Methods, devices, computer equipment, and storage media for identifying watermarks on the ground

Abstract

This application relates to a method, apparatus, computer equipment, and storage medium for identifying watermarks on the ground. The method includes: acquiring infrared thermal image data to be identified and reference thermal image data; marking a reference reference area, a first temperature reference point, and multiple feature marker points in the reference thermal image data; determining the area to be identified in the infrared thermal image data and the positional transformation relationship between the infrared thermal image data and the reference thermal image data based on the feature marker points and the reference reference area; determining a second temperature reference point in the infrared thermal image data corresponding to the first temperature reference point based on the positional transformation relationship and the first temperature reference point; determining a temperature correction value based on the first and second temperature reference points; calculating a temperature image based on the temperature values ​​of each point in the infrared thermal image data, the temperature values ​​of each point in the reference thermal image data, and the temperature correction value; and performing watermark identification based on the temperature image to obtain the identification result. This method can improve the accuracy of watermark identification.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method, apparatus, computer equipment, and storage medium for identifying watermarks on the ground. Background Technology

[0002] With the rapid development of nuclear power technology, it is necessary to monitor the pipelines of nuclear power plants in order to ensure their safe operation.

[0003] In related technologies, high-definition cameras are used to monitor the ground for water stains to determine if there are leaks in pipes. However, when the ground is smooth, transparent water stains cannot be detected by high-definition cameras, resulting in the inability to identify the presence of water stains. In other words, the monitoring methods in related technologies have flaws and are prone to inaccurate water stain identification. Therefore, how to improve the accuracy of water stain identification has become a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] Therefore, it is necessary to provide a ground watermark identification method, device, computer equipment, and storage medium that can improve the accuracy of watermark identification in response to the above-mentioned technical problems.

[0005] In a first aspect, this application provides a method for identifying ground watermarks. The method includes: acquiring infrared thermal image data to be identified and reference thermal image data corresponding to the infrared thermal image data;

[0006] A reference reference area, a first temperature reference point, and multiple feature marker points are marked in the reference heat map data.

[0007] Based on each of the aforementioned feature marker points and the aforementioned reference area, the region to be identified in the infrared thermal image data and the positional transformation relationship between the infrared thermal image data and the reference thermal image data are determined.

[0008] Based on the position conversion relationship and the first temperature reference point, determine the second temperature reference point corresponding to the first temperature reference point in the infrared thermal image data;

[0009] Determine the temperature correction value based on the first temperature reference point and the second temperature reference point;

[0010] A temperature image is calculated based on the temperature values ​​of each point in the infrared thermal image data, the temperature values ​​of each point in the reference thermal image data, and the temperature correction value.

[0011] Watermarks are identified based on the temperature image to obtain the identification result corresponding to the area to be identified.

[0012] In one embodiment, acquiring the infrared thermal image data to be identified and the reference thermal image data corresponding to the infrared thermal image data includes:

[0013] The corresponding baseline heat map data is obtained by taking pictures at each of the preset inspection points;

[0014] The infrared thermal image data to be identified is obtained, and the reference thermal image data is obtained by matching the infrared thermal image data.

[0015] In one embodiment, determining the region to be identified in the infrared thermal image data and the positional transformation relationship between the infrared thermal image data and the reference thermal image data based on each of the feature marker points and the reference reference region includes:

[0016] Arbitrarily select one of the aforementioned feature markers as the center, and select an infrared data block of the first region in the reference heat map data;

[0017] The second region with the highest similarity to the infrared data block was found in the infrared thermal image data;

[0018] Obtain the coordinates of the maximum value in the second region, and mark the coordinates as the matching position point corresponding to the feature marker point;

[0019] Repeat the above steps until the matching position points corresponding to all feature marker points are obtained;

[0020] Calculate the distance between each feature marker point to obtain the feature distance, and calculate the distance between each matching location point to obtain the matching distance;

[0021] If the difference between the feature distance and the matching distance is less than a first threshold, then the feature marker point is determined to be a matching alignment point;

[0022] The positional transformation relationship between the region to be identified and the infrared thermal image data and the reference thermal image data is determined based on the matching alignment point and the corresponding matching position point.

[0023] In one embodiment, determining the temperature correction value based on the first temperature reference point and the second temperature reference point includes:

[0024] Using the first temperature reference point as the center, a third region is determined, and the average temperature of the third region is obtained;

[0025] Using the second temperature reference point as the center, a fourth region is determined, and the average temperature of the fourth region is obtained;

[0026] The temperature correction value is calculated based on the average temperature of the third region and the average temperature of the fourth region.

