CN115876334A - Infrared thermal image indoor temperature measurement method and system and computer readable storage medium - Google Patents
Infrared thermal image indoor temperature measurement method and system and computer readable storage medium Download PDFInfo
- Publication number
- CN115876334A CN115876334A CN202310148242.4A CN202310148242A CN115876334A CN 115876334 A CN115876334 A CN 115876334A CN 202310148242 A CN202310148242 A CN 202310148242A CN 115876334 A CN115876334 A CN 115876334A
- Authority
- CN
- China
- Prior art keywords
- decoding
- feature map
- window
- temperature detection
- thermal image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Radiation Pyrometers (AREA)
Abstract
The invention discloses an infrared thermal image indoor temperature measurement method, a system and a computer readable storage medium. Wherein the method comprises the following steps: acquiring a real-time thermal image and a real-time high-definition image outside the unit building; inputting the real-time high-definition images into a pre-trained target detection deep learning network to carry out window positioning, and obtaining window position information; segmenting the real-time thermal image according to the window position information to obtain a window thermal image; and inputting the window thermal image into a first temperature detection model trained in advance for temperature identification to obtain an indoor temperature detection result, wherein the first temperature detection model is obtained by distillation training of a second temperature detection model. According to the method, the temperature of the acquired thermal image of the window outside the unit building is detected, so that the indoor temperature is detected in real time.
Description
Technical Field
The invention relates to the field of image processing, in particular to an infrared thermal image indoor temperature measurement method, an infrared thermal image indoor temperature measurement system and a computer readable storage medium.
Background
In the central heating system, the heat waste is reduced while the indoor temperature is ensured for heating in the building, and the heating and heat preservation are in a certain dynamic balance degree, so that the heat loss is less, and the daily unaffected of users is ensured. In view of the demand, the indoor temperature of the user needs to be monitored in real time, and the temperature of the user can be maintained at a temperature suitable for the user under the condition that the external temperature changes, so that the monitoring of the indoor temperature becomes an important task in the heat supply engineering. The infrared thermal imaging detection has the characteristics of long distance, non-contact, high precision, fast dynamic response, visual image and the like, so that the infrared thermal imaging detection is applied to indoor temperature monitoring, can observe more areas of the room temperature of a user, can observe the abnormal loss condition of the room temperature of the user, and can dynamically adjust a heating strategy. In the related technology, a method for rapidly acquiring indoor air temperature in batches from outdoors through infrared thermal imaging is used for carrying out thermal image acquisition on a user window area through thermal infrared imaging, and according to different window opening degrees, thermal image analysis calculation is carried out through a heat transfer model calculation formula according to a set threshold value and an outdoor temperature measurement result, so that the indoor temperature is calculated, but different building convective heat transfer coefficient differences exist, the multiplexing efficiency in various regions is low, and the actually measured temperature has certain errors.
Disclosure of Invention
The present invention is directed to solving, at least in part, one of the technical problems in the related art.
Therefore, the first purpose of the invention is to provide an infrared thermography indoor temperature measuring method, which realizes real-time detection of indoor temperature by detecting the temperature of the acquired thermal image of the window outside the unit building.
A second object of the invention is to propose a computer-readable storage medium.
The third purpose of the invention is to provide an infrared thermal image indoor temperature measuring system.
In order to achieve the above object, an embodiment of the first aspect of the present invention provides a method for measuring temperature in a thermal infrared image room, where the method includes: acquiring a real-time thermal image and a real-time high-definition image outside the unit building; inputting the real-time high-definition image into a pre-trained target detection deep learning network to perform window positioning, and acquiring window position information; segmenting the real-time thermal image according to the window position information to obtain a window thermal image; and inputting the window thermal image into a first temperature detection model trained in advance for temperature identification to obtain an indoor temperature detection result, wherein the first temperature detection model is obtained by distillation training of a second temperature detection model.
According to an embodiment of the present invention, the window position information includes a coordinate set of each window, wherein the segmenting process of the real-time thermal image according to the window position information includes:
and cutting the real-time thermal image according to the coordinate set of each window body to obtain the window body thermal image corresponding to each window body of the unit building.
According to an embodiment of the invention, before training the first temperature detection model, the method further comprises: acquiring a thermal image sample image, a high-definition sample image and temperature measurement sample data; inputting the high-definition sample image into the target detection deep learning network for window positioning to obtain a positioning coordinate; cutting the thermal image sample image according to the positioning coordinates to obtain a preliminary window thermal image; and screening the preliminary window thermal image according to the temperature measurement sample data to obtain training sample data.
According to an embodiment of the invention, after obtaining training sample data, the method further comprises:
sending the training sample data to an automatic training server, wherein the automatic training server trains the second temperature detection model according to the training sample data, and teaches the knowledge learned by the trained second temperature detection model to the first temperature detection model in a distillation learning mode so as to train the first temperature detection model; and receiving the trained first temperature detection model fed back by the automatic training server.
According to an embodiment of the invention, the first temperature detection model is an SRAnet-student deep learning network model, and the second temperature detection model is an SRAnet-teacher deep learning network model.
