Thermal distribution monitoring system and method based on thermal imaging

Abstract

The invention discloses a thermal distribution monitoring system and method based on thermal imaging, the system comprises a hardware layer, a management layer, a data processing layer and a control layer, thermal imaging cameras with infrared are arranged as basic acquisition equipment, and the thermal distribution condition in an area is obtained; the method comprises the steps of collecting and obtaining original infrared image data, preprocessing the image data, converting the image data to generate temperature data, generating a thermodynamic diagram, identifying personnel distribution conditions, and regulating and controlling environmental equipment. The method has the advantages that high-precision collection can be achieved, and layout and regulation can be better optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of building environment monitoring and Internet of Things, and particularly to a thermal distribution monitoring system and method based on thermal imaging. Background Art

[0002] In public buildings such as libraries and office buildings, traditional temperature monitoring devices mainly rely on temperature sensors at fixed positions. The existing solutions are mainly as follows:

[0003] Temperature monitoring: Multiple temperature sensors are installed to collect temperature data at different points, and then an algorithm is used for interpolation to generate a rough distribution map.

[0004] Personnel distribution monitoring: Detection is carried out by relying on ordinary cameras combined with video analysis technology.

[0005] The following problems exist in this solution:

[0006] The distribution of temperature sensor data collection is uneven, and the accuracy of the thermal map generated by interpolation is insufficient;

[0007] The performance of ordinary cameras is limited in complex environments, especially the recognition efficiency is low under low light conditions;

[0008] It is impossible to achieve dynamic linkage of real-time data and optimization of environmental control.

[0009] In summary, although these sensors can monitor local temperatures, they lack the ability to visualize the overall spatial temperature distribution and cannot accurately regulate the environmental comfort of each area. In addition, when traditional cameras are used for personnel distribution detection, they are restricted by lighting and privacy issues and are difficult to meet the requirements of real-time and efficient detection. Summary of the Invention

[0010] The purpose of the present invention is to provide a thermal distribution monitoring system and method based on thermal imaging. The present invention has the advantages of high-precision acquisition, better optimized layout and regulation.

[0011] The technical solution of the present invention: A thermal distribution monitoring system based on thermal imaging includes a hardware layer, a management layer, a data processing layer and a control layer;

[0012] The hardware layer includes environmental control devices, network communication devices and a thermal imaging camera cluster;

[0013] The management layer includes a data storage center, a visualization display platform and a remote management system;

[0014] The data processing layer includes a data acquisition module, an image processing algorithm and an intelligent analysis system;

[0015] The control layer includes an environmental regulation subsystem and a personnel distribution detection subsystem;

[0016] The environmental regulation subsystem is connected to the environmental control device; the data processing module is respectively connected to the thermal imaging camera cluster and the image processing algorithm; the intelligent analysis system is respectively connected to the image processing algorithm, the environmental regulation subsystem and the personnel distribution monitoring subsystem;

[0017] The thermal imaging camera cluster includes a plurality of thermal imaging cameras distributed in various places within the building to cover the entire monitoring area.

[0018] A thermal distribution monitoring method based on thermal imaging includes the following steps:

[0019] A. Collect and obtain original infrared image data: Based on the thermal imaging cameras, collect the original infrared image data of the surrounding environment;

[0020] B. Image data preprocessing: Perform denoising and correction on the collected original infrared image data to obtain infrared image data;

[0021] C. Convert and generate temperature data: Convert the infrared image data into temperature data;

[0022] D. Generate a thermal map: Generate a thermal map based on the obtained temperature data;

[0023] E. Identify the personnel distribution: Detect and identify the positions of personnel in the current image and generate a personnel distribution map;

[0024] F. Regulate the environmental equipment: Based on the thermal map and the personnel distribution map, regulate the corresponding environmental equipment to meet the personnel's environmental comfort requirements.

[0025] In the aforementioned thermal distribution monitoring method based on thermal imaging, the specific content of the image data preprocessing described in step B is as follows:

[0026] Perform denoising and correction on the collected original infrared image data through image processing technology, eliminate false alarm information, and ensure the accuracy of the data; the false alarm information includes at least background heat sources and reflected heat sources.

