KR101950433B1 - Object detection method and device in middle wavelength infrared video - Google Patents

Abstract

Provided are a method and an apparatus for detecting an object from a middle infrared image which can easily detect an object by removing a glittering phenomenon while using a middle infrared image. According to an embodiment of the present invention, the method for detecting an object from a middle infrared image comprises the steps of: obtaining a middle infrared image photographed by using a middle infrared camera; analyzing the middle infrared image and adjusting the brightness of the image using a reference value by using the apparatus for detecting an image; and outputting the image in which the brightness is adjusted by using the apparatus for detecting an image. The step of adjusting the brightness adjusts the brightness of the image for each pixel.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0002]

The present invention relates to a method and apparatus for detecting an object, and more particularly, to a method and apparatus for easily detecting an object in an image in which water-reflected light is captured using a medium-infrared ray.

Generally, the medium-infrared (MWIR) has high atmospheric permeability in a high-temperature and high-humidity environment compared with the far infrared ray (LWIR). Therefore, devices using mid-infrared rays are mainly used for devices operating in a high humidity environment such as marine environment. For example, a mid-infrared camera can be used to acquire a mid-infrared image for an image of the sea. At this time, a plateau histogram equalization and linear spreading are used for the contrast ratio processing.

Unlike far-infrared rays, infrared rays are reflected when they are incident on the sea surface, and the corresponding part is shiny black / white. In the contrast ratio processing method such as the flatness histogram smoothing and linear spreading described above, when the flashing phenomenon occurs, the object can not be easily detected in the image. Therefore, if tracking of the object using the image is required, There is an increasing problem.

KR 0522203 B

According to an aspect of the present invention, there is provided an apparatus and method for detecting an object in a medium-to-infrared (IR) image, in which an object is easily detected by removing a twinkling phenomenon while using a medium- do.

According to an aspect of the present invention, there is provided an object detection method in a medium-infrared image. The method for detecting an object in a medium-infrared image includes: obtaining a medium-infrared image photographed using a medium-infrared camera; Analyzing the mid-infrared image and adjusting brightness of the image using a reference value; And outputting the brightness-adjusted image to the user by the image detection device, wherein the adjusting brightness adjusts the brightness of each pixel of the image.

The step of adjusting the brightness of the image may include analyzing the middle infrared image to obtain a brightness histogram of the image; Applying the reference value to the brightness histogram to generate an adjusted brightness histogram by adjusting brightness per pixel; And adjusting the image using the adjusted brightness histogram to generate the adjusted image.

In the step of generating the adjusted brightness histogram, brightness of a pixel that is lighter than the reference value can be adjusted to the brightest.

The reference value may be obtained by calculating the light reflectance of the sea surface using the weather information and the sea information, or may be obtained using existing reference values.

The adjusting the image may generate the adjusted image by adjusting the pixel brightness of the image using the adjusted brightness histogram.

According to an aspect of the present invention, there is provided an apparatus for detecting an object in a medium-infrared image. The object detecting apparatus in the middle infrared ray image includes an image obtaining unit that obtains an image photographed using medium infrared rays; An image analyzer receiving the image and analyzing brightness of each pixel; An image processor for modifying the brightness of the image using a reference value to generate an adjusted image; And an image output unit for outputting the adjusted image to a user.

The reference value may be obtained by calculating the light reflectance of the sea surface using the weather information and the sea information, or may be acquired using existing reference values.

The image analyzing unit may generate a brightness histogram as an analysis result using the per-pixel brightness.

The image processor may apply the reference value to the brightness histogram to maximize the brightness of the pixel having the brightness equal to or greater than the reference value to generate an adjusted brightness histogram.

The image processor may generate the adjusted image by adjusting the brightness of the pixel included in the image using the adjusted brightness histogram.

The method and apparatus for detecting an object in a medium-infrared image according to an embodiment of the present invention can remove the sparkling characteristic in an image due to sunlight reflected on the sea surface.

In addition, the method and apparatus for detecting an object in a medium-infrared image according to an embodiment of the present invention have an effect of easily detecting an object by reducing image interference of sea-surface solar reflection.

1 is a flowchart briefly showing an object detection method in a medium-infrared image according to an embodiment of the present invention.
FIG. 2 is a diagram showing an infrared ray photographing image (a), a brightness histogram (c), an adjusted brightness histogram, and (d) an adjusted image according to an embodiment of the present invention.
3 is a block diagram briefly showing an object detecting apparatus in a medium-infrared image according to an embodiment of the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art to which the present invention pertains. The present invention may be embodied in many different forms and is not limited to the embodiments described herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and the same or similar components are denoted by the same reference numerals throughout the specification.

