A method and system for identifying black and odorous water bodies based on mobile phone photography

Abstract

The present invention relates to the technical field of image recognition, and specifically to a method and system for identifying black and odorous water bodies based on mobile phone photography, including the following steps: Based on the image information captured by the mobile phone, the position coordinates of the shooting location are recorded in real time, and the text information input by the user is analyzed to extract multiple keywords related to the water body state, generating a water body data set. In the present invention, by detecting and identifying the bottom of the water, the reflector, the light spot and the occlusion in the image, the image quality is evaluated in real time and the user is guided to reshoot, ensuring the quality standard of data input, improving the accuracy of data collection and the reliability of data analysis. By calculating the reflectivity difference between the water body and the reflector, combined with the geographical location information and the turbidity of the water body, a regional detection threshold for black and odorous water bodies is set, enabling the water body monitoring to reflect the actual situation of the water body, meeting the requirements of the geographical environment, providing higher accuracy and applicability for water body quality assessment, and helping to quickly identify water pollution problems.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and particularly to a method and system for identifying black and odorous water bodies based on mobile phone photography. Background Art

[0002] The technical field of image recognition involves using computer vision and machine learning methods to enable a computer to recognize and process the content in images or videos. By analyzing digital images or video frames, objects, scenes, and activities are recognized, including multiple processing steps such as image preprocessing, feature extraction, and classification. Combining convolutional neural networks and deep learning models can improve the accuracy and efficiency of recognition, and it is applied to multiple aspects such as security monitoring, medical image analysis, autonomous driving, interactive media, face recognition, industrial automation, and environmental monitoring.

[0003] Among them, the method for identifying black and odorous water bodies based on mobile phone photography uses the water body photos taken by the camera of a smart phone. Using image recognition technology, by recognizing the changes in water body color, the density of suspended particles, and various pollution indicators, it is determined whether it is a black and odorous water body, aiming to provide a convenient and economical way for water quality monitoring, providing a simple and economical water quality monitoring tool for environmental protection agencies and the public, and real-time monitoring of water quality conditions to quickly respond to and handle water pollution problems.

[0004] Traditional methods for identifying black and odorous water bodies rely on traditional water body monitoring technologies, which require complex equipment and professional personnel for operation. There are obvious deficiencies in real-time data processing and geographical environment adaptability, and it is impossible to provide real-time feedback on the quality of the collected images, resulting in subsequent analysis possibly being based on data with poor quality, affecting the accuracy of water quality judgment. When processing water body data in different geographical regions, a unified threshold standard is adopted, ignoring the important influence of geographical location and environmental factors on water quality assessment, making the monitoring results unable to accurately reflect the actual water quality conditions of local areas, reducing the scientific nature and applicability of monitoring, leading to incorrect water quality judgment, and bringing inappropriate environmental management and public health risks. Summary of the Invention

[0005] In order to solve the above technical problems existing in the prior art, an embodiment of the present invention provides a method and system for identifying black and odorous water bodies based on mobile phone photography. The technical solution is as follows:

[0006] On the one hand, a method for identifying black and odorous water bodies based on mobile phone photography is provided, and the method includes:

[0007] S1: Based on the image information taken by the mobile phone, the position coordinates of the shooting location are recorded in real time, and the text information input by the user is analyzed to extract multiple keywords related to the water body state, and a water body data set is generated;

[0008] S2: Based on the water body dataset, evaluate the image quality by identifying whether the image contains the water bottom, reflector, over-bright light spots, and occluding debris, mark the qualified status, and send a reshooting prompt message to the user to generate the image data review result;

[0009] S3: Based on the image data review result, analyze the qualified image data, extract the color data in the image, and identify the remote sensing reflectance of the water body by calculating the reflectance difference between the reflector and the water body to generate the water body reflectance calculation result;

[0010] S4: Utilize the water body reflectance calculation result to extract the spectral characteristics of the target water body, compare the spectral characteristics with the known characteristics of black and odorous water bodies, identify the key differences in the water body spectrum, calculate the black and odorous water body index, and generate the water body score calculation result;

[0011] S5: Based on the water body score calculation result, combine the geographical location information of the target water body, consider the turbidity of water bodies in multiple geographical locations, set the black and odorous water body detection threshold for multiple geographical regions, and judge the target water body according to the threshold to generate the black and odorous water body identification result.

[0012] Optionally, the water body dataset generation result includes the merged image file, geographical coordinate data, and keyword extraction record. The image data review result includes the image quality score, reshooting prompt information, and image status mark. The water body reflectance calculation result includes the color contrast analysis result between the water body and the reference board, the calculated reflectance difference value, and the water body reflectance data. The water body score calculation result includes the extracted spectral characteristic data, the known black and odorous water body characteristic information, and the black and odorous water body index. The black and odorous water body identification result includes the list of water body turbidity data in geographical regions, the set detection threshold, and the water body classification result.