[0027] In one embodiment, calculating the temperature image based on the temperature values ​​of each point in the infrared thermal image data, the temperature values ​​of each point in the reference thermal image data, and the temperature correction value includes:

[0028] Obtain the temperature value of each point in the infrared thermal image data, and the temperature value of the reference thermal image data at the corresponding location;

[0029] A temperature data matrix is ​​calculated based on the temperature values ​​of each point in the infrared thermal image data, the temperature values ​​of the reference thermal image data at the corresponding locations, and the temperature correction value.

[0030] The temperature image is constructed based on the temperature data matrix.

[0031] In one embodiment, the step of identifying watermarks based on the temperature image to obtain the identification result corresponding to the area to be identified includes:

[0032] Obtain the pixel value of each pixel in the temperature image;

[0033] The average pixel value is calculated based on the pixel value of each pixel.

[0034] Obtain the number of pixels that deviate from the preset value of the pixel mean;

[0035] If the number of pixels is greater than the second threshold, the recognition result for the area to be identified is that watermarks exist.

[0036] If the number of pixels is less than or equal to the second threshold, the recognition result for the area to be identified is that there is no watermark.

[0037] In one embodiment, the method further includes:

[0038] If the identification result indicates the presence of water traces, multiple water trace heat map data of the location to which the infrared heat map data belongs are obtained;

[0039] Multiple watermark thermal image data are superimposed on the infrared thermal image data to obtain the target watermark image.

[0040] Secondly, this application also provides a ground watermark identification device. The device includes:

[0041] The data acquisition module is used to acquire the infrared thermal image data to be identified and the reference thermal image data corresponding to the infrared thermal image data;

[0042] The marking module is used to mark the reference reference area, the first temperature reference point, and multiple feature marker points in the reference heat map data;

[0043] The first calculation module is used to determine the region to be identified in the infrared thermal image data and the positional transformation relationship between the infrared thermal image data and the reference thermal image data based on each of the feature marker points and the reference reference area;

[0044] The second calculation module is used to determine the second temperature reference point corresponding to the first temperature reference point in the infrared thermal image data based on the position conversion relationship and the first temperature reference point.

[0045] The temperature correction value determination module is used to determine the temperature correction value based on the first temperature reference point and the second temperature reference point;

[0046] The temperature image calculation module is used to calculate a temperature image based on the temperature values ​​of each point in the infrared thermal image data, the temperature values ​​of each point in the reference thermal image data, and the temperature correction value.

[0047] The water stain recognition module is used to recognize water stains based on the temperature image and obtain the recognition result corresponding to the area to be recognized.

[0048] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the aforementioned method for identifying watermarks on the ground.

[0049] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the above-described method for identifying watermarks on the ground.

[0050] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the aforementioned method for identifying watermarks on the ground.

[0051] The aforementioned ground watermark recognition method, device, computer equipment, and storage medium calculate a temperature image based on the temperature values ​​of each point in the infrared thermal image data, the temperature values ​​of each point in the reference thermal image data, and the temperature correction value. This separates the area to be identified from the background objects in the infrared thermal image data, thereby obtaining a more accurate temperature of the area to be identified. This avoids interference from the temperature of the background objects in the area to be identified, thus improving the accuracy of watermark recognition. Attached Figure Description

[0052] Figure 1This is an application environment diagram of the ground watermark recognition method in one embodiment;

[0053] Figure 2 This is a flowchart illustrating a ground watermark recognition method in one embodiment;

[0054] Figure 3 This is a schematic diagram of reference heatmap data after reference area marking in one embodiment;

[0055] Figure 4 This is a schematic diagram of the baseline heatmap data after feature marker points have been marked in one embodiment;

[0056] Figure 5 This is a schematic diagram of the reference thermal image data after marking the first temperature reference point in one embodiment;

[0057] Figure 6 This is a flowchart illustrating the steps for determining the region to be identified and the location transformation relationship in one embodiment;

[0058] Figure 7 This is a schematic diagram of a temperature image in one embodiment;

[0059] Figure 8 This is a schematic diagram of the target watermark map in one embodiment;

[0060] Figure 9 This is a structural block diagram of a ground watermark recognition device in one embodiment;

[0061] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0063] The ground watermark identification method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. The data storage system can store data that server 104 needs to process, such as baseline heatmap data. The data storage system can be integrated onto server 104 or placed in the cloud or on other network servers. The ground watermark recognition method provided in this embodiment can be executed by server 104 or terminal 102; this embodiment uses the execution of the ground watermark recognition method by terminal 102 as an example for explanation. Terminal 102 acquires the infrared thermal image data of the area to be identified and the corresponding reference thermal image data. It then marks a reference reference area, a first temperature reference point, and multiple feature markers in the reference thermal image data. Based on these feature markers and the reference reference area, it determines the area to be identified in the infrared thermal image data and the positional transformation relationship between the infrared thermal image data and the reference thermal image data. Based on the positional transformation relationship and the first temperature reference point, it determines the second temperature reference point corresponding to the first temperature reference point in the infrared thermal image data. Based on the first and second temperature reference points, it determines a temperature correction value. Based on the temperature values ​​of each point in the infrared thermal image data, the temperature values ​​of each point in the reference thermal image data, and the temperature correction value, it calculates a temperature image. Based on the temperature image, it performs watermark recognition to obtain the recognition result corresponding to the area to be identified. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, and tablets. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster composed of multiple servers.

