Cable trench detection method

Abstract

The invention discloses a cable trench detection method, and relates to the technical field of data transmission, and the method comprises the following steps: obtaining image data of different resolutions and color depths of a to-be-detected cable trench, carrying out the fragmentation processing of the image data, compressing the fragmented data, and transmitting the compressed data to a system; the system decompresses the received compressed image data to obtain transmission factor influence data of the image data; constructing a transmission factor model based on a machine learning algorithm according to the transmission factor influence data; adjusting transmission factor influence data based on a transmission factor model to achieve optimal transmission energy efficiency; the transmission factor is dynamically adjusted by adjusting the slice size, the resolution and the color depth, so that the optimal transmission efficiency and energy efficiency are achieved, and the problem that the quality of image data is ensured while the transmission speed meets the requirement is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data transmission, and more particularly to a cable trench detection method. Background Art

[0002] As an important infrastructure of the power system, the cable trench is mainly used for laying and replacing power or telecommunication cable facilities. The stability of its internal environment is crucial to the normal operation of the cable. With the development of information technology and sensor technology, modern cable trench detection methods have gradually adopted intelligent monitoring systems and robot inspection technologies. These technologies not only improve the detection efficiency, but also reduce the risk of manual inspections. The intelligent monitoring system monitors the environmental parameters inside the cable trench in real time through pre-buried sensors, and transmits the data to the monitoring center to achieve remote monitoring and early warning. The robot inspection technology uses the imaging equipment and thermal imaging sensors carried by the mobile robot to conduct all-round and no-dead-angle detection of the cable trench.

[0003] In addition, considering the harsh and complex environment inside the cable trench, the detection method also needs to have a high degree of stability and adaptability. Sensors and monitoring systems need to be able to work normally in harsh environments such as high temperature, humidity, and toxic gases, while robots need to have the function of self-adapting pipe diameters to adapt to cable trenches of different sizes and shapes.

[0004] The above disclosed technical solutions have at least the following technical problems: Traditional cable trench inspection uses drones to collect image data of the area to be inspected, uploads it to the system, and finds the problem of the cable trench by training artificial intelligence. However, different resolutions and color depths have an impact on the transmission of image data, and it is impossible to ensure the quality of image data while meeting the transmission speed requirements. In view of the above problems, the present invention proposes a solution. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a cable trench detection method, which dynamically adjusts the transmission factor by adjusting the slice size, resolution and color depth to achieve optimal transmission efficiency and energy efficiency, so as to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: A cable trench detection method comprises acquiring image data of different resolutions and color depths of a cable trench to be detected, slicing the image data, and compressing and transmitting the sliced ​​data to a system; the system decompresses the received compressed image data to acquire transmission factor influence data of the image data; constructs a transmission factor model based on a machine learning algorithm according to the transmission factor influence data; and adjusts the transmission factor influence data based on the transmission factor model to achieve optimal transmission energy efficiency.

[0007] In a preferred embodiment, the method of acquiring image data of different resolutions and color depths of the cable trench to be tested, slicing the image data, and compressing the sliced ​​data and transmitting it to the system is as follows: collecting original image data of the area to be tested, the original image data including image data of the same resolution but different color depths and image data of the same color depth but different resolutions, collecting multiple groups of original image data, and labeling the collected image data to construct an image data set; slicing the collected original image data to obtain multiple groups of image data of different slice sizes; encoding all slice data based on a hash function, compressing the slice data into data packets of different formats, the different formats including PNG, JPG, GIF and WEBP, and transmitting the data packets to the data processing center of the system via the TCP protocol.

[0008] In a preferred embodiment, the system decompresses the received compressed image data as follows: after receiving the data packet, the system selects a corresponding decompression algorithm according to the format of the data packet, and decompresses the data packet, the decompression algorithm including a discrete cosine transform algorithm, a PNG decompression algorithm and a Lempel-Ziv-Welch algorithm; after the decompression is completed, the integrity of the image data is verified based on a unique encoding method of a hash function, and after the verification is completed, the fragmented data is integrated to obtain processed image data.