[0013] Optionally, based on the mobile phone captured image information, the location coordinates of the shooting location are recorded in real time, and the text information input by the user is analyzed to extract multiple keywords related to the water body status. The steps for generating the water body dataset are specifically as follows:

[0014] S101: Based on the mobile phone captured image information, use the mobile phone to synchronously record the geographical coordinate data at the time of image capture to generate the geographical coordinate record;

[0015] S102: Based on the geographical coordinate record, analyze the descriptive text input by the user, extract various keywords in the description, including color, smell, and pollution signs, to generate the descriptive keyword set;

[0016] S103: Based on the descriptive keyword set, integrate the collected image data, location information, and text keywords to generate the water body dataset.

[0017] Optionally, based on the water body data set, the steps of evaluating the image quality, marking the qualified status, and sending a retake prompt message to the user to generate the image data review result by identifying whether the image contains the water bottom, the reflector, overbright light spots, and occluding debris are as follows:

[0018] S201: Analyze the captured image data based on the water body data set, detect the water bottom and the reflector in the image, identify the visibility and integrity of the target elements, and generate an element visibility detection result;

[0019] S202: Based on the element visibility detection result, detect and identify the visual obstacles in the image, including occluding objects, light spots, and debris, and generate an obstacle detection record;

[0020] S203: Based on the obstacle detection record, mark the qualified status of the image, match the retake prompt message according to the unqualified reasons, and send it to the user to generate the image data review result.

[0021] Optionally, based on the image data review result, the steps of analyzing the qualified image data, extracting the color data in the image, calculating the reflectance difference between the reflector and the water body, and identifying the remote sensing reflectance of the water body to generate the water body reflectance calculation result are as follows:

[0022] S301: Analyze the qualified image data based on the image data review result, perform color extraction on the picture, including measuring the colors of the water body and the reflector, and generate color extraction data;

[0023] S302: Based on the color extraction data, use the color information to calculate the reflectance difference between the water body and the reflector, and generate reflectance difference data;

[0024] S303: Based on the reflectance difference data, combine the actual color of the reflector and the light reflectance information to calculate the actual remote sensing reflectance of the water body and generate the water body reflectance calculation result.

[0025] Optionally, the specific formula for calculating the reflectance difference between the water body and the reflector is:

[0026]

[0027] Where represents the average pixel intensity of the water body in a specific spectral band, represents the average pixel intensity of the reflector in the same spectral band, represents the reflectance difference value, represents the adjustment coefficient for adapting to different ambient light conditions.

[0028] Optionally, using the calculation result of the water body reflectance, the spectral characteristics of the target water body are extracted, and the spectral characteristics are compared with the known characteristics of the black and odorous water body to identify the key differences in the water body spectrum. The steps of calculating the black and odorous water body index and generating the calculation result of the water body score are specifically as follows:

[0029] S401: Based on the calculation result of the water body reflectance, frequency analysis is performed on the water body spectral data to extract the key feature data of the water body in the spectrogram and generate spectral feature data;

[0030] S402: Based on the spectral feature data, the extracted spectral features are compared with the known spectrum of the black and odorous water body, the similarity is calculated, the spectral differences are identified, and a spectral difference analysis result is generated;

[0031] S403: Based on the spectral difference analysis result, the black and odorous water body index is calculated using the spectral differences to generate the calculation result of the water body score.

[0032] Optionally, the specific formula for calculating the similarity is:

[0033]

[0034] where, represents the reflection intensity of the target water body in the th spectral band, represents the reflection intensity of the corresponding spectral band in the black and odorous water body spectrum library, represents the similarity between the two, represents the total number of spectral bands, is the index of the spectral band.

[0035] Optionally, based on the calculation result of the water body score, combined with the geographical location information of the target water body, considering the water turbidity of multiple geographical locations, setting the black and odorous water body detection threshold for multiple geographical regions, and judging the target water body according to the threshold to generate the black and odorous water body identification result. The steps are specifically as follows:

[0036] S501: Based on the calculation result of the water body score, collect the water turbidity data of multiple geographical regions to generate water turbidity data;

[0037] S502: Based on the water turbidity data, adjust the black and odorous water body detection thresholds of multiple geographical regions to generate regional threshold settings;

[0038] S503: Based on the regional threshold settings, by comparing the black and odorous water body indices of multiple sampling points with the detection threshold of the region, mark the black and odorous water body status for the target location to generate the black and odorous water body identification result.

