WO2023185594A1

WO2023185594A1 - Data processing method and apparatus

Info

Publication number: WO2023185594A1
Application number: PCT/CN2023/083136
Authority: WO
Inventors: 姜蘅育; 金益如; 郝晓辉
Original assignee: 杭州微影软件有限公司
Priority date: 2022-03-28
Filing date: 2023-03-22
Publication date: 2023-10-05
Also published as: CN114419076A; CN114419076B

Abstract

A data processing method and apparatus. The method comprises: performing detection on a thermal imaging image to obtain a high-temperature target (S11); determining an imaging area of the high-temperature target of the thermal imaging image in a visible light image (S12); determining an overexposure area in the imaging area (S13); and if the proportion of the overexposure area in the imaging area is greater than a preset proportion threshold, executing on the high-temperature target a processing operation corresponding to a reflective point (S14).

Description

A data processing method and device

This application claims priority to the Chinese patent application with the application number 202210308508.2 and the invention title "A data processing method and device" submitted to the China Patent Office on March 28, 2022, the entire content of which is incorporated into this application by reference.

Technical field

The present application relates to the technical field of infrared thermal imaging, and in particular to a data processing method and device.

Background technique

The sun's infrared radiation energy is extremely strong. Sunlight still has extremely high energy after being reflected by objects with smooth surfaces and high reflectivity. When the reflected sunlight directly enters the thermal imaging lens, it will cause a pseudo-high temperature area in the thermal image imaged by the thermal imaging lens. The pseudo-high temperature area can also be called a reflective point, and the imaging grayscale value of the reflective point is much higher than The reflective point represents the imaging grayscale value corresponding to the actual temperature of the object, which seriously affects the accuracy of temperature measurement and high temperature alarm.

Contents of the invention

The purpose of the embodiments of the present application is to provide a data processing method and device to improve the accuracy of temperature measurement and high temperature alarm. The specific technical solutions are as follows:

In a first aspect, embodiments of the present application provide a data processing method, which method includes:

Detect thermal imaging images to obtain high-temperature targets;

Determine the imaging area of the high-temperature target in the thermal imaging image in the visible light image;

Determine the overexposed area in the imaging area;

If the ratio of the overexposed area to the imaging area is greater than the preset ratio threshold, processing operations corresponding to reflective points are performed on the high-temperature target.

Optionally, the attribute information of each pixel in the visible light image includes exposure information;

The step of determining the overexposed area in the imaging area includes:

From the imaging area, at least one target pixel whose exposure information matches the preset overexposure information is determined; a set of the at least one target pixel constitutes an overexposure area.

Optionally, the exposure information includes light intensity, and the preset overexposure information includes a preset light intensity threshold;

The step of determining at least one target pixel whose exposure information matches preset overexposure information from the imaging area includes:

From the imaging area, at least one target pixel whose light intensity is greater than a preset light intensity threshold is determined.

Optionally, the exposure information includes a value of a target color channel that causes the pixel to appear white, the preset overexposure information includes a preset white condition, and the preset white condition indicates that the color of the pixel is white;

From the imaging area, at least one target pixel whose value of the target color channel satisfies the preset white condition is determined.

Optionally, the exposure information includes light intensity and a value of a target color channel that makes the pixel appear white, and the preset overexposure information includes a preset light intensity threshold and a preset white condition, and the preset white condition indicates that the pixel The color is white; the visible light image includes a visible light Bayer image and an RGB image;

The step of determining at least one target pixel whose exposure information matches preset overexposure information from the imaging area. steps, including:

In the imaging area of the high-temperature target in the visible light Bayer image, at least one first pixel whose light intensity is greater than a preset light intensity threshold is determined;

In the imaging area corresponding to the high-temperature target in the RGB image, determine at least one second pixel whose value of the target color channel satisfies the preset white condition;

At least one target pixel is determined based on the at least one first pixel and the at least one second pixel.

Optionally, the step of determining at least one target pixel based on the at least one first pixel and the at least one second pixel includes:

A pixel that coincides with the at least one first pixel and the at least one second pixel is determined as a target pixel.

Optionally, each pixel in the RGB image has grayscale values of three color channels, and the preset white condition is that the grayscale values of the three color channels of the pixel exceed a preset grayscale threshold.

Optionally, the step of determining at least one target pixel whose exposure information matches preset overexposure information from the imaging area includes:

Perform pixel segmentation on the visible light image based on the segmentation mask to obtain a binary image. In the binary image, the pixels whose exposure information in the imaging area matches the preset overexposure information are the first pixel values. The imaging Pixels outside the area are the second pixel value;

The pixel with the first pixel value in the binary image is the target pixel.

Optionally, the step of performing pixel segmentation on the visible light image based on a segmentation mask to obtain a binary image includes:

Set the values of pixels in other areas outside the imaging area in the visible light image as second pixel values;

For each pixel in the imaging area, if the exposure information of the pixel matches the preset overexposure information, the value of the pixel is set to the first pixel value; otherwise, the value of the pixel is set to the second pixel value.

Optionally, the step of determining the imaging area of the high-temperature target in the visible light image in the thermal imaging image includes:

According to the calibration relationship between the thermal imaging image and the visible light image, the imaging area of the high-temperature target in the thermal imaging image in the visible light image is determined.

Optionally, the step of performing processing operations corresponding to reflective points on the high-temperature target includes:

Output prompt information indicating that the high-temperature target is a reflective point; or

Delete the high-temperature target from the high-temperature alarm list, which includes targets to be subjected to high-temperature alarm; or

Add a preset mark to the high temperature target in the high temperature alarm list, the preset mark indicating that the high temperature target is a reflective point; or

Stop executing the high temperature alarm for the high temperature target.

Optionally, the method also includes:

If the ratio of the overexposed area to the imaging area is less than or equal to the preset ratio threshold, a processing operation corresponding to the high-temperature object is performed on the high-temperature target.

In a second aspect, embodiments of the present application provide a data processing device, which includes:

A detection unit is used to detect thermal imaging images and obtain high-temperature targets;

A first determination unit configured to determine the imaging area of the high-temperature target in the thermal imaging image in the visible light image area;

a second determination unit configured to determine the overexposure area in the imaging area;

A first processing unit configured to perform processing operations corresponding to reflective points on the high-temperature target if the ratio of the overexposed area to the imaging area is greater than a preset ratio threshold.

The second determination unit is specifically used for:

Optionally, the second determination unit is specifically used for:

The pixel with the first pixel value in the binary image is the target pixel.