[0064] In one embodiment, such as Figure 2 As shown, a method for identifying watermarks on the ground is provided, which can be applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps:

[0065] Step 202: Obtain the infrared thermal image data to be identified and the corresponding baseline thermal image data.

[0066] Infrared thermal image data refers to infrared image data used to characterize water stains to be identified at inspection points. This infrared thermal image data can be image data obtained in real time by an infrared camera or infrared thermal imager at the inspection point.

[0067] Baseline thermal image data refers to standard infrared image data used to characterize inspection points. This baseline thermal image data can be pre-captured and stored at each inspection point using an infrared camera or infrared thermal imager. The baseline thermal image data can be stored in a storage unit on a terminal or in a data storage system on a server.

[0068] For example, infrared thermal image data captured at inspection points can be obtained via the network, and then a reference thermal image data corresponding to the infrared thermal image data can be obtained in the server.

[0069] For example, an inspection robot can capture infrared thermal image data at various inspection points. Then, the terminal receives the infrared thermal image data sent by the inspection robot, determines the corresponding inspection point, and then obtains the baseline thermal image data of that inspection point from the server.

[0070] Step 204: Mark the reference reference area, the first temperature reference point, and multiple feature marker points in the reference heat map data.

[0071] The reference area can refer to the location of water traces that need to be monitored in the reference heat map data.

[0072] The first temperature reference point can refer to a location in the baseline heat map data that is outside the baseline reference area, has a temperature that is basically the same as the ambient temperature, and is where there will be no water leakage. This first temperature reference point is the baseline temperature reference point for the ambient temperature in the baseline heat map data. For example, when identifying water leakage traces in pipelines in a nuclear power plant, this first temperature reference point could be a fixed support for the pipeline or a nearby wall, etc.

[0073] Feature markers can refer to location reference points in the baseline heatmap data. Generally, at least four feature markers are required.

[0074] For example, please see Figure 3 , Figure 4 , Figure 5 The reference area is obtained by marking the reference heatmap data using polygon marking. Figure 3 Then, four feature marker points were obtained by marking them on the baseline heatmap data. Figure 4 The first temperature reference point is marked on the fixed support of the pipe shown in the baseline thermal map data. Figure 5 ).

[0075] Step 206: Based on each feature marker point and the reference area, determine the region to be identified in the infrared thermal image data and the positional transformation relationship between the infrared thermal image data and the reference thermal image data.

[0076] The area to be identified can refer to the region in the infrared thermal image data used to characterize the area that needs to be identified for watermarks.

[0077] The position transformation relationship can refer to the transformation relationship between the coordinate position in the infrared thermal image data and the coordinate position in the reference thermal image data.

[0078] For example, based on the four feature markers in the reference heat map data, the corresponding matching position points on the infrared heat map data can be determined. Then, the position transformation relationship can be calculated based on the coordinate positions of the matching position points on the infrared heat map data and the coordinate positions of the feature markers on the reference heat map data.

[0079] Step 208: Based on the position conversion relationship and the first temperature reference point, determine the second temperature reference point corresponding to the first temperature reference point in the infrared thermal image data.

[0080] The second temperature reference point can refer to a location in the infrared thermal image data that, excluding the area to be identified, has a temperature that is basically the same as the ambient temperature and will not leak water. This second temperature reference point can be the location point in the infrared thermal image data corresponding to the location point of the first temperature reference point.

[0081] For example, based on the position transformation relationship and the first temperature reference point calculated in the aforementioned steps, the second temperature reference point in the infrared thermogram data can be calculated.

[0082] Step 210: Determine the temperature correction value based on the first temperature reference point and the second temperature reference point.

[0083] The temperature correction value refers to the value used to correct the temperature reference data. This temperature correction value is used to correct the temperature reference data to ensure that the ambient temperature of the reference thermal image data is basically consistent with the background temperature of the infrared thermal image data to be identified.

[0084] For example, the temperature value corresponding to the first temperature reference point and the temperature value corresponding to the second temperature reference point can be obtained, and then the corresponding temperature correction value can be determined based on the temperature value of the first temperature reference point and the temperature value of the second temperature reference point.

