A method for optimizing image quality for forward-looking sonar

By broadening, dimensionalizing, grading and regeneration processing of the forward-view sonar detection data, high-quality image data is generated, which solves the problem of low image quality in harsh underwater environments and improves the security of target recognition and navigation.

CN118710534BActive Publication Date: 2024-11-26ZHUHAI LANHENG TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411179358.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-11-26
Estimated Expiration
2044-08-27

AI Technical Summary

Technical Problem

The existing forward-view sonar has low image quality in harsh underwater environments, resulting in difficulty in identifying and positioning underwater targets and increasing the risk of detection accidents.

Method used

Sonar detection data and forward-view image data are collected, and high-quality image data is generated through broad-view processing, dimensionalization processing, degree processing, microfactor processing and regeneration processing, and new feature extraction is performed to generate sonar detection report information.

Benefits of technology

It improves the ability to identify underwater targets, enhances navigation safety, avoids collisions, improves detection effects, and provides more accurate identification of underwater obstacles and environmental features.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118710534B_ABST
    Figure CN118710534B_ABST
Patent Text Reader

Abstract

The invention discloses an image quality optimization method for a forward-looking sonar, relates to the field of image quality optimization, and comprises the following steps: collecting sonar detection data and forward-looking image data, and performing wide-view processing on the forward-looking image data according to the sonar detection data to obtain wide-view image data; performing dimensionalization processing and degree processing on the wide-view image data respectively to obtain dimensionalization values ​​and degree values, and performing micro-factor processing on the wide-view image data according to the dimensionalization values ​​and degree values ​​to obtain micro-view image values; performing re-growth processing on the wide-view image data according to the micro-view image values ​​to obtain re-growth image data; performing new feature extraction according to the re-growth data to obtain sonar detection report information, thereby improving the safety and efficiency of navigation and detection, improving target recognition capability, enhancing navigation safety, and improving environmental monitoring.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of image quality optimization, and in particular to an image quality optimization method for forward-looking sonar. Background Art

[0002] Forward-looking sonar uses the echo information of sound waves to form images. It is mainly used for underwater target detection, seabed survey and detection, underwater intrusion detection, underwater search and rescue, and navigation. Due to the influence of the complex underwater optical environment, the characteristics of underwater targets are difficult to obtain, and even difficult to image. Therefore, in environments with poor water quality conditions, such as turbid waters, sonar becomes a very important means for detection. Existing forward-looking sonar equipment uses an audio "lens" to generate images of almost the same as those of conventional waters in darkness or turbid waters. It can be used to identify intruders that sneak into the waters of large harbors;

[0003] Underwater sonar detection data often leads to underwater detection accidents due to low image quality, incomplete information acquisition, and users cannot more accurately identify and locate underwater obstacles, targets or environmental features. Therefore, an image quality optimization method for forward-looking sonar is provided. Summary of the invention

[0004] In order to solve the above technical problems, the object of the present invention is to provide an image quality optimization method for forward-looking sonar, comprising the following steps:

[0005] Step S1: collecting sonar detection data and forward-view image data, and performing wide-view processing on the forward-view image data according to the sonar detection data to obtain wide-view image data;

[0006] Step S2: performing dimensionalization processing and degree processing on the wide-view image data respectively to obtain a dimensionalization value and a degree value, and performing micro-factor processing on the wide-view image data according to the dimensionalization value and the degree value to obtain a micro-view image value;

[0007] Step S3: performing a re-growth process on the wide-view image data according to the micro-view image value to obtain re-growth image data;

[0008] Step S4: Extract new features based on the regrown data to obtain sonar detection report information.

[0009] Furthermore, the process of collecting sonar detection data and forward-looking image data includes:

[0010] An underwater detection terminal is provided, wherein the underwater detection terminal is used to transmit sound waves to monitor underwater conditions, collect reflected sound wave data and image data of the transmitted sound waves, and obtain corresponding sonar detection data and forward-view image data;

[0011] The sonar detection data includes sonar reflection data and sonar initial data; the sonar reflection data includes sound wave velocity, sound wave position, and sound wave intensity; the sonar initial data includes sound wave initial velocity, sound wave initial emission position, and sound wave initial intensity;

[0012] The forward-view image data includes forward-view terrain data, forward-view object data and forward-view waterscape data;

[0013] A detection cycle is set, and the underwater detection terminal collects sonar detection data and forward-looking image data in real time according to the detection cycle, and performs edge processing on the collected forward-looking image data to obtain forward-looking edge image data.