Optionally, the second determination unit is specifically used for:

Optionally, the first determining unit is specifically used for:

Optionally, the first processing unit is specifically used for:

If the ratio of the overexposed area to the imaging area is greater than the preset ratio threshold, prompt information is output, and the prompt information indicates that the high-temperature target is a reflective point; or

If the proportion of the overexposed area to the imaging area is greater than the preset proportion threshold, the high temperature target is deleted from the high temperature alarm list, which includes targets to be subjected to high temperature alarm; or

If the ratio of the overexposed area to the imaging area is greater than the preset ratio threshold, a preset mark is added to the high temperature target in the high temperature alarm list, and the preset mark indicates that the high temperature target is a reflective point. ;or

If the ratio of the overexposed area to the imaging area is greater than the preset ratio threshold, the high temperature alarm for the high temperature target is stopped.

Optionally, the device also includes:

The second processing unit is configured to perform processing operations corresponding to high-temperature objects on the high-temperature target if the ratio of the over-exposed area to the imaging area is less than or equal to the preset ratio threshold.

In a third aspect, embodiments of the present application provide a bispectral thermal imaging device, which includes a memory, a processor, a drive circuit, a thermal imaging image sensor, and a visible light image sensor;

The thermal imaging image sensor is used to collect thermal imaging images;

The visible light image sensor is used to collect visible light images;

The memory is used to store machine-executable instructions that can be executed by the processor;

The processor is configured to be driven by the driving circuit, execute the machine executable instructions, and implement any of the data processing method steps.

In the fourth aspect, embodiments of the present application provide a computer-readable storage medium. A computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, any one of the steps of the data processing method is implemented. .

Embodiments of the present application also provide a computer program product containing instructions that, when run on a computer, cause the computer to execute any of the above-mentioned data processing methods.

Beneficial effects of the embodiments of this application:

In the technical solution provided by the embodiment of the present application, the thermal imaging image is detected to obtain a high-temperature target, and the imaging area of the high-temperature target in the thermal imaging image in the visible light image is determined, and then the overexposure area in the imaging area is determined. If the ratio of the exposure area to the imaging area is greater than the preset ratio threshold, it means that the high-temperature target detected from the thermal imaging image is caused by reflection. At this time, the high-temperature target can be determined to be a reflective point, and the corresponding reflective point is performed on the high-temperature target. The processing operation effectively reduces the temperature measurement error and the probability of high temperature false alarm caused by mistaking the reflective point for the heat source point, thereby improving the accuracy of temperature measurement and high temperature alarm.

Of course, implementing any product or method of the present application does not necessarily require achieving all the above-mentioned advantages simultaneously.

Description of drawings

In order to explain the embodiments of the present application or the technical solutions in the prior art more clearly, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other embodiments can be obtained based on these drawings.

Figure 1 is a schematic flow chart of a first data processing method provided by an embodiment of the present application;

Figure 2 is a schematic flow chart of the second data processing method provided by the embodiment of the present application;

Figure 3 is a third flow diagram of the data processing method provided by the embodiment of the present application;

Figure 4 is a schematic flowchart of the fourth data processing method provided by the embodiment of the present application;

Figure 5 is a schematic flowchart of the fifth data processing method provided by the embodiment of the present application;

Figure 6 is a schematic flowchart of the sixth data processing method provided by the embodiment of the present application;

Figure 7 is a schematic flowchart of the seventh data processing method provided by the embodiment of the present application;

Figure 8 is a schematic structural diagram of a data processing device provided by an embodiment of the present application;

FIG. 9 is a schematic structural diagram of a bispectral thermal imaging device used to implement the data processing method provided by the embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art based on this application fall within the scope of protection of this application.

To facilitate understanding, the words appearing in the embodiments of this application are explained below.

Pixel: It is composed of small squares in the image. These small squares have a clear position and assigned color value. The color and position of the small squares determine the appearance of the image.

The area occupied by the pixel: The small square that represents the pixel at the position of the pixel in the image is the area occupied by the pixel.

Imaging area: The projection area of the target in the image. The projection area includes one or more pixels. That is, the imaging area can be understood as a set of areas occupied by one or more pixels. Simply put, it is the area occupied by one or more pixels. gather.

Overexposure: Due to reasons such as too large aperture and too slow shutter speed, the brightness in the imaging screen is too high and the photo is whitened.

Overexposed area: a collection of one or more pixels that are overexposed.

Dual-spectrum thermal imaging equipment: including thermal imaging lenses and visible light lenses, which can obtain dual-channel image information at the same time, that is, thermal imaging images and visible light images can be obtained at the same time.

Registration can also be called dual-light registration: the process of pixel-level matching of visible light images and thermal imaging images of dual-spectrum thermal imaging equipment through calibration of thermal imaging lenses and visible light lenses and digital image processing.

Visible light Bayer image: The original image output by the visible light image sensor, which has not been processed by ISP (Image Signal Processing).

RGB image: The image obtained by ISP processing the original image output by the visible light image sensor.

Exposure area ratio: the ratio of the area of the overexposed area in the visible light imaging area to the area of the visible light imaging area.

IR (Infrared Radiation, infrared) naked data can also be called thermal imaging image data: the original image data output by a thermal imaging image sensor based on infrared detection technology.

In order to solve the above problems, embodiments of the present application provide a data processing method, which can be applied to bispectral thermal imaging equipment or electronic equipment connected to bispectral thermal imaging equipment, without limitation. For ease of understanding, the following description takes bispectral thermal imaging equipment as the execution subject, and does not serve a limiting purpose.

The data processing method provided by the embodiment of the present application will be described in detail below through specific examples. As shown in Figure 1 As shown, the data processing method includes the following steps:

Step S11: Detect the thermal imaging image to obtain the high-temperature target.

Bispectral thermal imaging equipment monitors the monitoring area and can obtain thermal imaging images and visible light images. In the embodiment of the present application, the dual-spectrum thermal imaging equipment monitors the monitoring area and obtains the thermal imaging image and the visible light image simultaneously as an example for explanation, and does not serve a limiting purpose. For example, thermal imaging images and visible light images can be collected by different devices, as long as the coordinate systems between the two can be calibrated to each other.

In thermal imaging images, the higher the grayscale value of a pixel, the higher the temperature of the object corresponding to the pixel. After the bispectral thermal imaging equipment acquires the thermal imaging image, it detects the thermal imaging image and can obtain one or more pixels whose grayscale value is higher than the specified grayscale threshold in the thermal imaging image. The proportion occupied by this one or more pixels can be obtained. The area is the high temperature target.

In the embodiment of this application, the specified gray-scale threshold can be set according to actual needs. For example, the gray-scale value range of a thermal imaging image is [0, 255], and the specified gray-scale threshold can be 200, 230, or 254, etc.; For another example, the grayscale value range of a thermal imaging image is [0, 16383], and the specified grayscale threshold can be 16000, 16300, or 16382, etc.