[0027] In the aforementioned thermal distribution monitoring method based on thermal imaging, the specific content of the conversion and generation of temperature data described in step C is as follows:

[0028] The image ratio of the image data is 3:4, and it is converted and saved using a byte two-dimensional array. The corresponding temperature value of each pixel point of the image is placed into the corresponding byte.

[0029] In the aforementioned thermal distribution monitoring method based on thermal imaging, the specific content of the generation of the thermal map described in step D is as follows:

[0030] Generate a heat map based on temperature data and intuitively display the temperature distribution in the building using a color gradient.

[0031] Through the heat map, clearly show the temperature differences in each area, delimit the comfortable area according to the human comfort temperature standard, dynamically adjust the range of the comfortable area, and mark the high-temperature and low-temperature areas.

[0032] In the aforementioned thermal distribution monitoring method based on thermal imaging, the specific content of identifying the personnel distribution in step E is as follows:

[0033] Identify the positions of people in the current image by analyzing the hot spots in the thermal imaging image or using human detection.

[0034] When performing human detection on the image, limit the resolution to be greater than 32x32 pixels and less than 2000x2000 pixels, the proportion of the human figure is not less than 64x64 pixels. If the detection is successful, return the coordinates of a detection box. The format of the detection box coordinates is [left, top, right, bottom], where left is the abscissa of the upper left corner of the human detection box, top is the ordinate of the upper left corner of the human detection box, right is the abscissa of the lower right corner of the human detection box, and bottom is the ordinate of the lower right corner of the human detection box.

[0035] Generate a personnel distribution map according to the detection box coordinates.

[0036] In the aforementioned thermal distribution monitoring method based on thermal imaging, the specific content of regulating the environmental equipment in step F is as follows:

[0037] The system will input the heat map and the personnel distribution map into the environmental regulation subsystem, combine the real-time data of temperature and personnel density, analyze the matching degree between the temperature conditions in different areas and personnel activities, and identify the areas that need to be optimized.

[0038] According to the analysis results, automatically adjust the environmental equipment to ensure that the environment is in the best state.

[0039] Also, guide people into the comfortable area through guiding equipment to improve the personnel experience and the utilization efficiency of the space.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] High-precision temperature monitoring: Compared with temperature sensors, the thermal imaging camera used in this application can cover a larger area and generate a high-resolution heat map.

[0042] High efficiency in personnel distribution detection: Based on the thermal imaging camera, use hot spots for personnel detection and identification, overcome the limitation of light, and have strong privacy protection.

[0043] Real-time linkage control: Based on the generated heat map and personnel distribution map, combined with environmental data, dynamically adjust equipment such as air conditioners to improve comfort and reduce energy consumption.

[0044] In summary, the present invention has the advantages of high-precision acquisition, better optimized layout and regulation.

[0045] Description of the Drawings

[0046] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0047] Figure 2 It is a schematic diagram of the method flow of the present invention;

[0048] Figure 3 It is a schematic diagram of the environmental regulation process in the embodiment. Detailed Embodiment

[0049] The present invention will be further described below in conjunction with the description of the drawings and the embodiments, but it shall not be used as a basis for limiting the present invention.

[0050] Embodiment. A thermal distribution monitoring system based on thermal imaging, as Figure 1 shown, including a hardware layer, a management layer, a data processing layer and a control layer;

[0051] The hardware layer includes environmental control equipment, network communication equipment and a thermal imaging camera cluster;

[0052] The management layer includes a data storage center, a visualization display platform and a remote management system;

[0053] The data processing layer includes a data acquisition module, an image processing algorithm and an intelligent analysis system;

[0054] The control layer includes an environmental regulation subsystem and a personnel distribution detection subsystem;

[0055] The environmental regulation subsystem is connected to the environmental control equipment; the data processing module is respectively connected to the thermal imaging camera cluster and the image processing algorithm; the intelligent analysis system is respectively connected to the image processing algorithm, the environmental regulation subsystem and the personnel distribution monitoring subsystem;

[0056] The thermal imaging camera cluster includes multiple thermal imaging cameras distributed in various places within the building to cover the entire monitoring area;

[0057] Install thermal imaging cameras in key areas within the building (such as the lobby, reading area, corridor, etc.) to ensure full coverage of the target area. During deployment, pay attention to avoiding direct sunlight and interference from other heat sources to ensure the accuracy of the collected data.