[0014] Furthermore, the forward-view image data is subjected to wide-view processing according to the sonar detection data, and the process of obtaining the wide-view image data includes:

[0015] The sonar reflection data is processed by Gaussian filtering technology to obtain the sonar noise reflection data;

[0016] Perform similarity overlap matching on the sonar noise reflection data and the sonar initial data, extract similarity features from the sonar noise reflection data based on the sonar initial data, and obtain the sonar reflection initial data;

[0017] According to the initial sonar reflection data, non-overlapping matching is performed on the sonar noise reflection data and the initial sonar data to obtain the sonar reflection update data;

[0018] The forward-view edge image data is subjected to wide-view processing according to the sonar reflection update data to obtain wide-view image data.

[0019] Furthermore, the process of dimensionalizing the wide-view image data includes:

[0020] The wide-view image data is converted into wide-view signal data by Fourier transformation, and the wide-view image data is converted from the spatial domain to the frequency domain to obtain wide-view signal data with frequency distribution;

[0021] According to the frequency distribution and amplitude distribution of the wide-view signal data, the wide-view signal data is processed in layers to obtain frequency-amplitude metadata;

[0022] Set the dimensioning factor and degree factor;

[0023] The frequency jump span of the frequency amplitude metadata is obtained, which is recorded as the dimensioned frequency;

[0024] Get the amplitude jump span of the frequency-amplitude metadata, recorded as the dimensioned amplitude;

[0025] Process the frequency-amplitude metadata according to the dimensioning factor to obtain the dimension-frequency coefficient;

[0026] According to the dimensioned frequency and the dimension-frequency coefficient, the dimensioned value is obtained;

[0027] According to the dimensionalized value, the frequency-amplitude metadata is segmented to obtain the frequency-amplitude metadata.

[0028] Furthermore, the process of respectively processing the wide-view image data includes:

[0029] Process the frequency-amplitude meta-dimensional data according to the degree factor to obtain the amplitude coefficient;

[0030] According to the dimensioning amplitude and the dimensioning coefficient, the dimensioning value is obtained;

[0031] According to the degree value, the frequency-amplitude dimension data is obtained.

[0032] Furthermore, according to the dimension value and the degree value, the process of micro-factor processing on the wide-view image data includes:

[0033] According to the dimensionalization value and the degree value, the microscopic image value is obtained.

[0034] Furthermore, the process of performing regrowth processing on the wide-view image data according to the microscopic image value to obtain the regrowth image data includes:

[0035] According to the micro-view image value, the frequency-amplitude dimension data is processed to obtain the frame image data;

[0036] According to each frame image data and the wide-view image data, the forward-view image data collected by the underwater acquisition terminal is optimized, and each frame image data is combined and processed to obtain the coordinate parameters of each frame image data;

[0037] The frame image data are combined horizontally by using the coordinate parameters of the frame image data to obtain horizontal frame image data, the horizontal frame image data are combined vertically to obtain regrown data, and the regrown data are processed by inverse Fourier transform to obtain regrown image data.

[0038] Furthermore, the process of extracting new features based on the re-grown data and obtaining sonar detection report information includes:

[0039] Set the comparison period;

[0040] Obtaining the re-growth data of the previous comparison cycle, extracting new features from the re-growth data of the current comparison cycle based on the re-growth data of the previous comparison cycle, and marking the new features on the re-growth data;

[0041] The comparison period corresponding to the new feature is obtained, the new feature and the comparison period corresponding to the new feature are associated, and the sonar detection report information is generated.

