KR102204814B1 - Apparatus for processing thermogram image and method for the same - Google Patents

Abstract

The present application relates to a thermal image processing apparatus and a thermal image processing method, wherein the thermal image processing apparatus according to an embodiment of the present invention senses infrared rays emitted from an object to measure the temperature of the object, and the A thermal imaging camera for generating a thermal image by setting a pixel value corresponding to the measured temperature; A fire detector configured to determine that a fire has occurred in the object when a pixel having a pixel value equal to or higher than a preset fire temperature exists in the thermal image; An image processing unit for resetting the pixel value to a preset pixel reset value according to a size order of pixels included in the thermal image when the fire occurs; And an image output unit outputting a correction image in which pixel values of the thermal image are reset to the pixel reset value.

Description

Thermal image processing apparatus and thermal image processing method {Apparatus for processing thermogram image and method for the same}

The present application relates to a thermal image processing apparatus and a thermal image processing method, and to a thermal image processing apparatus and a thermal image processing method capable of improving visibility of a thermal image.

Typically, a thermal imaging camera is a device that converts radiant energy (infrared signal) due to a temperature difference between an object and a background into an electrical image signal. The radiant energy can be expressed in terms of shaded gradations, that is, gray levels (or pixel values) of a normal object's temperature difference. Due to the development of semiconductor technology and signal processing technology, such thermal imaging cameras are expanding their application range to various fields such as military as well as industrial and medical fields.

Registered Patent Publication No. 10-1339026

The present application is to provide a thermal image processing apparatus and a thermal image processing method capable of improving the visibility of a thermal image.

In the thermal image processing apparatus according to an embodiment of the present invention, the thermal image processing apparatus detects infrared rays emitted from the object, measures the temperature of the object, and sets a pixel value corresponding to the measured temperature to generate a thermal image. Video camera; A fire detector configured to determine that a fire has occurred in the object when a pixel having a pixel value equal to or higher than a preset fire temperature exists in the thermal image; An image processing unit for resetting the pixel value to a preset pixel reset value according to a size order of pixels included in the thermal image when the fire occurs; And an image output unit outputting a correction image in which pixel values of the thermal image are reset to the pixel reset value.

Here, the fire detection unit may determine that the fire occurs when there is a fire pixel having a pixel value equal to or higher than the fire temperature, and an area in which the fire pixels are grouped is greater than or equal to a preset minimized material area.

Here, the image processing unit arranges pixel values of pixels included in the thermal image in an ascending order according to size, and increases the unit brightness variation from a preset minimum brightness value for each of the pixel values arranged in the ascending order. The pixel reset values can be sequentially reset.

Here, the image processing unit may reset the same pixel reset value for pixels having the same pixel value among the pixel values arranged in ascending order.

Here, the image output unit outputs the corrected image by expressing the pixel reset value in n-bit, and the corrected pixel value of each pixel included in the corrected image is

으로, img_normalized는 상기 보정픽셀값, img는 각각의 픽셀들의 픽셀재설정값, Max(img)는 상기 보정영상의 픽셀재설정값의 최대값, Min(img)는 상기 보정영상의 픽셀재설정값의 최저값일 수 있다.

Here, img _normalized is the corrected pixel value, img is the pixel reset value of each pixel, Max (img) is the maximum value of the pixel reset value of the corrected image, and Min (img) is the lowest value of the pixel reset value of the corrected image. Can be

In the thermal image processing method according to an embodiment of the present invention, a thermal image processing method for generating a thermal image by detecting infrared rays emitted from an object, measuring the temperature of the object, and setting a pixel value corresponding to the measured temperature An image image capturing step; A fire detection step of determining that a fire has occurred in the object when a pixel having a pixel value equal to or higher than a preset fire temperature exists in the thermal image; An image processing step of resetting the pixel value to a preset pixel reset value according to a size order of each pixel value for pixels included in the thermal image when it is determined that the fire has occurred; And an image output step of outputting a correction image in which pixel values of the thermal image are reset to the pixel reset value.

