A heat-sensitive textile detection device and a detection method thereof

Abstract

The application discloses a kind of heat-sensitive textile detection device and its detection method, it is related to heat-sensitive detection technical field.The heat-sensitive textile detection device and its detection method, comprising: S1, acquisition heat-sensitive color original data, and heat-sensitive color original data is preprocessed;S2, assesses the response consistency level of each pixel of color developing area, generates response consistency distribution diagram, and judges whether pixel responds stably;S3, extract response stable pixel aggregation area, construct candidate area set, and assess the adaptability of heat-sensitive pattern in candidate layout area, carry out layout grade division, output layout zoning label map;S4, carry out heat-sensitive response stability evaluation, construct two-dimensional joint feature analysis diagram, carry out cluster analysis, and divide candidate layout area into four categories response area, and match corresponding layout optimization strategy.The problem that pattern layout area is difficult to adapt stably due to uneven heat-sensitive color response is solved.

Description

Technical Field

[0001] This invention relates to the field of thermal detection technology, specifically to a thermal textile detection device and its detection method. Background Technology

[0002] With the widespread application of thermochromic mechanisms in material testing, state indication, and structure recognition, some technologies have begun to introduce thermochromic materials into image analysis and physical field response to improve the intuitiveness and spatial resolution of detection.

[0003] For example, the invention with announcement number CN114324198B discloses a method for inspecting the quality of adhesive application in battery cells, including the following steps: preparing an adhesive solution, adding a reversible thermochromic material to the adhesive solution and stirring evenly; heating the adhesive solution to make it fluid; applying the adhesive solution mixed with the reversible thermochromic material to the adhesive application area on the surface of the battery cell; and acquiring an image of the surface of the battery cell after adhesive application using an image acquisition device to check for any missing adhesive lines. This invention, by adding a reversible thermochromic material to the adhesive solution, causes the adhesive lines formed by the solution to change color at different temperatures, thus allowing the adhesive lines to have a color significantly different from the aluminum-plastic film during inspection, facilitating the inspection of the adhesive line status. At room temperature, the adhesive lines do not show color and do not affect the battery appearance.

[0004] For example, the invention with announcement number CN114942244B discloses a device and method for detecting the strength grade of hard rock based on the thermal sensitivity properties of materials. The device includes: a hemispherical thermochromic coating cover with four ventilation openings around its bottom, four LED lights mounted on its lower inner wall, and a laser head mounted on its top; a high-definition camera mounted on the middle of the inner side of the thermochromic coating cover via a camera mounting bracket; an exhaust fan connected to the exhaust port via an air pipe; and a laser emitting device including a laser and a laser head connected via a transmission optical fiber. The method involves: preparation; radiating a high-energy laser beam vertically onto the surface of the rock mass to be tested through the laser head; expelling the smoke generated during the radiation process; acquiring high-definition images through the high-definition camera; performing image recognition and extracting index parameters, and comparing and analyzing them with a database to obtain the results.

[0005] However, existing technologies mainly focus on macroscopic color differences or binarized region identification, lacking a systematic evaluation mechanism for the temporal dynamic characteristics of the color development process, multidimensional thermal response consistency, pixel-level layout adaptability, and response stability. Especially when dealing with complex pattern layouts and response control requirements, existing methods struggle to achieve pixel-level adaptation planning and closed-loop optimization control based on temperature-sensitive response characteristics.

[0006] Therefore, in order to address the above problems, there is an urgent need for a heat-sensitive textile testing device and its testing method. Summary of the Invention

[0007] Technical problems to be solved

[0008] To address the shortcomings of existing technologies, this invention provides a thermal textile detection device and method, which solves the problem of uneven thermal color development response leading to difficulty in stably adapting the pattern layout area.

[0009] Technical solution

[0010] To achieve the above objectives, the present invention provides the following technical solution: a thermal textile detection device and its detection method, comprising: S1, acquiring thermal color development raw data, and performing alignment, mapping, removal, and normalization processing on the thermal color development raw data to obtain preprocessed thermal color development raw data; S2, constructing a thermal color development input dataset based on the preprocessed thermal color development raw data, evaluating the response consistency level of each pixel in the color development area, generating a response consistency distribution map based on the evaluation results, and determining whether the pixel response is stable; S3, based on the response consistency distribution... The layout process involves extracting stable pixel clusters, constructing a set of candidate layout regions, evaluating the adaptability of thermal patterns within these regions, classifying layout levels based on the evaluation results, and outputting a layout partition label map. In step S4, core optimal layout regions and stable layout regions are extracted for thermal response stability evaluation, and a two-dimensional joint feature analysis map is constructed based on regional adaptability features. Cluster analysis is then performed based on the two-dimensional joint feature analysis map to identify highly adaptable stable layout sub-regions and generate a layout strategy map. The candidate layout regions are divided into four types of response regions, and corresponding layout optimization strategies are matched.

[0011] Further, the raw thermal colorimetric data is collected, and aligned, mapped, removed, and normalized. The specific steps to obtain the preprocessed raw thermal colorimetric data are as follows: The raw thermal colorimetric data includes three-dimensional temperature data, material surface reflectivity, surface height map, local incident angle, image coordinate distance, and pixel calibration ratio; multi-source time-series unified processing is performed on the raw thermal colorimetric data using a time-label alignment method; image coordinates are converted to actual physical space using spatial coordinate mapping; outlier removal and sampling integrity checks are performed on the raw thermal colorimetric data using geometric structure verification rules; structural unification and standardization are performed on the raw thermal colorimetric data using format parsing and field organization processes; and normalization is performed on the raw thermal colorimetric data using unit conversion and scale normalization methods.

[0012] Furthermore, based on the preprocessed thermal colorimetric raw data, a thermal colorimetric input dataset is constructed. The specific steps for evaluating the response consistency level of each pixel in the colorimetric region are as follows: Based on the preprocessed thermal colorimetric raw data, a thermal colorimetric input dataset is constructed: the number of pixels exceeding the temperature threshold in the three-dimensional temperature data is counted and converted using pixel area to obtain the area of ​​the colorimetric region; a reflectivity compensation model is constructed using three-dimensional temperature data and material surface reflectivity to obtain the colorimetric time of each pixel, and the mean and standard deviation of the colorimetric time within the colorimetric region are calculated; the colorimetric propagation path length and colorimetric propagation speed are obtained by combining image coordinate distance and pixel calibration ratio; the colorimetric time and temperature change rate are differentially processed. The average temperature rise rate of the color development region is obtained. Based on the thermal color development input dataset, the response consistency of each pixel within the color development region is evaluated: the color development propagation speed is multiplied by the average temperature rise rate of the color development region to obtain the color development response intensity term; the difference between the color development time and the mean color development time is divided by the mean color development time and squared to obtain the color development time deviation term; the standard deviation of the color development time is divided by the mean color development time and then multiplied by the time series fluctuation adjustment coefficient to obtain the color development time series fluctuation term; the color development time deviation term and the color development time series fluctuation term are added together and one is added to obtain the instability factor; the color development response intensity term is divided by the instability factor, and after area integration within the color development region, it is divided by the area of ​​the color development region to obtain the thermal color development response consistency value.

[0013] Furthermore, the specific steps for generating a response consistency distribution map based on the evaluation results and determining whether a pixel's response is stable are as follows: The thermal colorimetric response consistency value is discretized and calculated pixel by pixel in the spatial dimension to output the response consistency distribution map of the color pattern; During the image update cycle, the thermal colorimetric response consistency value and the color response threshold of each pixel are compared in real time. If the thermal colorimetric response consistency value is greater than the color response threshold, the pixel is marked as a stable response pixel; if the thermal colorimetric response consistency value is less than or equal to the color response threshold, the pixel is marked as an unstable response pixel.

