River regulation method and system based on image processing technology

Abstract

The invention discloses a riverway treatment method and system based on an image processing technology, and relates to the technical field of urban riverway treatment, the system divides a treatment area into a plurality of sub-river reaches by using a GIS, river network distribution and a DEM model, and collects video frames, water quality images and pollution feature images; through image processing, extracting a motion track, a distribution characteristic, water body color information and an abnormal color development area of the floating object, and analyzing a pollution change trend and a mutation characteristic; the water surface garbage diffusion disturbance coefficient is monitored, the water surface garbage state is judged in combination with a threshold value, and strategy response is triggered; when the water quality is abnormal, judging whether the color of the water body is normal or not through water body color difference abnormal coefficient analysis; if pollution exists, the pollution gradient change is analyzed section by section in the countercurrent direction of the river channel, a pollution source is locked, and a pollution discharge upstream inference report is generated; according to the invention, the river pollution monitoring precision and response efficiency are effectively improved, and ecological management and environmental protection are assisted.

Description

Technical Field

[0001] The present invention belongs to the technical field of urban river management, and specifically relates to a method and system for river management based on image processing technology. Background Art

[0002] In urban river management, the rapid identification and source tracing of water pollutants have always been a key technical challenge in water environment management. Currently, common water quality monitoring methods rely on traditional manual sampling, physical and chemical analysis, or online sensor testing. While these methods offer some accuracy, they suffer from long response delays, limited spatial coverage, and difficulty tracking pollution paths in real time. These methods struggle to meet the demands for rapid early warning and dynamic management of complex urban water pollution incidents.

[0003] Especially in urban tributaries or areas with dense outfalls where the sources of pollutants are complex and changing rapidly, relying solely on point-based water quality data cannot fully restore the spatial distribution and evolution of pollution, which can easily lead to missed judgments and misjudgments, affecting the efficiency of governance. In addition, water pollution is often accompanied by visual characteristics such as increased surface floating objects, abnormal water color differences, and flow disturbances. These pollution manifestations have obvious image identifiability. Therefore, river management methods based on image processing technology can achieve non-contact monitoring and intelligent early warning of pollution events from dimensions such as video images, water surface color, and pollution dynamics, which has significant advantages. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention provides a method and system for river management based on image processing technology to solve the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a river management system based on image processing technology, including a data acquisition module, an image processing module, a floating object monitoring and tracking module, a water body monitoring module and a pollution source investigation module;

[0006] The data acquisition module divides the treatment area into several sub-river sections based on GIS, river network distribution and DEM model, and collects video frames, water quality images and pollution feature images through fixed high-definition cameras, bank image sampling equipment and drone multispectral cameras;

[0007] The image processing module is used to extract the movement trajectory and distribution characteristics of floating objects, water color information and abnormal color areas, and pollution change trends and mutation characteristics in multi-time images;

[0008] The floating object monitoring and tracking module is used to monitor the density changes and flow gradient changes of floating object target boundaries in the fused image of the sub-river section in real time, calculate the surface garbage diffusion disturbance coefficient FDI, and compare and analyze it with the first threshold Q1 to determine whether the overall state of the surface garbage in the sub-river section is stable. If it is unstable, a strategy is given;

[0009] The water monitoring module is used to monitor the water quality of the current sub-river section in real time upon receiving the first warning instruction, calculate the water color difference abnormality coefficient SCP based on historical water color standard data, and compare and analyze it with the second threshold value Q2 to determine whether the water color of the current sub-river section is normal. If it is abnormal, a strategy is given;

[0010] The pollution source investigation module is used to analyze the water quality of the river section by section along the upstream direction of the river when receiving the second warning instruction, and calculate the pollution gradient change rate ΔSCP j , and find and calculate the pollution gradient change rate ΔSCP j Maximum sub-channel area Jcq j , lock in the source of pollution and provide strategies.

[0011] Preferably, the data acquisition module includes a region division unit and an acquisition unit;

[0012] The regional division unit is used to establish a two-dimensional hydrological spatial coupling model of the river channel based on remote sensing geographic information GIS and urban river network distribution data, combined with a digital elevation model DEM, and divide the management area into several sub-river sections and mark them as: Jcq1, Jcq2, ..., JcqM; M represents the number of sub-river sections;

[0013] The acquisition unit is used to monitor the sub-river section area by deploying fixed high-definition water surface monitoring cameras along the river to collect continuous video frame sequences of the river; using static image sampling equipment deployed on the shore to collect high-definition water quality image samples; and using a multi-spectral camera equipped on an unmanned aerial vehicle to collect water surface pollution feature images and color feature images.