[0085] Step 212: Calculate the temperature image based on the temperature values ​​of each point in the infrared thermal image data, the temperature values ​​of each point in the reference thermal image data, and the temperature correction value.

[0086] The temperature image refers to an image that removes background objects from the infrared thermal image data, showing only the temperature data. Background objects can refer to background elements such as pipes, supports, and walls in the infrared thermal image data. This temperature image can indicate whether the infrared thermal image data includes watermarks.

[0087] For example, a temperature image is calculated based on the temperature values ​​of each point in the infrared thermal image data, the temperature values ​​of each point in the reference thermal image data, the temperature correction value, and the position transformation relationship.

[0088] For example, firstly, the temperature difference between each point is determined based on the position conversion relationship, the temperature value of each point in the infrared thermal image data, and the temperature value of each point in the reference thermal image data. Then, the temperature data matrix is ​​calculated based on the temperature difference and the temperature correction value. Finally, the corresponding temperature image is determined based on the temperature data matrix.

[0089] When watermarks on the ground exist for a certain period of time, their temperature will approach the ambient temperature (background temperature), and the infrared images of watermarks at the same temperature will differ against different backgrounds. Therefore, due to the interference of ambient temperature, watermarks cannot be identified directly from the infrared thermal image data corresponding to the inspection points. Thus, by removing background objects from the infrared thermal image data, the interference of the ambient temperature corresponding to the background objects on watermark identification can be eliminated, thereby improving the accuracy of watermark identification.

[0090] Step 214: Perform water mark recognition based on the temperature image to obtain the recognition result corresponding to the area to be recognized.

[0091] The identification result can refer to the result of watermark identification. This result indicates whether watermarks exist in the area to be identified or not.

[0092] For example, temperature anomalies can be found in temperature images to identify watermarks and obtain the identification result corresponding to the area to be identified.

[0093] The ground watermark recognition method of this application calculates a temperature image based on the temperature values ​​of each point in the infrared thermal image data, the temperature values ​​of each point in the reference thermal image data, and the temperature correction value. This separates the area to be recognized from the background objects in the infrared thermal image data, thereby obtaining a more accurate temperature of the area to be recognized. This avoids interference from the temperature of the background objects on the area to be recognized, thus improving the accuracy of watermark recognition.

[0094] In some embodiments, the step "acquiring the infrared thermal image data to be identified and the reference thermal image data corresponding to the infrared thermal image data" includes, but is not limited to, the following steps: taking corresponding reference thermal image data at each preset inspection point; acquiring the infrared thermal image data to be identified, and obtaining the reference thermal image data by matching the infrared thermal image data.

[0095] Among them, the inspection points can refer to the pre-set locations used for water stain identification.

[0096] For example, inspection points can be set at various locations where watermark identification is to be performed. Then, an inspection route can be constructed based on these inspection points. A pre-set program is then written into a robot equipped with an infrared camera or infrared thermal imager, enabling the robot to perform inspections along the route and capture infrared thermal image data corresponding to each inspection point. After capturing the infrared thermal image data, it is sent to a server or terminal via a network. The terminal receives the infrared thermal image data and, based on this data, retrieves the corresponding reference thermal image data from the server or its own storage unit (e.g., when sending to the server, the terminal can obtain the infrared thermal image data and the corresponding reference thermal image data from the server).

[0097] like Figure 6 As shown, in some embodiments, step 206 includes, but is not limited to, the following steps:

[0098] Step 602: Select any feature marker as the center and select the infrared data block of the first region in the reference heat map data.

[0099] The first region can refer to a region constructed by pre-selecting a preset length and width. The center of this first region is a feature marker point. For example, the length and width of the first region are both M. M can be 21 pixels.

[0100] For example, if each feature marker is named S1, S2, S3 and S4 respectively, for feature marker S1, a region with a length and width of 21 pixels can be selected with S1 as the center to obtain a first region. Then, the data of the first region in the reference heat map data is obtained to obtain an infrared data block, which can be represented by T.

[0101] It should be noted that the acquisition of infrared data blocks for other marker points can be similar to that for feature marker point S1.

[0102] Step 604: Search for the second region in the infrared thermal image data that has the highest similarity to the infrared data block.

[0103] The second region can refer to the area in the infrared thermal image data that has the highest similarity to the data in the infrared data block.

[0104] For example, a global search can be performed on the infrared thermal image data to find the second region with the highest similarity to the infrared database.

[0105] For example, the similarity can be calculated using the following formula (1), which is as follows:

[0106]

[0107] Among them, Sij It can refer to an infrared data block with a length and width of M centered at coordinates (i,j) in the infrared thermal image data. Here, the value of i ranges from M / 2 to (WM / 2), the value of j ranges from (M / 2) to (HM / 2), W is the width of the infrared thermal image data, H is the length of the infrared thermal image data, and T is the infrared thermal image data in the reference thermal image data.