[0014] Furthermore, the specific steps for extracting stable pixel clusters based on the response consistency distribution map, constructing a set of candidate deployment regions, and evaluating the adaptability of thermal patterns within the candidate deployment regions are as follows: A two-dimensional Cartesian coordinate system is constructed using the thermal image space, and the position coordinates of each pixel are output; based on the response consistency distribution map, continuous clusters of stable pixels are used as candidate deployment regions for patterns, a set of candidate deployment regions is constructed, and the area corresponding to each candidate deployment region is calculated; the adaptability of thermal patterns within the candidate deployment regions is evaluated: the thermal color development response consistency value is multiplied by the color development propagation speed and the average temperature rise rate of the color development region to obtain the deployment response performance term; the standard deviation of color development time is divided by the mean of color development time to obtain the response time fluctuation term; the deployment response performance term is integrated over the area of ​​the candidate deployment regions and divided by the area of ​​the deployment region to obtain the unit response score; the unit response score is then divided by the response time fluctuation term plus one to obtain the thermal pattern deployment adaptability evaluation value.

[0015] Further, the specific steps for classifying the layout levels based on the evaluation results and outputting the layout partition label map are as follows: Real-time comparison of the thermal pattern layout adaptation evaluation value and the layout adaptation threshold of each layout candidate area to classify the area into levels: If the thermal pattern layout adaptation evaluation value is greater than or equal to the first-level layout adaptation threshold, the area is marked as a core optimal layout area, used for priority layout of the main structure of the thermal pattern, the center line of text, and the visual focus area; if the thermal pattern layout adaptation evaluation value is less than the first-level layout adaptation threshold but greater than the second-level layout adaptation threshold, it is designated as a stable layout area, used for auxiliary graphics, edge embellishment, and structural extension; if the thermal pattern layout adaptation evaluation value is less than or equal to the second-level layout adaptation threshold, it is marked as a restricted layout area, which does not participate in thermal pattern graphic mapping and is used for subsequent pattern adjustment and material replacement design; the level classification results of each layout candidate area are written into the response adaptation layer, and the corresponding layout partition label map is generated.

[0016] Furthermore, the specific steps for extracting the core optimal distribution area and stable distribution area for thermal response stability assessment, and constructing a two-dimensional joint feature analysis map based on regional adaptability characteristics are as follows: Based on the distribution partition label map, extract all candidate distribution areas marked as core optimal distribution areas and stable distribution areas, and assess thermal response stability: use the square of the thermal pattern distribution adaptation assessment value minus one as the response mismatch term; use the square of the spatial gradient of the thermal color development response consistency value as the response equilibrium perturbation term; divide the standard deviation of color development time by the mean of color development time as the response temporal fluctuation term; and use the response... After multiplying the mismatch term, the response equilibrium disturbance term, and the response time fluctuation term, the area is integrated within the candidate pattern layout region. The integral result is divided by the area of ​​the layout region to obtain the thermal response stability evaluation value. The thermal pattern layout adaptation evaluation value and the thermal response stability evaluation value of each pixel in the candidate layout region are aligned at the pixel level, and a two-dimensional joint feature distribution map is constructed in the image coordinate space, where the horizontal axis is the layout adaptation evaluation value and the vertical axis is the response stability evaluation value. The distribution density of the pixels in the figure is used to reflect the aggregation trend and distribution structure of the response features within the layout region.

[0017] Furthermore, the specific steps for performing cluster analysis based on the two-dimensional joint feature analysis map to identify highly adaptable and stable deployment sub-regions and generate a deployment strategy map are as follows: Based on the two-dimensional joint feature distribution map, perform two-dimensional feature clustering operations on all pixels within the deployment candidate region to automatically divide pixel clusters of different response levels; extract the index of pixels contained in high-level clusters, map the corresponding pixel numbers back to the original image coordinate space, and generate a spatial distribution mask layer for highly adaptable and stable deployment sub-regions; based on the spatial distribution mask layer for highly adaptable and stable deployment sub-regions, perform image boundary fitting processing on the high-level clusters, and perform region fusion in conjunction with the deployment partition label map to generate a deployment recommendation region map; overlay this deployment recommendation region map with the response consistency distribution map and the deployment adaptation level map to output the deployment strategy map.

[0018] Furthermore, the specific steps for dividing the candidate deployment area into four types of response areas and matching them with corresponding deployment optimization strategies are as follows: Based on the deployment strategy map, extract the thermal pattern deployment adaptation evaluation value and thermal response stability evaluation value corresponding to each pixel; within the image coordinate space, divide the candidate deployment area into four types of response areas according to the adaptation threshold and stability threshold: when both evaluation values ​​are lower than the corresponding threshold, it is marked as a response insufficiency area, and deployment rejection and material replacement are performed; when the deployment adaptation evaluation value is higher than the adaptation threshold but the response stability evaluation value is lower than the stability threshold, it is marked as a response redundancy area, and thermal response correction is performed; when the stability evaluation value is higher than the adaptation threshold but the adaptation evaluation value is lower than the stability threshold, it is marked as a potential improvement area, and temperature control adjustment and pattern migration are performed; when both evaluation values ​​are higher than the corresponding threshold, it is marked as a stable deployment priority area, and deployment structure parameter locking is performed; generate a response deviation label map based on the response area division and corresponding strategy to realize dynamic adjustment of the thermal pattern deployment area and closed-loop control of response performance.

[0019] The second aspect of this invention provides a thermal textile detection device, comprising: a thermal color development raw data acquisition and preprocessing module, a thermal response consistency evaluation and pixel classification module, a layout adaptability evaluation and region classification module, and a response stability fusion optimization and strategy decision-making module. The thermal color development raw data acquisition and preprocessing module is used to acquire thermal color development raw data and perform alignment, mapping, removal, and normalization processing on the raw data to obtain preprocessed thermal color development raw data. The thermal response consistency evaluation and pixel classification module is used to construct a thermal color development input dataset based on the preprocessed thermal color development raw data, evaluate the response consistency level of each pixel in the color development region, and generate a response consistency distribution map based on the evaluation results. The system performs several optimizations, including: determining pixel stability; a deployment adaptability assessment and regional classification module, which extracts stable pixel clusters based on the response consistency distribution map, constructs a set of deployment candidate regions, assesses the adaptability of thermal patterns within these candidate regions, classifies deployment levels based on the assessment results, and outputs a deployment partition label map; a response stability fusion optimization and strategy decision module, which extracts core optimal deployment areas and stable deployment areas for thermal response stability assessment, and constructs a two-dimensional joint feature analysis map based on regional adaptability features; cluster analysis is performed based on the two-dimensional joint feature analysis map to identify highly adaptable stable deployment sub-regions and generate a deployment strategy map, dividing the deployment candidate regions into four types of response regions and matching corresponding deployment optimization strategies.

[0020] Beneficial effects

[0021] The present invention has the following beneficial effects:

[0022] (1) The thermal textile detection device and its detection method, by comprehensively considering the color development propagation speed, the average temperature rise rate of the color development area, the mean and standard deviation of the color development time, design a color development response intensity term and an instability factor to quantify the response consistency level of each pixel during the color development process. Based on this method, a response consistency distribution map can be output, thereby calibrating stable and unstable pixels and improving the reliability judgment ability of the initially selected area.