According to an embodiment of the present invention, the first temperature detection model includes a first convolution module, a first spatial cyclic neural module, a second spatial cyclic neural module, a third spatial cyclic neural module, a fourth spatial cyclic neural module, a first linking module, a first decoding module, and a second decoding module, wherein inputting the window thermographic image into a first temperature detection model trained in advance for temperature identification includes: performing feature extraction processing on the window thermal image through the first convolution module to obtain a first feature image;
respectively extracting features of the first feature map in different directions through the first spatial circulation neural module, the second spatial circulation neural module, the third spatial circulation neural module and the fourth spatial circulation neural module to obtain a first direction feature map, a second direction feature map, a third direction feature map and a fourth direction feature map; linking the first feature map, the first direction feature map, the second direction feature map, the third direction feature map and the fourth direction feature map through the first linking module to obtain a coding feature map; decoding the coding feature map through the first decoding module to obtain a first decoding intermediate feature map; and decoding the first decoding intermediate characteristic diagram through the second decoding module to obtain the indoor temperature detection result.
According to an embodiment of the present invention, the first decoding module includes a first multi-headed self-attention layer, a first normalization layer, a first feed-forward network layer, and a second normalization layer, which are connected in sequence, where decoding the encoded feature map by the first decoding module includes: performing feature extraction on the coding feature map through the first multi-head self-attention layer to obtain a first decoding feature map; normalizing the coding characteristic diagram and the first decoding characteristic diagram through the first normalization layer to obtain a second decoding characteristic diagram; processing the second decoding characteristic diagram through the first feedforward network layer to obtain a third decoding characteristic diagram; and normalizing the second decoding characteristic diagram and the third decoding characteristic diagram through the second normalization layer to obtain the first decoding intermediate characteristic diagram.
According to an embodiment of the present invention, the second decoding module includes a second multi-start self-attention layer, a third normalization layer, a second feed-forward network layer, and a fourth normalization layer, which are connected in sequence, and the decoding processing performed on the first decoded intermediate feature map by the second decoding module includes: performing feature extraction on the first decoding intermediate feature map through the second multi-head self-attention layer to obtain a fourth decoding feature map; normalizing the first decoding intermediate feature map and the fourth decoding feature map through the third normalization layer to obtain a fifth decoding feature map; processing the fifth decoding characteristic diagram through the second feedforward network layer to obtain a sixth decoding characteristic diagram; and normalizing the fifth decoding characteristic diagram and the sixth decoding characteristic diagram through the fourth normalization layer to obtain the indoor temperature detection result.
According to the infrared thermal image indoor temperature measurement method provided by the embodiment of the invention, the real-time thermal image and the real-time high-definition image outside the unit building are obtained; inputting real-time high-definition images into a pre-trained target detection deep learning network to perform window positioning, and obtaining window position information; segmenting the real-time thermal image according to the window position information to obtain a window thermal image; the window thermal image is input into a first temperature detection model trained in advance for temperature identification, an indoor temperature detection result is obtained, so that the intrinsic relation of the thermal image in spatial distribution and the intrinsic relation of the characteristics of the thermal image are extracted, the indoor temperature is predicted by combining the characteristic distribution condition of the thermal image, the first temperature detection model is lightened by a distillation learning method, and the efficiency of real-time prediction of the indoor temperature is realized.
In order to achieve the above object, a second aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for indoor temperature measurement of infrared thermography according to the first aspect of the present invention.
In order to implement the foregoing embodiments, an embodiment of a third aspect of the present invention provides an infrared thermography indoor temperature measurement system, including: the system comprises a binocular thermal imager and a 3D cloud platform, wherein the 3D cloud platform is used for carrying the binocular thermal imager so as to shoot images outside a unit building and obtain real-time thermal imagery images and real-time high definition images; the micro embedded control analysis device is used for inputting the real-time high-definition images into a pre-trained target detection deep learning network for window positioning to obtain window position information, segmenting the real-time thermal image according to the window position information to obtain a window thermal image, inputting the window thermal image into a pre-trained first temperature detection model for temperature identification to obtain an indoor temperature detection result, wherein the first temperature detection model is obtained by distillation training of a second temperature detection model.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is a schematic flow chart of a method for measuring temperature in an infrared thermographic chamber according to an embodiment of the present invention;
FIG. 2 is a schematic flowchart of an infrared thermographic indoor temperature measurement method according to a first embodiment of the present invention;
FIG. 3 is a schematic diagram of a first temperature detection model distillation learning second temperature detection model and a second temperature detection model according to one embodiment of the invention.
FIG. 4 is a schematic diagram of a first temperature sensing model according to one embodiment of the invention;
FIG. 5 is a schematic diagram of a first temperature sensing model according to an embodiment of the present application;
FIG. 6 is a block diagram of a first decoding module according to an embodiment of the present invention;
FIG. 7 is a block diagram of a second decoding module according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a second temperature sensing model according to an embodiment of the present invention;
FIG. 9 is a schematic structural diagram of a computer-readable storage medium according to one embodiment of the present invention;
FIG. 10 is a schematic structural diagram of an infrared thermographic indoor temperature measurement system according to an embodiment of the present invention;
FIG. 11 is a schematic workflow diagram of an auto-training server according to one embodiment of the invention.
Description of reference numerals:
410. a first convolution module; 420. a first spatial recurrent neural module; 430. a second spatial recurrent neural module; 440. a third spatial recurrent neural module; 450. a fourth spatial recurrent neural module; 460. a first linking module; 470. a first decoding module; 480. a second decoding module; 610. a first multi-headed self-attentive layer; 620. a first normalization layer; 630. a first feedforward network layer; 640. a second normalization layer; 710. a second multi-headed self-attentive layer; 720. a third normalization layer; 730. a second feed-forward network layer; 740. a fourth normalization layer; 900. a computer-readable storage medium; 901. a computer program; 1000. an infrared thermal imaging indoor temperature measurement system; 1010. a binocular thermal imager; 1020. a 3D pan-tilt; 1030. miniature embedded control analytical equipment.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The following describes a method, a system and a computer-readable storage medium for measuring temperature in a thermographic infrared room according to embodiments of the present invention with reference to fig. 1-11.