[0039] On the other hand, a black and odorous water body identification system based on mobile phone photography is provided. This system is applied to the method for identifying black and odorous water bodies based on mobile phone photography. The system includes:

[0040] A data collection and integration module, based on the mobile phone captured image information, records the geographical location where the image is taken, extracts keywords related to the water body state from the user input text, and generates a water body data set;

[0041] An image quality detection module, based on the water body data set, identifies whether the image contains the water bottom and the reflector, detects over-bright light spots and occluding debris in the image, evaluates the quality of the image and marks the status, and sends a prompt message for reshooting to the user according to the unqualified reason, generating an image data review result;

[0042] An image data analysis module, based on the image data review result, analyzes the color data in the image, calculates the reflectivity difference between the reflector and the water body, identifies the remote sensing reflectivity of the water body, and generates a water body reflectivity calculation result;

[0043] A spectral feature analysis module, using the water body reflectivity calculation result, extracts the spectral features of the water body in the image, compares the target features with the feature database of known black and odorous water bodies, identifies the key spectral differences, calculates the black and odorous water body index, and generates a water body score calculation result;

[0044] A threshold setting module, in combination with the water body score calculation result, considering the turbidity of the water body in the target area, sets black and odorous water body detection thresholds for multiple geographical regions, generating a threshold setting result;

[0045] A water body state identification module, using the threshold setting result, by comparing the actually measured water body index with the set threshold, judges the black and odorous water body state of each target water body, generating a black and odorous water body identification result.

[0046] The beneficial effects brought by the technical solution provided by the embodiments of the present invention at least include:

[0047] By detecting and identifying the water bottom, reflector, light spots and occlusions in the image, evaluating the image quality in real time and guiding the user to reshoot, the quality standard of data input is ensured, the accuracy of data collection and the reliability of data analysis are improved. By calculating the reflectivity difference between the water body and the reflector, combining geographical location information and water body turbidity to set regional black and odorous water body detection thresholds, the water body monitoring reflects the actual situation of the water body, adapts to the needs of the geographical environment, provides higher accuracy and applicability for water body quality assessment, and helps to quickly identify water pollution problems. Description of the Drawings

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0049] Figure 1 It is a schematic diagram of the working process of the present invention;

[0050] Figure 2 It is a detailed flowchart of S1 of the present invention;

[0051] Figure 3 It is a detailed flowchart of S2 of the present invention;

[0052] Figure 4 It is a detailed flowchart of S3 of the present invention;

[0053] Figure 5 It is a detailed flowchart of S4 of the present invention;

[0054] Figure 6 It is a detailed flowchart of S5 of the present invention;

[0055] Figure 7 It is a system flowchart of the present invention. Specific embodiments

[0056] The following will describe the technical solutions in the present invention with reference to the drawings.

[0057] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "example" in the present invention should not be interpreted as more preferred or more advantageous than other embodiments or design solutions. Exactly, the use of the word "example" is intended to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0058] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meaning they express is the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meaning they express is the same.

[0059] In the embodiments of the present invention, sometimes subscripts such as W 1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0060] To make the technical problems, technical solutions, and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0061] The embodiment of the present invention provides a method for identifying black and odorous water bodies based on mobile phone photography. As Figure 1 shown in the flowchart of the method for identifying black and odorous water bodies based on mobile phone photography, the processing flow of the method may include the following steps:

[0062] S1: Based on the image information captured by the mobile phone, record the position coordinates of the shooting location in real time, analyze the text information input by the user, extract multiple keywords related to the water body state, and generate a water body data set;

[0063] S2: Based on the water body data set, evaluate the image quality by identifying whether the image contains the bottom and the reflector, overbright light spots, and occluding debris, mark the qualified status, and send a re-shooting prompt message to the user to generate an image data review result;

[0064] S3: Based on the image data review result, analyze the qualified image data, extract the color data in the image, and identify the remote sensing reflectance of the water body by calculating the reflectance difference between the reflector and the water body to generate a water body reflectance calculation result;

[0065] S4: Utilize the water body reflectance calculation result, extract the spectral characteristics of the target water body, compare the spectral characteristics with the known characteristics of black and odorous water bodies, identify the key differences in the water body spectrum, calculate the black and odorous water body index, and generate a water body score calculation result;

[0066] S5: Based on the water body score calculation result, combine the geographical location information of the target water body, consider the turbidity of water bodies in multiple geographical locations, set a black and odorous water body detection threshold for multiple geographical regions, and judge the target water body according to the threshold to generate a black and odorous water body identification result.

[0067] The generation result of the water body data set includes the merged image file, geographical coordinate data, and keyword extraction record. The image data review result includes the image quality score, re-shooting prompt information, and image status mark. The water body reflectance calculation result includes the color contrast analysis result between the water body and the reference board, the calculated reflectance difference value, and the water body reflectance data. The water body score calculation result includes the extracted spectral characteristic data, the known black and odorous water body characteristic information, and the black and odorous water body index. The black and odorous water body identification result includes the water body turbidity data list of the geographical region, the set detection threshold, and the water body classification result.