[0023] (2) The thermal textile detection device and its detection method calculate the layout response performance term by combining the thermal color development response consistency value, color development propagation speed and average temperature rise rate of the color development area in the stable pixel cluster area, and introduce the ratio of color development time standard deviation to mean to construct the response time fluctuation term, thereby quantifying the response score level of the unit area; and divide the candidate area into core superior layout area, stable layout area and restricted layout area, thereby improving the matching accuracy of thermal pattern functional structure in the material area.

[0024] (3) This thermal textile testing device and method, by taking the core optimal distribution area and the stable distribution area as the evaluation target areas, couples the inverse index of the thermal pattern distribution adaptation evaluation value, the spatial gradient characteristics of the consistency distribution map, and the statistical fluctuation of color development time to calculate and output the thermal response stability evaluation value. It reflects the stability of the distribution area under the influence of factors such as temperature control load, material heterogeneity, and structural disturbance, and provides support for the stability verification of pattern distribution.

[0025] (4) The thermal textile detection device and its detection method generate a layout strategy map by overlaying and fusing the spatial distribution mask layer of the high-fit-high-stability layout sub-region, the response consistency distribution map and the layout fit level map. It also delineates the insufficient response area, the redundant response area, the potential improvement area and the stable optimal layout area, and guides the selection of strategies such as layout rejection, thermal control adjustment, structural migration and locking, thereby realizing the visualization and automated processing of layout optimization. Attached Figure Description

[0026] Figure 1 This is a flowchart of a testing method for heat-sensitive textiles;

[0027] Figure 2 This is a structural diagram of a heat-sensitive textile detection device;

[0028] Figure 3 To create a distribution map of candidate region levels;

[0029] Figure 4 To deploy a two-dimensional distribution map of the response characteristics of the candidate regions. Detailed Implementation

[0030] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] Please see Figures 1-4 This invention provides a technical solution: a thermal textile detection device and its detection method, comprising: S1, collecting thermal color development raw data, and performing alignment, mapping, elimination and normalization processing on the thermal color development raw data to obtain preprocessed thermal color development raw data; S2, constructing a thermal color development input dataset based on the preprocessed thermal color development raw data, evaluating the response consistency level of each pixel in the color development area, generating a response consistency distribution map based on the evaluation results, and determining whether the pixel response is stable; S3, extracting the stable pixel clustering area based on the response consistency distribution map, constructing a set of deployment candidate areas, evaluating the adaptability of the thermal pattern in the candidate deployment area, classifying the deployment level according to the evaluation results, and outputting a deployment partition label map; S4, extracting the core optimal deployment area and stable deployment area for thermal response stability evaluation, and constructing a two-dimensional joint feature analysis map based on the regional adaptability characteristics; performing cluster analysis based on the two-dimensional joint feature analysis map, identifying highly adaptable stable deployment sub-areas and generating a deployment strategy map, dividing the deployment candidate areas into four types of response areas, and matching corresponding deployment optimization strategies.

[0032] Specifically, the following steps are taken to collect raw thermal colorimetric data and perform alignment, mapping, elimination, and normalization on the raw data to obtain preprocessed raw thermal colorimetric data: First, raw thermal colorimetric data is collected, including three-dimensional temperature data, material surface reflectivity, surface height map, local incident angle, image coordinate distance, and pixel calibration ratio. Using a time-stamp alignment method, multi-source time-series unified processing is performed on the raw thermal colorimetric data to ensure that data from different sensors remain synchronized in time, and time synchronization error correction is performed to improve data consistency and reliability. Next, through spatial coordinate mapping, the image coordinates in the raw thermal colorimetric data are converted to the actual physical space to establish a precise correspondence between the two, ensuring spatial consistency in subsequent processing. During data processing, geometric structure verification rules are used to eliminate outliers and check sampling integrity in the raw thermal colorimetric data. Abnormal data points that do not conform to physical laws or exceed the measurement range are eliminated, and missing values ​​are filled to ensure data integrity and accuracy. Through format parsing and field organization, the raw thermal colorimetric data undergoes structural unification and standardization to ensure that data from different sources and formats can be stored and processed according to a unified standard, facilitating the efficient application of subsequent algorithms. Furthermore, unit conversion and scale normalization methods are employed to normalize the raw thermal colorimetric data, mapping all data to the same dimension and scale range. This avoids the impact of inconsistencies between different data dimensions on subsequent analysis, ensuring data uniformity and comparability, and further improving the reliability of the analytical results.

[0033] In this implementation scheme, a systematic alignment, mapping, removal, and normalization process for the raw thermal colorimetric data ensures temporal and spatial synchronization and consistency of multi-source data. Time-label alignment guarantees the temporal consistency of raw thermal colorimetric data from different sensors, reducing the impact of time synchronization errors. Spatial coordinate mapping ensures accurate conversion between image coordinates and actual physical space, thereby improving spatial consistency in data processing. Furthermore, geometric structure verification rules effectively eliminate outliers, guaranteeing data integrity and accuracy. Format parsing and field organization processes unify the data structure, enabling seamless integration of data from different data sources and improving the efficiency of subsequent processing. Finally, unit conversion and scale normalization standardize all data to a unified scale, avoiding inconsistencies between different units of measurement, providing a solid data foundation for subsequent analysis, and improving the reliability and accuracy of the results.

[0034] Specifically, the following steps are taken to construct a thermal color-sensing input dataset based on preprocessed thermal color-sensing raw data and evaluate the response consistency level of each pixel in the color-sensing region: First, a thermal color-sensing input dataset is constructed based on the preprocessed thermal color-sensing raw data. The area of ​​the color-sensing region is obtained by statistically analyzing the number of pixels exceeding the temperature threshold in the three-dimensional temperature data and converting this data with the actual area of ​​each pixel in the image. Furthermore, a reflectivity compensation model is constructed by correlating the three-dimensional temperature data with the reflectivity of the material surface to obtain the color-sensing time of each pixel. Next, the mean and standard deviation of the color-sensing time of all pixels within the color-sensing region are calculated to analyze the response characteristics of the color-sensing. The color-sensing propagation path length and propagation speed are calculated by combining the image coordinate distance and pixel calibration ratio, providing necessary parameters for further analysis. By differentially processing the color-sensing time and temperature change rate, the average temperature rise rate within the color-sensing region is obtained, providing a valid basis for subsequent response consistency evaluation. Based on the constructed thermal color-sensing input dataset, the response consistency performance of each pixel within the color-sensing region is further evaluated. First, the color development propagation speed is multiplied by the average temperature rise rate of the color development region to obtain the color development response intensity term, reflecting the overall intensity of the color development response. Then, the difference between the color development time and the mean color development time is divided by the mean color development time, and the squared result yields the color development time deviation term, which assesses the temporal stability during the color development process. Next, the standard deviation of the color development time is divided by the mean color development time and multiplied by a time-series fluctuation adjustment coefficient to obtain the color development time-series fluctuation term, reflecting the impact of time fluctuations on response consistency during the color development process. The time-series fluctuation adjustment coefficient is determined based on the ratio of the standard deviation of the color development time to the mean color development time, and is used to adjust the weight of the color development time-series fluctuation term in the response consistency assessment. Its value range is within the deployment strategy... Figure 1 .0 Deployment Strategy Diagram to Deployment Strategy Figure 2 5. The color development time deviation term and the color development time fluctuation term are then added together, along with a constant term as an instability factor, to comprehensively evaluate the instability of the response. Finally, the color development response intensity term is divided by the instability factor to obtain the stable response intensity of each pixel. This is then integrated over the color development area and divided by the area of ​​the color development area to obtain the thermal color development response consistency value, thereby quantifying the response consistency level of the entire color development area.

