A side scan sonar detection method and device based on big data

Abstract

The application discloses a side scan sonar detection method and device based on big data, which comprises the following steps: collecting detection performance parameters of side scan sonar technology, and classifying to obtain classification performance parameters corresponding to each evaluation detection performance index; obtaining a target analysis model corresponding to a target evaluation detection performance index, analyzing the classification performance parameters according to the target analysis model, and obtaining a performance index corresponding to each evaluation detection performance index; evaluating the qualified degree of each performance index to obtain a performance qualified degree corresponding to each evaluation detection performance index; obtaining a weight value corresponding to each performance qualified degree, obtaining a detection performance comprehensive index according to each performance qualified degree and the weight value corresponding thereto; and judging whether the detection performance comprehensive index exceeds a preset allowable range, and if yes, an alarm signal is sent. Through deep analysis and mining of massive sonar data by the big data technology, accurate feature extraction and classification of the sonar data are realized, and the data processing capacity and detection efficiency are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of side scan sonar, in particular to a side scan sonar detection method and device based on big data. BACKGROUND

[0002] Side scan sonar technology is an underwater detection technology that uses echo sounding principles to image underwater targets and topography. By measuring the propagation time and echo signal strength of sound waves, the distance, size and shape of the seabed topography or underwater target are calculated, and it is widely used in marine science, seabed resource exploration, underwater archaeology, port channel maintenance and other fields.

[0003] The traditional side scan sonar technology has a large working distance, resulting in low spatial resolution of the image, which in turn leads to a decrease in image quality. Moreover, in complex environments, side scan sonar images are severely contaminated by noise, which interferes with the accurate identification and positioning of target objects. At the same time, the amount of data collected by the side scan sonar system is extremely large, and the data often contains a large number of noise points, requiring automatic filtering and manual intervention processing of point cloud data. There is a lack of efficient processing and analysis capabilities for data, making it difficult to meet the increasingly complex needs of marine exploration. SUMMARY

[0004] The technical problem to be solved by the present application is to provide a side scan sonar detection method and device based on big data to improve the accuracy of side scan sonar detection.

[0005] To solve the above technical problems, the technical scheme adopted by the present application is:

[0006] A side scan sonar detection method based on big data, comprising:

[0007] Collecting detection performance parameters of side scan sonar technology and classifying to obtain classification performance parameters corresponding to each evaluation detection performance index;

[0008] Obtaining a target analysis model corresponding to a target evaluation detection performance index, analyzing the classification performance parameters according to the target analysis model, and obtaining a performance index corresponding to each evaluation detection performance index;

[0009] Evaluating the performance index to obtain a performance qualification degree corresponding to each evaluation detection performance index;

[0010] Obtaining a weight value corresponding to each performance qualification degree, and obtaining a detection performance comprehensive index according to each performance qualification degree and its corresponding weight value;

[0011] Judging whether the detection performance comprehensive index exceeds a preset allowable range, and if so, issuing an alarm signal.

[0012] To solve the above technical problems, another technical solution adopted by the present application is:

[0013] A side scan sonar detection device based on big data, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements each step of the above-mentioned side scan sonar detection method based on big data when executing the computer program.

[0014] The present application has the beneficial effects that: by collecting the detection performance parameters of the side scan sonar technology and classifying them to obtain the classification performance parameters corresponding to each evaluation detection performance index, i.e. by using big data technology to deeply analyze and mine massive sonar data, the accurate feature extraction and classification of sonar data are realized, and the data processing capability and detection efficiency are improved; and by analyzing and evaluating the performance qualification degree of each evaluation detection performance index in turn, and then combining all the performance qualification degrees to obtain the detection performance comprehensive index for comprehensive judgment of the performance of the side scan sonar, when the detection performance comprehensive index shows an abnormality, the management personnel are prompted to handle it in time, so as to improve the accuracy of detection. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 The step flow chart of the side scan sonar detection method based on big data in the embodiment of the present application;

[0016] Figure 2 The structural schematic diagram of the side scan sonar detection device based on big data in the embodiment of the present application;

[0017] Figure 3 The module schematic diagram of the side scan sonar detection device based on big data in the embodiment of the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0019] Please refer to Figure 1 A side scan sonar detection method based on big data, comprising:

[0020] Collecting the detection performance parameters of the side scan sonar technology and classifying them to obtain the performance parameters corresponding to each evaluation detection performance index;

[0021] obtain a target analysis model corresponding to the target evaluation detection performance index, analyze the classification performance parameters according to the target analysis model, and obtain a performance index corresponding to each evaluation detection performance index;

[0022] evaluate the eligibility of each classification performance index, and obtain a performance eligibility corresponding to each evaluation detection performance index;

[0023] obtain a weight value corresponding to each performance eligibility, and obtain a comprehensive detection performance index according to each performance eligibility and the weight value corresponding thereto;

[0024] determine whether the comprehensive detection performance index exceeds a preset allowable range, and if so, issue an alarm signal.

[0025] As can be seen from the above description, the beneficial effects of the present application are as follows: by collecting the detection performance parameters of the side-scan sonar technology and classifying the same to obtain the classification performance parameters corresponding to each evaluation detection performance index, i.e., by using big data technology to deeply analyze and mine massive sonar data, accurate feature extraction and classification of the sonar data are realized, and the data processing capability and detection efficiency are improved; and by sequentially analyzing the classification performance parameters corresponding to each evaluation detection performance index, evaluating the eligibility, obtaining the performance eligibility, and then obtaining the comprehensive detection performance index by combining all the performance eligibilities, the performance of the side-scan sonar is comprehensively determined, when the comprehensive detection performance index shows an abnormality, the management personnel are immediately prompted to handle, so as to improve the accuracy of detection.

[0026] Further, the evaluation detection performance index includes imaging clarity, target detection efficiency, target detection dynamic stability, and intelligent classification recognition accuracy;

[0027] The classification performance parameters corresponding to each evaluation detection performance index include:

[0028] The classification of the detection performance parameters includes imaging clarity parameters, target detection efficiency parameters, target detection dynamic stability parameters, and intelligent classification recognition accuracy parameters.

[0029] From the above description, by setting the imaging clarity, target detection performance, target detection dynamic stability and intelligent classification and recognition accuracy as the evaluation detection performance indicators, by analyzing the imaging quality evaluation parameters, the ability of the side scan sonar technology to retain image clarity and details in the underwater imaging process can be measured; by analyzing the underwater target detection capability parameters, the ability of the side scan sonar technology to detect targets underwater can be measured; by analyzing the detection stability parameters under the influence of dynamic environment, the ability of the side scan sonar technology to maintain image stability and continuity in dynamic environment can be measured; by analyzing the intelligent classification and recognition parameters, the accuracy and efficiency of the side scan sonar technology in target classification combined with big data and intelligent algorithms can be measured, and the multi-aspect ability of the side scan sonar technology can be analyzed.

[0030] Further, the target analysis model includes an imaging clarity model:

[0031]

[0032] wherein ICI represents an imaging clarity index, represents an imaging quality evaluation influence factor; PD represents an image pixel density, W_ip represents an image width pixel number, H_ip represents an image height pixel number, and W_sa represents a scanning area width; SNG represents an image signal-to-noise ratio gain; SNR aft represents a processed signal-to-noise ratio, SNR ori represents an original signal-to-noise ratio, Ps represents an image signal power, and Pn represents an image noise power; ES represents an image edge sharpening degree; G_x represents an image gradient component in x direction, and G_y represents an image gradient component in y direction; ICL represents an image compression loss, QI ori represents an original image quality index, QI aft a compressed image quality index, and PSNR represents an image peak signal-to-noise ratio, and SSIM represents an image structural similarity.

[0033] From the above description, by comprehensively considering the pixel density, signal-to-noise ratio gain, edge sharpening degree and image compression loss and other factors directly affecting the resolution and detail performance of the image, the imaging quality evaluation parameters can be effectively analyzed, and the image clarity and detail retention ability can be accurately determined.

[0034] Further, the target analysis model includes a target detection performance model:

[0035]

[0036] wherein TDE represents a target detection performance index; represents a target detection influence factor; MD maxrepresents the maximum detection depth of the side scan sonar; MD0 represents the theoretical detection depth; PLC represents the average proportion of the side scan sonar signal penetration loss, n represents the number of different target media, Sat i represents the received signal strength of the i-th medium, Sor represents the transmitted signal strength; FPR represents the false positive rate, Ne represents the number of false identifications of non-targets, Iq represents the identification number; DTE represents the detection time efficiency, S represents the target detection area, t sao represents the scanning time of the side scan sonar, t chu represents the data processing time, and DTE0 represents the theoretical detection time efficiency.