The above-mentioned detection methods of high-temperature targets may include, but are not limited to, threshold segmentation methods, Otsu segmentation methods, or deep neural network target detection methods.

Step S12: Determine the imaging area of the high-temperature target in the thermal imaging image in the visible light image.

In the embodiment of the present application, the bispectral thermal imaging device not only acquires the thermal imaging image, but also acquires the visible light image corresponding to the thermal imaging image. After detecting a high-temperature target in a thermal imaging image, the bispectral thermal imaging device can determine the imaging area of the high-temperature target in the visible light image.

In an optional embodiment, in order to make the determination of the imaging area more accurate and thereby improve the accuracy of the data processing method, the coordinate systems between the thermal imaging image and the visible light image can be calibrated to each other. When the bispectral thermal imaging device detects After selecting the high-temperature target, the high-temperature target in the thermal imaging image can be mapped to the visible light image according to the calibration relationship between the thermal imaging image and the visible light image, thereby obtaining the imaging area of the high-temperature target in the visible light image.

In the embodiment of the present application, the above-mentioned calibration relationship may be the relationship between one pixel of the thermal imaging image and one pixel of the visible light image (i.e., one-to-one correspondence), or may be the relationship between one pixel of the thermal imaging image and multiple pixels of the visible light image. The relationship between pixels (ie, one-to-many relationship) may also be the relationship between multiple pixels of the thermal imaging image and one pixel of the visible light image (ie, many-to-one relationship), which is not limited.

The calibration relationship between the thermal imaging image and the visible light image can be recorded in the bispectral thermal imaging device as a bi-optical registration rule. Every time a high-temperature target is acquired, the dual-spectrum thermal imaging equipment can directly run the dual-light registration rule to determine the imaging area of the high-temperature target in the thermal imaging image in the visible light image to improve calculation efficiency.

In the embodiment of the present application, the bispectral thermal imaging equipment determines the imaging area of the high-temperature target in the thermal imaging image in the visible light image based on the calibration relationship between the thermal imaging image and the visible light image. The imaging area obtained through this calibration relationship is more Accurate, thus improving the accuracy of the data processing method.

Step S13: Determine the overexposure area in the imaging area.

After the bispectral thermal imaging device determines the imaging area of the high-temperature target in the visible light image, it determines the overexposed area in the imaging area.

Step S14, if the ratio of the overexposed area to the imaging area is greater than the preset ratio threshold, a processing operation corresponding to the reflective point is performed on the high-temperature target.

In the embodiment of the present application, the ratio of the overexposed area to the imaging area can be measured based on the number or area of pixels.

Optionally, the dual-spectrum thermal imaging device can calculate the area of the imaging area in the visible light image, and calculate the imaging area The area of the overexposed area in the domain is calculated, and then the exposure area ratio is calculated, that is, the ratio of the area of the above overexposed area to the area of the above imaging area is calculated, and the exposure area ratio is used as the proportion of the overexposed area to the imaging area.

Optionally, the bispectral thermal imaging device can also calculate the first number of pixels included in the imaging area of the visible light image, and calculate the second number of pixels included in the overexposed area of the imaging area, and then calculate the exposure number ratio, That is, the ratio of the above-mentioned first quantity and the second quantity is calculated, and the ratio of the exposure quantity is used as the ratio of the overexposed area to the imaging area.

Bispectral thermal imaging equipment can also use other methods to calculate the proportion of the overexposed area to the imaging area, which is not limited.

In the embodiment of the present application, the bispectral thermal imaging device can set a proportional threshold in advance, that is, a preset proportional threshold. The preset proportion threshold can be limited according to actual needs, and there is no specific limit on this.

The dual-spectrum thermal imaging device determines whether the proportion of the overexposed area to the imaging area is greater than the preset proportion threshold. If the ratio of the overexposed area to the imaging area is greater than the preset ratio threshold, it means that the overexposed area occupies a larger proportion of the imaging area. The high-temperature target detected from the thermal imaging image is due to reflection. At this time, it can be determined The high-temperature target is a reflective point, and processing operations corresponding to the reflective points are performed on the high-temperature target. If the ratio of the overexposed area to the imaging area is less than or equal to the preset ratio threshold, it means that the high-temperature target detected in the thermal imaging image is caused by the temperature of the object corresponding to the high-temperature target. In other words, there is a high temperature in the monitoring area. Objects, dual-spectrum thermal imaging equipment can perform processing operations corresponding to high-temperature objects on the high-temperature targets to eliminate risks caused by high temperatures in a timely manner.

In an optional embodiment, if the proportion of the overexposed area to the imaging area is greater than the preset ratio threshold, the dual-spectrum thermal imaging device performs processing operations corresponding to reflective points on the high-temperature target, where the processing operations corresponding to the reflective points may include Any one or more of the following actions:

1) Output prompt information, which indicates that the high-temperature target is a reflective point.

For example, after determining that the proportion of the overexposed area to the imaging area is greater than the preset proportion threshold, the bispectral thermal imaging device can output the above prompt information in the form of a pop-up window, or can send the above prompt information to the connected terminal or server to prompt The user's high temperature target is a reflective point.

2) Delete high-temperature targets from the high-temperature alarm list, which includes targets to be subjected to high-temperature alarms.

In the embodiment of the present application, the high temperature alarm list includes at least one target to be subjected to high temperature alarm. The bispectral thermal imaging device can add the detected high temperature target to the high temperature alarm list, and subsequently can add the high temperature target included in the high temperature alarm list. Enable high temperature alarm.

For a high-temperature target, after adding the high-temperature target to the high-temperature alarm list, if the dual-spectrum thermal imaging equipment determines that the proportion of the overexposed area to the imaging area is greater than the preset proportion threshold, the dual-spectrum thermal imaging equipment can remove the high-temperature target from high temperature. Delete from the alarm list, that is, the dual-spectrum thermal imaging device refuses to execute high-temperature alarms for the high-temperature target.

3) Add a preset mark to the high temperature target in the high temperature alarm list. The preset mark indicates that the high temperature target is a reflective point.

After the dual-spectrum thermal imaging device determines that the proportion of the overexposed area to the imaging area is greater than the preset ratio threshold, it can regard the high-temperature target as a reflective point and add a preset mark indicating that the high-temperature target is a reflective point. Subsequently, the dual-spectrum thermal imaging equipment will no longer perform high-temperature alarms for the high-temperature target based on the preset identification.

The default logo can be represented by letters or numbers. For example, bispectral thermal imaging equipment can use the letter "F" or "S" to represent the preset logo, and bispectral thermal imaging equipment can also use the letters "1" or "0" to represent the preset logo.

4) Stop executing high temperature alarms for high temperature targets.