[0035] The specific formula for calculating the thermochromic colorimetric response consistency value is as follows:

[0036] ;

[0037] In the formula, S represents the uniformity of the thermosensitive colorimetric response, A represents the area of ​​the colorimetric region, Ω represents the colorimetric region, V represents the colorimetric propagation speed, R represents the average temperature rise rate of the colorimetric region, and T represents the colorimetric time. This represents the average color development time. This represents the standard deviation of the color development time. This represents the time-series fluctuation adjustment coefficient.

[0038] In this implementation scheme, by comprehensively processing the pre-processed thermal colorimetric raw data, the consistency level of the response of each pixel within the colorimetric region is accurately assessed. First, based on the combination of three-dimensional temperature data and material surface reflectivity, the accurate calculation of the colorimetric region area is ensured. Important parameters such as colorimetric time and colorimetric propagation path are obtained through a reflectivity compensation model, providing reliable data support for subsequent analysis. The temporal stability of the colorimetric process is evaluated by calculating the mean and standard deviation of the colorimetric time. Furthermore, the consistency and stability of the response are comprehensively evaluated by combining the colorimetric response intensity term, colorimetric time deviation term, and time series fluctuation term. Finally, the calculated thermal colorimetric response consistency value comprehensively quantifies the response characteristics of the colorimetric region, providing a scientific basis for layout optimization and material selection, thereby improving the layout effect and stability of the thermal pattern.

[0039] Specifically, the steps for generating a response consistency distribution map based on the evaluation results and determining whether a pixel's response is stable are as follows: First, the thermal colorimetric response consistency value is discretized and calculated pixel-by-pixel in the spatial dimension, and the calculation result is output as a response consistency distribution map of the colorimetric pattern. This distribution map shows the response consistency level of each pixel under different conditions. The response consistency distribution map provides intuitive visualization data for subsequent analysis and helps identify areas with poor response consistency during the color development process. Subsequently, within the image update cycle, the thermal colorimetric response consistency value of each pixel is compared with the colorimetric response threshold in real time to dynamically evaluate the response stability of the colorimetric region. If the thermal colorimetric response consistency value is greater than the colorimetric response threshold, the pixel is marked as a stable pixel, indicating that the pixel region exhibits stable response characteristics during the color development process. Conversely, if the thermal colorimetric response consistency value is less than or equal to the colorimetric response threshold, the pixel is marked as an unstable pixel, indicating that the region has problems with unstable color development or insufficient response, requiring further optimization of the layout or materials. Through this series of processes, the present invention effectively identifies stable and unstable response regions, thereby providing a scientific basis for subsequent optimization of thermal pattern layout and material selection.

[0040] In this implementation scheme, a comprehensive evaluation of pixel response consistency within the color development area is achieved through discretization calculation based on the thermosensitive color development response consistency value and the generation of a response consistency distribution map. By comparing the thermosensitive color development response consistency value of each pixel with the color development response threshold in real time, unstable areas that may occur during the color development process can be dynamically detected, thereby accurately identifying areas with poor color development effects and optimizing them in a timely manner. This process ensures the stability of the color development area, effectively improves the accuracy and reliability of the thermosensitive pattern layout, and provides a solid foundation for subsequent layout optimization and material selection.

[0041] Specifically, the steps for extracting stable pixel clusters based on the response consistency distribution map, constructing a set of candidate deployment regions, and evaluating the suitability of thermal patterns within these candidate deployment regions are as follows: First, a two-dimensional Cartesian coordinate system is constructed using the thermal image space to ensure a precise correspondence between the image coordinates and the actual physical space. This coordinate system maps the horizontal and vertical axes of the image to the horizontal and vertical axes of the actual physical space, providing each pixel with unique and precise position coordinates. During this process, the horizontal and vertical coordinates of each pixel in the image have clear values ​​in the thermal image, ensuring accurate spatial positioning. Next, based on the response consistency distribution map, the color rendering characteristics of the thermal pattern are analyzed, identifying continuous clusters of stable pixels. Stable pixels refer to pixels whose response time remains highly consistent with temperature changes during color rendering and exhibit stable color rendering characteristics. Through a clustering algorithm, all pixels with high response consistency are grouped into a cluster, thus identifying these regions as stable response regions. These stable response regions are defined as candidate deployment regions, possessing coherence and continuity within the image space and exhibiting high deployment suitability. Based on this response consistency distribution map, multiple stable pixel clusters were further identified and integrated into a set of candidate deployment regions. On this basis, the area of ​​each candidate deployment region was statistically analyzed to ensure accurate quantification of the spatial dimensions of each region. Then, the adaptability of the thermal pattern within the candidate deployment regions was evaluated. First, the deployment response performance term was obtained by multiplying the thermal color development response consistency value by the color development propagation speed and the average temperature rise rate of the color development region, which was used to quantify the response intensity of each candidate region. Next, the ratio of the standard deviation of color development time to the mean of color development time was calculated to assess the response time fluctuation during the color development process, resulting in a response time fluctuation term that reflects the stability during the response process. Next, the deployment response performance term was integrated over the area of ​​the candidate pattern deployment regions to ensure a comprehensive evaluation of the response performance, and then divided by the area of ​​the deployment region to obtain a unit response score. Finally, the unit response score was divided by the response time fluctuation term plus one to obtain the thermal pattern deployment adaptability evaluation value, providing a basis for subsequent deployment optimization and decision-making. Through the above processing, the present invention can efficiently identify the most suitable area for laying thermal patterns and quantitatively evaluate its adaptability, thereby ensuring the effect and stability of thermal patterns during the laying process.

[0042] The specific formula for calculating the thermal pattern layout adaptation evaluation value is as follows:

[0043] ;

[0044] In the formula, P represents the thermal pattern layout adaptation evaluation value, S represents the thermal colorimetric response consistency value, V represents the color propagation speed, and R represents the average temperature rise rate of the colorimetric area. This represents the standard deviation of the color development time. This represents the average color development time. Indicates the area of ​​the candidate deployment region. This represents the candidate area for pattern layout, where x represents the horizontal coordinate of a pixel and y represents the vertical coordinate of a pixel.

[0045] In this embodiment, Table 1 shows the thermal pattern layout adaptation evaluation data. The table includes the thermal color response consistency value, color propagation speed, average temperature rise rate of the color-developing area, standard deviation of color development time, mean color development time, area of ​​the candidate layout area, and the calculated thermal pattern layout adaptation evaluation value for five candidate layout areas. Specific data are as follows: Area 1: Thermal color response consistency value is 0.82, color propagation speed is 1.25, average temperature rise rate of the color-developing area is 0.90, standard deviation of color development time is 0.12, mean color development time is 1.00, area of ​​the candidate layout area is 1200, and the final calculated layout adaptation evaluation value is 0.82. Region 2: Thermosensitive colorimetric response consistency value is 0.76, colorimetric propagation speed is 1.1, average temperature rise rate of the colorimetric region is 0.85, standard deviation of colorimetric time is 0.15, mean colorimetric time is 1.10, candidate deployment area is 1350, and the final calculated deployment fit evaluation value is 0.63. Region 3: Thermosensitive colorimetric response consistency value is 0.91, colorimetric propagation speed is 1.35, average temperature rise rate of the colorimetric region is 1.00, standard deviation of colorimetric time is 0.09, mean colorimetric time is 0.95, candidate deployment area is 1100, and the final calculated deployment fit evaluation value is 1.12. Region 4: Thermosensitive colorimetric response consistency value is 0.68, colorimetric propagation speed is 1.05, average temperature rise rate of the colorimetric region is 0.80, standard deviation of colorimetric time is 0.20, mean colorimetric time is 1.20, candidate deployment area is 1400, and the final calculated deployment fit evaluation value is 0.49. Region 5: Thermosensitive colorimetric response consistency value is 0.79, colorimetric propagation speed is 1.20, average temperature rise rate of the colorimetric region is 0.88, standard deviation of colorimetric time is 0.13, mean colorimetric time is 1.05, candidate deployment area is 1250, and the final calculated deployment fit evaluation value is 0.74.