[0037] As can be seen from the above description, the maximum detection depth, the penetration loss proportion, the false positive rate, and the detection time efficiency and other aspects related to the target detection capability are comprehensively considered, which helps to improve the target detection capability in complex environments.

[0038] Further, the target analysis model includes a target detection dynamic stability model:

[0039]

[0040]

[0041] wherein DSC represents a target detection dynamic stability index, represents the influence factor of the dynamic environment; ACA represents the attitude correction offset degree, θ_cal represents the corrected ship attitude data, θ_ref represents the reference ship attitude data; VSI represents the speed fluctuation suppression, σ_wave represents the standard deviation of the scanning result image quality under speed fluctuation, σ_stable represents the standard deviation of the scanning result image quality under stable speed; ANI represents the dynamic environment noise suppression, SNR_pro represents the processed side scan sonar signal noise ratio, SNR_ori represents the original side scan sonar signal noise ratio; IC represents the image continuity rate, S_ove represents the area of the image overlap region, and S_tot represents the total image area.

[0042] As can be seen from the above description, the attitude correction accuracy, the speed fluctuation suppression, the environmental noise suppression, and the image continuity rate and other factors affecting the image quality are comprehensively considered, which helps to improve the signal-to-noise ratio and the definition of the image, and to maintain the continuity and stability of the image.

[0043] Further, the target analysis model includes an intelligent classification and identification accuracy model:

[0044]

[0045] wherein SCA represents an intelligent classification and identification accuracy index, BCA represents the basic recognition accuracy, Iq represents the number of recognitions, Cq represents the number of targets correctly recognized by the target detection, AOG represents the algorithm optimization gain, CA aft represents the target detection classification accuracy based on big data, CA ori represents the original target detection classification accuracy; CDS represents the classification decision speed, N_i represents the number of image classification processes, t chu represents the image processing time, CDS0 represents the original image classification decision speed.

[0046] As can be seen from the above description, the basic recognition accuracy, algorithm optimization gain, and classification decision speed are comprehensively considered, which helps to process and analyze data faster, improve processing efficiency and real-time performance.

[0047] Further, the performance qualification evaluation of each performance index comprises:

[0048] Each performance index is processed by the performance qualification evaluation model to obtain the performance qualification corresponding to each evaluation detection performance index, specifically:

[0049]

[0050] wherein, represents the performance qualification corresponding to the performance index, X0 represents the set value corresponding to the performance index, and X represents the performance index.

[0051] As can be seen from the above description, by setting the corresponding set value for each performance index, the performance qualification corresponding to each performance index can be accurately reflected.

[0052] Further, the detection performance comprehensive index is obtained according to each performance qualification and the corresponding weight value thereof, comprising:

[0053]

[0054] wherein, DCi represents the detection performance comprehensive index; represents the performance qualification of the imaging clarity index; represents the performance qualification of the target detection efficiency index; represents the performance qualification of the target detection dynamic stability index; represents the performance qualification of the intelligent classification recognition accuracy index; ξ1, ξ2, ξ3, and ξ4 represent the weight values corresponding to different performance qualifications.

[0055] From the above description, by assigning a corresponding weight value to each performance qualification, the performance of the side scan sonar is comprehensively evaluated by multiple indicators, which can more comprehensively reflect the performance of the side scan sonar than single indicator evaluation.

[0056] Another embodiment of the present application provides a side scan sonar detection device based on big data, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to realize each step of the above-mentioned side scan sonar detection method based on big data.

[0057] The side scan sonar detection method and device based on big data provided by the present application can be applied to the side scan sonar technology detection scene, which will be described in detail below through a specific embodiment.

[0058] Embodiment one

[0059] Please refer to Figure 1 A side scan sonar detection method based on big data, comprising:

[0060] S1, collecting detection performance parameters of side scan sonar technology, and classifying the detection performance parameters to obtain classification performance parameters corresponding to each evaluation detection performance indicator. For example, in the present embodiment, the evaluation detection performance indicators include imaging clarity, target detection efficiency, target detection dynamic stability, and intelligent classification recognition accuracy, and also include target region information and manager identity verification information; the detection performance parameters are classified to obtain imaging clarity parameters, target detection efficiency parameters, target detection dynamic stability parameters, and intelligent classification recognition accuracy parameters.