Here, in the fire detection step, if a fire pixel having a pixel value equal to or higher than the fire temperature exists, and an area in which the fire pixels are grouped is greater than or equal to a preset minimized material area, the fire may be determined.

Here, the image processing step may include a sorting process of sorting pixel values of pixels included in the thermal image in ascending order according to size; And a reset process of sequentially resetting pixel reset values that increase by a unit brightness variation amount from a preset minimum brightness value for each of the pixel values arranged in ascending order.

In the resetting process, the same pixel reset value may be reset for pixels having the same pixel value among the pixel values arranged in ascending order.

으로, img_normalized는 상기 보정픽셀값, img는 각각의 픽셀들의 픽셀재설정값, Max(img)는 상기 보정영상의 픽셀재설정값의 최대값, Min(img)는 상기 보정영상의 픽셀재설정값의 최저값일 수 있다. In the image output step, the correction image is output by expressing the pixel reset value in n-bit, and the correction pixel value of each pixel included in the correction image is

Here, img _normalized is the corrected pixel value, img is the pixel reset value of each pixel, Max (img) is the maximum value of the pixel reset value of the corrected image, and Min (img) is the lowest value of the pixel reset value of the corrected image. Can be

In addition, the solution to the above-described problem does not list all the features of the present invention. Various features of the present invention and advantages and effects thereof may be understood in more detail with reference to the following specific embodiments.

According to a thermal image processing apparatus and a thermal image processing method according to an embodiment of the present invention, an empty temperature value between a high temperature region such as a fire and a room temperature region is removed by equally correcting the interval of the temperature difference in the thermal image. It is possible to do. Accordingly, the visibility of the thermal image can be improved so that the overall background and object can be more easily checked with the naked eye.

That is, according to the thermal image processing apparatus and the thermal image processing method according to an embodiment of the present invention, it is difficult to distinguish between an object and a background because the brightness value distinction is blurred as in the conventional histogram equalization. It is possible to solve. In addition, compared with the conventional method of performing normalization for a specific temperature section, it is not necessary for the user to directly set a specific temperature section, and it is possible to improve visibility for areas other than the specific temperature section.

1 is a schematic diagram showing a thermal image processing apparatus according to an embodiment of the present invention.
2 is a diagram showing a thermal image using a conventional thermal image processing apparatus.
3 is a diagram showing a thermal image by the thermal image processing apparatus according to an embodiment of the present invention.
4 and 5 are flow charts illustrating a thermal image processing method according to an embodiment of the present invention.

Hereinafter, preferred embodiments will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art may easily implement the present invention. However, in describing a preferred embodiment of the present invention in detail, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the subject matter of the present invention, the detailed description thereof will be omitted. In addition, the same reference numerals are used throughout the drawings for portions having similar functions and functions.

In addition, throughout the specification, when a part is said to be'connected' to another part, it is not only'directly connected', but also'indirectly connected' with another element in the middle. Include. In addition, "including" a certain component means that other components may be further included rather than excluding other components unless specifically stated to the contrary. In addition, terms such as "~ unit" and "module" described in the specification mean units that process at least one function or operation, which may be implemented as hardware or software, or as a combination of hardware and software.

1 is a schematic diagram showing a thermal image processing apparatus according to an embodiment of the present invention.

1, a thermal image processing apparatus according to an embodiment of the present invention may include a thermal imaging camera 110, a fire detection unit 120, an image processing unit 130, and an image output unit 140. have.

Hereinafter, a thermal image processing apparatus according to an embodiment of the present invention will be described with reference to FIG. 1.

The thermal imaging camera 110 may measure the temperature of the object by sensing infrared rays emitted from the object being photographed, and may generate a thermal image by setting a pixel value corresponding to the measured temperature. That is, the thermal imaging camera 110 may generate a temperature-based thermal image by imaging the surface temperature of the object in two dimensions.