FIG. 1 is a schematic flow chart of a method for measuring temperature in an infrared thermographic chamber according to an embodiment of the present invention.
As shown in fig. 1, the method for measuring temperature in an infrared thermography chamber may include the following steps:
and S110, acquiring a real-time thermal image and a real-time high-definition image outside the unit building.
Exemplarily, a shooting device can be placed outside the unit building to acquire a real-time thermal image and a real-time high-definition image, wherein the shooting device can include a high-definition camera and an infrared thermal image camera, or an infrared dual-view image shooting device, wherein the high-definition camera is used for shooting the real-time high-definition image outside the unit building, the infrared thermal image camera is used for shooting the real-time thermal image outside the unit building, the high-definition camera and the infrared camera are arranged at the same position outside the unit building, and the high-definition camera and the infrared camera can simultaneously acquire the real-time thermal image and the real-time high-definition image at the same shooting angle in the same scene through a camera calibration mode.
Illustratively, the shooting device for the real-time thermal image and the real-time high-definition image can be arranged in the middle position outside the two unit buildings, and the real-time thermal image and the real-time high-definition image of the two unit buildings are respectively obtained by controlling the shooting device to rotate.
And S120, inputting the real-time high-definition image into a pre-trained target detection deep learning network to perform window positioning, and obtaining window position information.
And S130, segmenting the real-time thermal image according to the window position information to obtain a window thermal image.
Further, the position of the window body in the real-time high-definition image is detected through a target detection deep learning network, and the window body position information of the window body in the real-time high-definition image is obtained. And (4) segmenting the real-time thermal image according to the window position information, and segmenting the window part in the real-time thermal image to obtain a window thermal image.
It can be understood that the real-time thermal image and the real-time high-definition image are images of the outside of the unit building at the same time, at the same angle and in the same scene, so that the part of the window can be segmented from the real-time thermal image according to the position information of the window in the real-time high-definition image.
Illustratively, the target detection deep learning network may be a target detection network model such as YOLOv5, SSD, R-CNN, SPP-net, fast R-CNN, fasterR-CNN, etc., and the present invention is not limited thereto.
And S140, inputting the window thermal image into a first temperature detection model trained in advance for temperature identification to obtain an indoor temperature detection result, wherein the first temperature detection model is obtained by distillation training of a second temperature detection model.
Specifically, the temperature of the window is predicted by inputting the divided window thermograph into a first temperature detection model trained in advance, wherein the temperature of the window can represent the indoor temperature, and an indoor temperature detection result is further obtained by predicting the temperature of the window.
In some embodiments of the present invention, the window position information includes a coordinate set of each window, wherein the segmenting process of the real-time thermal image according to the window position information includes: and cutting the real-time thermal image according to the coordinate set of each window body to obtain a window body thermal image corresponding to each window body of the unit building.
The real-time high-definition images of the exterior of the unit building are acquired by using a target detection deep learning network, and the real-time high-definition images are acquired by using a target detection deep learning network.
FIG. 2 is a schematic flow chart of a method for measuring temperature in an infrared thermographic chamber according to a first embodiment of the present invention.
As shown in fig. 2, before training the first temperature detection model, the following steps may be included:
s210, acquiring a thermal image sample image, a high-definition sample image and temperature measurement sample data.
And S220, inputting the high-definition sample image into a target detection deep learning network for window positioning to obtain a positioning coordinate.
And S230, cutting the thermal image sample image according to the positioning coordinates to obtain a preliminary window thermal image.
And S240, screening the preliminary window thermal image according to the temperature measurement sample data to obtain training sample data.
For example, the temperature measurement sample data may be obtained from temperature measurement data of a temperature measurement sensor disposed indoors. Further positioning the position of the window in the high-definition sample image through a target detection deep learning network to obtain a positioning coordinate; and cutting out all the parts of the window body in the thermal image sample image according to the positioning coordinates of the window body, and attaching the coordinate information of the window body to obtain a preliminary window body thermal image. And further screening the preliminary window thermal image according to the window coordinates close to the temperature sensor, and screening the window thermal image close to the temperature sensor to obtain training sample data related to the window thermal image and the temperature measurement data corresponding to the window.
After obtaining training sample data in some embodiments of the invention, the method further comprises: sending training sample data to an automatic training server, wherein the automatic training server trains a second temperature detection model according to the training sample data, and transmits knowledge learned by the trained second temperature detection model to a first temperature detection model in a distillation learning mode so as to train the first temperature detection model; and receiving a trained first temperature detection model fed back by the automatic training server.
As an example, the first temperature detection model is an SRAnet-student deep learning network model, and the second temperature detection model is an SRAnet-teacher deep learning network model.
Illustratively, fig. 3 is a schematic diagram of a first temperature detection model distillation learning second temperature detection model and a second temperature detection model according to one embodiment of the invention. As shown in fig. 3, the second temperature detection model SRAnet-teacher is a trained deep learning network model, when the second temperature detection model is SRAnet-teacher training, the loss reduction converges to a stable range, the second temperature detection model is SRAnet-teacher tested by the test data set, after the accuracy of the test result is greater than or equal to the preset accuracy, the knowledge learned by the second temperature detection model SRAnet-teacher is transferred to the first temperature detection model SRAnet-student by distillation learning, so that the first temperature detection model is trained by the training data set, and after the loss reduction of the first temperature detection model SRAnet-student loss converges to a stable range and the accuracy of the test result is greater than or equal to the preset accuracy, the pre-trained first temperature detection model is obtained as SRAnet-student, and the first temperature detection model with light weight is obtained, thereby further improving the efficiency of temperature detection.