[0058] A monitoring method for a thermal distribution monitoring system based on thermal imaging, as Figure 2 shown, includes the following steps:

[0059] A. Collect and obtain original infrared image data: Collect the original infrared image data of the surrounding environment based on a thermal imaging camera;

[0060] B. Preprocess the image data: Denoise and correct the collected original infrared image data to obtain infrared image data;

[0061] C. Convert and generate temperature data: Convert the infrared image data into temperature data;

[0062] D. Generate a heat map: Generate a heat map based on the obtained temperature data;

[0063] E. Identify the personnel distribution: Detect and identify the positions of personnel in the current image and generate a personnel distribution map;

[0064] F. Regulate environmental equipment: Regulate the corresponding environmental equipment based on the heat map and the personnel distribution map to meet the requirements of personnel environmental comfort.

[0065] The specific content of the image data preprocessing described in step B is as follows:

[0066] Denoise and correct the collected original infrared image data through image processing technology, eliminate false alarm information, and ensure the accuracy of the data; the false alarm information at least includes background heat sources and reflected heat sources;

[0067] For example, when obtaining the original data, since there may be some human bodies, computers, hot water lamps, etc. that affect the temperature range of an area, at this time, some temperature heat sources exceeding the normal state are considered abnormal data, and the heat source data exceeding 30 degrees is eliminated.

[0068] The specific content of the conversion and generation of temperature data described in step C is as follows:

[0069] The image ratio of the image data is 3:4, and it is converted and saved using a byte two-dimensional array. The corresponding temperature value of each pixel point of the image is placed in the corresponding byte;

[0070] The array is actually created as a two-dimensional array of byte

[192]

[256] . The corresponding temperature value of each pixel point of the image is placed in the corresponding byte, such as byte[0][0] = 22.

[0071] The specific content of the generation of the heat map described in step D is as follows:

[0072] Generate a heat map based on the temperature data, and use a color gradient (such as blue representing low temperature and red representing high temperature) to intuitively display the temperature distribution in the building;

[0073] Through the heat map, the temperature differences in each area are clearly shown, and the comfortable area is delimited according to the human comfort temperature standard (usually between 16°C and 30°C), the range of the comfortable area is dynamically adjusted, and the high-temperature and low-temperature areas are marked.

[0074] The specific content of identifying the personnel distribution described in step E is as follows:

[0075] By analyzing the hot spots in the thermal imaging image or using human detection, identify the position of the human body in the current image;

[0076] When performing human detection on the image, the resolution is restricted to be greater than 32x32 pixels and less than 2000x2000 pixels, the proportion of the human figure is not less than 64x64 pixels. If the recognition is successful, a detection box coordinate is returned. The detection box coordinate format is [left, top, right, bottom], where left is the abscissa of the upper left corner of the human detection box, top is the ordinate of the upper left corner of the human detection box, right is the abscissa of the lower right corner of the human detection box, and bottom is the ordinate of the lower right corner of the human detection box;

[0077] Generate a personnel distribution map according to the detection box coordinates.

[0078] The specific content of regulating the environmental equipment described in step F is as follows:

[0079] The system will input the heat map and the personnel distribution map into the environmental regulation subsystem, combine the real-time data of temperature and personnel density, analyze the matching degree between the temperature conditions in different areas and the personnel activities, and identify the areas that need to be optimized; for example, when the temperature in an area exceeds the comfortable 26°C and the single-person activity range is less than 1 square meter, it is considered that the current area is not a comfortable area;

[0080] According to the analysis results, automatically adjust environmental equipment such as air conditioners, fans, and sunshades, and preferentially deliver cold / warm air to areas with dense personnel or unsuitable temperatures to ensure that the environment is in the best state and ensure that the current person's perceived temperature is around 24-26°C;

[0081] It also guides people into the comfortable area through guiding devices such as screens or lights in the building to improve the personnel experience and the utilization efficiency of the space.