[0061] The imaging quality (imaging clarity) evaluation parameters specifically include: image width pixel number, image height pixel number, scanning area width, image signal power, image noise power, image gradient component in x direction, image gradient component in y direction, image peak signal-to-noise ratio, and image structural similarity.

[0062] The underwater target detection capability (target detection efficiency) parameters specifically include: maximum detection depth of side scan sonar, theoretical detection depth, number of different target media types, received signal strength, transmitted signal strength, number of false non-target identifications, number of identifications, target detection area, side scan sonar scanning time, and data processing time.

[0063] The detection stability under dynamic environment (target detection dynamic stability) parameters specifically include: corrected ship attitude data, reference ship attitude data, standard deviation of image quality, signal signal-to-noise ratio, area of image overlap region, and total image area.

[0064] The intelligent classification and recognition rate parameters specifically include: the number of recognitions, the number of correctly recognized targets in target detection, the target detection classification accuracy, the number of image classification processes, and the image processing time.

[0065] S2, obtaining a target analysis model corresponding to the target evaluation detection performance index, analyzing the classification performance parameters according to the target analysis model, and obtaining a performance index corresponding to each evaluation detection performance index. The specific target analysis model and analysis method are as follows:

[0066] 1) Imaging clarity model:

[0067]

[0068] Wherein, ICI represents the imaging clarity index; represents the imaging quality evaluation influence factor, the value of the influence factor is determined according to the actual detection situation; PD represents the image pixel density, W_ip represents the image width pixel number, H_ip represents the image height pixel number, and W_sa represents the scanning area width; SNG represents the image signal-to-noise ratio gain; SNR aft represents the processed signal-to-noise ratio, SNR ori represents the original signal-to-noise ratio, Ps represents the image signal power, Pn represents the image noise power, the signal power and the noise power are obtained by Fourier transform of the original signal and the signal after noise suppression; ES represents the image edge sharpening degree; G_x represents the gradient component of the image in the x direction, and G_y represents the gradient component of the image in the y direction. The edges in the image are detected by using an edge detection algorithm, such as a Sobel operator, a Canny edge detector, etc., to obtain the gradient of the edge region; ICL represents the image compression loss, QI ori represents the original image quality index, QI aft the image quality index after compression, PSNR represents the image peak signal-to-noise ratio, and SSIM represents the image structural similarity.

[0069] 2) Target detection efficiency model:

[0070]

[0071]

[0072] Wherein, TDE represents the target detection efficiency index; represents the target detection influence factor; MD max represents the side scan sonar maximum detection depth; MD0 represents the theoretical detection depth; PLC represents the average proportion of side scan sonar signal penetration loss, n represents the number of different target media types, Sat iSor represents the received signal strength of the i-th medium, Sor represents the transmitted signal strength; FPR represents the false positive rate, Ne represents the number of false identifications of non-targets, Iq represents the number of identifications, and 0.01 is added to avoid a denominator of 0; DTE represents the detection time efficiency, S represents the target detection area, and t sao represents the side-scan sonar scanning time, t chu represents the data processing time, and DTE0 represents the theoretical detection time efficiency.

[0073] 3) Target detection dynamic stability model:

[0074]

[0075] wherein DSC represents a target detection dynamic stability index, represents an impact factor of dynamic environment; ACA represents an attitude correction offset degree, θ_cal represents corrected ship attitude data, θ_ref represents reference ship attitude data, ship attitude data is collected by high-precision attitude sensors and inertial navigation systems, including pitch angle, roll angle, heading angle, etc.; VSI represents velocity fluctuation suppression, σ_wave represents the standard deviation of the scanning result image quality under velocity fluctuation, σ_stable represents the standard deviation of the scanning result image quality under stable velocity, and 0.01 is added to avoid a denominator of 0; ANI represents dynamic environment noise suppression, SNR_pro represents the processed side-scan sonar signal noise ratio, and SNR_ori represents the original side-scan sonar signal noise ratio; IC represents the image continuity rate, S_ove represents the area of the image overlap region, and S_tot represents the total image area.