[0009] In a preferred embodiment, the transmission factor influencing data includes a compression influencing coefficient, and the steps for obtaining the compression influencing coefficient are as follows: obtaining the number of bytes of a segment of original image data and the number of bytes of sliced ​​data, and obtaining the compression rate of the image data by comparing the number of bytes of the original image data and the number of bytes of the sliced ​​data; collecting the frequency information of the image data during the compression process, and converting the frequency information into frequency domain coefficients through Fourier transform, and recording the quantized frequency domain coefficients; processing the quantized frequency domain coefficients to remove abnormal values, and then adding and averaging them to obtain the frequency domain average coefficient, and using the frequency domain average coefficient as a characteristic value; obtaining the basic quantization coefficient of the image data, and calculating based on the basic quantization coefficient and the frequency domain average coefficient based on a preset quality factor formula to obtain to the quality factor; obtaining the total number of pixels and the value of each pixel in the original image data and the total number of pixels and the value of each pixel in the compressed image data, and calculating the mean square error between the original image and the compressed image based on the preset mean square error formula according to the total number of pixels and the value of each pixel in the original image data and the total number of pixels and the value of each pixel in the compressed image data; obtaining the value of the maximum pixel in the compressed image data, and calculating the peak signal-to-noise ratio based on the preset peak signal-to-noise ratio formula according to the mean square error between the original image and the compressed image and the value of the maximum pixel in the compressed image data; and calculating the compression influence coefficient based on the preset compression influence coefficient formula according to the compression rate, quality factor and peak signal-to-noise ratio of the image data.

[0010] In a preferred embodiment, the transmission factor influencing data includes an electromagnetic field influence coefficient, and the steps for obtaining the electromagnetic field influence coefficient are as follows: obtaining current data of a cable in a section of the test area, screening out a current peak value based on the current data, adding and averaging the current peak values ​​to obtain a current threshold, screening out current data exceeding the current threshold based on the current threshold, adding and averaging the current data exceeding the current threshold to obtain a current extreme value; obtaining the installation distance between cables and the number of cables in the test area, and calculating based on a preset electromagnetic field calculation formula according to the installation distance between the cables, the number of cables and the current extreme value to obtain the total electromagnetic field generated by the cables; obtaining the brightness of each pixel in the compressed image data, and adding and averaging the brightness of each pixel. The average brightness of the pixel is obtained; the noise intensity of each pixel in the compressed image data is obtained, and the types of noise are classified, the types of noise include multiplicative noise and additive noise, the noise other than additive noise is removed, and the processed noise data is averaged to obtain the average noise intensity of the pixel; the standard deviation of the noise is obtained by calculating based on the standard deviation formula according to the noise intensity of each pixel and the average noise intensity; the signal-to-noise ratio of the image data is obtained according to the ratio of the average brightness of the pixel to the standard deviation of the noise; the distance between the cable and the image acquisition device is obtained, and the electromagnetic field influence coefficient is calculated based on the preset electromagnetic field influence coefficient formula according to the signal-to-noise ratio of the image data, the distance between the cable and the image acquisition device, and the total electromagnetic field generated by the cable.

[0011] In a preferred embodiment, the transmission factor influencing data includes a transmission rate coefficient, and the steps of obtaining the transmission rate coefficient are specifically as follows: obtaining the image transmission speed under the image data state of the same slice size and different resolutions, and recording the bandwidth speed during the data transmission process; The image transmission speed under the image data state of the same slice size and different resolutions and the bandwidth speed during the data transmission process are divided into multiple groups of data objects of the same time period; the average value of the total bandwidth speed is obtained, and the bandwidth fluctuation coefficient is calculated based on the contrast formula according to the average value of the total bandwidth speed and the bandwidth speed of each time period; the fluctuation coefficients of all bandwidths are compared, and the image transmission speed data under the image data state of the same slice size and different resolutions with the lowest fluctuation coefficient are selected; the image transmission speed data under the image data state of the same slice size and different resolutions are analyzed based on linear regression to obtain the influence index of resolution on transmission; the slice size of the image data, the bandwidth speed and the resolution of the image are obtained, and the transmission rate coefficient is calculated based on the slice size of the image data, the bandwidth speed, the resolution of the image and the influence index of resolution on transmission according to the preset transmission rate coefficient formula.