[0082] All heat maps and personnel distribution data will be stored in the database in real time for subsequent analysis and optimization to ensure the long-term stable operation of the system. Through regular historical data analysis, the laws of building temperature changes and the trends of personnel activities are discovered, providing a basis for building design, energy-saving management, and space optimization, and further enhancing the intelligence level of the system. For example, through historical data analysis, it can be known which time period requires a relatively lower temperature and which time period has a relatively stable temperature, and it can be predicted in advance.

[0083] Calibrate the thermal imaging camera regularly to ensure the accuracy of its temperature measurement and ensure the continuous and efficient operation of the system. With the continuous progress of artificial intelligence technology, the heat map generation and personnel recognition algorithms in the system are continuously optimized. For example, the generation range of the heat map becomes larger and the accuracy becomes smaller. The personnel algorithm currently supports faces and bodies, and supports complex calculations to improve the analysis accuracy of the system, ensuring that it can adapt to various complex scenarios.

[0084] This application is based on a thermal imaging camera with an infrared sensor. The scene is monitored through the original camera, and the camera is docked through the sdk provided by the camera. The infrared streaming data of the camera is obtained through the sdk to obtain the data stream.

[0085] Since the aspect ratio of the infrared data obtained by the camera is fixed, the data obtained will be a thermal image with a ratio of 3:4.

[0086] The thermal image is transmitted through the stream, the data stream is parsed, and a two-dimensional array of byte[][] is constructed.

[0087] Since the application scenarios are all indoors, and air conditioners are turned on both in winter and summer indoors, the temperature usually remains between 16 and 30 degrees Celsius. If the temperature is too high, such as the human body temperature is generally around 37 degrees, lighting, computers, hot water, etc., it is considered an incorrect data, and the data that affects the thermal distribution map is removed.

[0088] Due to reasons such as distance, the thermal map generated by the infrared camera also has a certain error, and there will be a process of data calibration and correction. Specifically, the temperatures that are too high or too low are removed, and the temperature is set to the average value of all temperatures, and a temperature difference of 2 degrees is allowed for all data. For example, if the temperature is greater than 21 degrees and less than or equal to 23 degrees, the temperature is considered to be 23 degrees.

[0089] After processing the data of a single camera, the data of all cameras are integrated. Finally, through the thermal imaging data of multiple cameras, a thermal distribution map of a complete area is integrated. Generally, color gradients (such as blue representing low temperature and red representing high temperature) are used to display the temperature distribution inside the building, and a 3D structural diagram of the building interior is drawn. After mapping the thermal data into colors, according to the area covered by the current camera, all the colors are mapped onto the area covered by the current camera. Finally, a 3D building model with a thermal distribution map can be formed.

[0090] Person detection is implemented based on a third-party open-source framework. Through interface calls, a person image or a human body image is obtained. By inputting a heat source image or a normal image, the coordinate position mapping of a person in the current picture can be returned, and the coordinate points of the person in the current picture are obtained. The point structure is [left, top, right, bottom]. The first two data are the horizontal and vertical coordinates of the upper left corner, and the last two data are the horizontal and vertical coordinates of the lower right corner. A rectangle can be confirmed through the points of the upper left and lower right corners, and a person is framed with a line.

[0091] As Figure 3 shown, according to the above calculations, thermal data and personnel distribution data can be obtained. By calculating the area of the current environment (this area needs to be set in advance), the density of the number of people in the current area is calculated to analyze the comfort level of the current environment; the comfort level is set in advance. For example, the comfort level is 0 - 1. When there is only one person in the occupied area and the temperature is also within the most suitable range of 24 - 26°C for people, the comfort level is considered 1. If the occupied area is smaller and exceeds a certain proportion, such as one person per square meter, and the temperature is no longer within the relatively suitable temperature range (the suitable temperature is related to the four seasons of the year, and the relatively suitable temperature range can be set according to the four seasons of the year). Finally, an evaluation is carried out. For example, if the suitability is lower than 0.5, it is considered that the current area is no longer at a suitable temperature; when it is not suitable, devices such as air conditioners or ventilation systems are adjusted to improve the comfort level of the current area;

[0092] The comfort of the current environment will also be color-coded by area. Based on the overall thermal distribution map, it is marked where the comfortable areas are and displayed on the page in real time.