[0068] Please refer to Figure 2, based on the information of the images captured by the mobile phone, the location coordinates of the shooting location are recorded in real time, and the text information input by the user is analyzed to extract multiple keywords related to the water body status. The specific steps for generating the water body dataset are as follows:

[0069] S101: Based on the information of the images captured by the mobile phone, use the mobile phone to synchronously record the geographical coordinate data at the time of image shooting to generate a geographical coordinate record;

[0070] In sub-step S101, based on the information of the images captured by the mobile phone, activate the GPS function of the mobile phone to capture and record the accurate geographical location coordinates at the time of image shooting. The process includes initializing the positioning service of the mobile phone to ensure sufficient GPS signal strength to provide stable positioning data. While the mobile phone camera captures an image, the GPS module captures the current longitude and latitude coordinates, timestamp, and altitude information. The target data is encoded and saved as a geographical location record file together to ensure that each image has a corresponding geographical coordinate, which is convenient to use the location data to associate environmental features with the water body status in subsequent analysis, provide data support for environmental protection agencies, help understand the environmental background of the image capture area and the existing water body pollution problems, and generate a geographical coordinate record.

[0071] S102: Based on the geographical coordinate record, analyze the descriptive text input by the user, and extract various keywords in the description, including color, smell, and pollution signs, to generate a set of descriptive keywords;

[0072] In sub-step S102, based on the geographical coordinate record, apply natural language processing technology to analyze the descriptive text input by the user through the mobile phone application, including starting the text analysis engine and loading advanced text processing models such as BERT or LSTM. The target model has been trained on a large amount of text data to understand and extract keywords. After the text is input into the model, the model parses the text content and identifies keywords related to the water body status, such as "color", "smell", and "pollution signs". The target keywords are determined by the model analyzing the semantic context and the co-occurrence frequency of words. After each keyword extraction is completed, the system integrates the target keywords into a set of descriptive keywords, and the set will be used as an important input parameter for water body status analysis to refine the content of the water body dataset and generate a set of descriptive keywords.

[0073] S103: Based on the set of descriptive keywords, integrate the collected image data, location information, and text keywords to generate a water body dataset;

[0074] In sub-step S103, based on the descriptive keyword set, integrate the collected image data with the previously generated geographical coordinate records, and adopt data fusion technologies such as data lake or data warehouse technology to achieve the storage and query of large-scale data. Align the image data and geographical coordinates according to the timestamp to ensure the consistency of each record. Associate the descriptive text keywords with the corresponding images and geographical coordinates, use relational database technology to build a multi-dimensional data model, conduct data retrieval and analysis, perform quality inspection and cleaning on the target comprehensive data to ensure the accuracy and integrity of the data set, generate a water body data set, and the data set will be directly applied to the subsequent water quality analysis and evaluation processes to provide a comprehensive perspective for monitoring and evaluating the water body health status.

[0075] Please refer to Figure 3 , based on the water body data set, the steps for evaluating the image quality, marking the qualified status, and sending a retake prompt message to the user to generate the image data review result by identifying whether the image contains the water bottom, reflector, over-bright light spots, and occluding debris are as follows:

[0076] S201: Based on the water body data set, analyze the captured image data, detect the water bottom and reflector in the image, identify the visibility and integrity of the target elements, and generate the element visibility detection result;

[0077] In sub-step S201, based on the water body data set, start the image processing software, adopt image segmentation technologies such as threshold segmentation method and edge detection algorithm, apply color analysis method to determine the boundary between the water body and non-water body areas, and identify the contours of the water bottom and reflector in the image through edge detection algorithms such as Canny edge detector. The system automatically evaluates the clarity and integrity of the target elements, such as the water bottom and reflector, to ensure that the target elements are not partially cropped or occluded in the image to guarantee the accuracy of water quality analysis. By comparing the proportion and position of the target elements in the image, the system evaluates the visibility of each element and generates the element visibility detection result, which is used in the subsequent quality assessment process to ensure the reliability and effectiveness of the analysis data.

[0078] S202: Based on the element visibility detection result, detect and identify the visual obstacles in the image, including occlusions, light spots, and debris, and generate the obstacle detection record;

[0079] In sub-step S202, based on the element visibility detection results, image processing techniques such as region growing method and template matching technique are used to analyze the image, identify visual obstacles affecting the image quality in the image, including occluders, light spots and debris. The region growing method is used to identify light spots or shadows in continuous regions by setting thresholds to grow regions that meet specific color ranges. The template matching technique detects debris similar to predefined shapes, such as fallen leaves or garbage. Each obstacle is marked and recorded in the system, and an obstacle detection record is generated according to the type and location information. The target record provides key data for image quality control to ensure that only undisturbed images are used for analysis.

[0080] S203: Based on the obstacle detection record, mark the qualified status of the image, match the reshooting prompt message according to the unqualified reason, and send it to the user to generate the image data review result;

[0081] In sub-step S203, based on the obstacle detection record, the system evaluates whether each image meets the quality standard, marks the qualified status of the image, and uses an image quality assessment algorithm, such as a machine learning-based image classification model, to automatically distinguish qualified and unqualified images. For each unqualified reason, the system matches an appropriate reshooting prompt message. The target message is customized based on the specific problems of the image, such as "Adjust the shooting angle to avoid light spots" or "Remove the debris in the picture". The target prompt is directly sent to the user through the user interface to guide the improvement of shooting and generate the image data review result. The result improves the efficiency of data collection, optimizes the quality of data, and ensures the accuracy of subsequent water body analysis.