[0046] Table 1. Evaluation Values ​​of Thermal Pattern Layout Adaptability

[0047]

[0048] like Figure 3The image shows a distribution map of candidate deployment regions. This map displays the thermal pattern deployment adaptation evaluation values ​​for five candidate deployment regions. Based on the first-level and second-level deployment adaptation thresholds, the regions are divided into three deployment levels: regions below the second-level deployment adaptation threshold are marked as restricted deployment regions, displayed in red, indicating insufficient adaptation; regions between the first-level and second-level deployment adaptation thresholds are marked as stable deployment regions, displayed in orange, indicating a certain degree of deployment stability; regions above the first-level deployment adaptation threshold are marked as core optimal deployment regions, displayed in green, suitable for critical deployment of thermal patterns. Figure 3 It helps to intuitively judge the deployment potential of each candidate area and provides a basis for decision-making on the structural layout of thermal patterns.

[0049] In this implementation scheme, stable pixel clusters are extracted based on the response consistency distribution map, enabling precise identification and quantification of candidate deployment regions. A two-dimensional Cartesian coordinate system is constructed to ensure accurate positioning of each pixel, providing a spatial reference for subsequent region division and evaluation. The deployment response performance is quantified by combining the thermal color development response consistency value, color propagation speed, and average temperature rise rate of the color development area. Furthermore, the response time fluctuation during the color development process is evaluated by the ratio of the standard deviation of the color development time to the mean of the color development time, ensuring the comprehensiveness and accuracy of the evaluation process. The thermal pattern deployment adaptation evaluation value is obtained through the calculation of area integral and response score, providing a scientific basis for deployment optimization and decision-making. While ensuring the thermal pattern deployment effect, the stability and adaptability of the deployment area are effectively improved, providing strong support for the fine deployment of thermal patterns and material selection.

[0050] Specifically, the steps for classifying the layout levels based on the evaluation results and outputting the layout partition label map are as follows: First, compare the thermal pattern layout adaptation evaluation value with the layout adaptation threshold of each layout candidate area in real time to classify the area into levels. If the thermal pattern layout adaptation evaluation value is greater than or equal to the first-level layout adaptation threshold, the area is marked as the core optimal layout area, which is suitable for the priority layout of the main structure of the thermal pattern, the center line of the text, and the visual focus area; if the thermal pattern layout adaptation evaluation value is less than the first-level layout adaptation threshold but greater than the second-level layout adaptation threshold, the area is marked as the stable layout area, which is suitable for the layout of auxiliary graphics, edge decorations, and structural extensions; if the thermal pattern layout adaptation evaluation value is less than or equal to the second-level layout adaptation threshold, it is marked as the restricted layout area, which does not participate in the thermal pattern graphic mapping and is mainly used for subsequent pattern adjustment and material replacement design. After classifying the regions into hierarchical levels, the classification results of each candidate deployment region are written into the response adaptation layer. This ensures that the deployment regions within the layer and their corresponding adaptation levels are clearly identified, providing a basis for subsequent pattern deployment decisions. Finally, based on these classification results, a corresponding deployment partition label map is generated. This map visually displays the response adaptability of each deployment region, providing guidance for the accurate deployment and optimization of thermal patterns.

[0051] In this implementation scheme, precise hierarchical classification of deployment areas is achieved by comparing the thermal pattern deployment adaptation evaluation values ​​and deployment adaptation thresholds of each candidate deployment area in real time. Based on different evaluation results, core optimal deployment areas, stable deployment areas, and restricted deployment areas are clearly identified, providing a clear priority order for thermal pattern deployment. By writing the hierarchical classification results into the response adaptation layer, the synchronization of the deployment area adaptation level information with the layer data is ensured, further improving the accuracy of deployment optimization. By generating a deployment partition label map, the response adaptability of each area can be intuitively displayed, facilitating subsequent decision support and layout adjustments. This allows for dynamic optimization and stability improvement of deployment areas while ensuring the effectiveness of thermal patterns.

[0052] Specifically, the steps for extracting core optimal distribution areas and stable distribution areas for thermosensitive response stability assessment, and constructing a two-dimensional joint feature analysis map based on regional adaptability characteristics, are as follows: First, based on the distribution partition label map, all candidate distribution areas marked as core optimal distribution areas and stable distribution areas are extracted. For each candidate distribution area, the thermosensitive response stability is assessed. First, the response mismatch term is calculated, obtained by subtracting the square of the thermosensitive pattern distribution adaptation assessment value, to quantify the degree of mismatch between adaptability and stability; next, the response equilibrium perturbation term is calculated, obtained by the square of the spatial gradient of the thermosensitive colorimetric response consistency value, to assess the uniformity change of the colorimetric response; subsequently, the response temporal fluctuation term is calculated, obtained by dividing the standard deviation of colorimetric time by the mean of colorimetric time, to assess the impact of temporal fluctuations during the colorimetric process. After multiplying these three indicators—response mismatch term, response equilibrium perturbation term, and response temporal fluctuation term—area integration is performed within the candidate pattern distribution area to ensure a comprehensive assessment of all response characteristics within the distribution area. Finally, the integral result is divided by the area of ​​the deployment region to obtain the thermal response stability evaluation value, providing quantitative data on the regional response stability. Next, the thermal pattern deployment adaptation evaluation value and the thermal response stability evaluation value of each pixel within the candidate deployment region are aligned at the pixel level, and a two-dimensional joint feature distribution map is constructed in the image coordinate space. In the figure, the horizontal axis represents the deployment adaptation evaluation value, and the vertical axis represents the response stability evaluation value. The pixel density in the figure reflects the aggregation trend and distribution structure of the response features within the deployment region, further revealing the consistency and stability of responses in different regions and helping to identify potential optimization areas.

[0053] The specific formula for calculating the thermal response stability evaluation value is as follows:

[0054] ;

[0055] In the formula, Q represents the thermal response stability evaluation value, P represents the thermal pattern layout adaptation evaluation value, and S represents the thermal color development response consistency value. The spatial gradient representing the uniformity of thermochromic response. This represents the standard deviation of the color development time. This represents the average color development time. Indicates the area of ​​the candidate deployment region. This represents the candidate area for pattern layout, where x represents the horizontal coordinate of a pixel and y represents the vertical coordinate of a pixel.

[0056] In this embodiment, Table 2 is a data table of thermal response stability evaluation values, showing the thermal response stability evaluation data for five candidate deployment areas. This includes the thermal pattern deployment adaptation evaluation value, color propagation speed, color development time standard deviation, color development time mean, deployment area, and calculated thermal response stability evaluation value for each candidate deployment area. Specific data are as follows: Area A: Thermal pattern deployment adaptation evaluation value is 0.35, color propagation speed is 2.49, color development time standard deviation is 1.93, color development time mean is 0.89, deployment area is 6.88, and the final calculated thermal response stability evaluation value is 0.83. Area B: Thermal pattern deployment adaptation evaluation value is 0.33, color propagation speed is 2.49, color development time standard deviation is 1.95, color development time mean is 0.98, deployment area is 7.73, and the final calculated thermal response stability evaluation value is 0.72. Region C: Thermal pattern placement adaptation evaluation value is 0.34, color propagation speed is 2.40, color development time standard deviation is 1.50, color development time mean is 0.88, candidate area is 5.03, and the final calculated thermal response stability evaluation value is 0.85. Region D: Thermal pattern placement adaptation evaluation value is 0.37, color propagation speed is 2.45, color development time standard deviation is 1.86, color development time mean is 1.07, candidate area is 5.13, and the final calculated thermal response stability evaluation value is 0.81. Region E: Thermal pattern placement adaptation evaluation value is 0.33, color propagation speed is 0.27, color development time standard deviation is 1.44, color development time mean is 0.94, candidate area is 5.10, and the final calculated thermal response stability evaluation value is 0.69.