Claims

1. A thermal distribution monitoring system based on thermal imaging, characterized in that: Includes hardware layer, management layer, data processing layer and control layer; The hardware layer includes environmental control equipment, network communication equipment and thermal imaging camera cluster; The management layer includes a data storage center, a visualization display platform and a remote management system; The data processing layer includes a data acquisition module, an image processing algorithm and an intelligent analysis system; The control layer includes an environment control subsystem and a personnel distribution detection subsystem; The environmental control subsystem is connected to the environmental control device; the data processing module is respectively connected to the thermal imaging camera cluster and the image processing algorithm; the intelligent analysis system is respectively connected to the image processing algorithm, the environmental control subsystem and the personnel distribution monitoring subsystem; The thermal imaging camera cluster includes a plurality of thermal imaging cameras distributed in various places in the building for covering a complete monitoring area.

2. The monitoring method of a thermal distribution monitoring system based on thermal imaging according to claim 1, characterized in that: The steps include: A. Collect and obtain original infrared image data: collect original infrared image data of the surrounding environment based on thermal imaging camera; B. Image data preprocessing: De-noising and correction processing is performed on the collected original infrared image data to obtain infrared image data; C. Convert and generate temperature data: convert infrared image data into temperature data; D. Generate thermal map: Generate a thermal map based on the obtained temperature data; E. Identify personnel distribution: detect and identify the location of personnel in the current image and generate a personnel distribution map; F. Adjust environmental equipment: Adjust the corresponding environmental equipment based on the thermal map and personnel distribution map to meet the personnel's environmental comfort needs.

3. The method for monitoring thermal distribution based on thermal imaging according to claim 2, characterized in that: The image data preprocessing described in step B is specifically as follows: The collected original infrared image data is denoised and corrected by image processing technology to eliminate false alarm information and ensure the accuracy of the data; the false alarm information at least includes background heat sources and reflected heat sources.

4. The method for monitoring thermal distribution based on thermal imaging according to claim 2, characterized in that: The conversion described in step C generates temperature data, which is as follows: The image data has an image ratio of 3:4 and is converted and saved using a byte array. The temperature value of each pixel of the image is placed in the corresponding byte.

5. The method for monitoring thermal distribution based on thermal imaging according to claim 2, characterized in that: The specific contents of generating the heat map described in step D are as follows: Generate a thermal map based on temperature data, using color gradients to visually display the temperature distribution in the building; The heat map clearly displays the temperature differences between different areas, and defines the comfort zone based on the human body's comfortable temperature standard. The range of the comfort zone is dynamically adjusted, and the high and low temperature areas are marked.

6. The method for monitoring thermal distribution based on thermal imaging according to claim 2, characterized in that: The distribution of identified personnel described in step E is specifically as follows: By analyzing the hot spots in the thermal imaging image or using human body detection, the location of the human body in the current image can be identified; When performing person detection on an image, the resolution is limited to be greater than 32x32 pixels and less than 2000x2000 pixels, and the portrait ratio is not less than 64x64 pixels. If the recognition is successful, a detection frame coordinate is returned. The detection frame coordinate format is [left, top, right, bottom], where left is the horizontal coordinate of the upper left corner of the human detection frame, top is the vertical coordinate of the upper left corner of the human detection frame, right is the horizontal coordinate of the lower right corner of the human detection frame, and bottom is the vertical coordinate of the lower right corner of the human detection frame; Generate a personnel distribution map according to the detection box coordinates.

7. The method for monitoring thermal distribution based on thermal imaging according to claim 2, characterized in that: The specific contents of the environmental control equipment described in step F are as follows: The system will input the thermal map and personnel distribution map into the environmental control subsystem, combine the real-time data of temperature and personnel density, analyze the matching degree between the temperature conditions in different areas and personnel activities, and identify the areas that need to be optimized; According to the analysis results, the environmental equipment is automatically adjusted to ensure that the environment is in the best condition; It also guides people into comfort zones through guidance equipment, improving personnel experience and space utilization efficiency.

Images