[0082] Please refer to Figure 4 , based on the image data review result, analyze the qualified image data, extract the color data in the image, and identify the remote sensing reflectance of the water body by calculating the reflectance difference between the reflector and the water body. The specific steps for generating the water body reflectance calculation result are as follows:

[0083] S301: Based on the image data review result, analyze the qualified image data, extract the color of the picture, including measuring the colors of the water body and the reflector, to generate color extraction data;

[0084] In sub-step S301, based on the review results of the image data, qualified images are selected for analysis. Using the color space conversion method in digital image processing technology, the images are converted from the RGB color space to the LAB color space to accurately measure the color differences. During the process, the water body area and the reflector area of each image are located and color data is extracted. The color characteristics of each area are described using the data of three channels in the LAB color space: brightness, color contrast from green to red, and color contrast from blue to yellow. The color data of the water body and the reflector are extracted, and the target data is recorded and processed to generate color extraction data, providing the basic color information for reflectance calculation and ensuring the accuracy of reflectance analysis.

[0085] S302: Based on the color extraction data, using the color information, calculate the reflectance difference between the water body and the reflector to generate reflectance difference data;

[0086] The specific formula for calculating the reflectance difference between the water body and the reflector is:

[0087]

[0088] Where, represents the average pixel intensity of the water body in a specific spectral band, represents the average pixel intensity of the reflector in the same spectral band, represents the reflectance difference value, represents the adjustment coefficient used to adapt to different ambient light conditions.

[0089] Formula:

[0090] ;

[0091] Detailed explanation of the formula and the derivation process of formula calculation:

[0092] The formula is used to calculate the reflectance difference between the water body and the reflector, which is used to evaluate the degree of water body pollution and determine whether the water body belongs to a black and odorous water body;

[0093] Meaning and setting values of parameters:

[0094] is the average pixel intensity of the water body in a specific spectral band. Assume the average pixel intensity in the red light band is 180;

[0095] is the average pixel intensity of the reflector in the same spectral band. Assume it is 220;

[0096] is the reflectance difference value, which is a numerical value directly measuring the reflection characteristics of the water body;

[0097] is an adjustment coefficient used to adapt to the influence of different environmental lighting conditions, assumed to be 0.8.

[0098] Substitute the parameters into the formula for calculation:

[0099] ;

[0100] The result indicates that the difference in reflectance between the water body and the reflector is 11.6%, reflecting the relatively low difference in the spectral reflectance characteristics of the water body compared to the standard reflector. The result is used to help calculate the actual remote sensing reflectance of the water body, providing a data basis for water quality management and treatment measures.

[0101] S303: Based on the reflectance difference data, combined with the actual color and light reflectance information of the reflector, calculate the actual remote sensing reflectance of the water body to generate the calculation result of the water body reflectance;

[0102] In sub-step S303, based on the reflectance difference data, calculate the actual remote sensing reflectance. During the process, combined with the color data of the reflector obtained from actual measurement and the reflectance standard information under the on-site lighting conditions, apply a correction algorithm to adjust the preliminarily calculated remote sensing reflectance. The process includes considering the influence of changes in light intensity on the color data and the influence of the reflector material on the light reflection characteristics. Through this composite correction method, ensure that the measurement result of the water body reflectance is closer to the optical characteristics of the water body under real conditions, and generate the calculation result of the water body reflectance. The result will be used for subsequent water quality analysis and evaluation work.

[0103] Please refer to Figure 5 , using the calculation result of the water body reflectance, extract the spectral characteristics of the target water body, and compare the spectral characteristics with the known characteristics of black and odorous water bodies to identify the key differences in the water body spectrum, calculate the black and odorous water body index, and generate the steps of the calculation result of the water body score specifically as follows:

[0104] S401: Based on the calculation result of the water body reflectance, perform frequency analysis on the water body spectral data, extract the key characteristic data of the water body in the spectrogram to generate spectral characteristic data;

[0105] In sub-step S401, based on the calculation result of the water body reflectance, perform frequency analysis on the water body spectral data. Adopt Fourier transform technology to convert time or space to the frequency domain, including obtaining time series data from the water body reflectance data, applying Fourier transform, converting the target time series data into spectral data in the frequency domain, and by analyzing the converted frequency distribution, extract the main frequency components in the water body spectrum, such as peaks and valleys at specific wavelengths. The target components characterize the spectral behavior and chemical composition of the water body. Each extracted feature is recorded and encoded to generate spectral characteristic data, providing an accurate scientific basis for water quality analysis.

[0106] S402: Based on the spectral feature data, compare the extracted spectral features with the known spectra of black and odorous water bodies, calculate the similarity, identify the spectral differences, and generate the spectral difference analysis results;

[0107] The specific formula for calculating the similarity is:

[0108]

[0109] where, represents the reflection intensity of the target water body in the th spectral band, represents the reflection intensity of the corresponding spectral band in the black and odorous water body spectrum library, represents the similarity between the two, represents the total number of spectral bands, is the index of the spectral band.