As a possible implementation manner, fig. 4 is a schematic structural diagram of a first temperature detection model according to an embodiment of the present invention.
As shown in fig. 4, the first temperature detection model includes a first convolution module 410, a first spatial cyclic neural module 420, a second spatial cyclic neural module 430, a third spatial cyclic neural module 440, a fourth spatial cyclic neural module 450, a first linking module 460, a first decoding module 470, and a second decoding module 480.
Wherein, carry out temperature identification with the first temperature detection model that window thermal image input trained in advance, include: performing feature extraction processing on the window thermal image through a first convolution module 410 to obtain a first feature image; respectively extracting features of the first feature map in different directions through a first spatial circulation neural module 420, a second spatial circulation neural module 430, a third spatial circulation neural module 440 and a fourth spatial circulation neural module 450 to obtain a first direction feature map, a second direction feature map, a third direction feature map and a fourth direction feature map; the first linking module 460 is used for linking the first feature map, the first direction feature map, the second direction feature map, the third direction feature map and the fourth direction feature map to obtain a coding feature map; decoding the encoded feature map by a first decoding module 470 to obtain a first decoded intermediate feature map; the second decoding module 480 decodes the first decoded intermediate feature map to obtain an indoor temperature detection result.
Illustratively, fig. 5 is a schematic structural diagram of a first temperature detection model according to a specific embodiment of the present application. As shown in fig. 5, the window thermal image is input into the first lightweight temperature detection model, spatial information of the thermal image outside the window in four directions is obtained through the spatial cyclic neural module, the spatial information is linked with the feature result obtained by the first layer convolution module, the coding feature image containing the spatial correlation feature information is output, and the coding feature image is decoded through the decoding module to obtain an indoor temperature detection result.
Fig. 6 is a schematic structural diagram of a first decoding module according to an embodiment of the present invention.
As shown in fig. 6, the first decoding module 470 includes a first multi-headed self-attention layer 610, a first normalization layer 620, a first feed-forward network layer 630 and a second normalization layer 640, which are connected in sequence, wherein the decoding process of the encoded feature map by the first decoding module 470 may include: extracting the features of the coding feature map through the first multi-head self-attention layer 610 to obtain a first decoding feature map; normalizing the coding feature map and the first decoding feature map through a first normalization layer 620 to obtain a second decoding feature map; processing the second decoding feature map through the first feedforward network layer 630 to obtain a third decoding feature map; the second decoded feature map and the third decoded feature map are normalized by the second normalization layer 640 to obtain a first decoded intermediate feature map.
Specifically, the first multi-head self-attention layer 610 is used for paying attention to information of different subspaces at different positions in the thermal image of the window body, the fitting difficulty and the risk of overfitting are reduced by losing a part of unimportant complex information through the first normalization layer 620, so that the convergence of the model is accelerated, the expression capability of image features is enhanced through the first feed-forward network layer 630 in an activation function mode, and the first decoding intermediate feature map is further obtained through the second normalization layer 640.
Fig. 7 is a schematic structural diagram of a second decoding module according to an embodiment of the present invention.
As shown in fig. 7, the second decoding module 480 includes a second multi-start self-attention layer 710, a third normalization layer 720, a second feed-forward network layer 730, and a fourth normalization layer 740, which are connected in sequence, wherein the decoding process performed on the first decoded intermediate feature map by the second decoding module 480 includes: performing feature extraction on the first decoding intermediate feature map through the second multi-head self-attention layer 710 to obtain a fourth decoding feature map; normalizing the first decoded intermediate feature map and the fourth decoded feature map through a third normalization layer 720 to obtain a fifth decoded feature map; processing the fifth decoding feature map through the second feedforward network layer 730 to obtain a sixth decoding feature map; and normalizing the fifth decoding characteristic diagram and the sixth decoding characteristic diagram through a fourth normalization layer 740 to obtain an indoor temperature detection result.
It should be noted that, in this embodiment, the second decoding module 480 has the same structure as the first decoding module 470, the input of the second decoding module 480 is the output of the first decoding module 470, and the indoor temperature detection result is obtained by performing decoding processing on the first decoded intermediate characteristic map and performing temperature prediction on the window thermal map.
As an example, fig. 8 is a schematic structural diagram of a second temperature detection model according to an embodiment of the present invention. As shown in fig. 8, firstly, the features of the image outside the window are preliminarily extracted through a layer of convolution module, then the spatial correlation information is extracted through the spatial cyclic neural modules in four different directions, meanwhile, in order to make the network pay attention to the effective information, a distribution weight w is obtained through an attention module, the obtained spatial correlation information feature maps in different directions are multiplied by the attention distribution weight, then the feature maps preliminarily extracted by the first layer of convolution module are supplementarily linked to form a coding feature map, each unit feature in the feature map comprises the spatial correlation features of the position and the image in the upper, lower, left and right directions, so that different complex thermal image distribution conditions can be fully associated in the coding process, the coding feature map is input into a decoding layer formed by a 6-layer decoding module decoder block to decode the feature information, and the decoding module is formed by a self-attention structure, thereby obtaining the indoor temperature detection result.