[0012] In a preferred embodiment, the transmission factor influence data is adjusted based on the transmission factor model to achieve the best transmission energy efficiency, specifically as follows: the value range of the transmission factor is between [0,1], the higher the transmission factor, the higher the overall transmission efficiency, and the lower the transmission factor, the lower the overall transmission efficiency; the transmission factor influence data is adjusted according to the transmission factor model, and the transmission factor influence data is related to the slice size, image resolution and color depth of the data; the value of the transmission factor influence data is changed by adjusting the slice size, image resolution and color depth, thereby improving the value of the transmission factor and achieving the best transmission energy efficiency.

[0013] Technical effects and advantages of a cable trench detection method of the present invention: 1. The present invention reduces the amount of image data transmission by slicing, compressing and encoding the image data and using different compression formats (such as PNG, JPG, GIF, WEBP). The compression process combines multiple algorithms, such as discrete cosine transform, PNG decompression algorithm and Lempel-Ziv-Welch algorithm, and through efficient encoding and transmission methods, greatly reduces the bandwidth requirements during data transmission and improves transmission efficiency.

[0014] 2. The present invention uses a hash function to verify the integrity of image data to ensure the consistency and accuracy of data during transmission. This measure effectively prevents detection errors caused by data loss or damage during transmission and ensures the reliability of cable trench detection. And by optimizing each link of image transmission, it can significantly reduce the energy consumption required during data transmission.

[0015] 3. Construct a transmission factor model through machine learning algorithms, and adjust the transmission parameters based on multiple transmission factors such as compression influence coefficient, electromagnetic field influence coefficient and transmission rate coefficient to optimize the energy efficiency during data transmission. For example, by adjusting the slice size, resolution and color depth of the image, the transmission factor can be dynamically adjusted to achieve the best transmission efficiency and energy efficiency and avoid unnecessary bandwidth waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The present invention is a schematic structural diagram of a cable trench detection method. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Embodiment 1, Figure 1 The present invention provides a cable trench detection method, comprising: S1, obtaining image data of different resolutions and color depths of the cable trench to be tested, slicing the image data, and compressing the sliced ​​data and transmitting it to the system.

[0019] In this embodiment, the image data of different resolutions and color depths of the cable trench to be tested are obtained, the image data is sliced, and the sliced ​​data is compressed and transmitted to the system, as follows: Collecting original image data of the area to be tested, the original image data includes image data with the same resolution but different color depths and image data with the same color depth but different resolutions, collecting multiple groups of original image data, and labeling the collected image data to construct an image data set; Slice the collected original image data to obtain multiple groups of image data with different slice sizes; All slice data are encoded based on a hash function, compressed into data packets in different formats, including PNG, JPG, GIF and WEBP, and the data packets are transmitted to the data processing center of the system through the TCP protocol.

[0020] It should be noted that the reason why TCP is chosen as the data transmission protocol is that compared with UDP, TCP transmission is more reliable and can ensure the complete arrival of data. UDP is mainly used for applications with high latency requirements, which will result in a high packet loss rate. TCP is chosen to effectively ensure the progress of the experiment.

[0021] The color depth is commonly 8 bits, 16 bits, and 24 bits. Color depth refers to the number of colors that can be represented by each pixel of the image. Usually, a 24-bit depth refers to an RGB image, with each color component (red, green, and blue) being 8 bits, for a total of 24 bits.

[0022] S2, the system decompresses the received compressed image data and obtains the transmission factor influence data of the image data.

[0023] In this embodiment, the system decompresses the received compressed image data as follows: After receiving the data packet, the system selects a corresponding decompression algorithm according to the format of the data packet to decompress the data packet, wherein the decompression algorithm includes a discrete cosine transform algorithm, a PNG decompression algorithm and a Lempel-Ziv-Welch algorithm; After decompression, the integrity of the image data is verified based on the unique encoding method of the hash function. After the verification is completed, the fragmented data is integrated to obtain the processed image data.

[0024] In this embodiment, the transmission factor affecting the acquisition of image data is as follows: The transmission factor impact data includes the compression impact coefficient, which is a comprehensive indicator to measure the image compression effect, calculated by balancing the three key factors of peak signal-to-noise ratio (PSNR), compression rate and quality factor. A high compression impact coefficient value indicates that the compressed image has achieved a high data compression rate while maintaining high quality, reflecting a good balance between compression efficiency and quality.