[0014] Preferably, the image processing module includes an optical flow field processing unit, a water chromatography processing unit and a pollution time series processing unit;

[0015] The optical flow processing unit is used to extract motion information from a continuous video image sequence of the river channel, using the optical flow estimation algorithm PWCNet to obtain the motion trajectory information of floating objects between images; extract the velocity vector characteristics and the aggregation area boundaries of the floating objects, and obtain the distribution status and movement trend diagram of the floating objects in the river channel; extract the image characteristics of the change in the density of floating objects in the area, and obtain the aggregation area of the floating objects in the current frame;

[0016] The water body chromatogram processing unit is used to extract color information from static water surface images, using the HSI color gamut conversion method to obtain hue, saturation and brightness characteristics in the image; compare the color difference maps of water bodies in different areas, extract abnormal color development areas, and generate water surface color feature layer data;

[0017] The pollution time series processing unit is used to dynamically extract pollution visual features from image sequences collected at different time points; analyze the changing trend images of floating object distribution maps, water body color maps and disturbance feature maps in the time dimension; identify sudden change areas during the pollution change process, and extract key image parameters before and after the change.

[0018] Preferably, the floating object monitoring and tracking module includes a first calculation unit and a first analysis unit;

[0019] The first calculation unit is used to monitor the density change of the floating object target boundary and the flow velocity gradient change in the fused image of the sub-river section in real time. After dimensionless processing, the water surface garbage diffusion disturbance coefficient FDI is calculated and obtained. The formula is as follows:

[0020]

[0021] Where, Represents the velocity vector set of floating objects in the optical flow field, represents the variance of the local velocity vector, A represents the density gradient change of floating objects boundary per unit time, c Indicates the real-time floating object concentration area, A t represents the mean total area of floating objects at time t in the past, w1, w2 and w3 represent weight coefficients;

[0022]

[0023] Where N represents the number of pixels in the image, represents the velocity vector modulus of the floating object on the i-th pixel, represents the average modulus of the velocity vector of the floating object;

[0024]

[0025] Where D t Denotes the pollution attribute parameter value in the image at time t, D t-1 It represents the pollution attribute parameter value in the image at the previous cycle time t, and Δt represents the time interval between image frames.

[0026] Preferably, the first analysis unit is used to preset a first threshold Q1 in advance, and compare and analyze the water surface garbage diffusion disturbance coefficient FDI with the first threshold Q1, and obtain the first evaluation result including:

[0027] When the water surface garbage diffusion disturbance coefficient FDI ≤ the first threshold Q1, it indicates that the overall state of water surface garbage in the current sub-river section is stable, with no signs of diffusion and no risk of increased garbage accumulation, and continuous monitoring is required;

[0028] When the surface garbage diffusion disturbance coefficient FDI is greater than the first threshold Q1, it indicates that the overall state of surface garbage in the current sub-river section is unstable, with signs of diffusion and the risk of increased garbage accumulation. This triggers the first warning instruction and generates the first strategy: activate floating object interception equipment along the line and arrange unmanned boats for path priority cleaning; adjust the flow rate of the upstream drainage gate to alleviate flow disturbances; and conduct water quality testing in the current sub-river section.

[0029] Preferably, the water body monitoring module includes a second calculation unit and a second analysis unit;

[0030] The second calculation unit is used to monitor the river water quality of the current sub-river section in real time when receiving the first warning instruction, and calculate the water color difference coefficient SCP after dimensionless processing based on the historical water color standard data. The formula is as follows:

[0031] SCP=a1*(1-uh) 2 +a2*qs+a3*|uI-Iref|+a4*Dspec;

[0032] Where uh represents the mean hue of the water body, qs represents the standard deviation of saturation, uI represents the mean brightness, Iref represents the standard brightness reference value, Dspec represents the chromatographic distribution difference value, and a1, a2, a3, and a4 represent weight coefficients.

[0033] Preferably, the second analysis unit is used to preset a second threshold value Q2 in advance, and compare and analyze the water color difference abnormal coefficient SCP with the second threshold value Q2, and obtain the second evaluation result including:

[0034] When the water color difference coefficient SCP is less than the second threshold Q2, it means that the water color in the current sub-river section is normal, there is no pollution feature, and continuous monitoring is required;

[0035] When the water color difference abnormality coefficient SCP ≥ the second threshold Q2, it means that the water color in the current sub-river section is abnormal and has pollution characteristics, triggering the second early warning instruction and generating the second strategy: starting the upstream investigation mechanism to investigate the source of pollution.

[0036] Preferably, the pollution source investigation module includes a third calculation unit, a fourth calculation unit and an analysis strategy unit;

[0037] The third calculation unit is used to analyze the water quality of the river section by section along the upstream direction of the river when receiving the second warning instruction, and calculate the pollution gradient change rate ΔSCP after dimensionless processing. j , the formula is as follows:

[0038] ΔSCP j =SCP j -SCP j-1 ;

[0039] Where SCP j The water color difference coefficient of the j-th sub-river section is represented by SCP j-1 It represents the water color difference constant coefficient of the j-1th sub-river region, where the j-1th sub-river region is the upstream adjacent sub-river region of the jth sub-river region;

[0040] The fourth calculation unit is used to obtain the pollution gradient change rate ΔSCP according to the calculation j , in all continuous sub-channel areas, after dimensionless processing, find and calculate the pollution gradient change rate ΔSCP j Maximum sub-channel area Jcq j , the formula is as follows:

[0041]

[0042] Where, ΔSCP j Indicates the rate of change of the pollution gradient.