[0057] Table 2. Data Table of Thermosensitive Response Stability Evaluation Values

[0058]

[0059] like Figure 4The figure shows a two-dimensional distribution map of the response characteristics of the candidate deployment regions. The horizontal axis represents the thermal pattern deployment adaptation evaluation value, and the vertical axis represents the thermal response stability evaluation value. The figure shows the evaluation results of five candidate deployment regions, and based on the adaptation threshold of 0.35 and the stability threshold of 0.82, they are divided into four types of response regions. In this study, Region A has both its thermal pattern layout adaptation evaluation value and thermal response stability evaluation value higher than the corresponding thresholds, placing it in the stable layout priority zone. It is displayed in green, indicating a balanced performance in both layout adaptability and response stability, making it suitable for the core structure layout of thermal patterns. Region C has a thermal pattern layout adaptation evaluation value lower than the adaptability threshold, but its thermal response stability evaluation value is higher than the stability threshold, placing it in the potential improvement zone. It is displayed in blue, indicating good stability performance, but still needs to improve adaptability through pattern adjustment or local optimization. Regions B and E both have thermal pattern layout adaptation evaluation values ​​and thermal response stability evaluation values ​​lower than the corresponding thresholds, placing them in the insufficient response zone. They are displayed in red and are not recommended for direct layout; they should be considered for removal or material replacement. Region D has a thermal pattern layout adaptation evaluation value higher than the adaptability threshold, but its thermal response stability evaluation value is lower than the stability threshold, placing it in the response redundancy zone. It is displayed in yellow, indicating that the adaptability of this region meets the requirements, but the stability is poor, requiring thermal response correction. Figure 4 It provides multi-dimensional response characteristics for deployment strategies, which helps to accurately identify preferred areas and potential weak areas in spatial partitioning, and realize the refined deployment and closed-loop optimization of thermal patterns.

[0060] In this implementation scheme, the core optimal deployment area and stable deployment area are extracted based on the deployment partition label map, enabling accurate evaluation of the response stability of the thermal pattern deployment area. By calculating the response mismatch term, response equilibrium disturbance term, and response time series fluctuation term, and then integrating them by area, a thermal response stability evaluation value is obtained, providing a quantitative basis for the response stability of the deployment area. Simultaneously, by constructing a two-dimensional joint feature distribution map, the adaptability and response stability distribution within the candidate deployment area can be visually displayed, helping to identify the clustering trend and distribution structure of response features within the area. This provides reliable data support for the optimization and adjustment of thermal pattern deployment, ensuring the comprehensiveness and accuracy of the deployment area in terms of adaptability and stability, and also achieving improved thermal pattern deployment effect and stability optimization.

[0061] Specifically, the steps for cluster analysis based on a two-dimensional joint feature analysis map to identify highly adaptable and stable deployment sub-regions and generate deployment strategy maps are as follows: First, based on the two-dimensional joint feature distribution map, two-dimensional feature clustering operations are performed on all pixels within the candidate deployment regions. The clustering algorithm automatically divides pixel clusters into different response levels, ensuring that each pixel is classified into its corresponding response region based on its adaptability and stability. The clustering process considers the combined performance of the thermal pattern deployment adaptability evaluation value and the thermal response stability evaluation value, ensuring that pixel clusters of different response levels accurately reflect the deployment potential and stability of the region. Next, for pixels contained in high-level clusters, index extraction is performed to ensure that the mapping relationship between the selected pixels and their respective regions in the image coordinate space is accurate. By mapping the corresponding pixel numbers back to the original image coordinate space, a spatial distribution mask layer for highly adaptable and stable deployment sub-regions is generated. The spatial distribution mask layer is a visualization data layer generated after quantifying and evaluating the response features of different regions in the image. This layer ensures the accurate spatial location of each pixel in the image by mapping the pixel number in the high-fit stable deployment sub-region back to the original image coordinate space. The mask layer identifies areas with priority in thermal pattern deployment and distinguishes them from other areas. The value corresponding to each pixel in the mask layer typically indicates that the pixel belongs to the high-fit stable deployment sub-region, while other areas that do not meet the criteria are marked as non-target areas. After obtaining the spatial distribution mask layer of the high-fit stable deployment sub-region, further image boundary fitting processing is performed on high-level clusters. Through algorithm optimization, the boundaries of clusters are accurately located, improving the accuracy and reliability of deployment area definition. Simultaneously, combined with the deployment partition label map, region fusion processing is performed to ensure the coordination and continuity between different deployment areas, thereby generating a deployment recommendation area map, providing clear guidance for deployment decisions. Finally, this deployment recommendation area map is overlaid with the response consistency distribution map and the deployment fit level map to output a deployment strategy map, providing a clear decision-making basis for the accurate deployment and optimization of thermal patterns, ensuring the maximization of deployment effects.

[0062] In this implementation scheme, cluster analysis based on a two-dimensional joint feature distribution map is used to accurately segment candidate deployment regions. By automatically segmenting pixel clusters with different response levels, highly adaptable and stable deployment sub-regions are effectively identified, providing data support for the precise optimization of thermal pattern deployment. By mapping pixel numbers back to the original image coordinate space and generating a spatial distribution mask layer for highly adaptable and stable deployment sub-regions, the spatial positioning accuracy of the deployment regions is ensured. Furthermore, image boundary fitting and region fusion processing optimize the boundary accuracy of the deployment regions and improve the overall coordination of the deployment strategy. Finally, the deployment recommendation region map is overlaid with the response consistency distribution map and the deployment adaptation level map to generate a deployment strategy map, providing a reliable basis for adjusting the layout of thermal patterns and ensuring comprehensive optimization of deployment effects and improved response stability.

[0063] Specifically, the steps for dividing the candidate deployment regions into four response regions and matching them with corresponding deployment optimization strategies are as follows: First, based on the deployment strategy map, extract the thermal pattern deployment adaptation evaluation value and thermal response stability evaluation value corresponding to each pixel to ensure that the response characteristics of all pixels are fully quantified. Within the image coordinate space, combine the adaptation threshold and the stability threshold to divide the candidate deployment regions into four response regions. Specifically, when both evaluation values ​​are below the corresponding threshold, it is marked as an insufficient response area, indicating that the area does not meet the standards in terms of adaptability and stability, and needs to be removed from the layout and replaced with materials according to actual needs; when the layout adaptability evaluation value is higher than the adaptability threshold but the response stability evaluation value is lower than the stability threshold, it is marked as a response redundancy area, indicating that the adaptability of the area meets the requirements, but the stability is poor, so thermal response correction needs to be performed to limit the occurrence of over-coloring; when the stability evaluation value is higher than the adaptability threshold but the adaptability evaluation value is lower than the stability threshold, it is marked as a potential improvement area, indicating that the stability of the area is good, but the adaptability is slightly inferior, and temperature control adjustment and pattern migration need to be performed to further improve the adaptability effect; when both evaluation values ​​are higher than the corresponding threshold, it is marked as a stable layout priority area, indicating that the area performs well in terms of adaptability and stability, is suitable for priority layout, and layout structure parameter locking is performed to ensure that the layout effect of the area remains stable in long-term use. A response deviation label map is generated based on the response area division and corresponding strategy. This map clearly shows the response performance of each area, providing guidance for the dynamic adjustment and optimization of the subsequent deployment area, and realizing closed-loop control of the response performance of the thermal pattern deployment area.