[0025] The steps for obtaining the compression influence coefficient are as follows: Obtaining the number of bytes of a segment of original image data and the number of bytes of the segmented data, and obtaining a compression ratio of the image data according to the comparison between the number of bytes of the original image data and the number of bytes of the segmented data; Collect the frequency information of the image data during the compression process, convert the frequency information into frequency domain coefficients through Fourier transform, and record the quantized frequency domain coefficients; Process the quantized frequency domain coefficients to remove abnormal values, then add and average them to obtain a frequency domain average coefficient and use the frequency domain average coefficient as a characteristic value; Obtaining a basic quantization coefficient of the image data, and calculating a quality factor based on a preset quality factor formula according to the basic quantization coefficient and the frequency domain average coefficient; Obtaining the total number of pixels and the value of each pixel in the original image data and the total number of pixels and the value of each pixel in the compressed image data, and calculating based on a preset mean square error formula according to the total number of pixels and the value of each pixel in the original image data and the total number of pixels and the value of each pixel in the compressed image data, to obtain a mean square error between the original image and the compressed image; Obtaining the value of the maximum pixel in the compressed image data, and calculating the peak signal-to-noise ratio based on a preset peak signal-to-noise ratio formula according to the mean square error between the original image and the compressed image and the value of the maximum pixel in the compressed image data; The compression influence coefficient is calculated based on a preset compression influence coefficient formula according to the compression rate, quality factor and peak signal-to-noise ratio of the image data to obtain the compression influence coefficient.

[0026] The calculation formula of the compression influence coefficient is as follows:

[0027] The calculation formula of the peak signal-to-noise ratio is as follows:

[0028] The calculation formula of the mean square error is as follows:

[0029] The calculation formula of the quality factor is as follows:

[0030] In the formula, is the compression influence coefficient, is the compression ratio of the image data, is the peak signal-to-noise ratio, is the value of the maximum pixel in the compressed image data, that is, the maximum color depth, is the mean square error, is the total number of pixels in the image, is the value of the i-th pixel in the original image, is the value of the corresponding original image pixel in the compressed image, is the quality factor, is the quantization coefficient in the current compression process, is a basic quantization coefficient.

[0031] It should be noted that, for an 8-bit grayscale image, the value of the maximum pixel is usually 255 (that is, the pixel value range is 0-255), and for a 16-bit image, the value of the maximum pixel is usually 65535 (the pixel value range is 0-65535); the quality factor is usually related to the compression quality of the compression algorithm (such as JPEG). The closer the quality factor is to 1, the better the image quality, and the closer it is to 0, the worse the quality.

[0032] The transmission factor influencing data includes the electromagnetic field influence coefficient. The electromagnetic field influence coefficient is an indicator to measure the influence of the electromagnetic field generated by the cable on the data transmission quality of the image acquisition device. It is calculated using a preset formula by comprehensively considering the cable current extreme value, cable layout, average brightness of the image data, noise standard deviation and the distance between the cable and the image acquisition device. It reflects the degree of reduction of the image signal-to-noise ratio by electromagnetic interference.

[0033] The steps for obtaining the electromagnetic field influence coefficient are specifically as follows: Acquire current data of a cable in a test area, filter out current peak values ​​according to the current data, add and average the current peak values ​​to obtain a current threshold, filter out current data exceeding the current threshold according to the current threshold, and add and average the current data exceeding the current threshold to obtain a current extreme value; Obtaining the installation distance between the cables and the number of cables in the test area, and calculating based on a preset electromagnetic field calculation formula according to the installation distance between the cables, the number of cables and the current extreme value to obtain the total electromagnetic field generated by the cables; Obtain the brightness of each pixel in the compressed image data, and add and average the brightness of each pixel to obtain the average brightness of the pixel; Obtaining the noise intensity of each pixel in the compressed image data, and classifying the types of noise, wherein the types of noise include multiplicative noise and additive noise, removing noise other than additive noise, and adding and averaging the processed noise data to obtain an average noise intensity of the pixel; The standard deviation of the noise is calculated based on the standard deviation formula according to the noise intensity of each pixel and the average noise intensity; The signal-to-noise ratio of the image data is obtained based on the ratio of the average brightness of the pixel to the standard deviation of the noise; The distance between the cable and the image acquisition device is obtained, and the electromagnetic field influence coefficient is calculated based on a preset electromagnetic field influence coefficient formula according to the signal-to-noise ratio of the image data, the distance between the cable and the image acquisition device, and the total electromagnetic field generated by the cable.