In the embodiment of the present application, the dual-spectrum thermal imaging equipment can add the above steps S11 to step S14 on the basis of the original high temperature alarm, that is, after detecting the high temperature target and before executing the high temperature alarm for the high temperature target, the above steps can be added. Step S11-Step S14. In this case, if the dual-spectrum thermal imaging equipment determines that the proportion of the overexposed area to the imaging area is greater than the preset proportion threshold, the dual-spectrum thermal imaging equipment can stop executing the high-temperature alarm for high-temperature targets and end the high-temperature alarm. deal with.

In the embodiment of the present application, the processing operation corresponding to the reflective point can also be implemented in other ways. For example, the processing operation corresponding to the reflective point can also be empty. In this case, the bispectral thermal imaging device performs the processing operation corresponding to the reflective point on the high-temperature target. The processing operation means no processing is done.

In an optional embodiment, if the ratio of the overexposed area to the imaging area is less than or equal to the preset ratio threshold, processing operations corresponding to the high-temperature object are performed on the high-temperature target. Among them, performing processing operations corresponding to high-temperature objects on high-temperature targets may include but is not limited to any one or more of the following operations:

Add the high temperature target to the high temperature alarm list;

Output a high-temperature alarm for the high-temperature target, such as outputting prompt information including the high-temperature target, controlling the flashing of the alarm light, or controlling a voice output device (such as a speaker) to output voice information indicating the presence of a high-temperature object, etc.;

Transmit the identification of the high-temperature target to the designated terminal, etc.

In one embodiment of the present application, the attribute information of each pixel in the visible light image includes exposure information, which may include but is not limited to light intensity, values of each color channel, brightness, luminous flux, etc. In this case, the embodiment of the present application also provides a data processing method, as shown in Figure 2. The method may include steps S21 to S24. Steps S21, S22 and S24 are in conjunction with the above-mentioned steps S11, S12 and S24. Step S14 is the same and will not be described again here. Step S23 is an implementable manner of step S13.

Step S23: From the imaging area, determine at least one target pixel whose exposure information matches the preset overexposure information. The set of at least one target pixel constitutes an overexposure area.

In the embodiment of the present application, the exposure information of each pixel in the visible light image may be obtained by detecting each pixel with a bispectral thermal imaging device, or may be obtained from other equipment, which is not limited.

Bispectral thermal imaging equipment can preset the overexposure information of pixels, that is, preset overexposure information. The preset overexposure information can indicate that the pixel is overexposed. The preset overexposure information can be limited according to actual needs, and there is no specific limit on this.

For each pixel in the imaging area of the visible light image, the bispectral thermal imaging device compares the exposure information of the pixel with the preset overexposure information. If the exposure information of the pixel matches the preset overexposure information, the bispectral thermal imaging device The imaging device may determine that the pixel is an overexposed pixel and use the pixel as a target pixel. The number of target pixels in the imaging area is one or more.

The matching conditions between the exposure information of the above pixels and the preset overexposure information can be adjusted according to the difference between the overexposure information and the preset overexposure information. For example, the exposure information is light intensity, and the preset overexposure information is the preset light intensity threshold. Then the matching condition between the exposure information of the pixel and the preset overexposure information is: the light intensity of the pixel is greater than or equal to the preset light intensity threshold; for another example, if the exposure information is brightness and the preset overexposure information is the preset brightness threshold, then the pixel's The matching conditions between exposure information and preset overexposure information are: The brightness of the pixel is greater than or equal to the preset brightness threshold.

After obtaining at least one target pixel, the bispectral thermal imaging device can use the area formed by the set of these target pixels as the overexposed area.

In the technical solution provided by the embodiment of the present application, the bispectral thermal imaging device can determine the target pixel in the imaging image whose exposure information matches the preset overexposure information, thereby obtaining the overexposure area. In this way, the overexposed area can be determined from the perspective of pixels, which improves the accuracy of the overexposed area, thereby improving the accuracy of the data processing method.

In one embodiment of the present application, the exposure information includes light intensity, and the preset overexposure information includes a preset light intensity threshold. In this case, the embodiment of the present application also provides a data processing method, as shown in Figure 3. The method may include steps S31 to S34. Steps S31, S32 and S34 are combined with the above-mentioned steps S21, S22 and S34. Step S24 is the same and will not be described again here. Step S33 is an implementable manner of step S23.

Step S33: Determine at least one target pixel whose light intensity is greater than a preset light intensity threshold from the imaging area, and a set of at least one target pixel constitutes an overexposure area.

In the embodiment of the present application, the light intensity of each pixel in the visible light image may be obtained by detecting each pixel with a bispectral thermal imaging device, or may be obtained from other equipment, which is not limited.

Bispectral thermal imaging equipment can pre-set a light intensity threshold, that is, a preset light intensity threshold. The preset light intensity threshold can indicate that the pixel is in a light intensity saturation state. The preset light intensity threshold can be limited according to actual needs, and there is no specific limit on this.

For each pixel in the imaging area of the visible light image, the bispectral thermal imaging device compares the light intensity of the pixel with the preset light intensity threshold. If the light intensity of the pixel is greater than the preset light intensity threshold, that is, the pixel's light intensity is If the light intensity matches the preset light intensity threshold, it means that the pixel is in a light intensity saturation state. The dual-spectrum thermal imaging device can determine that the pixel is an overexposed pixel and that the pixel is a target pixel.

In the technical solution provided by the embodiment of the present application, the dual-spectrum thermal imaging device can determine at least one target pixel whose light intensity is greater than the preset light intensity threshold from the imaging area, thereby obtaining the overexposed area. In this way, the dual-spectrum thermal imaging equipment can determine the overexposed area from the perspective of light intensity, which increases the applicability of the data processing method.

In one embodiment of the present application, the exposure information includes a value of a target color channel that causes the pixel to appear white, and the preset overexposure information includes a preset white condition, and the preset white condition indicates that the color of the pixel is white. White is a form of overexposure of pixels, and visible light images in different color spaces have different target color channels that make pixels appear white. For example, the values of the R color channel, the G color channel and the B color channel of a pixel in an RGB image work together to make the pixel appear white, then the target color channel in the RGB image can include the R color channel, G color channel and one or more color channels in the B color channel; the value of the S color channel of the pixel in the HSV image and the value of the V color channel work together to make the pixel appear white, then the target color channel in the HSV image can include the S color channel and one or more color channels in the V color channel; the value of the L color channel of the pixel in the HLV image acts to make the pixel appear white, then the target color channel of the HLV image can include the L color channel, etc.

In this case, the embodiment of the present application also provides a data processing method, as shown in Figure 4. The method may include steps S41 to S44. Steps S41, S42 and S44 are combined with the above-mentioned steps S21, S22 and S22. Step S24 is the same and will not be described again here. Step S43 is an implementable manner of step S23.