[0043] Preferably, the analysis strategy unit is used to convert the pollution gradient change rate ΔSCP j Maximum sub-channel area Jcq j , locked in as the source of sewage discharge, and carried out the sub-river area Jcq j , call historical image sequence comparison, conduct retrospective detection, and automatically generate the "Industrial Pollution Upstream Inference Report" to notify the ecological supervision unit for priority processing.

[0044] Preferably, a method for river management based on image processing technology comprises the following steps:

[0045] Step 1: Divide the treatment area into several sub-river sections based on GIS, river network distribution, and DEM models. Use fixed high-definition cameras, shore image sampling equipment, and drone multispectral cameras to collect video frames, water quality images, and pollution feature images.

[0046] Step 2: Extract the movement trajectory and distribution characteristics of floating objects, water color information and abnormal color areas, and pollution change trends and mutation characteristics in multi-time images;

[0047] Step 3: Monitor the density changes of floating debris target boundaries and flow velocity gradients in the fused image of the sub-river section in real time, calculate the surface garbage diffusion disturbance coefficient FDI, and compare and analyze it with the first threshold Q1 to determine whether the overall state of surface garbage in the sub-river section is stable. If it is unstable, a strategy is given;

[0048] Step 4: When the first warning instruction is received, the water quality of the current sub-river section is monitored in real time. The water color difference abnormality coefficient SCP is calculated based on the historical water color standard data. The water color difference abnormality coefficient SCP is compared with the second threshold Q2 to determine whether the water color of the current sub-river section is normal. If it is abnormal, a strategy is given;

[0049] Step 5: When the second warning instruction is received, analyze the water quality of the river section by section along the upstream direction of the river and calculate the pollution gradient change rate ΔSCP j , and find and calculate the pollution gradient change rate ΔSCP j Maximum sub-channel area Jcq j , lock in the source of pollution and provide strategies.

[0050] The present invention provides a method and system for river management based on image processing technology. It has the following beneficial effects:

[0051] (1) This method and system for river management based on image processing technology combines fixed high-definition cameras, static image sampling equipment, and drone multispectral camera technology to build a multi-angle, three-dimensional data acquisition network, realizing high-frequency image acquisition of multiple sub-river sections in urban rivers. Compared with traditional manual or sensor point monitoring methods, the present invention has the advantages of non-contact, no blind spots, and wide-area coverage. It can achieve full-process recording and real-time early warning of the dynamic evolution of water pollution incidents, significantly improving monitoring response speed and coverage accuracy.

[0052] (2) This method and system for river management based on image processing technology, by constructing an image processing module that integrates floating object optical flow tracking, water color difference analysis, and pollution time series extraction, can efficiently extract key features such as the movement of water pollution, color anomalies, and time series mutations from visual images, and construct quantitative indicators such as FDI (garbage diffusion disturbance coefficient) and SCP (water color difference abnormality coefficient). This processing method can achieve quantitative judgment of pollution risks.

[0053] (3) This method and system for river management based on image processing technology builds a tracking model based on the pollution gradient change rate. After a pollution anomaly is triggered, it can automatically analyze image data upstream along the river, calculate the area with the maximum pollution gradient change rate, and intelligently identify potential pollution sources. Compared with manual inspections, this method has the advantages of high automation, fast positioning speed, and high accuracy, effectively improving pollution tracking efficiency and regulatory disposal capabilities.

[0054] (4) This method and system for river management based on image processing technology, based on detection, identification and tracking, further designs multiple response strategies, such as initiating unmanned boat cleaning path planning, adjusting upstream sluice flow rate, and pushing pollution source tracing reports, to achieve closed-loop control of the entire process from pollution identification to management response. The system can also generate image sequence comparison reports for abnormal areas, providing data basis for urban water environment management, and improving the scientific nature and timeliness of management work. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a system block diagram and flow chart of a river management based on image processing technology of the present invention;

[0056] Figure 2 This is a schematic diagram of the steps of a river management method based on image processing technology according to the present invention. DETAILED DESCRIPTION

[0057] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0058] Example 1

[0059] See also Figure 1 The present invention provides a method and system for river management based on image processing technology, including a data acquisition module, an image processing module, a floating object monitoring and tracking module, a water body monitoring module and a pollution source investigation module;

[0060] The data acquisition module divides the treatment area into several sub-river sections based on GIS, river network distribution and DEM model, and collects video frames, water quality images and pollution feature images through fixed high-definition cameras, bank image sampling equipment and drone multispectral cameras;

[0061] The image processing module is used to extract the movement trajectory and distribution characteristics of floating objects, water color information and abnormal color areas, and pollution change trends and mutation characteristics in multi-time images;

[0062] The floating object monitoring and tracking module is used to monitor the density changes and flow gradient changes of floating object target boundaries in the fused image of the sub-river section in real time, calculate the surface garbage diffusion disturbance coefficient FDI, and compare and analyze it with the first threshold Q1 to determine whether the overall state of the surface garbage in the sub-river section is stable. If it is unstable, a strategy is given;