Here, the thermal imaging camera 110 may generate a thermal image by measuring a temperature distribution from a minimum of 0 degrees to a maximum of 275 degrees, but is not limited thereto, and the thermal imaging camera 110 is not limited to the type or setting of the thermal imaging camera 110. The temperature distribution representing the image may be set differently.

Meanwhile, pixels of the thermal image generated by the thermal imaging camera 110 may have pixel values corresponding to respective temperatures, and the contrast in the thermal image may be set according to the size of the pixel value. That is, each of the pixels included in the thermal image may be displayed darker because the pixel value is smaller as the temperature is lower, and brighter because the pixel value is larger as the temperature is higher.

In the case where there is no high temperature heat source in the area photographed by the thermal imaging camera 110, since the width of the temperature section is narrow, the user can easily distinguish and recognize the object and the background from the thermal image. On the other hand, when a fire or the like occurs in an area photographed by the thermal imaging camera 110, a flame or the like may be displayed as a maximum pixel value, and the pixel values may be set in the remaining areas according to a temperature difference with the flame. When a high-temperature heat source, such as a fire, is present, the width of a temperature section included in the thermal image is very wide, and thus pixels in a region having a relatively low temperature may be displayed darkly. Therefore, it may be very difficult for the user to recognize an area other than the area where the fire occurred. In particular, although the user can confirm the occurrence of a fire using the thermal imaging camera 110, it may be difficult to identify low temperature objects such as people or combustible materials located near the fire.

FIG. 2(a) is a thermal image generated by a conventional thermal image processing apparatus. Referring to FIG. 2(a), it can be seen that other areas other than the fire area are displayed darkly. FIG. 2(b) is a histogram showing pixels included in the thermal image of FIG. 2(a) for each brightness, and the x-axis indicates the brightness and the y-axis indicates the number of pixels. That is, as shown in Fig. 2(b), it can be seen that most of the pixels are located in a dark area. As described above, in the case of the conventional thermal image processing apparatus, there is a problem in that it is difficult to recognize the surrounding area when a heat source of high temperature exists. However, in the thermal image processing apparatus according to an embodiment of the present invention, by performing image processing on the thermal image generated by photographing the thermal imaging camera 110, it is intended to solve the above-described problems and the like.

The fire detection unit 120 may determine that a fire has occurred in the object if a pixel having a pixel value equal to or higher than a preset fire temperature exists in the thermal image. That is, it is possible to check whether a high temperature heat source such as a fire exists in the thermal image through the fire detection unit 120. When a fire or the like does not occur in the thermal image, there is no need for additional image processing, so the thermal image generated by the thermal imaging camera 110 may be output by the image output unit 140. On the other hand, when the fire detection unit 120 determines that a fire has occurred, the image processing unit 130 may perform image processing.

Specifically, the fire detection unit 120 may determine that a fire has occurred when a pixel value equal to or higher than a preset fire temperature exists among pixels included in the thermal image. For example, in the case of a flame, etc., since it may have a temperature of 700 degrees or more, 275 degrees, which is the maximum temperature that can be measured by the thermal imaging camera 110, may be set as the fire temperature. Accordingly, when a pixel having a pixel value equal to or higher than the fire temperature exists, the fire detection unit 120 may determine that a fire has occurred.

However, due to a measurement error, etc., even when no actual fire occurs, there may be a case in which any one pixel has a pixel value corresponding to a preset fire temperature such as 275 degrees. In order to prevent erroneous determination of whether a fire has occurred in this case, according to an embodiment, the fire detection unit 120 may check the size of an area occupied by fire pixels having a pixel value equal to or higher than the fire temperature. That is, the fire detection unit 120 may group fire pixels when there is a fire pixel, and check whether the area of the grouped fire pixels is greater than or equal to a preset minimized material area. When an actual fire occurs, at least the size of the minimum material area or more can be formed by flames, so it is possible to determine whether or not the actual fire occurs after checking whether pixels above the fire temperature correspond to the minimum material area or more.