Step S43: From the imaging area, determine at least one target pixel whose value of the target color channel satisfies the preset white condition. The set of at least one target pixel constitutes an overexposure area.

In the embodiment of the present application, the bispectral thermal imaging device can preset the white condition, that is, the preset white condition. Default The white condition indicates that the color of the pixel is white. The preset white condition can be limited according to actual needs and is not specifically limited.

For each pixel in the imaging area of the visible light image, the bispectral thermal imaging device can match the value of the target color channel of the pixel with the preset white condition. If the value of the target color channel meets the preset white condition, it means The color of this pixel is white, and this pixel is the target pixel.

In the technical solution provided by the embodiment of the present application, the bispectral thermal imaging device can determine at least one target pixel whose value of the target color channel satisfies the preset white condition from the imaging area, thereby obtaining the overexposed area. In this way, the bispectral thermal imaging device can determine the overexposed area from the perspective of color, which increases the applicability of the data processing method provided by the embodiments of the present application.

In one embodiment of the present application, the exposure information includes light intensity and a value of a target color channel that makes the pixel appear white, and the preset overexposure information includes a preset light intensity threshold and a preset white condition, and the preset white condition indicates the pixel's The color is white; visible light images include visible light Bayer images and RGB images.

In this case, the embodiment of the present application also provides a data processing method, as shown in Figure 5. The method may include steps S51 to S56. Steps S51, S52 and S56 are combined with the above-mentioned steps S21, S22 and S22. Step S24 is the same and will not be described again here. Step S53-Step S55 is an implementable manner of step S23.

Step S53: In the imaging area of the high-temperature target in the visible light Bayer image, determine at least one first pixel whose light intensity is greater than the preset light intensity threshold.

In the embodiment of the present application, the visible light image includes a visible light Bayer image, and accordingly, the imaging area in the visible light image includes the imaging area of the high-temperature target in the visible light Bayer image. Step S53 is similar to step S33 and will not be described again.

The visible light Bayer image contains rich light intensity information. Using the visible light Bayer image can effectively improve the accuracy of determining the first pixel, thereby improving the accuracy of determining the target pixel.

Step S54: In the imaging area corresponding to the high-temperature target in the RGB image, determine at least one second pixel whose value of the target color channel satisfies the preset white condition.

In the embodiment of the present application, the visible light image includes an RGB image, and accordingly, the imaging area in the visible light image includes the imaging area of the high-temperature target in the RGB image. Step S54 is similar to step S43 and will not be described again here.

The color information in RGB images is more accurate. Using RGB images can effectively improve the accuracy of determining the second pixel, thereby improving the accuracy of determining the target pixel.

Each pixel in the RGB image has a grayscale value of three color channels. In order to further improve the accuracy of the determined second pixel, when the visible light image uses an RGB image, the preset white condition is the grayscale value of the three color channels of the pixel. The values exceed the preset grayscale threshold. That is, the bispectral thermal imaging device determines at least one second pixel whose grayscale values of the three color channels exceed the preset grayscale threshold in the imaging area corresponding to the high-temperature target in the RGB image.

In the embodiments of this application, the preset grayscale threshold can be set according to actual needs. For example, the grayscale value range of a thermal imaging image is [0, 255], and the preset grayscale threshold can be 200, 230, or 254, etc. ; For another example, the grayscale value range of a thermal imaging image is [0, 16383], and the preset grayscale threshold can be 16000, 16300, or 16382, etc.

In the embodiment of the present application, the execution order of step S53 and step S54 is not limited.

Step S55: Determine at least one target pixel based on at least one first pixel and at least one second pixel, and a set of at least one target pixel constitutes an overexposure area.

In the embodiment of the present application, the bispectral thermal imaging device obtains the first pixel and RGB in the visible Bayer image. After the second pixel in the image, the first pixel and the second pixel are considered together to determine the target pixel in the imaging area.

Optionally, the above step S55 may be: the bispectral thermal imaging device determines a pixel that coincides with at least one first pixel and at least one second pixel as the target pixel, that is, determines from the imaging area that it is both the first pixel and the second pixel. The pixel of the pixel serves as the target pixel, that is, the light intensity of the target pixel is greater than the preset light intensity threshold, and the value of the target color channel of the target pixel satisfies the preset white condition. This effectively improves the accuracy of high temperature alarms.

Optionally, the above step S55 may be: the bispectral thermal imaging device determines a set of at least one first pixel and at least one second pixel as the target pixel, that is, both the first pixel and the second pixel are used as the target pixel. This effectively improves the safety of high temperature alarms.

In the technical solution provided by the embodiments of this application, when determining the over-exposed area, the dual-spectrum thermal imaging equipment comprehensively considers the light intensity of the pixel and the prior knowledge of the target color channel, thereby improving the accuracy of the over-exposed area and thereby improving the accuracy of the over-exposed area. Accuracy of high temperature alarm.

In one embodiment of the present application, the embodiment of the present application also provides a data processing method, as shown in Figure 6. The method may include steps S61-step S64, steps S61, step S62 and step S64 together with the above-mentioned step S21. , step S22 and step S24 are the same and will not be described again here. Step S63 is an implementable manner of step S23.

Step S63, perform pixel segmentation on the visible light image based on the segmentation mask to obtain a binary image. In the binary image, the pixels whose exposure information in the imaging area matches the preset overexposure information are the first pixel values, and the pixels outside the imaging area are The second pixel value, the pixel with the first pixel value in the binary image is the target pixel, and a set of at least one target pixel constitutes an overexposed area.

In this embodiment of the present application, the segmentation mask includes a first pixel value and a second pixel value, and the first pixel value and the second pixel value can be set according to actual needs. For example, the first pixel value is 0 and the second pixel value is 1, or the first pixel value is 1 and the second pixel value is 0, etc. Based on the segmentation mask, the bispectral thermal imaging device sets the pixel value of the pixel whose exposure information in the imaging area in the visible light image matches the preset overexposure information as the first pixel value; sets the pixel value of the other pixels as the second pixel value. Pixel values. At this time, the bispectral thermal imaging equipment can obtain a binary image.

In an optional embodiment, for each pixel in the visible light image, the bispectral thermal imaging device can determine whether the exposure information of the pixel matches the preset overexposure information, and determine whether the pixel is included in the imaging area; if If both are yes, then the pixel value of the pixel is set to the first pixel value; otherwise, the pixel value of the pixel is set to the second pixel value.