[0063] The water monitoring module is used to monitor the water quality of the current sub-river section in real time upon receiving the first warning instruction, calculate the water color difference abnormality coefficient SCP based on historical water color standard data, and compare and analyze it with the second threshold value Q2 to determine whether the water color of the current sub-river section is normal. If it is abnormal, a strategy is given;

[0064] The pollution source investigation module is used to analyze the water quality of the river section by section along the upstream direction of the river when receiving the second warning instruction, and calculate the pollution gradient change rate ΔSCP j , and find and calculate the pollution gradient change rate ΔSCP j Maximum sub-channel area Jcq j , lock in the source of pollution and provide strategies.

[0065] In this embodiment, by integrating GIS geographic information, river network distribution and DEM elevation model, and combining multi-source image acquisition and processing methods, it is possible to achieve refined segmented monitoring of urban rivers and accurate identification of pollution status, significantly improving the real-time detection of pollution incidents and the accuracy of regional positioning, and providing a scientific basis and efficient means for subsequent pollution prevention and control and source tracing management.

[0066] Example 2

[0067] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically, the data acquisition module includes a region division unit and an acquisition unit;

[0068] The regional division unit is used to establish a two-dimensional hydrological spatial coupling model of the river channel based on remote sensing geographic information GIS and urban river network distribution data, combined with a digital elevation model DEM, and divide the management area into several sub-river sections and mark them as: Jcq1, Jcq2, ..., JcqM; M represents the number of sub-river sections;

[0069] The acquisition unit is used to monitor the sub-river section area by deploying fixed high-definition water surface monitoring cameras along the river to collect continuous video frame sequences of the river; using static image sampling equipment deployed on the shore to collect high-definition water quality image samples; and using a multi-spectral camera equipped on an unmanned aerial vehicle to collect water surface pollution feature images and color feature images.

[0070] In this embodiment, by setting up regional division units and acquisition units in the data acquisition module, a two-dimensional hydrological spatial coupling model of the river channel is constructed using GIS, river network distribution and DEM models to achieve accurate segmentation and identification of the river channel. In addition, combined with multi-angle and multi-device image acquisition methods, the spatial coverage of pollution image information and the comprehensiveness of data acquisition are improved, providing high-quality, structured original data support for subsequent image recognition and pollution analysis.

[0071] Example 3

[0072] This embodiment is explained in Example 2, please refer to Figure 1 ,Specifically, the image processing module includes an optical flow field processing unit, a water chromatogram processing unit, and a pollution time series processing unit;

[0073] The optical flow processing unit is used to extract motion information from a continuous video image sequence of the river channel, using the optical flow estimation algorithm PWCNet to obtain the motion trajectory information of floating objects between images; extract the velocity vector characteristics and the aggregation area boundaries of the floating objects, and obtain the distribution status and movement trend diagram of the floating objects in the river channel; extract the image characteristics of the change in the density of floating objects in the area, and obtain the aggregation area of the floating objects in the current frame;

[0074] The water body chromatogram processing unit is used to extract color information from static water surface images, using the HSI color gamut conversion method to obtain hue, saturation and brightness characteristics in the image; compare the color difference maps of water bodies in different areas, extract abnormal color development areas, and generate water surface color feature layer data;

[0075] The pollution time series processing unit is used to dynamically extract pollution visual features from image sequences collected at different time points; analyze the changing trend images of floating object distribution maps, water body color maps and disturbance feature maps in the time dimension; identify sudden change areas during the pollution change process, and extract key image parameters before and after the change.

[0076] In this embodiment, by setting an optical flow field processing unit, a water body chromatogram processing unit, and a pollution time series processing unit in the image processing module, multi-dimensional in-depth analysis of river pollution images can be achieved. It can not only accurately obtain the movement trajectories and aggregation states of floating objects, but also extract abnormal water body color regions and dynamic characteristics of pollution evolution over time, effectively improving the accuracy and timeliness of pollution identification, and providing rich and high-dimensional image feature support for subsequent pollution early warning and traceability analysis.

[0077] Embodiment 4

[0078] This embodiment is an explanatory description based on Embodiment 3. Please refer to Figure 1 , specifically, the floating object monitoring and tracking module includes a first calculation unit and a first analysis unit;

[0079] The first calculation unit is used to monitor in real time the changes in the density of the floating object target boundary and the velocity gradient in the fused image of the sub-river section area. After dimensionless processing, the water surface garbage diffusion perturbation coefficient FDI is calculated and obtained. The formula is as follows:

[0080]

[0081] In the formula, represents the set of velocity vectors of floating objects in the optical flow field, represents the variance of the local velocity vector, represents the change in the density gradient of the floating object boundary per unit time, A c represents the area of the real-time floating object concentration area, A t represents the average value of the total area of floating objects at the past time t, and w1, w2, and w3 represent weight coefficients, where 0 < w1 < 1, 0 < w2 < 1, 0 < w3 < 1, and w1 + w2 + w3 = 1;

[0082]

[0083] In the formula, N represents the number of pixels in the image, represents the magnitude of the movement velocity vector of the floating object on the i-th pixel, and v represents the average magnitude of the floating object velocity vector;

[0084]

[0085] In the formula, D t represents the pollution attribute parameter value in the image at the t-th moment, D t-1 represents the pollution attribute parameter value in the image at the previous cycle moment before the t-th moment, and Δt represents the time interval between image frames.