[0042] Compared with the prior art, the present invention has the following beneficial effects: collecting sonar detection data and forward-view image data, and performing wide-view processing on the forward-view image data according to the sonar detection data to obtain wide-view image data, so as to better identify and analyze targets in the underwater environment, extracting underwater data from multiple sources, obtaining underwater information in a comprehensive and detailed manner, and filtering noise on the information to improve the authenticity of the data, performing dimensionalization processing and degree processing on the wide-view image data respectively to obtain dimensionalized values ​​and degree values, and performing micro-factor processing on the wide-view image data according to the dimensionalized values ​​and degree values ​​to obtain micro-view image values, so as to improve target recognition capability and enhance navigation safety, performing re-growth processing on the wide-view image data according to the micro-view image values ​​to obtain re-growth image data, which is helpful to avoid collisions, improve decision-making and enhance detection effects, performing new feature extraction according to the re-growth data to obtain sonar detection report information, so that users can more accurately identify and locate underwater obstacles, targets or environmental features. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a schematic diagram of an image quality optimization method for forward-looking sonar according to an embodiment of the present application. DETAILED DESCRIPTION

[0044] like Figure 1 As shown, a method for optimizing image quality for forward-looking sonar comprises the following steps:

[0045] Step S1: collecting sonar detection data and forward-view image data, and performing wide-view processing on the forward-view image data according to the sonar detection data to obtain wide-view image data;

[0046] Step S2: performing dimensionalization processing and degree processing on the wide-view image data respectively to obtain a dimensionalization value and a degree value, and performing micro-factor processing on the wide-view image data according to the dimensionalization value and the degree value to obtain a micro-view image value;

[0047] Step S3: performing a re-growth process on the wide-view image data according to the micro-view image value to obtain re-growth image data;

[0048] Step S4: extract new features based on the regrown data to obtain sonar detection report information;

[0049] It should be further explained that, in the specific implementation process, the sonar detection data and the forward-view image data are collected, and the forward-view image data is subjected to wide-view processing according to the sonar detection data. The process of obtaining the wide-view image data includes:

[0050] An underwater detection terminal is provided, wherein the underwater detection terminal is used to transmit sound waves to monitor underwater conditions, collect reflected sound wave data and image data of the transmitted sound waves, and obtain corresponding sonar detection data and forward-view image data;

[0051] The sonar detection data includes sonar reflection data and sonar initial data; the sonar reflection data includes sound wave velocity, sound wave position, and sound wave intensity; the sonar initial data includes sound wave initial velocity, sound wave initial emission position, and sound wave initial intensity;

[0052] The forward-view image data includes forward-view terrain data, forward-view object data and forward-view waterscape data;

[0053] The detection cycle is set, and the underwater detection terminal collects sonar detection data and forward-looking image data in real time according to the detection cycle, performs edge processing on the collected forward-looking image data, extracts the edge of the forward-looking image data through the Prewitt edge detection operator, and obtains the forward-looking edge image data;

[0054] The sonar reflection data is processed by Gaussian filtering technology to obtain the sonar noise reflection data;

[0055] It should be further explained that, in a specific implementation process, the process of performing signal processing on the sonar reflection data by using the Gaussian filtering technology includes: generating a sound wave signal change image according to the sonar reflection data, wherein the horizontal coordinate of the sound wave signal change image is the detection period, the vertical coordinate is the sound wave intensity, and the slope is the sound wave velocity; mapping the sound wave signal change image to the coordinate system; performing noise reduction processing on the sound wave signal change image by using the Gaussian filtering technology to obtain a sound wave signal denoised change image, wherein the sound wave signal denoised image includes the sound wave denoised velocity and the sound wave denoised intensity; and the sonar noise reflection data is the sound wave signal denoised image;

[0056] Perform similarity overlapping matching on the sonar noise reflection data and the sonar initial data, perform similarity feature extraction on the sonar noise reflection data according to the sonar initial data to obtain the sonar reflection initial data, perform non-overlapping matching on the sonar noise reflection data and the sonar initial data according to the sonar reflection initial data to obtain the sonar reflection update data;

[0057] Perform wide-view processing on the front-view edge image data according to the sonar reflection update data to obtain wide-view image data;

[0058] It should be further explained that, in the specific implementation process, the process of performing wide-view processing on the forward-looking edge image data according to the sonar reflection update data includes: reproducing the image data according to the sonar reflection update data to obtain the updated image data, and performing a similarity comparison between the updated image data and the forward-looking edge image data, deleting the redundant data of the forward-looking edge image data, and obtaining the wide-view image data.