In another optional embodiment, after determining the imaging area, the bispectral thermal imaging device can directly set the pixel value of the pixels in other areas outside the imaging area to the second pixel value for each pixel in the imaging area. , the bispectral thermal imaging device can determine whether the exposure information of the pixel matches the preset overexposure information; if so, the pixel value of the pixel is set to the first pixel value; otherwise, the pixel value of the pixel is set to the second pixel value. Pixel values. In this embodiment, the dual-spectrum thermal imaging device only needs to determine whether the exposure information of the pixels in the imaging area matches the preset overexposure information, and does not need to judge the pixels in other areas, which greatly improves the accuracy of determining overexposure. The efficiency of the area improves the calculation efficiency of the ratio of the overexposed area to the imaging area; in addition, using this binary image for reflective point identification can effectively reduce the impact of background factors on reflective point identification and improve the accuracy of reflective point identification. , thereby improving the accuracy of high temperature alarms.

In the technical solution provided by the embodiments of this application, the bispectral thermal imaging equipment obtains a binary image based on the segmentation mask, uses the binary image to determine the overexposed area, and uses the binary image to identify reflective points, which can effectively reduce the impact of background factors on The influence of reflective point recognition improves the accuracy of reflective point recognition, thereby improving the accuracy of high temperature alarms.

The data processing method provided by the embodiment of the present application will be described in detail below with reference to the flow chart of the data processing method shown in Figure 7 . In this method, the dual-spectrum thermal imaging equipment collects IR bare data and visible light Bayer images. The optical Bayer image is processed by ISP to obtain an RGB image.

Step S71, detect high-temperature targets.

Bispectral thermal imaging equipment detects high-temperature targets based on IR bare data. For the specific implementation process of step S71, please refer to the relevant description of step S11 above.

Step S72: Calculate the coordinates of the visible light exposure search area.

Among them, the visible light exposure retrieval area is the imaging area of the high-temperature target in the visible light image. The bispectral thermal imaging equipment obtains the imaging position (i.e., imaging area) of the high-temperature target in the visible light image based on the high-temperature target in the thermal imaging image and the visible light image (including the visible light Bayer image and the RGB image). For the specific implementation process of step S72, please refer to the relevant description of step S12 above.

The imaging area determined here is the subsequent search range.

Step S73: Search the light intensity saturation area.

The bispectral thermal imaging device searches the visible light exposure search area in the visible light Bayer image, and obtains at least one first pixel with a light intensity greater than a preset light intensity threshold. The bispectral thermal imaging device uses the area composed of a set of at least one first pixel as the light intensity. saturated area. For the specific implementation process of step S73, please refer to the above-mentioned FIG. 3 and the relevant description of step S53.

Step S74: Retrieve white areas.

Among them, the white area is the area where the grayscale values of the three color channels (i.e., R color channel, G color channel, and B color channel) in the RGB image have all reached saturation, that is, the grayscale values of the three color channels exceed the preset grayscale. A collection of pixels with a threshold value. The bispectral thermal imaging device searches the visible light exposure retrieval area in the RGB image, and obtains at least one second pixel whose grayscale value of the three color channels exceeds the preset grayscale threshold. as a white area. For the specific implementation process of step S74, please refer to the above-mentioned FIG. 4 and the related description of step S54.

Step S75: Combine the white area and the light intensity saturated area.

The dual-spectrum thermal imaging device combines the white area and the light intensity saturated area to obtain the overexposed area, that is, the overexposed area is determined based on the second pixel that constitutes the white area and the first pixel that constitutes the light intensity saturated area. For the specific implementation process of step S75, please refer to the relevant description of step S55 above.

Step S76: Calculate the exposure area ratio.

The bispectral thermal imaging equipment obtains a binary image based on the segmentation mask, determines the area of the overexposed area based on the binary image, and retrieves the area of the area based on the visible light exposure (that is, the area of the imaging area of the high-temperature target in the visible light image) and the overexposed area. The area of the region, the exposure area ratio is calculated. For the specific implementation process of step S76, please refer to the relevant descriptions of the above-mentioned steps S14 and step S63.

Step S77, detect whether the exposure area ratio is greater than a preset ratio threshold. If yes, step S78 is executed to perform processing operations corresponding to the reflective points on the high-temperature target; if not, step S79 is executed to output a high-temperature alarm.

The bispectral thermal imaging device detects whether the calculated exposure area ratio is greater than the preset ratio threshold. If the exposure area ratio is greater than the preset ratio threshold, it can be determined that the high-temperature target is a reflective point, and the bispectral thermal imaging device executes step S78, that is, , the bispectral thermal imaging equipment performs processing operations corresponding to the reflective points of the high-temperature target; if the exposure area ratio is less than or equal to the preset ratio threshold, it means that the high-temperature target is detected from the thermal imaging image due to the object corresponding to the high-temperature target itself. Caused by temperature, the dual-spectrum thermal imaging device executes step S79 and outputs a high temperature alarm. For the specific implementation process of steps S77 to S79, please refer to the relevant description of step S14 above.

In the embodiment of the present application, when the ratio of the overexposed area to the imaging area is less than or equal to the preset ratio threshold, Figure 7 only shows one processing operation corresponding to the high-temperature object, that is, outputting a high-temperature alarm, and corresponding to the high-temperature object. The processing operation may also include other operations, such as the description in step S14, adding the high-temperature target to the high-temperature alarm list, transmitting the identification of the high-temperature target to the designated terminal, etc., which are not limited.

The description of the above steps S71 to S79 is relatively simple. For details, please refer to the relevant descriptions of the above FIGS. 1 to 6 and will not be described again here.

Corresponding to the above data processing method, embodiments of the present application provide a data processing device, as shown in Figure 8. The device may include:

The detection unit 81 is used to detect thermal imaging images to obtain high-temperature targets;

The first determination unit 82 is used to determine the imaging area of the high-temperature target in the thermal imaging image in the visible light image;

The second determination unit 83 is used to determine the overexposure area in the imaging area;

The first processing unit 84 is configured to perform processing operations corresponding to reflective points on the high-temperature target if the ratio of the overexposed area to the imaging area is greater than the preset ratio threshold.

The second determination unit 83 can be specifically used for:

From the imaging area, at least one target pixel whose exposure information matches the preset overexposure information is determined; a set of at least one target pixel constitutes an overexposure area.

The second determination unit 83 can be specifically used for:

Optionally, the exposure information includes the value of the target color channel that makes the pixel appear white, and the preset overexposure information includes a preset white condition, and the preset white condition indicates that the color of the pixel is white;

The second determination unit 83 can be specifically used for:

Optionally, the exposure information includes light intensity and the value of the target color channel that makes the pixel appear white. The preset overexposure information includes a preset light intensity threshold and a preset white condition. The preset white condition indicates that the color of the pixel is white; visible light Images include visible light Bayer images and RGB images;

The second determination unit 83 can be specifically used for:

In the imaging area of the high-temperature target in the visible Bayer image, determine at least one first pixel whose light intensity is greater than a preset light intensity threshold;

At least one target pixel is determined based on at least one first pixel and at least one second pixel.