The image processing unit 130 may perform image processing on a thermal image. As shown in FIG. 2, surrounding areas other than a high-temperature heat source such as a flame displayed in a thermal image may be displayed relatively dark. Therefore, it is very difficult to clearly grasp a person or an object located in the surrounding areas. Accordingly, the image processing unit 130 may reset the pixel values of the pixels included in the thermal image to display regions around the high temperature heat source relatively brightly.

Specifically, the image processing unit 130 may reset the pixel values to a preset pixel reset value according to the order of size of each pixel value with respect to the pixels included in the thermal image. First, the image processing unit 130 may extract pixel values of each of the pixels included in the thermal image, and may sort the extracted pixel values in ascending order according to the size. Thereafter, the image processing unit 130 may sequentially reset the pixel values of the pixels arranged in ascending order to a preset pixel reset value. Here, pixels having the same pixel value may be set in the same order and reset to the same pixel reset value.

Meanwhile, the pixel reset value may be a value sequentially increased from the minimum brightness value by the unit brightness variation amount. For example, the image processing unit 130 may reset the pixel value to 0 for the darkest pixels, and then reset the pixel value to 1 for the second darkest pixels. In addition, the third darkest pixels may be reset to 2, and the fourth darkest pixels may be reset to 3. In this case, the minimum brightness value may be 0, and the unit brightness variation amount may be 1. That is, in the thermal image, the difference between the pixel value of the darkest pixel and the pixel value of the second darkest pixel may be less than 1, but here it can be uniformly reset to 1. FIG. For example, before correction, the pixel values may be set as [8.0, 8.0, 9.2, 9.3, 9.3, ..., 274.8, 274.8, 275], respectively, but if corrected by the image processing unit 130, [1, 1, 2, 3, 3, ..., 887, 887, 888]. That is, a difference in brightness according to a temperature difference between pixels can be kept constant.

In this way, when each pixel value is reset according to the order of pixel values of the pixels, the distribution of the pixel on the histogram can be expanded. That is, when the image processing unit 130 performs image processing on the thermal image, a correction image and a histogram as shown in FIG. 3 may be obtained. Compared with Fig. 2(a), it can be seen that the visibility of the surrounding fire in Fig. 3(a) is improved. In addition, referring to FIG. 3(b), it can be seen that the distribution of the histogram of pixels is wider than that of FIG. 2(b).

The image output unit 140 may output a correction image obtained by resetting the pixel values of the thermal image to a pixel reset value. That is, the image output unit 140 may receive a correction image in which pixel values of the thermal image are reset by the image processing unit 130, and may output the corrected image to the display apparatus 200.

Here, when the image output unit 140 outputs the corrected image, each pixel value may be displayed and output as a bit value. However, the number of bits used to represent the pixel value can be variously set, such as 8 bits and 16 bits. Accordingly, the image output unit 140 may express and output a pixel value of each pixel in n bits corresponding to the display apparatus 200. Here, n may be a natural number.

That is, the image output unit 140 may express and output the pixel reset value included in the corrected image in n bits, and the corrected pixel value of each pixel included in the corrected image may be obtained through the following equation.

Here, img _normalized is the corrected pixel value, img is the pixel reset value of each pixel, Max(img) is the maximum value of the pixel reset value included in the corrected image, and Min(img) is the pixel reset value included in the corrected image. It is the lowest value, and n may be the number of bits used to represent the pixel value.

4 and 5 are flow charts illustrating a thermal image processing method according to an embodiment of the present invention.

4 and 5, the thermal image processing method according to an embodiment of the present invention includes a thermal image capturing step (S10), a fire detection step (S20), an image processing step (S30), and an image output step (S40). ) Can be included.

Hereinafter, a thermal image processing method according to an embodiment of the present invention will be described with reference to FIGS. 4 and 5.