It can be understood that the first temperature detection model includes two decoding modules, namely a first decoding module 470 and a second decoding module 480, and the second temperature detection model includes six decoding modules, wherein the first decoding module 470 and the second decoding module 480 learn network parameters of any two decoding modules of the six decoding modules in the second temperature detection model by distillation to obtain network parameters of the first decoding module 470 and the second decoding module 480, the process of distillation learning is exemplarily shown in fig. 3, thereby reducing the burden of real-time prediction of the first temperature detection model, the first temperature detection model cuts out an attention module in a spatial attention circulation neural network in the second temperature detection model to obtain the structure of the first temperature detection model, because the characteristic distribution of network concentration has been obtained by distillation during distillation, four feature maps with spatial correlation information are output through the spatial circulation neural network and linked with a feature map output by the first layer convolution module, an encoded feature map is output, thereby the encoded feature map with the spatial correlation information is input into a temperature-related layer, thereby obtaining encoded feature map with encoded indoor prediction, and extracting potential thermal image prediction results from the encoded feature map.
According to the infrared thermal image indoor temperature measurement method provided by the embodiment of the invention, the real-time thermal image and the real-time high-definition image outside the unit building are obtained; inputting real-time high-definition images into a pre-trained target detection deep learning network to perform window positioning, and obtaining window position information; segmenting the real-time thermal image according to the window position information to obtain a window thermal image; the window thermal image is input into a first temperature detection model trained in advance for temperature identification, an indoor temperature detection result is obtained, so that the intrinsic relation of the thermal image in spatial distribution and the intrinsic relation of the characteristics of the thermal image are extracted, the indoor temperature is predicted by combining the characteristic distribution condition of the thermal image, the first temperature detection model is lightened by a distillation learning method, and the efficiency of real-time prediction of the indoor temperature is realized.
To implement the foregoing embodiment, the present invention further provides a computer-readable storage medium, and fig. 9 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention.
As shown in fig. 9, the computer-readable storage medium 900 has a computer program 901 stored thereon, and when executed by a processor, the computer program 901 implements the method for indoor temperature measurement of infrared thermography according to the above-mentioned embodiment of the present invention.
In order to implement the above embodiments, the present invention further provides an infrared thermography indoor temperature measurement system, and fig. 10 is a schematic structural diagram of the infrared thermography indoor temperature measurement system according to an embodiment of the present invention.
As shown in fig. 10, the infrared thermography indoor temperature measuring system 1000 may include: the binocular thermal imager 1010, the 3D cloud deck 1020 and the 3D cloud deck 1020 are used for carrying the binocular thermal imager 1010 to shoot images outside the unit building, and real-time thermal image images and real-time high-definition images are obtained; the micro embedded control analysis device 1030 is used for inputting a real-time high-definition image into a pre-trained target detection deep learning network for window positioning, obtaining window position information, segmenting the real-time thermal image according to the window position information to obtain a window thermal image, inputting the window thermal image into a pre-trained first temperature detection model for temperature identification, and obtaining an indoor temperature detection result, wherein the first temperature detection model is obtained by distilling and training a second temperature detection model.
Illustratively, the infrared thermography indoor temperature measuring system 1000 may acquire a real-time thermography image and a real-time high-definition image through a binocular thermal imager 1010 and a 3D holder 1020, cut a position of a window in the real-time thermography image through a micro embedded control analysis device 1030, input a second temperature detection model of the window thermography and temperature information corresponding to the window thermography image into an automatic training server for training during training, and distill and train a first temperature detection model through the second temperature detection model to obtain a pre-trained second temperature detection model, push the trained first temperature detection model to the micro embedded control analysis device 1030, input the cut window thermography into a first target detection model distilled and learned in the micro embedded control analysis device 1030 during real-time indoor temperature prediction, thereby obtain an indoor temperature corresponding to the window, and push the predicted indoor temperature, and corresponding real-time video and real-time video to a high-definition network transmission radio station and a cloud live broadcast platform system to realize real-time monitoring of the indoor temperature. As an example, an image of each frame within a preset time of the video may be acquired from the real-time thermographic video and the real-time high definition video according to a preset interval time as the real-time thermographic image and the real-time high definition image.
As an example, FIG. 11 is a schematic workflow diagram of an auto-training server according to one embodiment of the invention. As shown in fig. 11, each region may pack and push a training set including a window thermograph and window temperature information to an automatic training server, and train a first temperature detection model, thereby monitoring indoor temperatures of each region in real time.
Illustratively, the binocular thermal imager 1010 may be a grid excellent telecommunication YRH600D infrared binocular camera dual-view system, the infrared resolution is 384 × 288, the visible light resolution is 2560 × 1440, the system is mounted on the 3D pan/tilt 1020, and is configured with a micro embedded control analysis device 1030, the device may cut real-time thermal imagery images through a target detection network YOLOv5n, operate a first temperature detection model to predict indoor temperature, push training data to an automatic training server and push prediction results and thermal imagery high definition images or videos to a high definition network transmission radio station and a cloud live broadcast system, the automatic training server operates an automatic reinforcement training service, trains a second temperature detection model and a distillation training first temperature detection model, and is responsible for sending the updated first temperature detection model back to the micro embedded control analysis device 1030. The cloud live broadcast system displays and predicts indoor temperature conditions in real time, and the high-definition network transmission radio station sends the packaged indoor temperature information of the user to the heat supply network balance server to be used as a basis for regulating and controlling heat supply of the user by the heat supply network.