[0110] Formula:

[0111] ;

[0112] Detailed explanation of the formula and the derivation process of the formula calculation:

[0113] The formula is used to calculate the similarity between the water body and the black and odorous water body spectrum library, and the obtained result is used to evaluate whether the water body belongs to the black and odorous water body;

[0114] Parameter meanings and setting values:

[0115] is the reflection intensity of the target water body in the th spectral band. Assume that the reflection intensities of the target water body in the three spectral bands are 0.5, 0.6, and 0.55 respectively, which reflects the spectral response state of the target water body in the spectral band;

[0116] is the average reflection intensity of the black and odorous water body spectrum library in the th spectral band. Assume that the reflection intensities of the black and odorous water body in the three spectral bands are 0.8, 0.75, and 0.78 respectively, which reflects the spectral response state of the black and odorous water body in this spectral band;

[0117] is the total number of spectral bands;

[0118] Substitute the parameters into the formula for calculation:

[0119] ;

[0120] ;

[0121] ;

[0122] ;

[0123] ;

[0124] The result of 0.995 indicates that the spectral characteristics of the target water body and the black and odorous water body are extremely similar. The data is used to calculate the black and odorous water body index to determine whether the target water body belongs to the black and odorous water body.

[0125] S403: Based on the results of spectral difference analysis, using the spectral difference, calculate the black and odorous water body index to generate the water body score calculation result;

[0126] In sub-step S403, based on the results of spectral difference analysis, use the target spectral difference data to calculate the black and odorous water body index. Adopt a comprehensive scoring method to conduct a comprehensive evaluation according to the influence degree of different spectral characteristics and the corresponding difference size. Assign an influence weight to each spectral characteristic, and combine the corresponding difference degree to calculate the overall pollution level of the water body, evaluate the black and odorous water body index of each water body sample, generate the water body score calculation result, provide accurate data support for environmental protection supervision, and accelerate the response and handling of water pollution problems.

[0127] Please refer to Figure 6 , based on the water body score calculation result, combined with the geographical location information of the target water body, considering the turbidity of water bodies in multiple geographical locations, setting the black and odorous water body detection threshold for multiple geographical regions, and judging the target water body according to the threshold to generate the black and odorous water body identification result. The specific steps are as follows:

[0128] S501: Based on the water body score calculation result, collect the turbidity data of water bodies in multiple geographical regions to generate the water body turbidity data;

[0129] In sub-step S501, based on the water body score calculation result, collect the water body turbidity data. Define multiple geographical regions, and for each region, deploy water quality monitoring equipment to measure the turbidity of the water body. The target equipment regularly records the turbidity of the water body and automatically uploads the data to the central monitoring system. The system collects the water body turbidity data from different regions and organizes it into a detailed database. The target turbidity data provides a direct insight into the water quality status of each region and provides basic data for analysis and decision-making to generate the water body turbidity data.

[0130] S502: Based on the water body turbidity data, adjust the black and odorous water body detection thresholds for multiple geographical regions to generate the regional threshold setting;

[0131] In sub-step S502, based on the water turbidity data, the detection thresholds for black and odorous waters in multiple geographical regions are adjusted. A linear adjustment formula is used, taking into account the correlation between water turbidity and historical black and odorous events for threshold adjustment. According to the formula , calculate the regional detection threshold and generate the regional threshold setting;

[0132] In the formula, represents the new detection threshold for the th region, is the basic threshold, reflecting the detection baseline of black and odorous waters in the general environment, is the adjustment coefficient, indicating the sensitivity of threshold adjustment for each unit change in turbidity data, is the th region's currently measured water turbidity, is the average turbidity of all regions;

[0133] Detailed explanation of the formula and the derivation process of formula calculation:

[0134] Assume that the current water turbidity of the target region is 0.5 and the average turbidity is 0.4. Substitute the parameters for calculation:

[0135] ;

[0136] The result 0.305 indicates that the new detection threshold for black and odorous waters in the region is 0.305. The value is used to adjust the detection threshold for black and odorous waters, adapt to water quality changes in different regions, and improve the accuracy and adaptability of black and odorous water identification.

[0137] S503: Based on the regional threshold setting, by comparing the black and odorous water indices of multiple sampling points with the detection threshold of the region, mark the black and odorous water status for the target location and generate the black and odorous water identification result;

[0138] In sub-step S503, based on the regional threshold setting, determine the black and odorous water status. By comparing the black and odorous water indices of each sampling point with the detection threshold of the corresponding region, determine which locations have waters in the black and odorous state. The comparison process is automatically executed. The system evaluates the water indices of each sampling point according to the set threshold, marks the locations exceeding the threshold as potential polluted areas, quickly identifies the problem waters, provides a clear direction for local environmental protection actions, guides resources and attention to the areas that need intervention, and generates the black and odorous water identification result.