[0059] It should be further explained that, in the specific implementation process, the wide-view image data is dimensionalized and metrically processed respectively to obtain the dimensionalized value and metrically processed value, and the wide-view image data is micro-factored according to the dimensionalized value and metrically processed value to obtain the micro-view image value. The process includes:

[0060] Converting the wide-view image data into wide-view signal data by Fourier transform, converting the wide-view image data from the spatial domain to the frequency domain, and obtaining wide-view signal data with frequency distribution, wherein the wide-view signal data includes the frequency distribution and amplitude distribution of the signal;

[0061] According to the frequency distribution and amplitude distribution of the wide-view signal data, the wide-view signal data is processed in layers to obtain frequency-amplitude metadata;

[0062] It should be further explained that, in the specific implementation process, according to the frequency distribution and amplitude distribution of the wide-view signal data, the process of performing segment processing on the wide-view signal data includes: setting a frequency jump range and an amplitude jump range, first segmenting the wide-view signal data by the frequency jump range to obtain a plurality of wide-view signal segment data, and then segmenting each wide-view signal segment data by the amplitude jump range to obtain frequency-amplitude metadata;

[0063] The frequency jump span of the frequency-amplitude metadata is less than or equal to the frequency jump range, and the amplitude jump span is less than or equal to the amplitude jump range;

[0064] Setting a dimensioning factor and a metric factor, wherein the dimensioning factor is expressed in a function form, the metric factor is expressed in a function form, and the function form of the dimensioning factor is different from the function form of the metric factor;

[0065] The frequency jump span of the frequency amplitude metadata is obtained, which is recorded as the dimensioned frequency;

[0066] Get the amplitude jump span of the frequency-amplitude metadata, recorded as the dimensioned amplitude;

[0067] Processing the frequency-amplitude metadata according to the dimensioning factor, recording the frequency-amplitude metadata by scaling the frequency distribution through the dimensioning factor, and obtaining the dimension-frequency coefficient;

[0068] According to the dimensioned frequency and the dimension-frequency coefficient, a dimensioned value is obtained, and the obtained dimensioned value is marked as Wio, where: , ve represents the minimum frequency value in the frequency-amplitude metadata, T represents the dimensioned frequency, t represents the dimension-frequency coefficient, j represents the number of dimension-frequency coefficients, Ac represents the maximum frequency value in the frequency-amplitude metadata, and X represents the dimensioned amplitude;

[0069] According to the dimensionalized value, the frequency-amplitude metadata is segmented to obtain the frequency-amplitude metadata;

[0070] The segmentation process refers to segmenting the signal width of the frequency-amplitude metadata into a plurality of data segments according to the dimensionalization value to obtain the frequency-amplitude metadata;

[0071] Process the frequency-amplitude meta-dimensional data according to the scaling factor, and record the frequency-amplitude meta-dimensional data by scaling the amplitude distribution through the scaling factor to obtain the amplitude coefficient;

[0072] According to the dimensioning amplitude and the dimensioning coefficient, the dimensioning value is obtained, and the obtained dimensioning value is marked as U, where , ge represents the minimum frequency in the frequency-amplitude meta-dimensional data, Y represents the dimensioned amplitude, y represents the dimension-amplitude coefficient, c represents the number of dimension-amplitude coefficients, Si represents the maximum frequency in the frequency-amplitude meta-dimensional data, and H represents the dimensioned frequency;

[0073] According to the degree value, the frequency-amplitude meta-dimensional data is segmented to obtain the frequency-amplitude meta-dimensional data;

[0074] The segmentation process refers to segmenting the signal width of the frequency-amplitude meta-dimensional data into a plurality of data segments according to the degree value to obtain the frequency-amplitude meta-dimensional data;

[0075] According to the dimension value and the degree value, the frequency-amplitude dimension data is processed by micro-factor to obtain the microscopic image value, and the obtained microscopic image value is marked as Sto, where: , Represents the micro-viewing image factor.