[0108] Step 606: Obtain the coordinates of the maximum value in the second region and mark the coordinates as the matching position point corresponding to the feature marker point.

[0109] The coordinate position can refer to the position of the maximum value in R(i,j).

[0110] Matching location points can refer to the location points in infrared thermal image data that match the various feature marker points.

[0111] For example, when using the search method in step 604, the second region of the infrared data block with the maximum similarity of feature marker point S1 is searched in the infrared thermal image data. Then, the center position of the second region is obtained, the corresponding coordinate position is obtained, and the coordinate position is marked as the matching position point T1 of feature marker point S1.

[0112] Step 608: Repeat the above steps until the matching position points corresponding to all feature marker points are obtained.

[0113] For example, steps 602 to 606 are executed repeatedly until the matching position points corresponding to each feature marker point are obtained, that is, the matching position points T1 to T4 corresponding to feature marker points S1 to S4 need to be obtained.

[0114] Step 610: Calculate the distance between each feature marker point to obtain the feature distance, and calculate the distance between each matching position point to obtain the matching distance.

[0115] Feature distance can refer to the distance between each feature marker point.

[0116] Matching distance can refer to the distance between each matching location point.

[0117] For example, for feature marker S1, the Euclidean distances between feature marker S1 and feature markers S2, S3, and S4 can be calculated to obtain the feature distances between S1 and S2, S1 and S3, and S1 and S4. Similarly, the Euclidean distances between the corresponding matching point T1 and each matching point T2, T3, and T4 can be calculated to obtain the matching distances between T1 and T2, T1 and T3, and T1 and T4.

[0118] Step 612: If the difference between the feature distance and the matching distance is less than the first threshold, then the feature marker point is determined as the matching alignment point.

[0119] The first threshold is a pre-set threshold.

[0120] Matching alignment points can refer to the locations where the baseline thermal image data and the infrared thermal image data are matched.

[0121] For example, when the difference between the feature distance between S1 and S2 and the matching distance between T1 and T2 is less than a first threshold, the difference between the feature distance between S1 and S3 and the matching distance between T1 and T3 is less than a first threshold, and the difference between the feature distance between S1 and S4 and the matching distance between T1 and T4 is less than a first threshold, the feature marker point S1 is set as the matching alignment point.

[0122] Step 614: Determine the positional transformation relationship between the area to be identified and the infrared thermal image data and the reference thermal image data based on the matching alignment point and the corresponding matching position point.

[0123] For example, the position transformation relationship can be calculated based on the coordinate positions of the matching position points T1 to T4 and the coordinate positions of the matching alignment points, and then the corresponding region to be identified can be determined based on the position transformation relationship and the reference area.

[0124] The technical solution of this application embodiment can determine the matching position point corresponding to each feature marker point through a global search method, and then determine the position transformation relationship based on the matching position point and the feature marker point, thereby facilitating the subsequent calculation of the temperature reference point and improving the accuracy of water mark recognition.

[0125] In some embodiments, step 210 includes, but is not limited to, the following steps: determining a third region centered on a first temperature reference point and obtaining the average temperature of the third region; determining a fourth region centered on a second temperature reference point and obtaining the average temperature of the fourth region; and calculating a temperature correction value based on the average temperature of the third region and the average temperature of the fourth region.

[0126] The third region can refer to the area in the baseline heat map data that is centered on the first temperature reference point and has a length and width of K. For example, K can be 5.

[0127] The fourth region can refer to the area in the infrared thermal image data that is centered on the second temperature reference point and has a length and width of K.

[0128] For example, the temperature values ​​of each point in the third region can be obtained, and then the average temperature of the third region can be calculated. The temperature values ​​of each point in the fourth region can be obtained, and then the average temperature of the fourth region can be calculated. Finally, the temperature correction value can be calculated using the average temperature of the third region and the average temperature of the fourth region.

[0129] For example, the temperature correction value can be the difference between the average temperature of the third region and the average temperature of the fourth region.

[0130] The technical solution of this application embodiment calculates a temperature correction value using the temperature values ​​of the third region and the fourth region to correct the temperature and ensure that the background temperature of the infrared thermal image data and the reference thermal image data are basically consistent, thereby avoiding interference from temperature differences on water mark recognition and improving the accuracy of water mark recognition.

[0131] like Figure 7 As shown, in some embodiments, step 212 includes, but is not limited to, the following steps: obtaining the temperature value of each point in the infrared thermal image data and the temperature value of the reference thermal image data at the corresponding location; calculating a temperature data matrix based on the temperature value of each point in the infrared thermal image data, the temperature value of the reference thermal image data at the corresponding location, and the temperature correction value; and constructing a temperature image based on the temperature data matrix.