[0034] The calculation formula of the electromagnetic field influence coefficient is as follows:

[0035] The calculation formula of the electromagnetic field is as follows:

[0036] In the formula, is the electromagnetic field influence coefficient, is the signal-to-noise ratio of the image data, is the distance between the cable and the image acquisition device, is the total electromagnetic field generated by the cable, is the vacuum permeability, , is the current extreme value of the ith cable, The distance from the center of the cable trench cross section to the center of the i-th cable, is the total number of cables.

[0037] It should be noted that multiplicative noise and additive noise can be further subdivided. For example, multiplicative noise includes Rayleigh noise and Poisson noise; additive noise includes Gaussian noise and salt and pepper noise.

[0038] The transmission factor influencing data includes the transmission rate coefficient, which is an indicator of data transmission efficiency under given network bandwidth, image resolution and slice size. It reflects the mutual influence between network bandwidth and image quality (resolution) and transmission unit (slice size), and is used to optimize image transmission efficiency in high bandwidth environments.

[0039] The steps for obtaining the transmission rate coefficient are specifically as follows: Obtain the image transmission speed under the image data state of the same slice size and different resolutions, and record the bandwidth speed during the data transmission process; Dividing the image transmission speed in the image data state of the same slice size and different resolutions and the bandwidth speed in the data transmission process into a plurality of groups of data objects in the same time period; The average value of the total bandwidth speed is obtained, and the bandwidth fluctuation coefficient is calculated based on the contrast formula according to the average value of the total bandwidth speed and the bandwidth speed in each time period; Compare the fluctuation coefficients of all bandwidths, and select the image transmission speed data with the lowest fluctuation coefficient under the image data state of the same slice size and different resolutions; Based on linear regression analysis of image transmission speed data under the same slice size and different resolution image data states, the influence index of resolution on transmission is obtained; The slice size, bandwidth speed and resolution of the image data are obtained, and the transmission rate coefficient is calculated based on a preset transmission rate coefficient formula according to the slice size, bandwidth speed, resolution of the image data and the influence index of the resolution on transmission, to obtain the transmission rate coefficient.

[0040] The calculation formula of the transmission rate coefficient is as follows:

[0041] In the formula, is the transmission rate coefficient, is the bandwidth speed, is the resolution of the image, is the index of the impact of resolution on transmission, is the slice size.

[0042] It should be noted that the higher the transmission rate coefficient, the faster the data transmission speed, and the transmission rate coefficient is proportional to the bandwidth. The transmission rate coefficient can be effectively increased by increasing the bandwidth speed.

[0043] S3, constructing a transfer factor model based on a machine learning algorithm according to the transfer factor impact data.

[0044] In this embodiment, the transmission factor model is constructed based on the machine learning algorithm according to the transmission factor impact data, as follows: The calculation formula of the transfer factor model is as follows:

[0045] In the formula, is the transfer factor, is the electromagnetic field influence coefficient, is the compression influence coefficient, , and is the constant adjustment factor, is the transmission rate coefficient, is an exponential function.

[0046] S4, adjusts the transmission factor impact data based on the transmission factor model to achieve the best transmission energy efficiency.

[0047] In this embodiment, the transmission factor model is used to adjust the transmission factor impact data to achieve the best transmission energy efficiency, as follows: The value range of the transmission factor is between [0,1]. The higher the transmission factor, the higher the overall transmission efficiency, and the lower the transmission factor, the lower the overall transmission efficiency. The transfer factor impact data are adjusted according to the transfer factor model, and the transfer factor impact data are related to the slice size, image resolution and color depth of the data; By adjusting the slice size, image resolution and color depth, the value of the transmission factor affecting the data is changed, thereby improving the value of the transmission factor and achieving optimal transmission energy efficiency.