[0076] It should be further explained that, in the specific implementation process, the process of performing regrowth processing on the wide-view image data according to the microscopic image value to obtain the regrowth image data includes:

[0077] According to the micro-view image value, the frequency-amplitude dimension data is processed, and the signal distribution of the frequency-amplitude dimension data is screened to obtain the frame image data;

[0078] It should be further explained that, in the specific implementation process, the process of screening the signal distribution of the frequency-amplitude meta-dimensional data includes: modifying the signal in the frequency-amplitude meta-dimensional data through the micro-viewing image value, if the product of the frequency distribution and the amplitude distribution of the signal is less than the micro-viewing image value, marking the signal points of the frequency distribution and the amplitude distribution, and recording the micro-viewing image value as the iteration coefficient, and iterating the frequency distribution and the amplitude distribution of the signal point according to the micro-viewing image value, respectively, wherein the iterative processing refers to the iterative coefficient being the exponent of the number of iterations and the ratio calculation of the frequency or amplitude, until the product of the frequency distribution and the amplitude distribution is greater than the micro-viewing image value, then the frame image data is obtained;

[0079] According to each frame image data and the wide-view image data, the forward-view image data collected by the underwater acquisition terminal is optimized, and each frame image data is combined and processed to obtain the coordinate parameters of each frame image data;

[0080] It should be further explained that, in a specific implementation process, the process of combining and processing each frame image data includes: sequentially positioning each frame image data through the wide-view image data, the sequential positioning refers to the corresponding position of each frame image data on the wide-view image, after the sequence of all frame image data is restored, the position mark is performed on each frame image data, the position mark includes a horizontal position and a vertical position, and the horizontal position and the vertical position are sequentially combined to obtain coordinate parameters, for example, the horizontal position of the frame image data is 01, and the vertical position is 05, then the coordinate parameter of the frame image data is 0105;

[0081] Combining the frame image data horizontally according to the coordinate parameters of the frame image data to obtain horizontal frame image data, and combining the horizontal frame image data vertically to obtain re-growth data;

[0082] It should be further explained that, in a specific implementation process, the process of combining the frame image data horizontally is: extracting overlapping elements from the coordinate parameters of all the frame image data, setting the horizontal position digit to mo and the vertical position digit to mi, and if the first mo digits of the frame image data are all and continuously overlapped, then combining the frame image data horizontally in the order of the last mi digits;

[0083] It should be further explained that, in a specific implementation process, the process of combining the horizontal frame image data vertically is as follows: obtaining the last mi digits of the horizontal frame image data, and extracting overlapping elements; if the last mi digits of the frame image data are complete and continuously overlapped, combining the frame image data vertically to obtain regrown data;

[0084] Processing the re-growth data by inverse Fourier transform to obtain re-growth image data;

[0085] It should be further explained that, in a specific implementation process, the regrown data is all signal data, and processing the regrown data by inverse Fourier transform means converting the signal data into image data by inverse Fourier transform.

[0086] It should be further explained that, in the specific implementation process, the process of extracting new features based on the re-grown data and obtaining the sonar detection report information includes:

[0087] Set the comparison period;

[0088] The new features refer to different image features obtained by comparing the regrown data according to the comparison cycle;

[0089] It should be further explained that, in the specific implementation process, the comparison cycle is used to discover new features in real time and monitor underwater changes;

[0090] Obtaining the re-growth data of the previous comparison cycle, extracting new features from the re-growth data of the current comparison cycle based on the re-growth data of the previous comparison cycle, and marking the new features on the re-growth data;

[0091] It should be further explained that in the specific implementation process, new features refer to unknown aquatic organisms, aquatic plants, water flow conditions and water quality conditions that appear underwater, which are used to observe changes in underwater conditions;

[0092] The comparison period corresponding to the new feature is obtained, the new feature and the comparison period corresponding to the new feature are associated, and the sonar detection report information is generated.