[0132] The temperature data matrix can refer to the matrix used to represent the temperature data at each point.

[0133] For example, the temperature data matrix can be calculated using the following formula (2), which is as follows:

[0134] V(i,j)=V0(i,j)-V1(i,j)-Vd (2)

[0135] Where V0(i,j) is the temperature value corresponding to coordinate position (i,j) in the baseline thermal image data, V1(i,j) is the temperature value corresponding to coordinate position (i,j) in the infrared thermal image data, and Vd is the temperature correction value.

[0136] After calculating the temperature data matrix according to the above formula (2), a temperature image is constructed based on the temperature data matrix. The temperature image can be as follows: Figure 7 As shown.

[0137] The technical solution of this application embodiment, by constructing a temperature image, avoids interference from background objects on water mark recognition and improves the accuracy of water mark recognition.

[0138] In some embodiments, step 212 includes, but is not limited to, the following steps: obtaining the pixel value of each pixel in the temperature image; calculating the pixel mean based on the pixel value of each pixel; obtaining the number of pixels that deviate from the preset value of the pixel mean; if the number of pixels is greater than a second threshold, the recognition result corresponding to the area to be recognized is that there is water; if the number of pixels is less than or equal to the second threshold, the recognition result corresponding to the area to be recognized is that there is no water.

[0139] The preset mean value can refer to a pre-defined percentage of the pixel mean. For example, the preset mean value could be 10% of the pixel mean. The preset offset mean value can refer to values ​​that are greater than or less than the preset mean value. For example, an offset of 10% from the pixel mean means that the pixel value is less than 90% of the pixel mean and greater than 110% of the pixel mean.

[0140] The second threshold can refer to a pre-set threshold. For example, the second threshold could be 60.

[0141] For example, the pixel value of each pixel in the temperature image can be obtained, the pixel mean can be calculated, and the number of pixels corresponding to the pixel value offset by 10% of the pixel mean can be obtained. If the number of pixels is greater than a second threshold (e.g., 60), it is determined that there are traces of water leakage on the ground, that is, the identification result is that there are water traces; if the number of pixels is less than or equal to the second threshold, it is determined that there are no traces of water leakage on the ground, that is, the identification result is that there are no water traces.

[0142] In some embodiments, such as Figure 8 As shown, in some embodiments, the ground watermark identification method further includes, but is not limited to, the following steps: if the identification result indicates the presence of watermarks, acquiring multiple watermark heat map data of the location to which the infrared heat map data belongs; and superimposing the multiple watermark heat map data onto the infrared heat map data to obtain the target watermark map.

[0143] The location of the infrared thermal image data can refer to the inspection point corresponding to the infrared thermal image data.

[0144] Watermark thermal image data can refer to infrared image data collected at this inspection point.

[0145] Overlaying multiple watermark heatmap data can refer to directly accumulating the watermark heatmap data based on the corresponding location points.

[0146] The target watermark map can refer to the infrared image data resulting from the overlay of watermark thermal image data and infrared thermal image data.

[0147] For example, when it is determined that there are water traces at the inspection point, multiple infrared images can be continuously collected at the inspection point at a preset time interval to obtain multiple water trace heat map data. Then, according to the matching alignment point and position conversion relationship obtained in the previous steps, the water trace heat map data is superimposed on the infrared heat map data to obtain the corresponding target water trace map.

[0148] For example, when water stains are detected at an inspection point, the robot continuously collects 10 infrared images of that point at one-minute intervals, obtaining 10 water stain heatmaps. Then, based on the matching alignment points and position conversion relationships obtained in the previous steps, the water stain heatmaps are overlaid on the infrared heatmaps to obtain the corresponding target water stain map. This target water stain map is shown below. Figure 8 As shown.

[0149] The technical solution of this application embodiment, when the identification result shows the presence of water traces, obtains multiple water trace heat map data of the location of the infrared heat map data, and superimposes the multiple water trace heat map data onto the infrared heat map data to obtain the target water trace map, which can enhance the display effect of water traces, so as to facilitate managers or maintenance personnel to manually observe the water trace effect on the ground.

[0150] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0151] Based on the same inventive concept, this application also provides a ground watermark recognition device for implementing the above-described ground watermark recognition method. The solution provided by this device is similar to the solution described in the above-described method.

[0152] In one embodiment, such as Figure 9 As shown, a ground watermark recognition device is provided, comprising:

[0153] The data acquisition module 902 is used to acquire the infrared thermal image data to be identified and the reference thermal image data corresponding to the infrared thermal image data.

[0154] The marking module 904 is used to mark the reference reference area, the first temperature reference point and multiple feature marker points in the reference heat map data.