It should be noted that the logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following technologies, which are well known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," "circumferential," and the like are used in the orientations and positional relationships indicated in the drawings for convenience in describing the invention and to simplify the description, and are not intended to indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be considered limiting of the invention.
Furthermore, the terms "first", "second", and the like used in the embodiments of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated in the embodiments. Thus, a feature of an embodiment of the present invention that is defined by the terms "first," "second," etc. may explicitly or implicitly indicate that at least one of the feature is included in the embodiment. In the description of the present invention, the word "plurality" means at least two or two and more, such as two, three, four, etc., unless specifically limited otherwise in the examples.
In the present invention, unless otherwise explicitly stated or limited by the relevant description or limitation, the terms "mounted," "connected," and "fixed" in the embodiments are to be understood in a broad sense, for example, the connection may be a fixed connection, a detachable connection, or an integrated connection, and it may be understood that the connection may also be a mechanical connection, an electrical connection, etc.; of course, they may be directly connected or indirectly connected through an intermediate medium, or they may be interconnected or in mutual relationship. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to specific implementation situations.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. An indoor temperature measurement method of infrared thermography is characterized by comprising the following steps:
acquiring a real-time thermal image and a real-time high-definition image outside the unit building;
inputting the real-time high-definition image into a pre-trained target detection deep learning network to perform window positioning, and acquiring window position information;
segmenting the real-time thermal image according to the window position information to obtain a window thermal image;
and inputting the window thermal image into a first temperature detection model trained in advance for temperature identification to obtain an indoor temperature detection result, wherein the first temperature detection model is obtained by distillation training of a second temperature detection model.
2. The method for measuring the temperature in the infrared thermography chamber according to claim 1, wherein the window position information includes a coordinate set of each window, and the segmenting the real-time thermography image according to the window position information includes:
and cutting the real-time thermal image according to the coordinate set of each window body to obtain the window body thermal image corresponding to each window body of the unit building.
3. The method for indoor temperature measurement according to claim 1 or 2, wherein before training the first temperature detection model, the method further comprises:
acquiring a thermal image sample image, a high-definition sample image and temperature measurement sample data;
inputting the high-definition sample image into the target detection deep learning network for window positioning to obtain a positioning coordinate;
cutting the thermal image sample image according to the positioning coordinates to obtain a preliminary window thermal image;
and screening the preliminary window thermal image according to the temperature measurement sample data to obtain training sample data.
4. The thermographic indoor temperature measurement method of claim 3, wherein after obtaining training sample data, the method further comprises:
sending the training sample data to an automatic training server, wherein the automatic training server trains the second temperature detection model according to the training sample data, and teaches the knowledge learned by the trained second temperature detection model to the first temperature detection model in a distillation learning mode so as to train the first temperature detection model;
and receiving the trained first temperature detection model fed back by the automatic training server.
5. The infrared thermographic indoor temperature measuring method of claim 4, wherein the first temperature detection model is an SRAnet-student deep learning network model, and the second temperature detection model is an SRAnet-teacher deep learning network model.
6. The indoor temperature measurement method of the infrared thermography according to claim 1, wherein the first temperature detection model comprises a first convolution module, a first spatial circulation neural module, a second spatial circulation neural module, a third spatial circulation neural module, a fourth spatial circulation neural module, a first link module, a first decoding module and a second decoding module, wherein the window thermal image is input into a first temperature detection model trained in advance for temperature identification, and the method comprises the following steps:
performing feature extraction processing on the window thermal image through the first convolution module to obtain a first feature image;
respectively extracting features of the first feature map in different directions through the first space circulation neural module, the second space circulation neural module, the third space circulation neural module and the fourth space circulation neural module to obtain a first direction feature map, a second direction feature map, a third direction feature map and a fourth direction feature map;
linking the first feature map, the first direction feature map, the second direction feature map, the third direction feature map and the fourth direction feature map through the first linking module to obtain a coding feature map;
decoding the coding feature map through the first decoding module to obtain a first decoding intermediate feature map;
and decoding the first decoding intermediate characteristic diagram through the second decoding module to obtain the indoor temperature detection result.
7. The indoor temperature measurement method of the infrared thermography according to claim 6, wherein the first decoding module comprises a first multi-headed self-attention layer, a first normalization layer, a first feed-forward network layer and a second normalization layer, which are connected in sequence, wherein the decoding process of the encoded feature map by the first decoding module comprises:
performing feature extraction on the coding feature map through the first multi-head self-attention layer to obtain a first decoding feature map;
normalizing the coding feature map and the first decoding feature map through the first normalization layer to obtain a second decoding feature map;
processing the second decoding characteristic diagram through the first feedforward network layer to obtain a third decoding characteristic diagram;
and normalizing the second decoding characteristic diagram and the third decoding characteristic diagram through the second normalization layer to obtain the first decoding intermediate characteristic diagram.
8. The indoor temperature measurement method of the infrared thermography according to claim 7, wherein the second decoding module comprises a second multi-headed self-attention layer, a third normalization layer, a second feed-forward network layer and a fourth normalization layer, which are sequentially connected, wherein the decoding process of the first decoded intermediate feature map by the second decoding module comprises:
performing feature extraction on the first decoding intermediate feature map through the second multi-head self-attention layer to obtain a fourth decoding feature map;
normalizing the first decoding intermediate feature map and the fourth decoding feature map through the third normalization layer to obtain a fifth decoding feature map;
processing the fifth decoding characteristic diagram through the second feedforward network layer to obtain a sixth decoding characteristic diagram;
and normalizing the fifth decoding characteristic diagram and the sixth decoding characteristic diagram through the fourth normalization layer to obtain the indoor temperature detection result.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method for thermographic indoor temperature measurement according to any of claims 1-8.