[0086] In this embodiment, by setting a first calculation unit and a first analysis unit in the floating object monitoring and tracking module, a plurality of image dynamic features are used to construct the water surface garbage diffusion disturbance coefficient FDI, and combined with dimensionless processing and weight factor optimization, the dynamic change state of floating object pollution in the sub-river section can be accurately assessed, and real-time early warning of abnormal diffusion trends of water surface garbage can be achieved, effectively improving the sensitivity and response efficiency of water quality monitoring.

[0087] Example 5

[0088] This embodiment is explained in Example 4. Please refer to Figure 1 Specifically, the first analysis unit is used to preset a first threshold value Q1 in advance, and compare and analyze the water surface garbage diffusion disturbance coefficient FDI with the first threshold value Q1, and obtain the first evaluation result including:

[0089] When the water surface garbage diffusion disturbance coefficient FDI ≤ the first threshold Q1, it indicates that the overall state of water surface garbage in the current sub-river section is stable, with no signs of diffusion and no risk of increased garbage accumulation, and continuous monitoring is required;

[0090] When the water surface garbage diffusion disturbance coefficient FDI is greater than the first threshold Q1, it indicates that the overall state of surface garbage in the current sub-river section is unstable, with signs of diffusion and the risk of increased garbage accumulation. This triggers the first warning instruction and generates the first strategy: activate floating object interception equipment along the line and arrange unmanned boats for path priority cleaning; adjust the flow rate of the upstream drainage gate to alleviate flow disturbances; and conduct water quality testing in the current sub-river section.

[0091] In this embodiment, the first analysis unit uses a preset first threshold Q1 to perform real-time comparative analysis of the surface debris diffusion disturbance coefficient (FDI), enabling timely identification of surface debris diffusion trends within sub-river sections. When unstable debris levels are detected, an alert is automatically triggered and effective strategies are implemented, such as activating floating debris interception equipment and unmanned boat cleanup, adjusting water flow, and conducting water quality testing. This effectively prevents further accumulation of debris and ensures stable river water quality.

[0092] Example 6

[0093] This embodiment is explained in Example 5, please refer to Figure 1 ,Specifically, the water body monitoring module includes a second calculation unit and a second analysis unit;

[0094] The second calculation unit is used to monitor the river water quality of the current sub-river section in real time when receiving the first warning instruction, and calculate the water color difference coefficient SCP after dimensionless processing based on the historical water color standard data. The formula is as follows:

[0095] SCP=a1*(1-uh)2 +a2*qs + a3*|uI - Iref| + a4*Dspec;

[0096] Where, uh represents the average water body tone, qs represents the standard deviation of saturation, uI represents the average brightness, Iref represents the standard brightness reference value, Dspec represents the chromatographic distribution difference value, a1, a2, a3 and a4 represent weight coefficients, 0 < a1 < 1, 0 < a2 < 1, 0 < a3 < 1, 0 < a4 < 1, and a1 + a2 + a3 + a4 = 1.

[0097] In this embodiment, the second calculation unit is used to monitor the water quality status of the river channel in real time and calculate the water body color difference abnormal coefficient SCP. The present invention can effectively identify abnormal changes in the water body color and timely detect signs of water pollution. When the water body color is abnormal, the system can automatically trigger an alarm and conduct a detailed analysis, providing an accurate basis for subsequent investigation and treatment measures of pollution sources, and improving the sensitivity and accuracy of pollution detection.

[0098] Embodiment 7

[0099] This embodiment is an explanatory description based on Embodiment 6. Please refer to Figure 1 , specifically, the second analysis unit is used to preset a second threshold Q2 in advance and compare and analyze the water body color difference abnormal coefficient SCP with the second threshold Q2 to obtain the second evaluation result, including:

[0100] When the water body color difference abnormal coefficient SCP < the second threshold Q2, it indicates that the water body color in the current sub - river section area is normal and there is no pollution characteristic, and continuous monitoring is carried out;

[0101] When the water body color difference abnormal coefficient SCP ≥ the second threshold Q2, it indicates that the water body color in the current sub - river section area is abnormal and there is a pollution characteristic, triggering a second warning instruction and generating a second strategy: start the upstream investigation mechanism to investigate the pollution source.

[0102] In this embodiment, through the comparison and analysis of the water body color difference abnormal coefficient SCP and the second threshold Q2 by the second analysis unit, the present invention can accurately identify abnormal water body colors, timely detect pollution signs and trigger an alarm. The system can quickly start the pollution source investigation mechanism, help locate the pollution source in time, optimize the pollution treatment process, and ensure the real - time and accuracy of water quality monitoring.