[0155] The first calculation module 906 is used to determine the region to be identified in the infrared thermal image data and the positional transformation relationship between the infrared thermal image data and the reference thermal image data based on each feature marker point and the reference reference area.

[0156] The second calculation module 908 is used to determine the second temperature reference point in the infrared thermal image data corresponding to the first temperature reference point based on the position conversion relationship and the first temperature reference point.

[0157] The temperature correction value determination module 910 is used to determine the temperature correction value based on the first temperature reference point and the second temperature reference point.

[0158] The temperature image calculation module 912 is used to calculate the temperature image based on the temperature values ​​of each point in the infrared thermal image data, the temperature values ​​of each point in the reference thermal image data, and the temperature correction value.

[0159] The water stain recognition module 914 is used to recognize water stains based on temperature images and obtain the recognition result corresponding to the area to be recognized.

[0160] In some embodiments, the data acquisition module is further configured to capture corresponding reference thermal image data at each preset inspection point; acquire infrared thermal image data to be identified; and obtain reference thermal image data by matching the infrared thermal image data.

[0161] In some embodiments, the first calculation module is further configured to: arbitrarily select one feature marker as the center among all feature markers; select an infrared data block of a first region in the reference heatmap data; search for a second region in the infrared heatmap data that has the highest similarity to the infrared data block; obtain the coordinate position of the maximum value in the second region and mark the coordinate position as the matching position point corresponding to the feature marker; repeatedly execute the above steps until the matching position points corresponding to all feature markers are obtained; calculate the distance between each feature marker to obtain the feature distance, and calculate the distance between each matching position point to obtain the matching distance; if the difference between the feature distance and the matching distance is less than a first threshold, then determine the feature marker as a matching alignment point; and determine the positional transformation relationship between the region to be identified and the infrared heatmap data and the reference heatmap data based on the matching alignment point and the corresponding matching position point.

[0162] In some embodiments, the temperature correction value determination module is further configured to determine a third region centered on a first temperature reference point and obtain the average temperature of the third region; determine a fourth region centered on a second temperature reference point and obtain the average temperature of the fourth region; and calculate the temperature correction value based on the average temperature of the third region and the average temperature of the fourth region.

[0163] In some embodiments, the temperature image calculation module is further configured to acquire the temperature value of each point in the infrared thermal image data, and the temperature value of the reference thermal image data at the corresponding location; calculate the temperature data matrix based on the temperature value of each point in the infrared thermal image data, the temperature value of the reference thermal image data at the corresponding location, and the temperature correction value; and construct a temperature image based on the temperature data matrix.

[0164] In some embodiments, the watermark recognition module is further configured to acquire the pixel value of each pixel in the temperature image; calculate the pixel mean based on the pixel value of each pixel; acquire the number of pixels that deviate from the preset value of the pixel mean; if the number of pixels is greater than the second threshold, the recognition result corresponding to the area to be recognized is that watermarks exist; if the number of pixels is less than or equal to the second threshold, the recognition result corresponding to the area to be recognized is that watermarks do not exist.

[0165] In some embodiments, the ground watermark detection device also includes, but is not limited to:

[0166] The watermark thermal image data acquisition module is used to acquire multiple watermark thermal image data of the location of the infrared thermal image data when the identification result indicates the presence of watermarks.

[0167] The overlay module is used to overlay multiple watermark thermal image data onto infrared thermal image data to obtain the target watermark image.

[0168] Each module in the aforementioned ground watermark recognition device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0169] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 10As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for identifying watermarks on the ground. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0170] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0171] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method for identifying watermarks on the ground.

[0172] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described method for identifying watermarks on the ground.

[0173] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the above-described method for identifying ground watermarks.

[0174] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0175] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0176] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for identifying watermarks on the ground, characterized in that, The method includes: Obtain the infrared thermal image data to be identified and the reference thermal image data corresponding to the infrared thermal image data; A reference reference area, a first temperature reference point, and multiple feature marker points are marked in the reference heat map data. Based on each of the aforementioned feature marker points and the aforementioned reference area, the region to be identified in the infrared thermal image data and the positional transformation relationship between the infrared thermal image data and the reference thermal image data are determined. Based on the position conversion relationship and the first temperature reference point, determine the second temperature reference point corresponding to the first temperature reference point in the infrared thermal image data; Determine the temperature correction value based on the first temperature reference point and the second temperature reference point; A temperature image is calculated based on the temperature values ​​of each point in the infrared thermal image data, the temperature values ​​of each point in the reference thermal image data, and the temperature correction value. Watermarks are identified based on the temperature image to obtain the identification result corresponding to the area to be identified. The step of determining the temperature correction value based on the first temperature reference point and the second temperature reference point includes: determining a third region centered on the first temperature reference point and obtaining the average temperature of the third region; determining a fourth region centered on the second temperature reference point and obtaining the average temperature of the fourth region; and calculating the temperature correction value based on the average temperature of the third region and the average temperature of the fourth region. The step of identifying watermarks based on the temperature image to obtain the identification result corresponding to the area to be identified includes: obtaining the pixel value of each pixel in the temperature image; calculating the pixel mean based on the pixel value of each pixel; obtaining the number of pixels that deviate from the preset value of the pixel mean; if the number of pixels is greater than a second threshold, the identification result corresponding to the area to be identified is that watermarks exist; if the number of pixels is less than or equal to the second threshold, the identification result corresponding to the area to be identified is that watermarks do not exist.