10. An indoor temperature measurement system of infrared thermal imagery, comprising:
the system comprises a binocular thermal imager and a 3D cloud deck, wherein the 3D cloud deck is used for carrying the binocular thermal imager so as to shoot images outside a unit building and obtain real-time thermal image images and real-time high-definition images;
the micro embedded control analysis device is used for inputting the real-time high-definition image into a pre-trained target detection deep learning network for window positioning to obtain window position information, segmenting the real-time thermal image according to the window position information to obtain a window thermal image, and inputting the window thermal image into a pre-trained first temperature detection model for temperature identification to obtain an indoor temperature detection result, wherein the first temperature detection model is obtained by distilling and training a second temperature detection model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310148242.4A CN115876334B (en) | 2023-02-22 | 2023-02-22 | Infrared thermal image indoor temperature measurement method, system and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310148242.4A CN115876334B (en) | 2023-02-22 | 2023-02-22 | Infrared thermal image indoor temperature measurement method, system and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115876334A true CN115876334A (en) | 2023-03-31 |
| CN115876334B CN115876334B (en) | 2023-05-30 |
Family
ID=85761494
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310148242.4A Active CN115876334B (en) | 2023-02-22 | 2023-02-22 | Infrared thermal image indoor temperature measurement method, system and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115876334B (en) |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100296694A1 (en) * | 2007-12-11 | 2010-11-25 | Irt Surveys Ltd. | Quantification of energy loss from buildings |
| CN105701495A (en) * | 2016-01-05 | 2016-06-22 | 贵州大学 | Image texture feature extraction method |
| KR20190107789A (en) * | 2018-03-13 | 2019-09-23 | 상명대학교산학협력단 | How to judge the insulation index of a building by measuring the outside temperature |
| CN111561732A (en) * | 2020-05-18 | 2020-08-21 | 瑞纳智能设备股份有限公司 | Heat exchange station heat supply adjusting method and system based on artificial intelligence |
| CN112013966A (en) * | 2020-08-24 | 2020-12-01 | 电子科技大学 | Power equipment infrared image processing method based on measured temperature |
| CN112964370A (en) * | 2021-03-30 | 2021-06-15 | 清华大学 | Method for rapidly acquiring indoor air temperature from outdoor in batch through infrared thermal imaging |
| CN113267258A (en) * | 2021-05-18 | 2021-08-17 | 烟台艾睿光电科技有限公司 | Infrared temperature measurement method, device, equipment, intelligent inspection robot and storage medium |
| CN113449680A (en) * | 2021-07-15 | 2021-09-28 | 北京理工大学 | Knowledge distillation-based multimode small target detection method |
| CN214309201U (en) * | 2021-03-24 | 2021-09-28 | 瑞纳智能设备股份有限公司 | Room temperature collector with multiple temperature sensors |
| CN113705788A (en) * | 2021-08-27 | 2021-11-26 | 齐鲁工业大学 | Infrared image temperature estimation method and system based on full convolution neural network |
| CN113888737A (en) * | 2021-09-16 | 2022-01-04 | 杭州英集动力科技有限公司 | Hot user room temperature measuring method and system based on temperature measurement image shot by intelligent equipment |
| CN114298973A (en) * | 2021-12-01 | 2022-04-08 | 哈尔滨工业大学 | Intelligent heat supply monitoring method based on infrared image segmentation |
| CN115063418A (en) * | 2022-08-10 | 2022-09-16 | 北京航空航天大学 | Power battery temperature detection method based on image recognition |
| CN115077717A (en) * | 2022-06-14 | 2022-09-20 | 深圳弘洁凯电子科技有限公司 | Millimeter wave infrared temperature measurement method and device, electronic equipment and storage medium |
| CN115118928A (en) * | 2022-06-14 | 2022-09-27 | 江苏国信协联能源有限公司 | Heat supply pipeline video intelligent vision perception alarm system |
| CN115359338A (en) * | 2022-10-20 | 2022-11-18 | 南京信息工程大学 | Sea surface temperature prediction method and system based on hybrid learning model |
| CN115410003A (en) * | 2022-08-31 | 2022-11-29 | 广东电网有限责任公司广州供电局 | Power distribution room temperature early warning method, system and medium based on deep learning and infrared detection |
| CN115541030A (en) * | 2022-09-21 | 2022-12-30 | 中冶南方工程技术有限公司 | Method and device for identifying temperature distribution of blast furnace top charge level and storage medium |
| CN115661016A (en) * | 2022-12-08 | 2023-01-31 | 瑞纳智能设备股份有限公司 | Fault monitoring method and system of heat exchange station and embedded image diagnosis control platform |
-
2023
- 2023-02-22 CN CN202310148242.4A patent/CN115876334B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100296694A1 (en) * | 2007-12-11 | 2010-11-25 | Irt Surveys Ltd. | Quantification of energy loss from buildings |
| CN105701495A (en) * | 2016-01-05 | 2016-06-22 | 贵州大学 | Image texture feature extraction method |
| KR20190107789A (en) * | 2018-03-13 | 2019-09-23 | 상명대학교산학협력단 | How to judge the insulation index of a building by measuring the outside temperature |
| CN111561732A (en) * | 2020-05-18 | 2020-08-21 | 瑞纳智能设备股份有限公司 | Heat exchange station heat supply adjusting method and system based on artificial intelligence |