Optional, the second determination unit 83 can be specifically used for:

A pixel in which at least one first pixel coincides with at least one second pixel is determined as a target pixel.

Optionally, each pixel in the RGB image has grayscale values of three color channels, and the preset white condition is that the grayscale values of the three color channels of the pixel exceed the preset grayscale threshold.

Optional, the second determination unit 83 can be specifically used for:

Based on the segmentation mask, the visible light image is segmented into pixels to obtain a binary image. The pixels in the imaging area in the binary image are The pixels whose exposure information matches the preset overexposure information are the first pixel values, and the pixels outside the imaging area are the second pixel values;

The pixel with the first pixel value in the binary image is the target pixel.

Optional, the second determination unit 83 can be specifically used for:

Set the value of the pixel in other areas outside the imaging area in the visible light image as the second pixel value;

Optionally, the first determining unit 82 can be specifically used for:

Optionally, the first processing unit 84 can be specifically used for:

If the proportion of the overexposed area to the imaging area is greater than the preset ratio threshold, a prompt message is output, indicating that the high-temperature target is a reflective point; or

If the proportion of the overexposed area to the imaging area is greater than the preset ratio threshold, the high-temperature target is deleted from the high-temperature alarm list, which includes targets to be subjected to high-temperature alarm; or

If the proportion of the overexposed area to the imaging area is greater than the preset ratio threshold, a preset mark is added to the high temperature target in the high temperature alarm list, and the preset mark indicates that the high temperature target is a reflective point; or

If the ratio of the overexposed area to the imaging area is greater than the preset ratio threshold, the high-temperature alarm for high-temperature targets will be stopped.

Optionally, the above data processing device may also include:

The second processing unit is configured to perform processing operations corresponding to the high-temperature object on the high-temperature target if the ratio of the overexposed area to the imaging area is less than or equal to the preset ratio threshold.

Corresponding to the above data processing method, embodiments of the present application also provide a dual-spectrum thermal imaging device, as shown in Figure 9, including a memory 91, a processor 92, a drive circuit 93, a thermal imaging image sensor 94, and a visible light image sensor 95 ;

Thermal imaging image sensor 94 is used to collect thermal imaging images;

Visible light image sensor 95, used to collect visible light images;

Memory 91 for storing machine-executable instructions that can be executed by the processor;

The processor 92 is configured to be driven by the driving circuit 93 to execute machine executable instructions to implement the steps of any of the above data processing methods.

In the embodiment of the present application, the bispectral thermal imaging device may also include an alarm, which is used to output a high temperature alarm. For example, when the processor 92 determines that the ratio of the overexposed area to the imaging area is less than or equal to a preset ratio threshold, the processor 92 generates a high temperature alarm and outputs it through an alarm.

The memory may include Random Access Memory (RAM) or non-volatile memory. Non-Volatile Memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located far away from the aforementioned processor.

The processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (Network Processor, NP), etc.; it can also be a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (ASIC) Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

In yet another embodiment provided by the present application, a computer-readable storage medium is also provided. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the steps of any of the above data processing methods are implemented. .

In yet another embodiment provided by this application, a computer program product containing instructions is also provided, which when run on a computer causes the computer to perform the steps of any of the data processing methods in the above embodiments.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, e.g., the computer instructions may be transferred from a website, computer, server, or data center Transmission to another website, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more available media integrated. The available media may be magnetic media (eg, floppy disk, hard disk, tape), optical media (eg, DVD), or Solid State Disk (SSD), etc.

It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that these entities or operations are mutually exclusive. any such actual relationship or sequence exists between them. Furthermore, the terms "comprises," "comprises," or any other variations thereof are intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements, but also those not expressly listed other elements, or elements inherent to the process, method, article or equipment. Without further limitation, an element defined by the statement "comprises a..." does not exclude the presence of additional identical elements in a process, method, article, or apparatus that includes the stated element.

Each embodiment in this specification is described in a related manner. The same and similar parts between the various embodiments can be referred to each other. Each embodiment focuses on its differences from other embodiments. In particular, the device, bispectral thermal imaging equipment, storage medium and computer program product embodiments are described simply because they are basically similar to the method embodiments. For relevant details, please refer to the partial description of the method embodiments.

The above descriptions are only preferred embodiments of the present application and are not intended to limit the protection scope of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this application are included in the protection scope of this application.

Claims

A data processing method, characterized in that the method includes:

Detect thermal imaging images to obtain high-temperature targets;

Determine the imaging area of the high-temperature target in the thermal imaging image in the visible light image;

Determine the overexposed area in the imaging area;

If the ratio of the overexposed area to the imaging area is greater than the preset ratio threshold, processing operations corresponding to reflective points are performed on the high-temperature target.
The method according to claim 1, wherein the attribute information of each pixel in the visible light image includes exposure information;

The step of determining the overexposed area in the imaging area includes:

From the imaging area, at least one target pixel whose exposure information matches the preset overexposure information is determined; a set of the at least one target pixel constitutes an overexposure area.
The method of claim 2, wherein the exposure information includes light intensity, and the preset overexposure information includes a preset light intensity threshold;

The step of determining at least one target pixel whose exposure information matches preset overexposure information from the imaging area includes:

From the imaging area, at least one target pixel whose light intensity is greater than a preset light intensity threshold is determined.
The method of claim 2, wherein the exposure information includes a value of a target color channel that causes the pixel to appear white, the preset overexposure information includes a preset white condition, and the preset white condition indicates that the pixel The color is white;

The step of determining at least one target pixel whose exposure information matches preset overexposure information from the imaging area includes:

From the imaging area, at least one target pixel whose value of the target color channel satisfies the preset white condition is determined.
The method of claim 2, wherein the exposure information includes light intensity and a value of a target color channel that makes the pixel appear white, and the preset overexposure information includes a preset light intensity threshold and a preset white condition. , the preset white condition indicates that the color of the pixel is white; the visible light image includes a visible light Bayer image and an RGB image;

The step of determining at least one target pixel whose exposure information matches preset overexposure information from the imaging area includes:

In the imaging area of the high-temperature target in the visible light Bayer image, at least one first pixel whose light intensity is greater than a preset light intensity threshold is determined;

In the imaging area corresponding to the high-temperature target in the RGB image, determine at least one second pixel whose value of the target color channel satisfies the preset white condition;

At least one target pixel is determined based on the at least one first pixel and the at least one second pixel.
The method of claim 5, wherein the step of determining at least one target pixel based on the at least one first pixel and the at least one second pixel includes:

A pixel that coincides with the at least one first pixel and the at least one second pixel is determined as a target pixel.
The method according to claim 5, characterized in that each pixel in the RGB image has a grayscale value of three color channels, and the preset white condition is that the grayscale value of the three color channels of the pixel exceeds a preset value. Set the grayscale threshold.
The method of claim 2, wherein the step of determining at least one target pixel whose exposure information matches preset overexposure information from the imaging area includes:

Perform pixel segmentation on the visible light image based on the segmentation mask to obtain a binary image. In the binary image, the pixels whose exposure information in the imaging area matches the preset overexposure information are the first pixel values. The imaging Pixels outside the area are the second pixel value;

The pixel with the first pixel value in the binary image is the target pixel.
The method according to claim 8, characterized in that the step of performing pixel segmentation on the visible light image based on a segmentation mask to obtain a binary image includes:

Set the values of pixels in other areas outside the imaging area in the visible light image as second pixel values;

For each pixel in the imaging area, if the exposure information of the pixel matches the preset overexposure information, the value of the pixel is set to the first pixel value; otherwise, the value of the pixel is set to the second pixel value.
The method according to claim 1, wherein the step of determining the imaging area of the high-temperature target in the thermal imaging image in the visible light image includes:

According to the calibration relationship between the thermal imaging image and the visible light image, the imaging area of the high-temperature target in the thermal imaging image in the visible light image is determined.
The method of claim 1, wherein the step of performing processing operations corresponding to reflective points on the high-temperature target includes:

Output prompt information indicating that the high-temperature target is a reflective point; or

Delete the high-temperature target from the high-temperature alarm list, which includes targets to be subjected to high-temperature alarm; or

Add a preset mark to the high temperature target in the high temperature alarm list, the preset mark indicating that the high temperature target is a reflective point; or

Stop executing the high temperature alarm for the high temperature target.
The method according to any one of claims 1-11, characterized in that the method further includes:

If the ratio of the overexposed area to the imaging area is less than or equal to the preset ratio threshold, a processing operation corresponding to the high-temperature object is performed on the high-temperature target.
A data processing device, characterized in that the device includes:

A detection unit is used to detect thermal imaging images and obtain high-temperature targets;

A first determination unit configured to determine the imaging area of the high-temperature target in the thermal imaging image in the visible light image;

a second determination unit configured to determine the overexposure area in the imaging area;

A first processing unit configured to perform processing operations corresponding to reflective points on the high-temperature target if the ratio of the overexposed area to the imaging area is greater than a preset ratio threshold.
The device according to claim 13, wherein the attribute information of each pixel in the visible light image includes exposure information;

The second determination unit is specifically configured to: determine at least one target pixel whose exposure information matches preset overexposure information from the imaging area; a set of the at least one target pixel constitutes an overexposure area.
The device according to claim 14, wherein the exposure information includes light intensity, and the preset overexposure information includes a preset light intensity threshold;

The second determination unit is specifically configured to determine at least one target pixel whose light intensity is greater than a preset light intensity threshold from the imaging area.
The device of claim 14, wherein the exposure information includes a value of a target color channel that causes the pixel to appear white, the preset overexposure information includes a preset white condition, and the preset white condition indicates that the pixel The color is white;

The second determination unit is specifically configured to determine at least one target pixel whose value of the target color channel satisfies the preset white condition from the imaging area.
The device according to claim 14, wherein the exposure information includes light intensity and a value of a target color channel that makes the pixel appear white, and the preset overexposure information includes a preset light intensity threshold and a preset white condition. , the preset white condition indicates that the color of the pixel is white; the visible light image includes a visible light Bayer image and an RGB image;

The second determination unit is specifically configured to: determine at least one first pixel whose light intensity is greater than a preset light intensity threshold in the imaging area of the high-temperature target in the visible Bayer image; and In the imaging area corresponding to the high-temperature target, determine at least one second pixel whose value of the target color channel satisfies the preset white condition; determine based on the at least one first pixel and the at least one second pixel. At least one target pixel.
The device according to claim 17, wherein the second determining unit is specifically configured to determine a pixel that coincides with the at least one first pixel and the at least one second pixel as the target pixel.
The device according to claim 17, characterized in that each pixel in the RGB image has a grayscale value of three color channels, and the preset white condition is that the grayscale value of the three color channels of the pixel exceeds a preset value. Set the grayscale threshold.
The device according to claim 14, characterized in that the second determination unit is specifically configured to perform pixel segmentation on the visible light image based on a segmentation mask to obtain a binary image, and the binary image is The pixels whose exposure information in the imaging area matches the preset overexposure information are the first pixel values, and the pixels outside the imaging area are the second pixel values; the pixels with the first pixel value in the binary image are the target pixels.
The device according to claim 20, wherein the second determination unit is specifically configured to: set values of pixels in other areas outside the imaging area in the visible light image as second pixel values; for For each pixel in the imaging area, if the exposure information of the pixel matches the preset overexposure information, the value of the pixel is set to the first pixel value; otherwise, the value of the pixel is set to the second pixel value. .
The device according to claim 13, wherein the first determination unit is specifically configured to determine the high temperature in the thermal imaging image according to the calibration relationship between the thermal imaging image and the visible light image. The imaged area of the target in the visible light image.
The device according to claim 13, characterized in that the first processing unit is specifically used for:

If the ratio of the overexposed area to the imaging area is greater than the preset ratio threshold, prompt information is output, and the prompt information indicates that the high-temperature target is a reflective point; or

If the proportion of the overexposed area to the imaging area is greater than the preset proportion threshold, the high temperature target is deleted from the high temperature alarm list, which includes targets to be subjected to high temperature alarm; or

If the ratio of the overexposed area to the imaging area is greater than the preset ratio threshold, a preset mark is added to the high temperature target in the high temperature alarm list, and the preset mark indicates that the high temperature target is a reflective point. ;or

If the ratio of the overexposed area to the imaging area is greater than the preset ratio threshold, the high temperature alarm for the high temperature target is stopped.
The device according to any one of claims 13-23, characterized in that the device further includes:

The second processing unit is configured to perform processing operations corresponding to high-temperature objects on the high-temperature target if the ratio of the over-exposed area to the imaging area is less than or equal to the preset ratio threshold.
A bispectral thermal imaging device, characterized in that the bispectral thermal imaging device includes a memory, a processor, a drive circuit, a thermal imaging image sensor and a visible light image sensor;

The thermal imaging image sensor is used to collect thermal imaging images;

The visible light image sensor is used to collect visible light images;

The memory is used to store machine-executable instructions that can be executed by the processor;

The processor is configured to be driven by the driving circuit, execute the machine executable instructions, and implement the method steps described in any one of claims 1-12.
A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method steps described in any one of claims 1-12 are implemented.
A computer program product containing instructions that, when run on a computer, causes the computer to perform the method steps described in any one of claims 1-12.