2. The method according to claim 1, characterized in that, The process of acquiring the infrared thermal image data to be identified and the corresponding reference thermal image data includes: The corresponding baseline heat map data is obtained by taking pictures at each of the preset inspection points; The infrared thermal image data to be identified is obtained, and the reference thermal image data is obtained by matching the infrared thermal image data.

3. The method according to claim 1, characterized in that, The step of determining the region to be identified in the infrared thermal image data and the positional transformation relationship between the infrared thermal image data and the reference thermal image data based on each of the feature marker points and the reference reference area includes: Arbitrarily select one of the aforementioned feature markers as the center, and select an infrared data block of the first region in the reference heat map data; The second region with the highest similarity to the infrared data block was found in the infrared thermal image data; Obtain the coordinates of the maximum value in the second region, and mark the coordinates as the matching position point corresponding to the feature marker point; Repeat the above steps until the matching position points corresponding to all feature marker points are obtained; Calculate the distance between each feature marker point to obtain the feature distance, and calculate the distance between each matching location point to obtain the matching distance; If the difference between the feature distance and the matching distance is less than a first threshold, then the feature marker point is determined to be a matching alignment point; The positional transformation relationship between the region to be identified and the infrared thermal image data and the reference thermal image data is determined based on the matching alignment point and the corresponding matching position point.

4. The method according to claim 1, characterized in that, The step of calculating a temperature image based on the temperature values ​​of each point in the infrared thermal image data, the temperature values ​​of each point in the reference thermal image data, and the temperature correction value includes: Obtain the temperature value of each point in the infrared thermal image data, and the temperature value of the reference thermal image data at the corresponding location; A temperature data matrix is ​​calculated based on the temperature values ​​of each point in the infrared thermal image data, the temperature values ​​of the reference thermal image data at the corresponding locations, and the temperature correction value. The temperature image is constructed based on the temperature data matrix.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: If the identification result indicates the presence of water traces, multiple water trace heat map data of the location to which the infrared heat map data belongs are obtained; Multiple watermark thermal image data are superimposed on the infrared thermal image data to obtain the target watermark image.

6. A ground water stain recognition device, characterized in that, The device includes: The data acquisition module is used to acquire the infrared thermal image data to be identified and the reference thermal image data corresponding to the infrared thermal image data; The marking module is used to mark the reference reference area, the first temperature reference point, and multiple feature marker points in the reference heat map data; The first calculation module is used to determine the region to be identified in the infrared thermal image data and the positional transformation relationship between the infrared thermal image data and the reference thermal image data based on each of the feature marker points and the reference reference area; The second calculation module is used to determine the second temperature reference point corresponding to the first temperature reference point in the infrared thermal image data based on the position conversion relationship and the first temperature reference point. The temperature correction value determination module is used to determine the temperature correction value based on the first temperature reference point and the second temperature reference point; The temperature image calculation module is used to calculate a temperature image based on the temperature values ​​of each point in the infrared thermal image data, the temperature values ​​of each point in the reference thermal image data, and the temperature correction value. The water stain recognition module is used to recognize water stains based on the temperature image and obtain the recognition result corresponding to the area to be recognized. The step of determining the temperature correction value based on the first temperature reference point and the second temperature reference point includes: determining a third region centered on the first temperature reference point and obtaining the average temperature of the third region; determining a fourth region centered on the second temperature reference point and obtaining the average temperature of the fourth region; and calculating the temperature correction value based on the average temperature of the third region and the average temperature of the fourth region. The step of identifying watermarks based on the temperature image to obtain the identification result corresponding to the area to be identified includes: obtaining the pixel value of each pixel in the temperature image; calculating the pixel mean based on the pixel value of each pixel; obtaining the number of pixels that deviate from the preset value of the pixel mean; if the number of pixels is greater than a second threshold, the identification result corresponding to the area to be identified is that watermarks exist; if the number of pixels is less than or equal to the second threshold, the identification result corresponding to the area to be identified is that watermarks do not exist.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images