In the thermal imaging step S10, the temperature of the object may be measured by detecting infrared rays emitted from the object, and a thermal image may be generated by setting a pixel value corresponding to the measured temperature. That is, a temperature-based thermal image may be generated by imaging the surface temperature of an object in two dimensions. Here, the contrast in the thermal image is set according to the size of each pixel value, and the lower the temperature, the darker the display and the higher the temperature, the brighter the display.

In the fire detection step (S20), if a pixel having a pixel value equal to or higher than a preset fire temperature exists in the thermal image, it may be determined that a fire has occurred in the object. Here, when a fire or the like does not occur in the thermal image, additional image processing is not required, so the image processing step S30 may be omitted and the image output step S40 may be performed (A). On the other hand, when it is determined that a fire has occurred, the image processing may be performed through the image processing step S30 (A).

Specifically, in the fire detection step S20, if a pixel value equal to or higher than a preset fire temperature exists among pixels included in the thermal image, it may be determined that a fire has occurred. For example, in the case of a flame, etc., since the temperature may be 700 degrees or higher, the maximum temperature that can be measured by the thermal imaging camera, 275 degrees, can be set as the fire temperature. However, due to a measurement error, etc., even when no actual fire occurs, there may be a case in which any one pixel has a pixel value corresponding to a preset fire temperature such as 275 degrees. In order to prevent erroneous determination of whether a fire has occurred in this case, according to an embodiment, the size of an area occupied by fire pixels having a pixel value equal to or higher than the fire temperature may be checked. That is, in the fire detection step S20, fire pixels may be grouped when fire pixels exist, and it is possible to check whether the area of the grouped fire pixels is greater than or equal to a preset minimized material area. When an actual fire occurs, at least the size of the minimum material area or more can be formed by flames, so it is possible to determine whether or not the actual fire occurs after checking whether pixels above the fire temperature correspond to the minimum material area or more.

In the image processing step (S30), image processing for the thermal image is performed for resetting the pixel value to a preset pixel reset value according to the size order of each pixel value for the pixels included in the thermal image. I can. That is, the image processing step (S30) performs a sorting process of sorting pixel values of pixels included in the thermal image in ascending order according to size, and then, for each of the pixel values arranged in ascending order, a preset minimum Image processing may be performed by performing a reset process of sequentially resetting pixel reset values that increase from a brightness value by a unit brightness variation amount.

Specifically, as shown in Fig. 5, the thermal image IMAGE(X,Y) can be first input (S31), and the pixel values of the pixels included in the received thermal image are sorted in ascending order, and Sort_data[X *Y] can be saved (S32). Thereafter, the variables i and val may be initialized to 1 and 0, respectively (S33), and pixel coordinate values [x,y] of pixels having the i-th largest pixel value may be extracted (S34). Here, the pixel values for the i-th pixels may be reset to the pixel reset value val (S35). After that, i can be increased (S36) to reset the pixel value of the next sequence. If Sort_data[i]> sort_data[i-1] does not hold, it is the case that pixels in the same order exist in ascending order. Then, by moving to step S43 again, the same pixel reset value may be set for pixels in the same order (B). On the other hand, when there are no more pixels in the same order, the pixel reset value may be increased by a certain unit brightness variation (S37). Thereafter, it is checked whether or not the pixel reset values have been set for all pixels included in the thermal image (C), and if not completed for all pixels, the pixel coordinates of the i-th order are extracted again to extract the pixel reset values ( S34), when all pixels are completed, a correction image may be generated (S38).

In the image output step S40, a correction image obtained by resetting the pixel values of the thermal image to a pixel reset value may be output. That is, in the image output step S40, a correction image in which pixel values are reset in the image processing step S30 may be received, and the corrected image may be output through a display device or the like.

Here, when outputting the corrected image, each pixel value may be displayed and output as a bit value. However, the number of bits used to represent the pixel value can be variously set, such as 8 bits and 16 bits. Accordingly, corresponding to the display device, the pixel value of each pixel can be expressed and output as n bits. Here, n corresponds to a natural number.