FIG. 1 is a flow chart briefly showing an object detection method in a medium-infrared image according to an embodiment of the present invention. FIG. 2 is a diagram illustrating a histogram of the brightness of an image taken during (a) c) an adjusted brightness histogram, and (d) an adjusted image, respectively. Hereinafter, an apparatus using the method is referred to as an object detecting apparatus for convenience of explanation of an object detection method in a medium-infrared image. However, the present invention is not limited to this, and various digital apparatuses Can also be used. Hereinafter, a method of detecting an object in a medium-infrared image according to an embodiment of the present invention will be described in detail with reference to FIGS. 1 and 2. FIG.

1, a method 100 for detecting an object in a medium-infrared image according to an exemplary embodiment of the present invention includes a step of obtaining an image (S110), a step of analyzing an image and adjusting brightness of an image using a reference value (S120) and outputting a brightness adjusted image (S130).

In the method 100 for detecting an object in a medium-infrared image according to an embodiment of the present invention, an object detection apparatus acquires an image (step S110). The object detection apparatus can acquire an image photographed in the medium infrared ray from the outside as shown in FIG. 2A, and the object exists at the point A in this embodiment. Meanwhile, the object detecting device may be connected to the middle infrared ray camera through a wired or wireless connection to acquire a middle infrared ray image, or may be connected to an internal or external storage device to acquire a previously stored middle infrared ray image have.

Next, the object detecting apparatus analyzes the image and adjusts the brightness of the image using the reference value (step S120). The object detecting apparatus can obtain the adjusted image by analyzing the brightness of each of the pixels of the medium infrared image obtained in step S110 and changing the brightness of some pixels using the reference value. In operation S 120, a brightness histogram of the image is obtained by analyzing the image in operation S 121, a brightness histogram is generated by applying a reference value to the brightness histogram in operation S 123, and a brightness histogram adjusted using the adjusted brightness histogram And generating an image (S125).

The object detecting apparatus first analyzes the medium-infrared image to acquire a brightness histogram of the image (step S121). The brightness histogram is a histogram obtained by acquiring the brightness of each pixel included in the image. In the histogram, the x-axis represents the brightness of the pixel, the y-axis represents the number of pixels, and the photographed image of Fig. 2A can be represented by the brightness histogram of Fig.

Next, the object detecting apparatus applies a reference value to the brightness histogram to generate an adjusted brightness histogram (step S123). Here, the reference value is a value representing a brightness reference of the pixel whose brightness is to be adjusted.

Referring to FIG. 2B, B is a portion where pixels of an object to be tracked are collected, C is a portion where pixels of a background sky are gathered, D is a sun reflection Is a portion where the pixels of the pixel are gathered. Accordingly, in the object detection method in the medium-infrared image according to the embodiment of the present invention, by applying the reference value to the brightness histogram of FIG. 2B obtained using the step S121, The adjusted brightness histogram can be adjusted to the brightest value as shown in FIG. 2C.

At this time, the reference value can be defined by various methods. For example, the user may directly specify the reference value by using an external input device or may define the value using the previously used reference values, or may obtain the weather information and the marine information from the outside And the light reflectance of the sea surface can be calculated and obtained using the acquired information.

The object detecting apparatus generates an adjusted image using the adjusted brightness histogram (step S125). The object detecting apparatus obtains the adjusted brightness histogram by collectively setting the brightness to be the brightest so that the brightness of the pixels having the brightness higher than the reference value represented by E is formed at the point F as shown in FIG. The image obtained in step S110 can be processed or adjusted using the adjusted brightness histogram.

For example, the object detecting apparatus can generate an adjusted image in which the brightness of the pixel having sunlight reflection is converted to the brightest brightness by adjusting the brightness of the pixel whose brightness is changed by using the adjusted brightness histogram, Is shown in Fig. 2D.

Comparing FIGS. 2A and 2D, an object existing at point F in FIG. 2D can be more easily observed because there is no sparkle caused by sunlight reflected from an object located at point A in FIG. 2A.

Finally, the object detecting apparatus outputs the image whose brightness is adjusted to the user (step S130). The object detecting apparatus can output the adjusted brightness-acquired image to the user in step S120 (or step S125). At this time, the object detecting apparatus may adjust the tilting angle of the middle infrared ray camera so that the object detected in the image can be automatically tracked according to the setting of the user, or alert when the object disappears from the image by sending an alarm You may.