[0103] Embodiment 8

[0104] This embodiment is an explanatory description based on Embodiment 7. Please refer to Figure 1 , specifically, the pollution source investigation module includes a third calculation unit, a fourth calculation unit and an analysis strategy unit;

[0105] The third calculation unit is used to analyze the water quality of the river section by section along the upstream direction of the river when receiving the second warning instruction, and calculate the pollution gradient change rate ΔSCP after dimensionless processing. j , the formula is as follows:

[0106] ΔSCP j =SCP j -SCP j-1 ;

[0107] Where SCP j The water color difference coefficient of the j-th sub-river section is represented by SCP j-1 It represents the water color difference constant coefficient of the j-1th sub-river region, where the j-1th sub-river region is the upstream adjacent sub-river region of the jth sub-river region;

[0108] The fourth calculation unit is used to obtain the pollution gradient change rate ΔSCP according to the calculation j , in all continuous sub-channel areas, after dimensionless processing, find and calculate the pollution gradient change rate ΔSCP j Maximum sub-channel area Jcq j , the formula is as follows:

[0109]

[0110] Where, ΔSCP j Indicates the rate of change of pollution gradient.

[0111] In this embodiment, through the combined efforts of the third and fourth calculation units of the pollution source identification module, the present invention accurately calculates the rate of change of pollution gradients and, by analyzing river water quality section by section, rapidly identifies sub-river channel areas with the greatest pollution gradient changes. This system can efficiently pinpoint pollution source areas, optimize pollution source identification and control strategies, and improve the accuracy and response speed of pollution source identification.

[0112] Example 9

[0113] This embodiment is explained in Example 8, please refer to Figure 1 Specifically, the analysis strategy unit is used to convert the pollution gradient change rate ΔSCP j Maximum sub-channel area Jcq j , locked in as the source of sewage discharge, and carried out the sub-river area Jcq j , call historical image sequence comparison, conduct retrospective detection, and automatically generate the "Industrial Pollution Upstream Inference Report" to notify the ecological supervision unit for priority processing.

[0114] In this embodiment, by analyzing the strategy unit's automated retrospective detection and comparing it with historical image sequences, the present invention can accurately identify pollution sources and automatically generate an "Industrial Pollution Upstream Inference Report," providing a scientific basis for ecological regulators to prioritize pollution source treatment. This strategy improves the accuracy of pollution source location and response efficiency, ensuring the timeliness and effectiveness of water pollution control.

[0115] Example 10

[0116] A river management method based on image processing technology, please refer to Figure 2 , including the following steps:

[0117] Step 1: Divide the treatment area into several sub-river sections based on GIS, river network distribution, and DEM models. Use fixed high-definition cameras, shore image sampling equipment, and drone multispectral cameras to collect video frames, water quality images, and pollution feature images.

[0118] Step 2: Extract the movement trajectory and distribution characteristics of floating objects, water color information and abnormal color areas, and pollution change trends and mutation characteristics in multi-time images;

[0119] Step 3: Monitor the density changes of floating debris target boundaries and flow velocity gradients in the fused image of the sub-river section in real time, calculate the surface garbage diffusion disturbance coefficient FDI, and compare and analyze it with the first threshold Q1 to determine whether the overall state of surface garbage in the sub-river section is stable. If it is unstable, a strategy is given;

[0120] Step 4: When the first warning instruction is received, the water quality of the current sub-river section is monitored in real time. The water color difference abnormality coefficient SCP is calculated based on the historical water color standard data. The water color difference abnormality coefficient SCP is compared with the second threshold Q2 to determine whether the water color of the current sub-river section is normal. If it is abnormal, a strategy is given;

[0121] Step 5: When the second warning instruction is received, analyze the water quality of the river section by section along the upstream direction of the river and calculate the pollution gradient change rate ΔSCP j , and find and calculate the pollution gradient change rate ΔSCP j Maximum sub-channel area Jcq j , lock in the source of pollution and provide strategies.

[0122] In this embodiment, through the linkage monitoring and analysis of five steps, efficient and accurate identification and response to river water quality and pollution sources can be achieved. First, by combining GIS, river network distribution and DEM model, the treatment area is accurately divided to ensure the comprehensiveness of monitoring. Secondly, based on the collaborative collection of multiple devices and multi-period image processing, the distribution of floating objects, water color changes and pollution mutation characteristics can be monitored in real time. Furthermore, by calculating and comparing the threshold of the water surface garbage diffusion disturbance coefficient FDI and the water color difference abnormal coefficient SCP, the abnormal conditions of water surface garbage and water color can be effectively judged, and early warnings can be triggered in time to generate response strategies. Finally, through the analysis of the pollution gradient change rate, the pollution source is automatically locked and an upstream pollution discharge inference report is generated, providing an accurate basis for governance for ecological supervision units.