[0076] 4) Intelligent classification and identification accuracy model:

[0077]

[0078] wherein SCA represents an intelligent classification and identification accuracy index, represents an impact factor of intelligent classification and identification; BCA represents the basic identification accuracy, Iq represents the number of identifications, and Cq represents the number of correctly identified targets in target detection; AOG represents the algorithm optimization gain, CA aft represents the target detection classification accuracy based on big data, CA ori represents the original target detection classification accuracy; CDS represents the classification decision speed, N_i represents the number of image classification processes, and t chu represents the image processing time, and CDS0 represents the original image classification decision speed.

[0079] S3, evaluate the qualification degree of each performance index to obtain the performance qualification degree corresponding to each evaluation detection performance index; in an optional embodiment, each performance index is processed by a performance qualification degree evaluation model to obtain the performance qualification degree corresponding to each evaluation detection performance index, and the expression of the performance qualification degree evaluation model is as follows:

[0080]

[0081] wherein, represents the performance qualification degree corresponding to the performance index, X0 represents the set value corresponding to the performance index, and X represents the performance index. For example, the imaging clarity index ICI, the target detection efficiency index TDE, the target detection dynamic stability index DSC, and the intelligent classification and recognition accuracy rate index SCA are sequentially brought into the above formula, and the following is obtained respectively:

[0082]

[0083]

[0084] wherein, represents the performance qualification degree of the imaging clarity index; represents the performance qualification degree of the target detection efficiency index; represents the performance qualification degree of the target detection dynamic stability index; represents the performance qualification degree of the intelligent classification and recognition accuracy rate index; ICI0, TDE0, DSC0, and SCA0 represent the set values corresponding to the indexes; it needs to be specifically pointed out that: if the imaging quality is qualified, otherwise the imaging quality is abnormal; if the target detection efficiency is qualified; if the target detection dynamic stability is qualified; if the intelligent classification and recognition accuracy rate is qualified.

[0085] S4, obtain the weight value corresponding to each performance qualification degree, and obtain the detection performance comprehensive index according to each performance qualification degree and the weight value corresponding thereto; in an optional embodiment, the detection performance comprehensive index is obtained by a comprehensive analysis model, and the comprehensive analysis model is as follows:

[0086]

[0087] wherein, DCi represents the detection performance comprehensive index; represents the performance qualification degree of the imaging clarity index; represents the performance qualification degree of the target detection efficiency index; represents the performance qualification degree of the target detection dynamic stability index; Performance qualification degree representing intelligent classification recognition accuracy index; ξ1, ξ2, ξ3 and ξ4 represent weight values corresponding to different performance qualification degrees, and the weight values are generally determined according to the contribution degree of a single index to the evaluation of detection performance.

[0088] S5, whether the detection performance comprehensive index exceeds the preset allowable range, if yes, an alarm signal is sent. That is, the detection performance comprehensive index obtained by analysis is subjected to human-computer interaction, and when the detection performance comprehensive index belongs to the set allowable range, it is indicated that the detection performance of the side scan sonar technology is good, and if the detection performance comprehensive index exceeds the allowable range, the management personnel are prompted to take measures in time. For example: optimizing signal acquisition and processing algorithm, improving signal sampling rate and processing precision; optimizing sonar beam forming and scanning strategy, improving detection range and depth, adjusting scanning parameters and strategy in real time according to speed fluctuation, strengthening data preprocessing and feature extraction link to meet the increasingly complex and diversified underwater task requirements.

[0089] Embodiment two

[0090] Please refer to Figure 2 A side scan sonar detection device based on big data, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements each step of a kind of based on big data side scan sonar detection method as in embodiment one when executing computer program. Among them, in a specific embodiment, the memory and the processor form side scan sonar technology detection data acquisition module, side scan sonar technology detection data analysis module, side scan sonar technology detection data evaluation module, side scan sonar technology detection comprehensive analysis module and side scan sonar technology detection human-computer interaction module.

[0091] Please refer to Figure 3 Side scan sonar technology detection data acquisition module is connected with side scan sonar technology detection data analysis module, side scan sonar technology detection data evaluation module is connected with side scan sonar technology detection comprehensive analysis module and side scan sonar technology detection data analysis module respectively, and side scan sonar technology detection comprehensive analysis module is connected with side scan sonar technology detection data evaluation module and side scan sonar technology detection human-computer interaction module respectively.