[0048] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0049] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0050] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0051] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0052] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0053] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A cable trench detection method, characterized in that: The steps include: Obtain image data of different resolutions and color depths of the cable trench to be tested, slice the image data, and compress the sliced ​​data and transmit it to the system; The system decompresses the received compressed image data and obtains the transmission factor influence data of the image data; Constructing a transfer factor model based on a machine learning algorithm according to the transfer factor impact data; The transmission factor impact data is adjusted based on the transmission factor model to achieve optimal transmission energy efficiency.

2. A cable trench detection method according to claim 1, characterized in that: The method of obtaining image data of different resolutions and color depths of the cable trench to be tested, slicing the image data, and compressing the sliced ​​data and transmitting it to the system is as follows: Collecting original image data of the area to be tested, wherein the original image data includes image data with the same resolution but different color depths and image data with the same color depth but different resolutions; Collecting multiple sets of original image data, and labeling the collected original image data to construct an image data set; Slice the collected original image data to obtain multiple groups of image data with different slice sizes; All slice data are encoded based on a hash function, compressed into data packets in different formats, including PNG, JPG, GIF and WEBP, and the data packets are transmitted to the data processing center of the system through the TCP protocol.

3. A cable trench detection method according to claim 2, characterized in that: The system decompresses the received compressed image data as follows: After receiving the data packet, the system selects a corresponding decompression algorithm according to the format of the data packet to decompress the data packet, wherein the decompression algorithm includes a discrete cosine transform algorithm, a PNG decompression algorithm and a Lempel-Ziv-Welch algorithm; After decompression, the integrity of the image data is verified based on the unique encoding method of the hash function. After the verification is completed, the fragmented data is integrated to obtain the processed image data.

4. A cable trench detection method according to claim 3, characterized in that: The transmission factor impact data includes a compression impact coefficient, and the steps for obtaining the compression impact coefficient are as follows: Obtaining the number of bytes of the original image data and the number of bytes of the slice data, and obtaining a compression ratio of the image data according to the comparison between the number of bytes of the original image data and the number of bytes of the slice data; Collect the frequency information of the image data during the compression process, and convert the frequency information into frequency domain coefficients through Fourier transform; Process the quantized frequency domain coefficients to remove abnormal values, then add and average them to obtain a frequency domain average coefficient and use the frequency domain average coefficient as a characteristic value; Obtaining a basic quantization coefficient of the image data, and calculating a quality factor based on a preset quality factor formula according to the basic quantization coefficient and the frequency domain average coefficient; Obtaining the total number of pixels and the value of each pixel in the original image data and the total number of pixels and the value of each pixel in the compressed image data; Calculating based on a preset mean square error formula according to the total number of pixels and the value of each pixel in the original image data and the total number of pixels and the value of each pixel in the compressed image data, to obtain a mean square error between the original image and the compressed image; Obtaining the value of the maximum pixel in the compressed image data, and calculating the peak signal-to-noise ratio based on a preset peak signal-to-noise ratio formula according to the mean square error between the original image and the compressed image and the value of the maximum pixel in the compressed image data; The compression influence coefficient is calculated based on a preset compression influence coefficient formula according to the compression rate, quality factor and peak signal-to-noise ratio of the image data to obtain the compression influence coefficient.

5. A cable trench detection method according to claim 4, characterized in that: The transmission factor influence data includes an electromagnetic field influence coefficient, and the steps for obtaining the electromagnetic field influence coefficient are as follows: Acquire current data of the cable, filter out current peak values ​​according to the current data, add and average the current peak values ​​to obtain a current threshold, filter out current data exceeding the current threshold according to the current threshold, and add and average the current data exceeding the current threshold to obtain a current extreme value; Obtaining the installation distance between the cables and the number of cables in the test area, and calculating based on a preset electromagnetic field calculation formula according to the installation distance between the cables, the number of cables and the current extreme value to obtain the total electromagnetic field generated by the cables; Obtain the brightness of each pixel in the compressed image data, and add and average the brightness of each pixel to obtain the average brightness of the pixel; Obtaining the noise intensity of each pixel in the compressed image data, and classifying the types of noise, wherein the types of noise include multiplicative noise and additive noise, removing noise other than additive noise, and adding and averaging the processed noise data to obtain an average noise intensity of the pixel; The standard deviation of the noise is calculated based on the standard deviation formula according to the noise intensity of each pixel and the average noise intensity; The signal-to-noise ratio of the image data is obtained based on the ratio of the average brightness of the pixel to the standard deviation of the noise; The distance between the cable and the image acquisition device is obtained, and the electromagnetic field influence coefficient is calculated based on a preset electromagnetic field influence coefficient formula according to the signal-to-noise ratio of the image data, the distance between the cable and the image acquisition device, and the total electromagnetic field generated by the cable.