[0123] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0124] The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The coefficients in the formula are set by those skilled in the art according to actual conditions. The above is only a preferred specific implementation method of the present invention, but the protection scope of the present invention is not limited to this. Any technician familiar with this technical field, within the technical scope disclosed by the present invention, can make equivalent replacements or changes based on the technical solution and inventive concept of the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A river management system based on image processing technology, characterized in that: It includes data acquisition module, image processing module, floating object monitoring and tracking module, water body monitoring module and pollution source investigation module; The data acquisition module divides the treatment area into several sub-river sections based on GIS, river network distribution and DEM model, and collects video frames, water quality images and pollution feature images through fixed high-definition cameras, bank image sampling equipment and drone multispectral cameras; The image processing module is used to extract the movement trajectory and distribution characteristics of floating objects, water color information and abnormal color areas, and pollution change trends and mutation characteristics in multi-time images; The floating object monitoring and tracking module is used to monitor the density changes and flow gradient changes of floating object target boundaries in the fused image of the sub-river section in real time, calculate the surface garbage diffusion disturbance coefficient FDI, and compare and analyze it with the first threshold Q1 to determine whether the overall state of the surface garbage in the sub-river section is stable. If it is unstable, a strategy is given; The water monitoring module is used to monitor the water quality of the current sub-river section in real time upon receiving the first warning instruction, calculate the water color difference abnormality coefficient SCP based on historical water color standard data, and compare and analyze it with the second threshold value Q2 to determine whether the water color of the current sub-river section is normal. If it is abnormal, a strategy is given; The pollution source investigation module is used to analyze the water quality of the river section by section along the upstream direction of the river when receiving the second warning instruction, and calculate the pollution gradient change rate ΔSCP j , and find and calculate the pollution gradient change rate ΔSCP j Maximum sub-channel area Jcq j , lock in the source of pollution and provide strategies.

2. A river management system based on image processing technology according to claim 1, characterized in that: The data acquisition module includes a region division unit and an acquisition unit; The regional division unit is used to establish a two-dimensional hydrological spatial coupling model of the river channel based on remote sensing geographic information GIS and urban river network distribution data, combined with a digital elevation model DEM, and divide the management area into several sub-river sections and mark them as: Jcq1, Jcq2, ..., JcqM; M represents the number of sub-river sections; The acquisition unit is used to monitor the sub-river section area by deploying fixed high-definition water surface monitoring cameras along the river to collect continuous video frame sequences of the river; using static image sampling equipment deployed on the shore to collect high-definition water quality image samples; and using a multi-spectral camera equipped on an unmanned aerial vehicle to collect water surface pollution feature images and color feature images.

3. The system for river management based on image processing technology according to claim 2 is characterized in that: The image processing module includes an optical flow field processing unit, a water body chromatography processing unit and a pollution time series processing unit; The optical flow processing unit is used to extract motion information from a continuous video image sequence of the river channel, using the optical flow estimation algorithm PWCNet to obtain the motion trajectory information of floating objects between images; extract the velocity vector characteristics and the aggregation area boundaries of the floating objects, and obtain the distribution status and movement trend diagram of the floating objects in the river channel; extract the image characteristics of the change in the density of floating objects in the area, and obtain the aggregation area of the floating objects in the current frame; The water body chromatogram processing unit is used to extract color information from a static water surface image and obtain hue, saturation and brightness characteristics in the image using an HSI color gamut conversion method; Compare the color difference maps of water bodies in different areas, extract abnormal color areas, and generate water surface color feature layer data; The pollution time sequence processing unit is used to dynamically extract pollution visual features from image sequences collected at different time points; Analyze the changing trend images of floating object distribution map, water color map and disturbance characteristic map in the time dimension; identify the mutation areas in the pollution change process and extract the key image parameters before and after the change.

4. The system for river management based on image processing technology according to claim 3 is characterized in that: The floating object monitoring and tracking module includes a first calculation unit and a first analysis unit; The first calculation unit is used to monitor the density change of the floating object target boundary and the flow velocity gradient change in the fused image of the sub-river section in real time. After dimensionless processing, the water surface garbage diffusion disturbance coefficient FDI is calculated and obtained. The formula is as follows: Where, Represents the velocity vector set of floating objects in the optical flow field, represents the variance of the local velocity vector, A represents the density gradient change of floating objects boundary per unit time, c Indicates the real-time floating object concentration area, A t represents the mean total area of floating objects at time t in the past, w1, w2 and w3 represent weight coefficients; Where N represents the number of pixels in the image, represents the modulus of the velocity vector of the floating object at the i-th pixel, and v represents the average modulus of the velocity vector of the floating object; Where D t Denotes the pollution attribute parameter value in the image at time t, D t-1 It represents the pollution attribute parameter value in the image at the previous cycle time t, and Δt represents the time interval between image frames.