[0064] In this implementation scheme, by dividing the candidate deployment area into four response regions and combining them with corresponding deployment optimization strategies, precise classification and optimization of the thermal pattern deployment area are achieved. By comparing the thermal pattern deployment adaptation evaluation value and thermal response stability evaluation value of each pixel in real time, areas with insufficient response, redundant response, potential improvement areas, and stable deployment priority areas can be accurately identified, thereby formulating corresponding optimization strategies for each region. This ensures dynamic adjustment of the deployment area and closed-loop control of response performance, improving the adaptability, stability, and overall effect of the thermal pattern deployment. The generation of response deviation label maps further optimizes the precise control of the deployment area, providing a solid basis for refined thermal pattern deployment and material selection, ensuring maximum deployment effect and improved stability.

[0065] like Figure 2 As shown, a second aspect of the present invention provides a thermal textile detection device, comprising: a thermal color development raw data acquisition and preprocessing module, a thermal response consistency evaluation and pixel classification module, a layout adaptability evaluation and regional level division module, and a response stability fusion optimization and strategy decision-making module, wherein: the thermal color development raw data acquisition and preprocessing module is used to acquire thermal color development raw data and perform alignment, mapping, removal, and normalization processing on the thermal color development raw data to obtain preprocessed thermal color development raw data; the thermal response consistency evaluation and pixel classification module is used to construct a thermal color development input dataset based on the preprocessed thermal color development raw data, evaluate the response consistency level of each pixel in the color development area, and generate a response consistency distribution based on the evaluation results. The system analyzes the thermal pattern and determines whether the pixel response is stable. A deployment adaptability assessment and regional classification module is used to extract stable pixel clusters based on the response consistency distribution map, construct a set of deployment candidate regions, evaluate the adaptability of the thermal pattern within the candidate deployment regions, classify deployment levels based on the evaluation results, and output a deployment partition label map. A response stability fusion optimization and strategy decision module is used to extract core optimal deployment areas and stable deployment areas for thermal response stability assessment, and construct a two-dimensional joint feature analysis map based on regional adaptability characteristics. Based on the two-dimensional joint feature analysis map, cluster analysis is performed to identify highly adaptable stable deployment sub-regions and generate a deployment strategy map, dividing the deployment candidate regions into four types of response regions and matching corresponding deployment optimization strategies.

[0066] This implementation plan achieves accuracy and efficiency in the detection of thermal textiles by integrating a thermal colorimetric raw data acquisition and preprocessing module, a thermal response consistency assessment and pixel classification module, a layout adaptability assessment and regional classification module, and a response stability fusion optimization and strategy decision-making module. The thermal colorimetric raw data acquisition and preprocessing module ensures spatiotemporal alignment and standardization of data, improving the reliability of subsequent analysis. The thermal response consistency assessment and pixel classification module quantifies the response consistency of each pixel in the colorimetric area, generating a response consistency distribution map to further determine pixel response stability and provide a basis for layout area optimization. The layout adaptability assessment and regional classification module accurately assesses the adaptability of the thermal pattern within the candidate layout area by identifying areas of stable pixel clusters, and classifies the layout based on the assessment results, generating a layout partition label map to ensure the scientific and rational nature of the layout process. The response stability fusion optimization and strategy decision-making module uses a two-dimensional joint feature analysis map to perform cluster analysis, identify highly adaptable and stable deployment sub-regions, and generate a deployment strategy map. This provides customized optimization strategies for different response regions, ensuring the efficiency and stability of thermal pattern deployment. Through the synergistic effect of the above modules, this invention provides comprehensive support for the refined deployment and optimization of thermal patterns.

[0067] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0068] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for detecting heat-sensitive textiles, characterized in that, Includes the following steps: S1, collect the raw thermal colorimetric data, and perform alignment, mapping, elimination and normalization processing on the raw thermal colorimetric data to obtain the preprocessed raw thermal colorimetric data; S2. Construct a thermal colorimetric input dataset based on the preprocessed thermal colorimetric raw data, evaluate the response consistency level of each pixel in the colorimetric region, generate a response consistency distribution map based on the evaluation results, and determine whether the pixel response is stable. The specific steps for constructing a thermal colorimetric input dataset based on the preprocessed thermal colorimetric raw data and evaluating the response consistency level of each pixel in the colorimetric region are as follows: Based on the preprocessed thermal colorimetric raw data, a thermal colorimetric input dataset is constructed: the number of pixels exceeding the temperature threshold in the 3D temperature data is counted and converted by pixel area to obtain the area of ​​the colorimetric region; a reflectivity compensation model is constructed by using 3D temperature data and material surface reflectivity to obtain the colorimetric time of each pixel, and the mean and standard deviation of the colorimetric time within the colorimetric region are calculated; the colorimetric propagation path length and colorimetric propagation speed are obtained by combining image coordinate distance and pixel calibration ratio; the colorimetric time and temperature change rate are differentially processed to obtain the average temperature rise rate of the colorimetric region. Based on the thermal color rendering input dataset, the response consistency of each pixel within the color rendering area is evaluated: the color rendering propagation speed is multiplied by the average temperature rise rate of the color rendering area to obtain the color rendering response intensity term; the difference between the color rendering time and the mean color rendering time is divided by the mean color rendering time and squared to obtain the color rendering time deviation term. Divide the standard deviation of color development time by the mean of color development time and then multiply by the time series fluctuation adjustment coefficient to obtain the color development time series fluctuation term; Add the color development time deviation term and the color development time fluctuation term, and add a constant term as an instability factor; Divide the colorimetric response intensity term by the instability factor, integrate it over the colorimetric region, and then divide it by the area of ​​the colorimetric region to obtain the thermosensitive colorimetric response uniformity value. S3. Based on the response consistency distribution map, extract the stable pixel clustering region, construct the deployment candidate region set, evaluate the adaptability of the thermal pattern in the candidate deployment region, classify the deployment level according to the evaluation results, and output the deployment partition label map. The specific steps for extracting stable pixel cluster regions based on the response consistency distribution map, constructing a set of candidate deployment regions, and evaluating the adaptability of the thermal pattern within the candidate deployment regions are as follows: A two-dimensional Cartesian coordinate system is constructed using the thermal image space to output the position coordinates of each pixel. Based on the response consistency distribution map, the continuous clustering region of stable response pixels is used as the candidate region for pattern layout. A set of candidate regions is constructed, and the area corresponding to each candidate region is calculated. To evaluate the suitability of thermal patterns within the candidate deployment area: multiply the thermal color development response consistency value by the color development propagation speed and the average temperature rise rate of the color development area to obtain the deployment response performance term; divide the standard deviation of color development time by the mean of color development time to obtain the response time fluctuation term. The unit response score is obtained by integrating the area of ​​the pattern placement candidate region and dividing it by the area of ​​the placement region. Divide the unit response score by the response time fluctuation term plus one to obtain the thermal pattern layout adaptation evaluation value; S4. Extract the core optimal deployment area and stable deployment area to evaluate the thermal response stability, and construct a two-dimensional joint feature analysis map based on the regional adaptability characteristics; perform cluster analysis based on the two-dimensional joint feature analysis map to identify highly adaptable stable deployment sub-regions and generate deployment strategy maps, divide the deployment candidate areas into four types of response areas, and match the corresponding deployment optimization strategies.