[0092] Among them, the side scan sonar technology detection data acquisition module is used for collecting the detection performance parameters of the side scan sonar technology, obtaining each parameter for evaluating the detection performance index, and transmitting each parameter to the side scan sonar technology detection data analysis module.

[0093] The side-scan sonar technology detection data analysis module is configured to analyze various parameters to obtain various indexes of the side-scan sonar technology detection. For example, the imaging quality evaluation index analysis unit, the underwater target detection capability index analysis unit, the detection stability index analysis unit under the influence of dynamic environment, and the intelligent classification and identification index analysis unit are respectively configured to analyze corresponding detection performance parameters to obtain the imaging clarity index ICI, the target detection efficiency index TDE, the target detection dynamic stability index DSC, and the intelligent classification and identification accuracy index SCA as described in Embodiment 1. Subsequently, the indexes are transmitted to the side-scan sonar technology detection data evaluation module.

[0094] The side-scan sonar technology detection data evaluation module is configured to compare the various indexes of the side-scan sonar technology detection obtained by the data analysis module with the set values. For example, the performance qualification evaluation model in Embodiment 1 is configured to process each performance index to obtain the performance qualification corresponding to each evaluation detection performance index. Subsequently, the comparison and evaluation results are transmitted to the side-scan sonar technology detection comprehensive analysis module.

[0095] The side-scan sonar technology detection comprehensive analysis module is configured to comprehensively analyze the results calculated by the data evaluation module. For example, the comprehensive analysis model in Embodiment 1 is configured to perform comprehensive analysis to obtain the detection performance comprehensive index, and the detection performance comprehensive index is output to the side-scan sonar technology detection human-computer interaction module.

[0096] The side-scan sonar technology detection human-computer interaction module is configured to output the detection performance comprehensive index input from the above modules to the management personnel information terminal.

[0097] In summary, the present application provides a side-scan sonar detection method and device based on big data, which analyzes the imaging quality evaluation parameters, underwater target detection capability parameters and detection stability parameters under dynamic environmental influence respectively. Based on the imaging quality index, the side-scan sonar technology is evaluated in the underwater imaging process, the image clarity and detail retention capability, pixel density directly affect the resolution and detail performance of the image, clear image helps to reduce misjudgment and missed judgment, improve the accuracy and reliability of target identification; based on the underwater target detection capability index, the side-scan sonar technology is evaluated in the ability and efficiency of underwater target detection, which helps to accurately identify and locate the underwater target object, so as to help users make more accurate judgment, help to quickly process a large amount of sonar data, improve work efficiency and reduce detection cost; and based on the detection stability index under dynamic environmental influence, the side-scan sonar technology is evaluated in the ability to maintain image stability and continuity in dynamic environment, which helps to adapt to these environmental changes, maintain stable detection performance, avoid detection result error caused by dynamic environmental influence, and further improve the quality of detection data. Through big data technology, massive sonar data can be deeply analyzed and mined, accurate feature extraction and classification of sonar data can be realized, data processing capability and detection efficiency are improved, and detection accuracy is improved. It provides more scientific decision support for marine resource development, environmental protection, underwater archaeology and other fields to meet the increasingly complex and diversified underwater task requirements.

[0098] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0099] The above content is only an example and description of the concept of the present application. Those skilled in the art can make various modifications, supplements or use similar ways to replace the described specific embodiments, as long as they do not deviate from the concept of the present application or exceed the scope defined by the present application, which shall be within the protection scope of the present application.