That is, in the image output step S40, a pixel reset value included in the corrected image may be expressed in n bits and output, and the corrected pixel value of each pixel included in the corrected image may be obtained through the following equation.

Here, img _normalized is the corrected pixel value, img is the pixel reset value of each pixel, Max(img) is the maximum value of the pixel reset value included in the corrected image, and Min(img) is the pixel reset value included in the corrected image. It is the lowest value, and n may be the number of bits used to represent the pixel value.

The present invention is not limited by the above-described embodiments and the accompanying drawings. It will be apparent to those of ordinary skill in the art to which the present invention pertains, that components according to the present invention can be substituted, modified, and changed within the scope of the technical spirit of the present invention.

110: thermal imaging camera 120: fire detection unit
130: image processing unit 140: image output unit
200: display device
S10: Thermal image processing step S20: Fire detection step
S30: image processing step S40: image output step

Claims (10)

A thermal imaging camera that senses infrared rays emitted from an object, measures a temperature of the object, sets a pixel value corresponding to the measured temperature, and generates a thermal image;
A fire detection unit for determining that a fire has occurred in the object when a pixel having a pixel value equal to or higher than a preset fire temperature exists in the thermal image;
In the event of the fire, the pixel values of the pixels included in the thermal image are arranged in ascending order according to the size of the pixel values, and the pixel values arranged in the ascending order are arranged from a preset minimum brightness value to a unit brightness change amount. An image processing unit that sequentially resets the pixel reset values to increase; And
A thermal image processing apparatus comprising an image output unit configured to output a corrected image obtained by resetting the pixel values of the thermal image to the pixel reset value.
The method of claim 1, wherein the fire detection unit
And if there is a fire pixel having a pixel value equal to or higher than the fire temperature, and the area in which the fire pixels are grouped is greater than or equal to a preset minimized material area, it is determined that the fire occurs.
delete The method of claim 1 , wherein the image processing unit
And resetting pixels having the same pixel value among the pixel values arranged in ascending order to the same pixel reset value.
The method of claim 1, wherein the image output unit
The corrected image is output by expressing the pixel reset value in n-bit, and the corrected pixel value of each pixel included in the corrected image is

Here, img _normalized is the corrected pixel value, img is the pixel reset value of each pixel, Max (img) is the maximum value of the pixel reset value of the corrected image, and Min (img) is the lowest value of the pixel reset value of the corrected image. Thermal image processing apparatus, characterized in that.
A thermal image capturing step of detecting infrared rays emitted from an object, measuring a temperature of the object, and generating a thermal image by setting a pixel value corresponding to the measured temperature;
A fire detection step of determining that a fire has occurred in the object if a pixel having a pixel value equal to or higher than a preset fire temperature exists in the thermal image;
When it is determined that the fire has occurred, the pixel values of the pixels included in the thermal image are arranged in ascending order according to the size of the pixel values, and the pixel values arranged in the ascending order are arranged in unit brightness from a preset minimum brightness value. An image processing step of sequentially resetting a pixel reset value that increases by a variation amount; And
And an image output step of outputting a correction image obtained by resetting the pixel values of the thermal image to the pixel reset value.
The method of claim 6, wherein the fire detection step
And if there is a fire pixel having a pixel value equal to or higher than the fire temperature, and the area in which the fire pixels are grouped is greater than or equal to a preset minimum material area, it is determined that the fire occurs.
delete The method of claim 6 , wherein the image processing step,
And resetting the same pixel reset values for pixels having the same pixel values among the pixel values arranged in ascending order.
The method of claim 6, wherein the image output step
The corrected image is output by expressing the pixel reset value in n-bit, and the corrected pixel value of each pixel included in the corrected image is

Here, img _normalized is the corrected pixel value, img is the pixel reset value of each pixel, Max (img) is the maximum value of the pixel reset value of the corrected image, and Min (img) is the lowest value of the pixel reset value of the corrected image. Thermal image processing method, characterized in that.

Images