6. A cable trench detection method according to claim 5, characterized in that: The transmission factor influencing data includes a transmission rate coefficient, and the steps for obtaining the transmission rate coefficient are specifically as follows: Obtain the image transmission speed under the image data state of the same slice size and different resolutions, and record the bandwidth speed during the data transmission process; Dividing the image transmission speed in the image data state of the same slice size and different resolutions and the bandwidth speed in the data transmission process into a plurality of groups of data objects in the same time period; The average value of the total bandwidth speed is obtained, and the bandwidth fluctuation coefficient is calculated based on the contrast formula according to the average value of the total bandwidth speed and the bandwidth speed in each time period; Compare the fluctuation coefficients of all bandwidths, and select the image transmission speed data with the lowest fluctuation coefficient under the image data state of the same slice size and different resolutions; Based on linear regression analysis of image transmission speed data under the same slice size and different resolution image data states, the influence index of resolution on transmission is obtained; The slice size, bandwidth speed and resolution of the image data are obtained, and the transmission rate coefficient is calculated based on a preset transmission rate coefficient formula according to the slice size, bandwidth speed, resolution of the image data and the influence index of the resolution on transmission, to obtain the transmission rate coefficient.

7. A cable trench detection method according to claim 6, characterized in that: The transmission factor model is used to adjust the transmission factor impact data to achieve the best transmission energy efficiency, as follows: The value range of the transmission factor is between [0,1]. The higher the transmission factor, the higher the overall transmission efficiency, and the lower the transmission factor, the lower the overall transmission efficiency. The transfer factor impact data are adjusted according to the transfer factor model, and the transfer factor impact data are related to the slice size, image resolution and color depth of the data; By adjusting the slice size, image resolution and color depth, the value of the transmission factor affecting the data is changed, thereby improving the value of the transmission factor and achieving optimal transmission energy efficiency.

8. A cable trench detection method according to claim 7, characterized in that: The calculation formula of the compression influence coefficient is as follows: The calculation formula of the peak signal-to-noise ratio is as follows: The calculation formula of the mean square error is as follows: The calculation formula of the quality factor is as follows: In the formula, is the compression influence coefficient, is the compression ratio of the image data, is the peak signal-to-noise ratio, is the value of the maximum pixel in the compressed image data, that is, the maximum color depth, is the mean square error, is the total number of pixels in the image, is the value of the i-th pixel in the original image, is the value of the corresponding original image pixel in the compressed image, is the quality factor, is the quantization coefficient in the current compression process, is a basic quantization coefficient.

9. A cable trench detection method according to claim 8, characterized in that: The calculation formula of the electromagnetic field influence coefficient is as follows: The calculation formula of the electromagnetic field is as follows: The calculation formula of the transmission rate coefficient is as follows: In the formula, is the electromagnetic field influence coefficient, is the signal-to-noise ratio of the image data, is the distance between the cable and the image acquisition device, is the total electromagnetic field generated by the cable, is the vacuum permeability, , is the current extreme value of the ith cable, The distance from the center of the cable trench cross section to the center of the i-th cable, is the total number of cables, is the transmission rate coefficient, is the bandwidth speed, is the resolution of the image, is the index of the impact of resolution on transmission, is the slice size.

10. A cable trench detection method according to claim 9, characterized in that: The transfer factor model is constructed based on the machine learning algorithm according to the transfer factor impact data, as follows: The calculation formula of the transfer factor model is as follows: In the formula, is the transfer factor, is the electromagnetic field influence coefficient, is the compression influence coefficient, , and is the constant adjustment factor, is the transmission rate coefficient, is an exponential function.

Images