5. The system for river management based on image processing technology according to claim 4 is characterized in that: The first analysis unit is used to preset a first threshold Q1 in advance, and compare and analyze the water surface garbage diffusion disturbance coefficient FDI with the first threshold Q1 to obtain a first evaluation result including: When the water surface garbage diffusion disturbance coefficient FDI ≤ the first threshold Q1, it indicates that the overall state of water surface garbage in the current sub-river section is stable, with no signs of diffusion and no risk of increased garbage accumulation, and continuous monitoring is required; When the water surface garbage diffusion disturbance coefficient FDI is greater than the first threshold Q1, it indicates that the overall state of surface garbage in the current sub-river section is unstable, with signs of diffusion and the risk of increased garbage accumulation. This triggers the first warning instruction and generates the first strategy: activate floating object interception equipment along the line and arrange unmanned boats for path priority cleaning; adjust the flow rate of the upstream drainage gate to alleviate flow disturbances; and conduct water quality testing in the current sub-river section.

6. The system for river management based on image processing technology according to claim 5 is characterized in that: The water body monitoring module includes a second calculation unit and a second analysis unit; The second calculation unit is used to monitor the river water quality of the current sub-river section in real time when receiving the first warning instruction, and calculate the water color difference coefficient SCP after dimensionless processing based on the historical water color standard data. The formula is as follows: <h2 style=";text-align:left;direction:ltr">SCP=a1*(1-uh)<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> +a2*qs+a3*|uI-Iref|+a4*Dspec; Where uh represents the mean hue of the water body, qs represents the standard deviation of saturation, uI represents the mean brightness, Iref represents the standard brightness reference value, Dspec represents the chromatographic distribution difference value, and a1, a2, a3, and a4 represent weight coefficients.

7. The system for river management based on image processing technology according to claim 6 is characterized in that: The second analysis unit is used to preset a second threshold value Q2 in advance, and compare and analyze the water color difference abnormal coefficient SCP with the second threshold value Q2 to obtain a second evaluation result including: When the water color difference coefficient SCP is less than the second threshold Q2, it means that the water color in the current sub-river section is normal, there is no pollution feature, and continuous monitoring is required; When the water color difference abnormality coefficient SCP ≥ the second threshold Q2, it means that the water color in the current sub-river section is abnormal and has pollution characteristics, triggering the second early warning instruction and generating the second strategy: starting the upstream investigation mechanism to investigate the source of pollution.

8. The system for river management based on image processing technology according to claim 7 is characterized in that: The pollution source investigation module includes a third calculation unit, a fourth calculation unit and an analysis strategy unit; The third calculation unit is used to analyze the water quality of the river section by section along the upstream direction of the river when receiving the second warning instruction, and calculate the pollution gradient change rate ΔSCP after dimensionless processing. j , the formula is as follows: ΔSCP j =SCP j -SCP j-1 ; Where SCP j The water color difference coefficient of the j-th sub-river section is represented by SCP j-1 It represents the water color difference constant coefficient of the j-1th sub-river region, where the j-1th sub-river region is the upstream adjacent sub-river region of the jth sub-river region; The fourth calculation unit is used to obtain the pollution gradient change rate ΔSCP according to the calculation j , in all continuous sub-channel areas, after dimensionless processing, find and calculate the pollution gradient change rate ΔSCP j Maximum sub-channel area Jcq j , the formula is as follows: Where, ΔSCP j Indicates the rate of change of pollution gradient.

9. The system for river management based on image processing technology according to claim 8, characterized in that: The analysis strategy unit is used to convert the pollution gradient change rate ΔSCP j Maximum sub-channel area Jcq j , locked in as the source of sewage discharge, and carried out the sub-river area Jcq j , call historical image sequence comparison, conduct retrospective detection, and automatically generate the "Industrial Pollution Upstream Inference Report" to notify the ecological supervision unit for priority processing.

10. A method for river management based on image processing technology, comprising a system for river management based on image processing technology according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Divide the treatment area into several sub-river sections based on GIS, river network distribution, and DEM models. Use fixed high-definition cameras, shore image sampling equipment, and drone multispectral cameras to collect video frames, water quality images, and pollution feature images. Step 2: Extract the movement trajectory and distribution characteristics of floating objects, water color information and abnormal color areas, and pollution change trends and mutation characteristics in multi-time images; Step 3: Monitor the density changes of floating debris target boundaries and flow velocity gradients in the fused image of the sub-river section in real time, calculate the surface garbage diffusion disturbance coefficient FDI, and compare and analyze it with the first threshold Q1 to determine whether the overall state of surface garbage in the sub-river section is stable. If it is unstable, a strategy is given; Step 4: When the first warning instruction is received, the water quality of the current sub-river section is monitored in real time. The water color difference abnormality coefficient SCP is calculated based on the historical water color standard data. The water color difference abnormality coefficient SCP is compared with the second threshold Q2 to determine whether the water color of the current sub-river section is normal. If it is abnormal, a strategy is given; Step 5: When the second warning instruction is received, analyze the water quality of the river section by section along the upstream direction of the river and calculate the pollution gradient change rate ΔSCP j , and find and calculate the pollution gradient change rate ΔSCP j Maximum sub-channel area Jcq j , lock in the source of pollution and provide strategies.

Images