2. The method for detecting heat-sensitive textiles according to claim 1, characterized in that: The specific steps for collecting raw thermal colorimetric data and performing alignment, mapping, elimination, and normalization on the raw thermal colorimetric data to obtain preprocessed raw thermal colorimetric data are as follows: Collect raw data for thermochromic development, including three-dimensional temperature data, material surface reflectivity, surface height map, local incident angle, image coordinate distance, and pixel calibration ratio; The thermal color development raw data is processed using a time-stamp alignment method to achieve multi-source time-series unified processing; the thermal color development raw data is processed to convert image coordinates to actual physical space using spatial coordinate mapping; the thermal color development raw data is processed to remove outliers and check sampling integrity using geometric structure verification rules; and the thermal color development raw data is processed to achieve structural unification and standardization through format parsing and field organization processes. The raw thermal colorimetric data were normalized using unit conversion and scale normalization methods.

3. The method for detecting heat-sensitive textiles according to claim 1, characterized in that: The specific steps for generating a response consistency distribution map based on the evaluation results and determining whether a pixel's response is stable are as follows: The thermal color response consistency value is discretized pixel by pixel in the spatial dimension to output the response consistency distribution map of the color pattern. During the image update cycle, the thermal color response consistency value and the color response threshold of each pixel are compared in real time. If the thermal color response consistency value is greater than the color response threshold, the pixel is marked as a stable pixel. If the thermal color response consistency value is less than or equal to the color response threshold, the pixel is marked as an unstable pixel.

4. The method for detecting heat-sensitive textiles according to claim 1, characterized in that: The specific steps for classifying deployment levels based on the evaluation results and outputting a deployment zone label map are as follows: The system compares the thermal pattern adaptation evaluation value with the adaptation threshold of each candidate area in real time to classify the areas: If the thermal pattern adaptation evaluation value is greater than or equal to the first-level adaptation threshold, the area is marked as the core optimal area, which is used for priority placement of the main structure of the thermal pattern, the center line of the text, and the visual focus area; If the thermal pattern adaptation evaluation value is less than the first-level adaptation threshold but greater than the second-level adaptation threshold, it is designated as a stable area, which is used for auxiliary graphics, edge decoration, and structural extension; If the thermal pattern adaptation evaluation value is less than or equal to the second-level adaptation threshold, it is marked as a restricted area, which does not participate in the thermal pattern graphic mapping and is used for subsequent pattern adjustment and material replacement design. Write the hierarchical classification results of each deployment candidate area into the response adaptation layer and generate the corresponding deployment partition label map.

5. The method for detecting heat-sensitive textiles according to claim 1, characterized in that: The specific steps for extracting the core optimal distribution area and stable distribution area, evaluating the thermal response stability, and constructing a two-dimensional joint feature analysis map based on regional adaptability characteristics are as follows: Based on the deployment partition label map, all deployment candidate areas marked as core optimal deployment areas and stable deployment areas are extracted, and the thermal response stability is evaluated: the square of the thermal pattern deployment adaptation evaluation value minus one is used as the response mismatch term; the square of the spatial gradient of the thermal color rendering response consistency value is used as the response equilibrium perturbation term. Divide the standard deviation of color development time by the mean of color development time as the response time fluctuation term; After multiplying the response mismatch term, the response equilibrium disturbance term, and the response time series fluctuation term, the area is integrated within the candidate area of ​​the pattern layout. The result of the integration is divided by the area of ​​the layout area to obtain the thermal response stability evaluation value. The thermal pattern placement adaptation evaluation value and thermal response stability evaluation value of each pixel in the candidate placement area are aligned at the pixel level, and a two-dimensional joint feature distribution map is constructed in the image coordinate space, where the horizontal axis is the placement adaptation evaluation value and the vertical axis is the response stability evaluation value. The distribution density of the pixels in the map is used to reflect the aggregation trend and distribution structure of the response features in the placement area.

6. The method for detecting heat-sensitive textiles according to claim 1, characterized in that: The specific steps for performing cluster analysis based on the two-dimensional joint feature analysis map to identify highly adaptable and stable deployment sub-regions and generate a deployment strategy map are as follows: Based on the two-dimensional joint feature distribution map, two-dimensional feature clustering operation is performed on all pixels in the candidate area to automatically divide pixel clusters with different response levels; and the pixels contained in the high-level clusters are indexed and extracted, and the corresponding pixel numbers are mapped back to the original image coordinate space to generate a spatial distribution mask layer of highly adaptable and stable sub-regions. Based on the spatial distribution mask layer of the highly adaptable and stable deployment sub-region, the image boundary of the high-level cluster is fitted, and region fusion is performed in combination with the deployment partition label map to generate a deployment recommendation region map. The deployment recommendation region map is then overlaid with the response consistency distribution map and the deployment adaptation level map to output the deployment strategy map.

7. The method for detecting heat-sensitive textiles according to claim 1, characterized in that: The specific steps for dividing the candidate deployment area into four types of response areas and matching them with corresponding deployment optimization strategies are as follows: Based on the deployment strategy map, the thermal pattern deployment adaptation evaluation value and thermal response stability evaluation value corresponding to each pixel are extracted. In the image coordinate space, the deployment candidate region is divided into four response regions according to the adaptation threshold and the stability threshold: when both evaluation values ​​are lower than the corresponding threshold, it is marked as a response insufficiency region, and deployment rejection and material replacement are performed; when the deployment adaptation evaluation value is higher than the adaptation threshold but the response stability evaluation value is lower than the stability threshold, it is marked as a response redundancy region, and thermal response correction is performed; when the stability evaluation value is higher than the adaptation threshold but the adaptation evaluation value is lower than the stability threshold, it is marked as a potential improvement region, and temperature control adjustment and pattern migration are performed; when both evaluation values ​​are higher than the corresponding threshold, it is marked as a stable deployment priority region, and deployment structure parameter locking is performed. Based on the division of the response area and the corresponding strategy, a response deviation label map is generated to realize the dynamic adjustment of the thermal pattern layout area and the closed-loop control of the response performance.

8. A thermal textile detection device, employing the thermal textile detection method as described in any one of claims 1-7, characterized in that, include: The system comprises a thermal colorimetric raw data acquisition and preprocessing module, a thermal response consistency evaluation and pixel classification module, a deployment adaptability evaluation and regional level division module, and a response stability fusion optimization and strategy decision-making module, among which: The thermal colorimetric raw data acquisition and preprocessing module is used to acquire thermal colorimetric raw data and perform alignment, mapping, elimination and normalization processing on the thermal colorimetric raw data to obtain preprocessed thermal colorimetric raw data. The thermal response consistency evaluation and pixel classification module is used to construct a thermal color-developing input dataset based on the preprocessed thermal color-developing raw data, evaluate the response consistency level of each pixel in the color-developing area, generate a response consistency distribution map based on the evaluation results, and determine whether the pixel response is stable. The deployment adaptability assessment and regional classification module is used to extract the stable pixel clustering region based on the response consistency distribution map, construct a set of deployment candidate regions, evaluate the adaptability of the thermal pattern in the candidate deployment regions, classify the deployment level according to the evaluation results, and output the deployment partition label map. The response stability fusion optimization and strategy decision module is used to extract the core optimal deployment area and stable deployment area for thermal response stability assessment, and construct a two-dimensional joint feature analysis map based on regional adaptability characteristics; based on the two-dimensional joint feature analysis map, cluster analysis is carried out to identify highly adaptable stable deployment sub-regions and generate deployment strategy maps, dividing the deployment candidate areas into four types of response areas and matching corresponding deployment optimization strategies.

Images