[0139] Please refer to Figure 7, a black and odorous water body recognition system based on mobile phone photography, a black and odorous water body recognition system based on mobile phone photography is used to execute the above-mentioned black and odorous water body recognition method based on mobile phone photography, and the system includes:

[0140] The data collection and integration module records the geographical location of the image based on the image information captured by the mobile phone, and extracts keywords related to the water body status from the user input text to generate a water body data set;

[0141] Image quality detection module, based on water body data set, identifies whether the image contains the bottom and reflector, detects over-bright spots and obstructions in the image, evaluates the image quality and marks the status, and sends a prompt message to the user to reshoot according to the reason for failure, generating image data review results;

[0142] The image data analysis module analyzes the color data in the image based on the image data review results, calculates the reflectivity difference between the reflector and the water body, identifies the remote sensing reflectivity of the water body, and generates the water body reflectivity calculation results;

[0143] The spectral feature analysis module uses the water body reflectance calculation results to extract the spectral features of the water body in the image, compares the target features with the feature database of known black and odorous water bodies, identifies key spectral differences, calculates the black and odorous water body index, and generates the water body score calculation results;

[0144] The threshold setting module combines the water body score calculation results, considers the turbidity of the water body in the target area, sets the black and odorous water body detection threshold for multiple geographical areas, and generates the threshold setting results;

[0145] The water body status recognition module uses the threshold setting results to compare the actually measured water body index with the set threshold, judges the black and odorous water state of each target water body, and generates a black and odorous water body recognition result.

[0146] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0147] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0148] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0149] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0150] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0151] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices, apparatuses, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0152] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0153] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0154] In addition, the functional units in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0155] When the above-mentioned function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0156] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for identifying black and smelly water bodies based on mobile phone photography, characterized in that: The method comprises: Based on the image information captured by the mobile phone, the location coordinates of the shooting location are recorded in real time, and the text information entered by the user is analyzed to extract multiple keywords related to the water body status and generate a water body data set; Based on the water body dataset, by identifying whether the image contains the bottom of the water and a reflector, overly bright spots, and obstructing debris, the image quality is evaluated, a qualified state is marked, and a reshoot prompt message is sent to the user to generate an image data review result; Based on the image data review results, the qualified image data is analyzed, the color data in the image is extracted, the remote sensing reflectivity of the water body is identified by calculating the reflectivity difference between the reflector and the water body, and the water body reflectivity calculation result is generated; Utilizing the water body reflectance calculation result, extracting the spectral characteristics of the target water body, and comparing the spectral characteristics with known black and odorous water body characteristics, identifying key differences in the water body spectrum, calculating the black and odorous water body index, and generating a water body score calculation result; Based on the water body score calculation result, combined with the geographical location information of the target water body, considering the water turbidity in multiple geographical locations, setting black and odorous water body detection thresholds for multiple geographical areas, and judging the target water body according to the thresholds to generate black and odorous water body identification results; The steps of analyzing qualified image data based on the image data review result, extracting color data in the image, identifying the remote sensing reflectivity of the water body by calculating the reflectivity difference between the reflector and the water body, and generating the water body reflectivity calculation result are as follows: Based on the image data review results, analyzing qualified image data, performing color extraction on the image, including measuring the color of the water body and the reflector, and generating color extraction data; Based on the color extraction data, using color information, calculating the reflectivity difference between the water body and the reflector to generate reflectivity difference data; Based on the reflectivity difference data, combined with the actual color and light reflectivity information of the reflector, the actual remote sensing reflectivity of the water body is calculated to generate a water body reflectivity calculation result; The specific formula for calculating the reflectivity difference between the water body and the reflector is: ； in, represents the average pixel intensity of water in a specific spectral band, represents the average pixel intensity of the reflector in the same spectral band, represents the reflectivity difference value, Represents the adjustment factor, which is used to adapt to different ambient lighting conditions.

2. The method for identifying black and odorous water bodies based on mobile phone photography according to claim 1 is characterized in that: The water body data set generation result includes merged image files, geographic coordinate data, and keyword extraction records; the image data review result includes image quality score, re-shooting prompt information, and image status mark; the water body reflectivity calculation result includes color comparison analysis results between the water body and the reference plate, calculated reflectivity difference value, and water body reflectivity data; the water body score calculation result includes extracted spectral feature data, known black and odorous water body feature information, and a black and odorous water body index; the black and odorous water body identification result includes a list of water body turbidity data in a geographical area, a set detection threshold, and a water body classification result.

3. The black and odorous water body identification method based on mobile phone photography according to claim 1 is characterized in that: Based on the image information captured by the mobile phone, the location coordinates of the shooting location are recorded in real time, and the text information entered by the user is analyzed to extract multiple keywords related to the water body status. The specific steps for generating the water body data set are as follows: Based on the image information captured by the mobile phone, the geographical coordinate data when the image is captured is synchronously recorded by the mobile phone to generate a geographical coordinate record; Based on the geographic coordinate record, analyzing the descriptive text input by the user, extracting multiple keywords in the description, including color, smell, and pollution signs, and generating a descriptive keyword set; Based on the descriptive keyword set, the collected image data, location information and text keywords are integrated to generate a water body dataset.