Claims

1. A side scan sonar detection method based on big data, characterized in that, The method comprises the following steps: Collecting detection performance parameters of the side scan sonar technology, and classifying the detection performance parameters to obtain classified performance parameters corresponding to each evaluation detection performance index; Obtaining a target analysis model corresponding to a target evaluation detection performance index, analyzing the classified performance parameters according to the target analysis model, and obtaining a performance index corresponding to each evaluation detection performance index; Evaluating the performance index to obtain a performance qualification degree corresponding to each evaluation detection performance index; Obtaining a weight value corresponding to each performance qualification degree, and obtaining a comprehensive detection performance index according to each performance qualification degree and the weight value corresponding thereto; Judging whether the comprehensive detection performance index exceeds a preset allowable range, and if so, issuing an alarm signal; The evaluation detection performance index comprises imaging clarity, target detection efficiency, target detection dynamic stability, and intelligent classification and recognition accuracy. The classified performance parameters corresponding to each evaluation detection performance index comprise: The detection performance parameters are classified to obtain imaging clarity parameters, target detection efficiency parameters, target detection dynamic stability parameters, and intelligent classification and recognition accuracy parameters. 2.The side scan sonar detection method based on big data of claim 1, wherein, The target analysis model comprises an imaging clarity model. ； ； ； ； ； ； ； wherein, represents an imaging sharpness index, represents an imaging quality evaluation influence factor; represents an image pixel density, represents an image width pixel number, represents an image height pixel number, represents a scanning area width; represents an image signal-to-noise ratio gain; represents a processed signal-to-noise ratio, represents an original signal-to-noise ratio, represents an image signal power, represents an image noise power; represents an image edge sharpness degree; represents a gradient component of an image in direction, represents a gradient component of an image in direction; represents an image compression loss, represents an original image quality index, a compressed image quality index, represents an image peak signal-to-noise ratio, represents a structural similarity of an image. 3.The side scan sonar detection method based on big data of claim 1, wherein, The target analysis model comprises a target detection efficiency model. ； ； ； ； wherein, represents a target detection performance index; represents a target detection impact factor; represents a side scan sonar maximum detection depth; represents a theoretical detection depth; represents a side scan sonar signal penetration loss average proportion, represents a number of different target media types, represents a received signal strength of a represents a transmitted signal strength; represents a false positive rate, represents a number of false non-target identifications, represents an identification number; represents a detection time efficiency, represents a target detection area, represents a side scan sonar scanning time, represents a data processing time, represents a theoretical detection time efficiency.​ 4.The side scan sonar detection method based on big data of claim 1, wherein, The target analysis model comprises a target detection dynamic stability model. ； ； ； ； ； wherein, represents a target detection dynamic stability index, represents an impact factor of a dynamic environment; represents a pose correction offset degree, represents corrected ship pose data, represents reference ship pose data; represents a speed fluctuation suppression, represents a standard deviation of a scan result image quality under a speed fluctuation, represents a standard deviation of a scan result image quality under a stable speed; represents a dynamic environment noise suppression, represents a processed side scan sonar signal noise ratio, represents a side scan sonar original signal signal-to-noise ratio; represents an image continuity rate, represents an area of an image overlapping region, represents a total image area.

5. The side scan sonar detection method based on big data according to claim 1, characterized in that, The target analysis model comprises an intelligent classification and recognition accuracy model. ； ； ； ； wherein, represents an intelligent classification recognition accuracy index, represents an intelligent classification recognition influence factor; represents a basic recognition accuracy, represents a recognition number, represents a target number of correct recognition of target detection; represents an algorithm optimization gain, represents a target detection classification accuracy based on big data, represents an original target detection classification accuracy; represents a classification decision speed, represents a number of image classification processing, represents an image processing time, represents an original image classification decision speed.

6. The side scan sonar detection method based on big data according to claim 1, characterized in that, The performance qualification degree evaluation comprises: Processing each performance index by a performance qualification degree evaluation model to obtain a performance qualification degree corresponding to each evaluation detection performance index.

7. The side scan sonar detection method based on big data according to claim 6, characterized in that, The performance qualification degree evaluation model comprises: ； wherein, represents a performance index corresponding to a performance qualification degree, represents a set value corresponding to a performance index, represents a performance index. 8.The side scan sonar detection method based on big data of claim 1, wherein, The comprehensive detection performance index is obtained according to each performance qualification degree and the weight value corresponding thereto. ； wherein, represents a detection performance comprehensive index; represents a performance qualification degree of an imaging definition index; represents a performance qualification degree of a target detection efficiency index; represents a performance qualification degree of a target detection dynamic stability index; represents a performance qualification degree of an intelligent classification and recognition accuracy rate index; , , and represents a weight value corresponding to different performance qualification degrees. 9.A side scan sonar detection device based on big data, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, The processor executes the computer program to realize each step in the side scan sonar detection method based on big data according to any one of claims 1-8.

Images