[0093] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for optimizing image quality of forward-looking sonar, characterized in that: The following steps are involved: Step S1: collecting sonar detection data and forward-view image data, and performing wide-view processing on the forward-view image data according to the sonar detection data to obtain wide-view image data; Step S2: performing dimensionalization processing and degree processing on the wide-view image data respectively to obtain a dimensionalization value and a degree value, and performing micro-factor processing on the wide-view image data according to the dimensionalization value and the degree value to obtain a micro-view image value; Step S3: performing a re-growth process on the wide-view image data according to the micro-view image value to obtain re-growth image data; Step S4: extract new features based on the regrown data to obtain sonar detection report information; The process of dimensionalizing the wide-view image data includes: The wide-view image data is converted into wide-view signal data by Fourier transformation, and the wide-view image data is converted from the spatial domain to the frequency domain to obtain wide-view signal data with frequency distribution; According to the frequency distribution and amplitude distribution of the wide-view signal data, the wide-view signal data is processed in layers to obtain frequency-amplitude metadata; Set the dimensioning factor and degree factor; The frequency jump span of the frequency amplitude metadata is obtained, which is recorded as the dimensioned frequency; Get the amplitude jump span of the frequency-amplitude metadata, recorded as the dimensioned amplitude; Process the frequency-amplitude metadata according to the dimensioning factor to obtain the dimension-frequency coefficient; According to the dimensioned frequency and the dimension-frequency coefficient, the dimensioned value is obtained; According to the dimensionalized value, the frequency-amplitude metadata is segmented to obtain the frequency-amplitude metadata; The process of quantizing the wide-view image data includes: Process the frequency-amplitude meta-dimensional data according to the degree factor to obtain the amplitude coefficient; According to the dimensioning amplitude and the dimensioning coefficient, the dimensioning value is obtained; According to the degree value, the frequency-amplitude dimension data is obtained; According to the dimension value and the degree value, the process of micro-factor processing of the wide-view image data includes: According to the dimensionalization value and the degree value, the microscopic image value is obtained.

2. The image quality optimization method for forward-looking sonar according to claim 1, characterized in that: The process of collecting sonar detection data and forward-looking image data includes: An underwater detection terminal is provided, wherein the underwater detection terminal is used to transmit sound waves to monitor underwater conditions, collect reflected sound wave data and image data of the transmitted sound waves, and obtain corresponding sonar detection data and forward-view image data; The sonar detection data includes sonar reflection data and sonar initial data; the sonar reflection data includes sound wave velocity, sound wave position, and sound wave intensity; the sonar initial data includes sound wave initial velocity, sound wave initial emission position, and sound wave initial intensity; The forward-view image data includes forward-view terrain data, forward-view object data and forward-view waterscape data; A detection cycle is set, and the underwater detection terminal collects sonar detection data and forward-looking image data in real time according to the detection cycle, and performs edge processing on the collected forward-looking image data to obtain forward-looking edge image data.

3. The image quality optimization method for forward-looking sonar according to claim 2, characterized in that: According to the sonar detection data, the forward-view image data is processed with wide-view technology, and the process of obtaining the wide-view image data includes: The sonar reflection data is processed by Gaussian filtering technology to obtain the sonar noise reflection data; Perform similarity overlap matching on the sonar noise reflection data and the sonar initial data, extract similarity features from the sonar noise reflection data based on the sonar initial data, and obtain the sonar reflection initial data; According to the initial sonar reflection data, non-overlapping matching is performed on the sonar noise reflection data and the initial sonar data to obtain the sonar reflection update data; The forward-view edge image data is subjected to wide-view processing according to the sonar reflection update data to obtain wide-view image data.

4. The image quality optimization method for forward-looking sonar according to claim 3, characterized in that: The process of regrowing the wide-view image data according to the microscopic image value to obtain the regrown image data includes: According to the micro-view image value, the frequency-amplitude dimension data is processed to obtain the frame image data; According to each frame image data and the wide-view image data, the forward-view image data collected by the underwater acquisition terminal is optimized, and each frame image data is combined and processed to obtain the coordinate parameters of each frame image data; The frame image data are combined horizontally by using the coordinate parameters of the frame image data to obtain horizontal frame image data, the horizontal frame image data are combined vertically to obtain regrown data, and the regrown data are processed by inverse Fourier transform to obtain regrown image data.

5. The image quality optimization method for forward-looking sonar according to claim 4, characterized in that: The process of extracting new features based on regrown data and obtaining sonar detection report information includes: Set the comparison period; Obtaining the re-growth data of the previous comparison cycle, extracting new features from the re-growth data of the current comparison cycle based on the re-growth data of the previous comparison cycle, and marking the new features on the re-growth data; The comparison period corresponding to the new feature is obtained, the new feature and the comparison period corresponding to the new feature are associated, and the sonar detection report information is generated.