4. The method for identifying black and odorous water bodies based on mobile phone photography according to claim 1 is characterized in that: Based on the water body dataset, the steps of generating the image data review result are as follows: Based on the water body data set, the captured image data is analyzed, the bottom of the water and the reflector in the image are detected, the visibility and integrity of the target element are identified, and the element visibility detection result is generated; Based on the element visibility detection result, detect and identify visual obstacles in the image, including occlusions, light spots, and debris, and generate obstacle detection records; Based on the obstacle detection record, the qualified status of the image is marked, and a re-shooting prompt message is matched according to the unqualified reason and sent to the user to generate an image data review result.

5. The method for identifying black and odorous water bodies based on mobile phone photography according to claim 1 is characterized in that: The steps of extracting the spectral features of the target water body by using the water body reflectance calculation result, comparing the spectral features with the known black and odorous water body features, identifying the key differences in the water body spectrum, calculating the black and odorous water body index, and generating the water body score calculation result are as follows: Based on the water body reflectance calculation result, frequency analysis is performed on the water body spectral data, key feature data of the water body in the spectrum is extracted, and spectral feature data is generated; Based on the spectral feature data, the extracted spectral features are compared with the known black and odorous water spectra, similarities are calculated, spectral differences are identified, and spectral difference analysis results are generated; Based on the spectral difference analysis results, the black and odorous water index is calculated using the spectral difference to generate a water body score calculation result.

6. The method for identifying black and odorous water bodies based on mobile phone photography according to claim 5 is characterized in that: The specific formula for calculating the similarity is: ； in, Represents the target water body in The reflection intensity of each spectral band, Represents the reflection intensity of the corresponding spectral band in the black and odorous water spectral library, Represents the similarity between the two. represents the total number of spectral bands, is the index of the spectral band.

7. The method for identifying black and odorous water bodies based on mobile phone photography according to claim 1 is characterized in that: Based on the water body score calculation result, combined with the geographical location information of the target water body, considering the water turbidity of multiple geographical locations, setting black and odorous water body detection thresholds for multiple geographical areas, and judging the target water body according to the threshold, the steps of generating black and odorous water body identification results are specifically as follows: Based on the water body score calculation result, collecting water body turbidity data of multiple geographical areas to generate water body turbidity data; Based on the water turbidity data, adjusting the black and odorous water detection thresholds for multiple geographical regions to generate regional threshold settings; Based on the regional threshold setting, the black and odorous water body indices of multiple sampling points are compared with the detection threshold of the region, the black and odorous water body status is marked for the target location, and a black and odorous water body identification result is generated.

8. A black and odorous water body identification system based on mobile phone photography, characterized in that: According to any one of claims 1 to 7, the method for identifying black and odorous water bodies based on mobile phone photography comprises: The data collection and integration module records the geographical location of the image based on the image information captured by the mobile phone, and extracts keywords related to the water body status from the user input text to generate a water body data set; An image quality detection module, based on the water body data set, identifies whether the image contains the bottom of the water and the reflector, detects overly bright spots and obstructions in the image, evaluates the quality of the image and marks the status, and sends a prompt message to the user to reshoot according to the reason for failure, and generates an image data review result; An image data analysis module, based on the image data review result, analyzes the color data in the image, calculates the reflectivity difference between the reflector and the water body, identifies the remote sensing reflectivity of the water body, and generates a water body reflectivity calculation result; A spectral feature analysis module, using the water body reflectance calculation result, extracts the spectral features of the water body in the image, compares the target features with the feature database of known black and odorous water bodies, identifies key spectral differences, calculates the black and odorous water body index, and generates a water body score calculation result; A threshold setting module, combining the water body score calculation result, taking into account the turbidity of the water body in the target area, setting black and odorous water body detection thresholds for multiple geographical areas, and generating threshold setting results; The water body state identification module uses the threshold setting result to compare the actually measured water body index with the set threshold value to determine the black and odorous water body state of each target water body and generate a black and odorous water body identification result; The image data analysis module is specifically used to analyze qualified image data based on the image data review results, and perform color extraction on the image, including measuring the color of the water body and the reflector to generate color extraction data; based on the color extraction data, using color information, calculating the reflectivity difference between the water body and the reflector to generate reflectivity difference data; based on the reflectivity difference data, combined with the actual color of the reflector and the light reflectivity information, calculating the actual remote sensing reflectivity of the water body to generate a water body reflectivity calculation result; The specific formula for calculating the reflectivity difference between the water body and the reflector is: ； in, represents the average pixel intensity of water in a specific spectral band, represents the average pixel intensity of the reflector in the same spectral band, represents the reflectivity difference value, Represents the adjustment factor, which is used to adapt to different ambient lighting conditions.

Images