3 is a block diagram briefly showing an object detecting apparatus in a medium-infrared image according to an embodiment of the present invention. The object detecting apparatus 300 in the middle infrared ray image according to an embodiment of the present invention includes an image obtaining unit 310, an image analyzing unit 330, a reference setting unit 350, an image processing unit 370, (390).

The image acquiring unit 310 acquires a medium-infrared image. The image acquiring unit 310 may be formed of a middle infrared ray camera to directly acquire a middle infrared ray image or a communication module for acquiring a previously stored intermediate infrared ray image from an internal or external storage device. The infrared ray image is shown in Fig. 2A as described above.

The image analyzer 330 analyzes the mid-infrared image acquired through the image acquiring unit 310 to generate a brightness histogram as shown in FIG. 2B. The brightness histogram is a histogram obtained by acquiring the brightness of each pixel included in the image. The x-axis represents the brightness of the pixel and the y-axis represents the number of pixels.

The reference setting unit 350 sets a reference value for selecting a pixel whose brightness is to be adjusted in the brightness histogram. The reference value is a value indicating a brightness reference of the pixel whose brightness is to be adjusted.

At this time, the reference value can be defined by various methods. For example, the user may directly specify the reference value by using an external input device or may define the value using the previously used reference values, or may obtain the weather information and the marine information from the outside And the light reflectance of the sea surface can be calculated and obtained using the acquired information.

The image processor 370 generates the adjusted brightness histogram using the reference value, and processes the adjusted brightness histogram to generate the adjusted image.

Referring to FIG. 2B, B is a portion where pixels of an object to be tracked are collected, C is a portion where pixels of a background sky are gathered, D is a sun reflection Is a portion where the pixels of the pixel are gathered. Accordingly, the image processor 370 adjusts the brightness of the pixels having brightness brighter than the reference brightness value to the brightest value by applying the reference value set by the reference setting unit 350 to the brightness histogram of FIG. 2B The histogram of brightness can be generated as shown in FIG. 2C.

Then, the image processor 370 may process the intermediate infrared image acquired by the image acquiring unit 310 using the adjusted brightness histogram to generate an adjusted image.

For example, the image processor 370 can adjust the brightness of the pixel whose brightness has been changed to the brightest by using the adjusted brightness histogram, thereby generating an adjusted image in which the brightness of the pixel having the sun reflected light is converted to the brightest brightness The corresponding image is shown in Fig. 2D.

Comparing FIGS. 2A and 2D, an object existing at point F in FIG. 2D can be more easily observed because there is no sparkle caused by sunlight reflected from an object located at point A in FIG. 2A.

The video output unit 390 outputs an image whose brightness is adjusted externally. The image output unit 390 can receive the adjusted image from the image processing unit 370 and output it to the outside. At this time, the image output unit 390 may adjust the tilting angle of the image acquisition unit 310 formed by the middle infrared ray camera so that the object detected in the image may be automatically tracked according to the user's setting, The warning may be provided to the user by sending an alarm.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

300: Object detection device in medium infrared image
310: Image acquisition unit 330: Image analysis unit
350: Reference setting unit 370:
390: Video output section

Claims (10)

Obtaining an intermediate infrared image photographed using a middle infrared camera;
Analyzing the mid-infrared image and adjusting brightness of the image using a reference value;
And the image detection device outputting the brightness-adjusted image to a user,
Wherein the step of analyzing the medium infrared image and adjusting the brightness of the image using the reference value comprises:
Analyzing the intermediate infrared image to obtain a brightness histogram of the image;
Generating an adjusted brightness histogram by adjusting the brightness of each pixel by applying the reference value to a brightness histogram of a region in which sunlight reflected by sunlight is reflected on a sea surface,
And adjusting the image using the adjusted brightness histogram to generate the adjusted image,
Wherein the step of generating the adjusted brightness histogram by adjusting the brightness of each pixel by applying the reference value to the brightness histogram,
The brightness of a pixel that is lighter than the reference value is adjusted to be the brightest,
Wherein the step of analyzing the medium infrared image and adjusting the brightness of the image using the reference value comprises:
The reference value for automatically calculating the light reflectance of the sea surface using the weather information and the sea information and reducing the image interference due to the sunlight reflected on the sea surface to eliminate the sparkling characteristic of the image And detecting the object in the middle infrared ray image. delete delete delete delete delete delete delete delete delete

Images