256)

i. Calculate the bin values of the histogram

ii. Calculates the maximum of 256 bins

iii. Scales Bin values to their maximum values.

b. Frequency Mean and Data Mean

i. Calculate the average of scaled bin values (frequency average)

ii. Calculate data average from bin values (data average)

c. Road scene identification - setting of thresholds

i. Calculate the mean of the frequency average for the last 5 frames (FM)

ii. Set thresholds for FM and DM (FM_THR, DM_THR, EXIT_THR)

d. Road Scene Identification - Method

i. weekly

One. If FM> FM_THR

2. Else if FM <FM_THR but DM> DM_THR

3. Else if FM <FM_THR && DM <DM_THR but FM_ROI> FM_THR

a. Counter 1 = Counter 1-1;

ii. Possible Tunnel

One. If FM <FM_THR, DM <DM_THR && FM_ROI <FM_THR

2. Counter 1 = Counter 1 + 1;

iii. Entering tunnel

One. If Counter 1> 5, in_tunnel_flag = 0

2. Counter 2 = Counter 2 + 1;

3. Repeat 'tunnel entry' display until Counter 2 = 10

4. In_tunnel_flag = 1

iv. In_tunnel

One. If Counter 2> 10 && In_tunnel_flag = 1 && FM> FM_THR

v. Exit

One. If in_tunnel_flag = 1, Counter 2> 10 but FM <EXIT_THR

2. Exit_flag = 1

3. Counter 3 = Counter 3 + 1

vi. Final Exit

One. If Counter 3 == 15

2. If FM <EXIT_THR, display the 'advance' notation

3. Else if FM> FM_THR, display 'weekly' notation

Procedures for detecting ambient light, i.e., daytime, tunnel potential, tunnel entry, tunnel entry, tunnel entry and final entry conditions are described in detail below:

a. Histogram Computation

범위의 강도(n)를 갖는 크기

의 소정의 그레이 레벨 이미지(

)에 대해, 히스토그램은 다음과 같이 계산된다:

The size with the intensity (n) of the range

A predetermined gray-level image (

), The histogram is calculated as: &lt; RTI ID = 0.0 &gt;

Step 1 : Calculate the histogram bin values.

If 'p' denotes the histogram bin of the image, and 'I' denotes the bin index,

p _i = total number of pixels with intensity n _i .

[식 1] here,

[Formula 1]

Step 2 : Calculate the maximum frequency value.

And calculates a maximum value of the calculated histogram bin values. This value provides the maximum frequency value.

[식 2]Max_p = max (pi) (

[Formula 2]

Step 3 : Scale bin data with the maximum frequency value.

=

[식 3]

=

[Formula 3]

Scaling bin data with a maximum frequency value provides different frequency averages for every histogram, thus providing information about the distribution. The details are explained below.

b. Frequency Mean & Data Mean

The histogram provides a distribution of frequency or a distribution of brightness values.

4 is a schematic diagram illustrating different ambient light conditions and corresponding histograms in accordance with an embodiment of the present invention. The distribution of frequencies for various road conditions such as daytime, tunnel entry, tunnel entry, tunnel entry and final entry (outside the tunnel) is disclosed. The histograms are generated for different ambient light conditions and are different for each road condition. In the case of a non-normalized histogram, for example, the sum of the frequencies of the histogram bin is equal to the size of the image, and in the case of a normalized histogram it is equal to one.

In order to obtain a singular value that may provide information on the distribution of frequencies, the maximum frequency value of the frequency distribution is calculated and the histogram value is scaled.

[식 4]

[Formula 4]

The frequency mean value from the scaled bin value is calculated as:

[식 5]

[Formula 5]

here,

For a tunnel entry or tunnel entry condition, the histogram may reach a peak close to 0 or 255, respectively, so that the maximum frequency value will remain similar and the frequency average value will also be in the same range. To avoid false judgments, the data / brightness average value of the image is also compared because the frequency average value will also be in the same range.

The data average or brightness value of the image is calculated from the histogram. The histogram values obtained in Equation 1 are normalized as:

[식 6]

[Formula 6]

The range of p _i is between 0 and 1.

[식 7]

[Equation 7]

c. Field identification: threshold setting

The system is considered to turn on during daylight conditions to identify ambient light conditions. A typical range of frequency average and data mean values for various ambient light conditions is described as follows:

Comparison of two images to calculate the threshold for frequency average and data mean values Scenario Video1 Video2 Condition DM FM DM FM
weekly
101.23 27.55 120.87 39.95 DM> 80
FM <30
113.67 74.5 68.64 29.02 99.60 48.99 128.5 48.7
enter
40.33 24.58 78.4 24.75 DM <80
FM> 30
31.9 7.37 66.25 21.9 19.8 11.92 49.41 21.21 Inside the tunnel
69.5 32.86 81.06 29.96 In-tunnel
flag set 56.0 31.43 110.32 36 69.83 36.49 111 46.2
debouchment
108.37 17.14 103 19.61 FM <20
DM> 80
Exit flag set 151.4 5.64 135.3 5.67 182.2 2.31 168.27 2.69

As shown in Table 1, the range of brightness values during daytime varies between 90 and 150, while FM exceeds 30. To clearly distinguish between daytime and low ambient light conditions, the predetermined DM threshold is set to 80 (DM_THR). It is observed that there is a variation, especially in the mean frequency value, when the vehicle passes under the bridge or under dense water pipes. To avoid error detection, an average value of the frequency averages is calculated. The average of several previous frames is stored and estimated for the current frame. The FM is updated as follows.

Initially, the mean values of the frequencies of the first K frames are stored in a row, and then for the current frame, the average of the previous K frames is calculated as:

[식 8]

[Equation 8]

(현재 이미지의 FM)

(FM of current image)

The threshold set for FM is 30 (FM_THR). As shown in Table 1, there is a sudden drop in the frequency average among the entry conditions. For the distinction between entry conditions and daytime conditions, the entry threshold for FM is set at 20 (EXIT_THR).

The thresholds defined for this system FM_THR 30 DM_THR 80 EXIT_THR 20

d. Method to distinguish road scenes

The following ambient conditions / situations are identified using this system: day time, possible tunnel, entering tunnel, in tunnel, exiting tunnel ) And final exit.

5A and 5B are schematic diagrams illustrating daytime conditions having a low contrast image and a good contrast image, in accordance with an embodiment of the present invention. As shown in FIG. 5A, for example, the FM value is 54.2, the DM value is 101.2, and both FM and DM exceed their threshold values of 30 and 80, respectively. Also in FIG. 5B, the FM value is 48.7 and the DM value is 128.05, where both FM and DM exceed their threshold values of 30 and 80, respectively. Therefore, if FM is greater than the predetermined FM threshold (FM_THR), the current frame is marked 'Day Time'. An averaging of the previous frames is taken and if there is a sudden decrease in ambient light then an erroneous decision on the road condition may be avoided.

 Figures 6A and 6B are schematic diagrams illustrating daytime conditions where the average frequency mean value (FM) is lower but the data mean value (DM) is higher, according to one embodiment of the present invention. As shown in FIG. 6B, the FM value is 7.28 and the DM value is 87.5. Here, the FM is smaller than the predetermined FM threshold (FM_THR) 30, but the DM of the current image is larger than the predetermined DM threshold (DM_THR) 80, so that the current frame is labeled (weekly).

In addition, as shown in FIG. 6A, the FM value is 29.02 and the DM value is 68.64. Here, since FM and DM are both smaller than their respective thresholds 30 and 80, extraction of the ROI at the center of the image of fixed width and height is achieved. The FM of the current ROI is compared to the predetermined FM threshold (FM_THR) described above, and if it is found to be larger, the current frame is marked as 'Week'.

 7a and 7b are schematic diagrams illustrating possible tunnel conditions, in accordance with an embodiment of the present invention. In the last case as shown in FIG. 6, if the FM of the current ROI is below the predetermined FM threshold (FM_THR), the current frame is marked as &quot; Tunneling Probability &quot;. This condition is monitored by increasing the counter value (counter_1) until it reaches five frames.

 8a and 8b are schematic diagrams illustrating entering and tunnel conditions according to an embodiment of the present invention. If the counter value counter_1 is larger than 5, the current frame labeling is switched to 'tunnel entry' as shown in FIG. 8A. The counter value counter_1 is decreased when it meets a daytime situation. After five frames, the tunnel entry condition is maintained for the next consecutive 10 frames ((counter_2), after which the aforementioned 'in tunnel' flag is set as shown in Figure 8b. If the FM exceeds the entry threshold EXIT_THR ) Until the current frame falls down.

FIG. 9A is a schematic view illustrating an exiting tunnel condition according to an embodiment of the present invention. FIG. Only when the tunnel flag is set, the above-mentioned tunnel entry conditions are monitored. If FM falls below the entry threshold (EXIT_THR), the current frame is labeled (tunneled) and the entry counter (counter_3) is incremented. Also, it is observed that the brightness value greatly increases during the advancement. These conditions are also monitored to avoid error detection of entry conditions. The advance condition is displayed for about 15 frames (counter_3). Thereafter, the tunnel advance flag is set, and the final advance condition is monitored.

FIG. 9B is a schematic view illustrating the tunnel advancement according to an embodiment of the present invention. FIG. If FM is below the entry threshold (EXIT_THR), the current frame is marked 'tunnel entry', otherwise the current frame is marked 'weekly'. The flags and counters described above are reset to detect conditions such as another tunnel.

The above three counters are set so that the step of switching over from one scene to another is not abruptly performed. The first counter counter_1 monitors possible tunnel conditions for five frames. The first counter is decremented if it meets the &quot; weekly &quot; condition described above. The second counter counter_2 monitors the tunnel entry condition and maintains the 'tunnel entry' condition for the next consecutive 10 frames. The third counter counter_3 maintains the tunnel entry condition for about 15 frames.

Two additional flags (in-tunnel and outbound flags) ensure that transitions from in-tunnel conditions to daytime conditions and from transition conditions to daytime conditions do not occur in a random manner. Once a tunnel entry is detected, a flag in the tunnel is set, which ensures that the next condition is in the tunnel until the entry condition is reached. Weekly conditions are monitored only after the advance flag is set, otherwise it is marked as tunnel advance.

The method and system of the present invention is a simple and accurate ambient light detection system. The detection method of the present invention is useful for distinguishing between various low light conditions such as, but not limited to, conditions such as tunnels, parking lots, under the bridge, trees in the trees, and the like. The present invention appropriately provides appropriate warnings such as &quot; tunnel possibility &quot; and &quot; tunnel entry &quot;. Further, the ECU performs a predefined control function based on the detected amount of ambient light. The ECU controls the functions of one or more vehicles based on the detected ambient light. The predefined control functions include, but are not limited to, headlight adjustment, instrument panel illumination, automatic light direction control according to road conditions, and the like. As described in the present invention, the road category conditions and the overall classification of ambient light detection are performed using only two parameters, the average frequency mean value (FM) and the data mean value (DM).

All equivalent relationships to those described in the present application and illustrated in the drawings are intended to be encompassed by the present invention. The examples used to illustrate the embodiments of the present invention do not limit the application of the present invention to them in any way. It should be understood by those of ordinary skill in the art that various modifications and alternatives to the details may be developed in light of the overall teachings of the disclosure without departing from the scope of the invention something to do.

Claims (8)

A method for detecting ambient light,
Capturing one or more visible images;
Converting the captured image to a gray color image;
Determining a histogram of each of the gray color images;
Calculating an average frequency average value (FM) and a data average value (DM) of the determined histogram; And
The following steps:
a) comparing the FM with a predetermined FM threshold and detecting the ambient light as optimal when the compared FM is greater than the predetermined FM threshold;
b) comparing the FM to a predetermined FM threshold, comparing the DM to a predetermined DM threshold, and if the compared FM is less than the predetermined FM threshold and the compared DM is greater than the predetermined DM threshold Detecting the ambient light at the maximum when it is large; And
c) comparing the FM with a predetermined FM threshold and also comparing the DM with a predetermined DM threshold;
If the FM is less than the predetermined FM threshold and the DM is less than the predetermined DM threshold,
Compare the FM of the identified ROI with a predetermined FM threshold; And
Detecting ambient light as being less than the optimal light when the compared FM of the ROI is less than the predetermined FM threshold;
&Lt; / RTI &gt;
The method according to claim 1,
Determining an FM of the identified ROI;
Identifying a region of interest in the captured image; And
Further comprising determining FM of the identified ROI when the FM is less than the predetermined FM threshold and the DM is less than the predetermined DM threshold.
2. The method of claim 1, wherein calculating the FM of the determined histogram comprises:
Determining a frequency average value of the determined histogram for a predefined number of frames; And
And determining the FM for the predefined number of frames.
2. The method of claim 1, further comprising detecting a day time when the detected ambient light is greater than the optimal light.
2. The method of claim 1, further comprising detecting the likelihood of entry into and exit from the tunnel when the detected ambient light is less than the optimal light.
2. The method of claim 1, further comprising performing a predefined control function based on detection of one or more states of the ambient light.
An image capture device configured to capture one or more images;
And a processing device coupled to the image capture device and configured to perform the following steps:
Converting a color of each of the captured images into a gray color image;
Determining a histogram of each of the captured images of the gray color;
Calculating an average frequency average value (FM) and a data average value (DM) of the determined histogram; And
The following steps:
a) comparing the FM with a predetermined FM threshold and detecting the ambient light as optimal when the compared FM is greater than the predetermined FM threshold;
b) comparing the FM to a predetermined FM threshold, comparing the DM to a predetermined DM threshold, and if the compared FM is less than the predetermined FM threshold and the compared DM is greater than the predetermined DM threshold Detecting the ambient light at the maximum when it is large;
c) comparing the FM with a predetermined FM threshold;
Compare the DM to a predetermined DM threshold;
If the FM is less than the predetermined FM threshold and the DM is less than the predetermined DM threshold,
Compare the FM of the identified ROI with a predetermined FM threshold; And
Detecting the ambient light as being less than the optimal light when the compared FM of the ROI is less than the predetermined FM threshold;
The method comprising the steps of:
8. The method of claim 7,
The processor is further configured to determine an FM of the identified ROI,
Identifying a region of interest in the captured image; And
And to determine FM of the identified ROI when the FM is less than the predetermined FM threshold and the DM is less than the predetermined DM threshold.

Images