| CN112013966A (en) * | 2020-08-24 | 2020-12-01 | 电子科技大学 | Power equipment infrared image processing method based on measured temperature |
| CN214309201U (en) * | 2021-03-24 | 2021-09-28 | 瑞纳智能设备股份有限公司 | Room temperature collector with multiple temperature sensors |
| CN112964370A (en) * | 2021-03-30 | 2021-06-15 | 清华大学 | Method for rapidly acquiring indoor air temperature from outdoor in batch through infrared thermal imaging |
| CN113267258A (en) * | 2021-05-18 | 2021-08-17 | 烟台艾睿光电科技有限公司 | Infrared temperature measurement method, device, equipment, intelligent inspection robot and storage medium |
| CN113449680A (en) * | 2021-07-15 | 2021-09-28 | 北京理工大学 | Knowledge distillation-based multimode small target detection method |
| CN113705788A (en) * | 2021-08-27 | 2021-11-26 | 齐鲁工业大学 | Infrared image temperature estimation method and system based on full convolution neural network |
| CN113888737A (en) * | 2021-09-16 | 2022-01-04 | 杭州英集动力科技有限公司 | Hot user room temperature measuring method and system based on temperature measurement image shot by intelligent equipment |
| CN114298973A (en) * | 2021-12-01 | 2022-04-08 | 哈尔滨工业大学 | Intelligent heat supply monitoring method based on infrared image segmentation |
| CN115118928A (en) * | 2022-06-14 | 2022-09-27 | 江苏国信协联能源有限公司 | Heat supply pipeline video intelligent vision perception alarm system |
| CN115077717A (en) * | 2022-06-14 | 2022-09-20 | 深圳弘洁凯电子科技有限公司 | Millimeter wave infrared temperature measurement method and device, electronic equipment and storage medium |
| CN115063418A (en) * | 2022-08-10 | 2022-09-16 | 北京航空航天大学 | Power battery temperature detection method based on image recognition |
| CN115410003A (en) * | 2022-08-31 | 2022-11-29 | 广东电网有限责任公司广州供电局 | Power distribution room temperature early warning method, system and medium based on deep learning and infrared detection |
| CN115541030A (en) * | 2022-09-21 | 2022-12-30 | 中冶南方工程技术有限公司 | Method and device for identifying temperature distribution of blast furnace top charge level and storage medium |
| CN115359338A (en) * | 2022-10-20 | 2022-11-18 | 南京信息工程大学 | Sea surface temperature prediction method and system based on hybrid learning model |
| CN115661016A (en) * | 2022-12-08 | 2023-01-31 | 瑞纳智能设备股份有限公司 | Fault monitoring method and system of heat exchange station and embedded image diagnosis control platform |
Non-Patent Citations (1)
| Title |
|---|
| 主编韩蕊: "《阿里巴巴B2B电商算法实战》", 北京机械工业出版社 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115876334B (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107707810B (en) | Thermal infrared imager-based heat source tracking method, device and system | |
| US8384783B2 (en) | Infrared camera and method for calculating output power value indicative of an amount of energy dissipated in an image view | |
| US8282274B2 (en) | Remote temperature sensing device | |
| CN111753712A (en) | Method, system and equipment for monitoring safety of power production personnel | |
| CN112673241A (en) | Infrared thermal imaging temperature measurement method, electronic equipment, unmanned aerial vehicle and storage medium | |
| CN109752722A (en) | Multi-modal acoustics imaging tool | |
| KR102344031B1 (en) | Plant health monitoring method and device | |
| US10991217B2 (en) | System and methods for computerized safety and security | |
| CN111189545B (en) | High-precision wide-area intelligent infrared body temperature screening method and system | |
| CN111751003A (en) | Thermal imager temperature correction system and method and thermal imager | |
| CN110567964A (en) | method and device for detecting defects of power transformation equipment and storage medium | |
| CN109752721A (en) | Portable acoustics imaging tool with scanning and analysis ability | |
| CN113273178A (en) | Animal house monitoring method and animal house monitoring system | |
| CN111854964A (en) | Method and device for measuring body temperature, temperature measuring tool and storage medium | |
| CN114035606A (en) | Pole tower inspection system, pole tower inspection method, control device and storage medium | |
| CN115588040A (en) | System and method for counting and positioning coordinates based on full-view imaging points | |
| CN105160799B (en) | A kind of condition of a fire based on infrared thermal imaging uncorrected data and thermal source detection method and device | |
| CN115876334A (en) | Infrared thermal image indoor temperature measurement method and system and computer readable storage medium | |
| KR101929539B1 (en) | Method and System for detecting fire using genetic algorithm | |
| CN116999026A (en) | Traditional Chinese medicine physique identification method and equipment combining edge calculation and infrared imaging | |
| SE541887C2 (en) | Systems and methods for determining likelihood of states in cattle animal | |
| CN116224884A (en) | Poultry house environment and poultry temperature sensing control system and method based on AI vision | |
| CN116559713A (en) | Intelligent monitoring method and device for power supply of communication base station | |
| CN115205714A (en) | Fire point positioning method and device, electronic equipment and storage medium | |
| CN115661016A (en) | Fault monitoring method and system of heat exchange station and embedded image diagnosis control platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |