A method, device and medium for automatically monitoring the disorderly discharge of rainwater outlets

Abstract

The present invention discloses a method, device and medium for automatically monitoring the disorderly discharge of rainwater outlets, which belongs to the technical field of water environment supervision and governance, and is used to solve the technical problems that the disorderly discharge phenomenon of existing rainwater outlets is difficult to manage, the manual inspection method is costly and inefficient, and it is easy to generate false alarms, which reduces the efficiency of alarm disposal. The method includes: collecting real-time video stream data of rainwater outlets; automatically identifying and processing the real-time video stream data for drainage, and determining the dynamic time series information of drainage; based on the corresponding rainwater outlet label in the dynamic time series information of drainage, obtaining the rainfall monitoring information of the rain gauge station within a preset range; monitoring and processing the meteorological data of the area, and obtaining local meteorological monitoring information; judging abnormal drainage on the dynamic time series information of drainage through rainfall monitoring data and local meteorological monitoring information, and obtaining disorderly drainage alarm information; classifying the disorderly drainage alarm information into events, and obtaining alarm events.

Description

Technical Field

[0001] The present application relates to the field of water environment supervision and management, and in particular to a method, device and medium for automatically monitoring the disorderly discharge of rainwater outlets. Background Art

[0002] In the process of protecting the water environment, the monitoring and management of outfalls are crucial. With the acceleration of the industrialization process, a large amount of wastewater and sewage are discharged into rivers, lakes and seas, posing a serious threat to aquatic ecosystems. Outfalls are the direct channels for these pollutants to enter the water environment, and their management is directly related to the improvement of water environment quality and the protection of the city's lifeline. Some companies even illegally discharge sewage through rainwater outlets, which not only violates environmental protection laws and regulations, but also causes serious pollution to the surrounding environment.

[0003] The main function of stormwater outlets is to help drain water from the ground during and after rainfall. Once the rainfall stops, these outlets usually no longer need to drain water. If water is discharged on sunny days, it proves that there is a situation of illegal drainage or wrong connection of pipes. Untreated sewage is directly discharged into the stormwater pipes through illegal means. This behavior not only violates relevant environmental protection regulations, but also causes serious damage to the urban drainage system. This behavior often occurs in urban management. In order to save trouble or avoid treatment costs, some units or individuals discharge untreated sewage directly into the stormwater pipes, resulting in the mixing of rainwater and sewage, causing chaos in the urban drainage system, and thus affecting the drainage efficiency and environmental quality of the city.

[0004] In order to effectively protect the environment, manual inspections are usually used to check and manage the disorderly discharge of rainwater outlets, but this has high labor costs, low efficiency, and cannot timely detect problems that lead to environmental pollution. In order to solve this problem, many places use AI intelligent analysis methods, which leads to false alarms when normal drainage occurs during rain. Since AI intelligent analysis is monitored at a certain time, if the outlet continues to drain, it will cause multiple alarm messages to be issued, greatly increasing the workload of staff and reducing the efficiency of alarm handling. Summary of the invention

[0005] The embodiments of the present application provide a method, device and medium for automatically monitoring disorderly discharge of rainwater outlets, which are used to solve the following technical problems: the disorderly discharge of existing rainwater outlets is difficult to manage, and the manual inspection method is costly and inefficient, which is prone to false alarms and reduces the efficiency of alarm handling.

[0006] The present application embodiment adopts the following technical solutions:

[0007] On the one hand, an embodiment of the present application provides a method for automatically monitoring disorderly discharge of rainwater outlets, comprising: collecting real-time video stream data of the rainwater outlet according to a camera preset at the rainwater outlet; automatically identifying and processing the drainage on the real-time video stream data to determine dynamic timing information of the drainage; obtaining rainfall monitoring information of rain gauges within a preset range based on the rainwater outlet number corresponding to the rainwater outlet number in the dynamic timing information of the drainage; monitoring and processing meteorological data of the area according to the rainwater outlet number to obtain local meteorological monitoring information; judging abnormal drainage on the dynamic timing information of the drainage through the rainfall monitoring data and the local meteorological monitoring information to obtain disorderly drainage alarm information; classifying the disorderly drainage alarm information into events to obtain alarm events.

[0008] The embodiment of the present application collects real-time video stream data of the rainwater outlet through a preset camera, so that the drainage situation of the rainwater outlet can be understood in real time and abnormal drainage behavior can be discovered in time. It can also automatically identify and process the drainage of the real-time video stream data, and can quickly and accurately determine the dynamic time series information of the drainage, thereby improving the monitoring efficiency. At the same time, combined with the rainfall monitoring information of the rain gauge station and the local meteorological monitoring information, the abnormal drainage judgment of the drainage dynamic time series information can be performed, so that the drainage situation can be understood more comprehensively and the accuracy of the judgment can be improved. It can also detect abnormal drainage behavior in time and issue an alarm message for disorderly drainage, which helps the relevant departments to take measures in time to prevent environmental pollution and waste of water resources. It also helps the relevant departments to analyze and process abnormal drainage behavior and improve management efficiency.

[0009] In a feasible implementation manner, according to the camera pre-installed at the rainwater outlet, real-time video stream data of the rainwater outlet is collected, specifically including: based on the geographical location information of the rainwater outlet, the terrain trend of the rainwater outlet is modeled and processed to obtain a rainwater outlet terrain model; according to the rainwater outlet terrain model, the rainwater flow trend is simulated and analyzed to determine the rainwater flow trajectory information; through the rainwater flow trajectory information and the geographical location information, the wide-angle range of the camera is overlapped and covered so that the wide-angle range can fully cover the rainwater flow trajectory information and the location information, and the camera installation location information is determined; based on the camera installation location information, the camera is pre-installed; based on the geographical location information of the rainwater outlet and the current timing information, and through the camera, real-time video stream data of the rainwater outlet is collected; wherein, the real-time video stream data includes: outlet water flow location information, outlet geographical location information, current time node and water flow dynamic change information.

[0010] In a feasible implementation, the real-time video stream data is automatically identified and processed for drainage to determine the dynamic timing information of drainage, which specifically includes: performing data access processing on the real-time video stream data and a preset visual AI analysis platform; performing video frame extraction processing on the real-time video stream data through the visual AI analysis platform to obtain a number of key video frame images; wherein the key video frame images are video frames extracted based on the same period time; performing sequential comparison processing on a number of the key video frame images to identify the changed video frame images; performing regional pixel identification processing on the changed video frame images related to drainage characteristics to obtain drainage dynamic video frame images; extracting the time node information and the rainwater outlet number corresponding to the drainage dynamic video frame image; generating the drainage dynamic timing information based on the time node information and the rainwater outlet number, and storing the drainage dynamic timing information in the database of the visual AI analysis platform.

[0011] In a feasible implementation, based on the rainwater outlet number corresponding to the drainage dynamic timing information, the rainfall monitoring information of the rain gauge station within a preset range is obtained, specifically including: based on a preset time interval, performing information generation judgment on the drainage dynamic timing information; if the drainage dynamic timing information is detected, extracting the corresponding rainwater outlet number; based on the geographical location information of the rainwater outlet corresponding to the rainwater outlet number, and through the GIS map, performing a range selection process of the center point of the geographical area within the preset range to obtain a local geographical location area; performing a short distance judgment between the rain gauge station in the local geographical location area and the rainwater outlet corresponding to the rainwater outlet number to determine the neighboring rain gauge station; extracting the rainfall monitoring information monitored in the neighboring rain gauge station, and locating the rainfall monitoring information as the rainfall monitoring information at the geographical location where the rainwater outlet number is located.

[0012] In a feasible implementation manner, the meteorological data of the area is monitored and processed according to the rainwater outlet number to obtain local meteorological monitoring information, specifically including: obtaining the meteorological data of the area according to the geographical location information of the rainwater outlet corresponding to the rainwater outlet number; querying and processing the meteorological data in the local area and range time based on the time node information in the drainage dynamic time series information to obtain the local meteorological monitoring information.

[0013] In a feasible implementation, the drainage dynamic time series information is judged as abnormal drainage through the rainfall monitoring data and the local meteorological monitoring information to obtain disorderly drainage alarm information, specifically including: extracting the rainfall monitoring data and the local meteorological monitoring information based on the time node information in the drainage dynamic time series information currently identified and the rainwater outlet number; if the rainfall monitoring data shows that there is rainfall data, and the local meteorological monitoring information shows that there is local rainfall information, then the drainage dynamic time series information is judged as normal rainfall drainage information; otherwise, the drainage dynamic time series information is judged as abnormal rainfall drainage information; the abnormal rainfall drainage information is fed back to the visual AI analysis platform, and the drainage dynamic time series information is marked as an alarm to be determined as the disorderly drainage alarm information.

[0014] In a feasible implementation, the disorderly drainage alarm information is classified as an event to obtain an alarm event, which specifically includes: configuring the cycle time for identifying the drainage dynamic timing information in the visual AI analysis platform to obtain the alarm interval time; according to the alarm interval time, classifying several disorderly drainage alarm information in the same cycle time as the same event to obtain the alarm event, and using several disorderly drainage alarm information as supporting display information corresponding to the alarm event.

[0015] In a feasible implementation manner, after classifying the disorderly drainage alarm information as an event and obtaining an alarm event, the method further includes: obtaining the alarm geographical location information of the disorderly drainage alarm information in the alarm event; based on the alarm geographical location information, performing a nearest geographical distance query on the location of the patrol staff, and determining the optimal patrol staff, so that the optimal patrol staff can complete the handling of the alarm event.

[0016] In a second aspect, an embodiment of the present application also provides a device for automatically monitoring disorderly discharge of rainwater outlets, the device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, so that the at least one processor can execute a method for automatically monitoring disorderly discharge of rainwater outlets as described in any of the above-mentioned embodiments.

[0017] In the third aspect, an embodiment of the present application also provides a non-volatile computer storage medium, characterized in that the storage medium is a non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium stores at least one program, each of which includes instructions, and when the instructions are executed by a terminal, the terminal executes a method for automatically monitoring the disorderly discharge of rainwater outlets as described in any of the above-mentioned embodiments.

[0018] The present application provides a method, device and medium for automatically monitoring the disorderly discharge of rainwater outlets. Compared with the prior art, the embodiments of the present application have the following beneficial technical effects:

[0019] 1. Real-time monitoring: By collecting real-time video stream data of the rainwater outlet through the pre-installed camera, you can understand the drainage situation of the rainwater outlet in real time and detect abnormal drainage behavior in time.

[0020] 2. Automatic identification and processing: Automatic identification and processing of drainage in real-time video stream data can quickly and accurately determine the dynamic timing information of drainage and improve monitoring efficiency.

[0021] 3. Multi-source data fusion: Combining the rainfall monitoring information from the rain gauge station and the local meteorological monitoring information, abnormal drainage judgment can be made on the drainage dynamic time series information, which can provide a more comprehensive understanding of the drainage situation and improve the accuracy of the judgment.

[0022] 4. Illegal drainage alarm: Timely detection of abnormal drainage behavior and issuance of illegal drainage alarm information will help relevant departments take timely measures to prevent environmental pollution and waste of water resources.

[0023] 5. Event classification: Classify the illegal drainage alarm information into events and obtain alarm events, which will help relevant departments analyze and handle abnormal drainage behaviors and improve management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0025] Figure 1 A flow chart of a method for automatically monitoring the disorderly discharge of rainwater outlets provided in an embodiment of the present application;

[0026] Figure 2 A flow chart for judging disorderly discharge of rainwater outlets provided in an embodiment of the present application;

[0027] Figure 3 A schematic diagram of the structure of a device for automatically monitoring disorderly discharge of rainwater outlets provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0029] The present application embodiment provides a method for automatically monitoring the disorderly discharge of rainwater outlets, such as Figure 1 As shown, the method for automatically monitoring the disorderly discharge of rainwater outlets specifically includes steps S101-S106:

[0030] S101. Collect real-time video stream data of the rainwater outlet according to the camera pre-installed at the rainwater outlet.

[0031] Specifically, firstly, it is necessary to model the terrain trend of the rainwater outlet based on the geographical location information of the rainwater outlet to obtain the rainwater outlet terrain model. Then, according to the rainwater outlet terrain model, the rainwater flow trend is simulated and analyzed to obtain the rainwater flow trajectory information.

[0032] Furthermore, the wide-angle range of the camera is overlapped and covered by the rainwater flow trajectory information and the geographical location information, so that the wide-angle range can fully cover the rainwater flow trajectory information and the location information, and determine the camera installation location information.

[0033] Furthermore, based on the camera installation position information, the camera is pre-installed.

[0034] Furthermore, based on the geographical location information and current time sequence information of the rainwater outlet, real-time video stream data of the rainwater outlet is collected through a camera, wherein the real-time video stream data includes: outlet water location information, outlet geographical location information, current time node and water flow dynamic change information.

[0035] In one embodiment, Figure 2 A flow chart for judging disorderly discharge of rainwater outlets provided in an embodiment of the present application is as follows: Figure 2 As shown, by using the stormwater outlet terrain model, a suitable location can be selected at the stormwater outlet and a high-definition camera can be deployed to view the outlet flow position more intuitively and clearly, and then further collect real-time video stream data about the stormwater outlet.

[0036] S102: Automatically identify and process drainage on real-time video stream data to determine dynamic time sequence information of drainage.

[0037] Specifically, the real-time video stream data is first connected to the preset visual AI analysis platform for data access processing. Through the visual AI analysis platform, the real-time video stream data is processed by video frame extraction to obtain several key video frame images. Among them, the key video frame images are video frames extracted based on the same cycle time.

[0038] Furthermore, a plurality of key video frame images are sequentially compared to identify the changed video frame images.

[0039] Furthermore, the changing video frame image is processed with regional pixel recognition related to drainage characteristics to obtain a drainage dynamic video frame image.

[0040] Furthermore, the time node information and the rainwater outlet label corresponding to the drainage dynamic video frame image are extracted.

[0041] Furthermore, based on the time node information and the rainwater outlet number, the drainage dynamic timing information is generated, and the drainage dynamic timing information is stored in the database of the visual AI analysis platform.

[0042] In one embodiment, Figure 2 As shown, the supporting video AI intelligent recognition system can realize intelligent real-time warning of outlet problems. It is necessary to configure the algorithm model for the camera association, and then through the built visual AI analysis platform, it can realize the functions of monitoring access, video frame extraction, algorithm reasoning and AI alarm, and realize AI recognition and real-time alarm of outlet drainage and other problem scenes 24 hours a day. Whether it is day or night, as long as the outlet is draining, the system can trigger automatic recognition. Then, after repeatedly comparing the key video frame image at the previous time node with the key video frame image at the next time node, the changed video frame image is determined, and then the regional pixel recognition is used to obtain the drainage dynamic video frame image, and the time node information corresponding to the drainage dynamic video frame image and the rainwater outlet label are recorded.

[0043] S103: Based on the corresponding rainwater outlet number in the drainage dynamic time series information, obtain rainfall monitoring information of the rain gauge station within a preset range.

[0044] Specifically, it is necessary to first use a preset time interval to perform information generation judgment on the drainage dynamic time series information; if the drainage dynamic time series information is detected, the corresponding rainwater outlet label is extracted.

[0045] Furthermore, according to the geographical location information of the rainwater outlet corresponding to the rainwater outlet number, the geographical area within the preset range is range-selected by center point through the GIS map to obtain the local geographical location area.

[0046] Furthermore, the shortest distance between the rain gauge station in the local geographical area and the rain outlet corresponding to the rain outlet number is judged to determine the adjacent rain gauge station.

[0047] Furthermore, rainfall monitoring information monitored in adjacent rain gauge stations is extracted, and the rainfall monitoring information is located at the geographical location where the rainwater outlet number is located.

[0048] As a feasible implementation method, for rainwater outlets, there is no need to issue an alarm when discharging on rainy days. An alarm is only needed when discharging on sunny days. In order to accurately issue an alarm, it is necessary to filter the information of the alarm identified by intelligent analysis. Based on the GIS map, the system automatically searches for rain gauges near the outlet and obtains the rainfall monitoring data of the rain gauges, which is used as one of the conditions for subsequent normal drainage. That is, after judging the shortest distance between the rain gauges in the local geographical area and the rainwater outlet corresponding to the rainwater outlet number, the rainfall monitoring information monitored in the neighboring rain gauges is extracted.

[0049] S104. According to the rainwater outlet number, the meteorological data of the area is monitored and processed to obtain local meteorological monitoring information.

[0050] Specifically, the meteorological data of the area is obtained according to the geographical location information of the rainwater outlet corresponding to the rainwater outlet number. Based on the time node information in the drainage dynamic time series information, the meteorological data is queried and processed in the local area and range time to obtain the local meteorological monitoring information.

[0051] As a feasible implementation method, in order to avoid the monitoring equipment in the rain gauge station being offline or malfunctioning, which results in the inability to obtain the data information of the rain gauge station, the rainfall data of the meteorological area where the outlet is located is also used as one of the conditions for whether the subsequent drainage is normal. And the time node information in the drainage dynamic time series information and the meteorological data of the area are used to obtain local meteorological monitoring information.

[0052] S105. Using rainfall monitoring data and local meteorological monitoring information, abnormal drainage is judged on the drainage dynamic time series information to obtain disorderly drainage alarm information.

[0053] Specifically, rainfall monitoring data and local meteorological monitoring information are first extracted based on the time node information and rainwater outlet number in the currently identified drainage dynamic time series information.

[0054] If the rainfall monitoring data indicates that there is rainfall data, and the local meteorological monitoring information indicates that there is local rainfall information, the drainage dynamic time series information is determined to be normal rainfall drainage information. Otherwise, the drainage dynamic time series information is determined to be abnormal rainfall drainage information.

[0055] Furthermore, the abnormal rainfall drainage information is fed back to the visual AI analysis platform, and the drainage dynamic time series information is marked as an alarm and determined as disorderly drainage alarm information.

[0056] In one embodiment, Figure 2 As shown, when the monitoring of the rain gauge station and the monitoring of the meteorological data both show that there is no rainfall, that is, if the rainfall monitoring data shows that there is no rainfall data, and the local meteorological monitoring information shows that there is no local rainfall information, the rainwater outlet number corresponding to the drainage dynamic time series information will be determined as having abnormal sewage discharge behavior, and an illegal drainage alarm information will be generated.

[0057] S106: Classify the illegal drainage alarm information into events to obtain alarm events.

[0058] Specifically, it is also necessary to configure the cycle time of identifying the dynamic time series information of drainage in the visual AI analysis platform to obtain the alarm interval time. According to the alarm interval time, several disorderly drainage alarm information in the same cycle time are classified as the same event to obtain the alarm event, and several disorderly drainage alarm information are used as the supporting information of the corresponding alarm event.

[0059] As a feasible implementation method, the alarm geographical location information of the illegal drainage alarm information in the alarm event can also be obtained. Based on the alarm geographical location information, the nearest geographical distance query is performed on the location of the patrol staff to determine the optimal patrol staff so that the optimal patrol staff can complete the handling of the alarm event.

[0060] In one embodiment, for most of the indiscriminate sewage discharge scenarios, the indiscriminate sewage discharge behavior lasts for a period of time. The video AI analysis sets the interval time for alarm. For example, the alarm interval is 1 minute monitoring. If an abnormality is found, an abnormal event is generated. Multiple abnormal events will be generated. For the subsequent inspection personnel to deal with it, a lot of workload will be added, which will reduce the efficiency of event handling. Therefore, the alarm collection time is set, that is, the collection time in the same cycle time is needed to classify the indiscriminate drainage alarm information of the same outlet into one event, and the corresponding multiple indiscriminate drainage alarm information is displayed as evidence of the alarm event.

[0061] Therefore, through AI analysis and multi-factor analysis, the accuracy of rainwater outlet monitoring and alarm can be improved, the system false alarm rate can be reduced, and the rainwater outlet can be effectively monitored to achieve a complete monitoring system of prior warning, real-time monitoring, and post-event tracing, thereby reducing illegal activities, effectively protecting the environment, reducing the workload of manual inspections, and improving efficiency.

[0062] In addition, the embodiment of the present application also provides a device for automatically monitoring the disorderly discharge of rainwater outlets, such as Figure 3 As shown in the figure, the automatic monitoring equipment for disorderly discharge of rainwater outlets specifically includes:

[0063] At least one processor 301. And a memory 302 in communication with the at least one processor 301. The memory 302 stores instructions that can be executed by the at least one processor 301, so that the at least one processor 301 can execute:

[0064] According to the camera pre-installed at the rainwater outlet, real-time video stream data of the rainwater outlet is collected;

[0065] Automatically identify and process drainage of real-time video stream data to determine dynamic timing information of drainage;

[0066] Based on the corresponding rainwater outlet number in the drainage dynamic time series information, the rainfall monitoring information of the rain gauge station within the preset range is obtained;

[0067] According to the rainwater outlet number, the meteorological data of the area is monitored and processed to obtain local meteorological monitoring information;

[0068] Through rainfall monitoring data and local meteorological monitoring information, abnormal drainage is judged on the drainage dynamic time series information to obtain disorderly drainage alarm information;

[0069] The illegal drainage alarm information is classified into events to obtain alarm events.

[0070] The embodiment of the present application collects real-time video stream data of the rainwater outlet through a preset camera, so that the drainage situation of the rainwater outlet can be understood in real time and abnormal drainage behavior can be discovered in time. It can also automatically identify and process the drainage of the real-time video stream data, and can quickly and accurately determine the dynamic time series information of the drainage, thereby improving the monitoring efficiency. At the same time, combined with the rainfall monitoring information of the rain gauge station and the local meteorological monitoring information, the abnormal drainage judgment of the drainage dynamic time series information can be performed, so that the drainage situation can be understood more comprehensively and the accuracy of the judgment can be improved. It can also detect abnormal drainage behavior in time and issue an alarm message for disorderly drainage, which helps the relevant departments to take measures in time to prevent environmental pollution and waste of water resources. It also helps the relevant departments to analyze and process abnormal drainage behavior and improve management efficiency.

[0071] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0072] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0073] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0074] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0075] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0076] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0077] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0078] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0079] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0080] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0081] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for automatically monitoring the disorderly discharge of rainwater outlets, characterized in that: The method comprises: According to the camera pre-installed at the rainwater outlet, real-time video stream data of the rainwater outlet is collected; Automatically identify and process the drainage of the real-time video stream data to determine dynamic time sequence information of the drainage; Based on the rainwater outlet number corresponding to the drainage dynamic time series information, obtaining rainfall monitoring information of the rain gauge station within a preset range; According to the rainwater outlet number, the meteorological data of the area is monitored and processed to obtain local meteorological monitoring information; By using the rainfall monitoring data and the local meteorological monitoring information, the drainage dynamic time series information is judged to be abnormally drained, and the disorderly drainage alarm information is obtained, which specifically includes: Extracting the rainfall monitoring data and the local meteorological monitoring information based on the time node information in the currently identified drainage dynamic time series information and the rainwater outlet number; If the rainfall monitoring data indicates that there is rainfall data, and the local meteorological monitoring information indicates that there is local rainfall information, the drainage dynamic time series information is determined to be normal rainfall drainage information; Otherwise, the drainage dynamic time series information is determined as abnormal rainfall drainage information; Feeding back the abnormal rainfall drainage information to the visual AI analysis platform, and marking the drainage dynamic time series information as the disorderly drainage alarm information; The illegal drainage alarm information is classified into events to obtain alarm events.

2. The method for automatically monitoring the disorderly discharge of rainwater outlets according to claim 1 is characterized in that: According to the camera pre-installed at the rainwater outlet, real-time video stream data of the rainwater outlet is collected, specifically including: Based on the geographical location information of the rainwater outlet, modeling the terrain trend of the rainwater outlet is performed to obtain a rainwater outlet terrain model; According to the rainwater outlet terrain model, the rainwater flow trend is simulated and analyzed to obtain rainwater flow trajectory information; Through the rainwater flow trajectory information and the geographical location information, the wide-angle range of the camera is overlapped and covered so that the wide-angle range can fully cover the rainwater flow trajectory information and the location information, and the camera installation location information is determined; Pre-installing the camera based on the camera installation position information; Based on the geographical location information and current time sequence information of the rainwater outlet, real-time video stream data of the rainwater outlet is collected through the camera; wherein the real-time video stream data includes: outlet water flow position information, outlet geographical location information, current time node and water flow dynamic change information.

3. The method for automatically monitoring the disorderly discharge of rainwater outlets according to claim 1 is characterized in that: Automatically identify and process drainage on real-time video stream data to determine drainage dynamic timing information, including: The real-time video stream data is accessed and processed with a preset visual AI analysis platform; Through the visual AI analysis platform, the real-time video stream data is subjected to video frame extraction processing to obtain a number of key video frame images; wherein the key video frame images are video frames extracted within the same cycle time; Performing sequential comparison processing on a plurality of the key video frame images to identify the changed video frame images; Performing regional pixel recognition processing on the change video frame image related to drainage characteristics to obtain a drainage dynamic video frame image; Extracting the time node information and rainwater outlet label corresponding to the drainage dynamic video frame image; Based on the time node information and the rainwater outlet number, the drainage dynamic timing information is generated, and the drainage dynamic timing information is stored in the database of the visual AI analysis platform.

4. The method for automatically monitoring the disorderly discharge of rainwater outlets according to claim 1 is characterized in that: Based on the rainwater outlet number corresponding to the drainage dynamic time series information, obtaining the rainfall monitoring information of the rain gauge station within the preset range specifically includes: Based on a preset time interval, performing information generation judgment on the drainage dynamic time series information; If the drainage dynamic time sequence information is detected, the corresponding rainwater outlet number is extracted; According to the geographical location information of the rainwater outlet corresponding to the rainwater outlet number, a range selection process of the center point of the geographical area within the preset range is performed through the GIS map to obtain a local geographical location area; Determine the shortest distance between the rain gauge station in the local geographical location area and the rain outlet corresponding to the rain outlet number to determine the adjacent rain gauge station; The rainfall monitoring information monitored in the adjacent rain gauge station is extracted, and the rainfall monitoring information is located at the geographical location where the rainwater outlet number is located.

5. The method for automatically monitoring the disorderly discharge of rainwater outlets according to claim 1 is characterized in that: According to the rainwater outlet number, the meteorological data of the area is monitored and processed to obtain local meteorological monitoring information, which specifically includes: According to the geographical location information of the rainwater outlet corresponding to the rainwater outlet number, obtaining the meteorological data of the area; Based on the time node information in the drainage dynamic time series information, the meteorological data is queried and processed in the local area and range time to obtain the local meteorological monitoring information.

6. The method for automatically monitoring the disorderly discharge of rainwater outlets according to claim 1 is characterized in that: The illegal drainage alarm information is classified into events to obtain alarm events, which specifically include: The cycle time for identifying the dynamic timing information of drainage in the visual AI analysis platform is configured to obtain the alarm interval time; According to the alarm interval, several pieces of the disorderly drainage alarm information in the same cycle time are classified as the same event to obtain the alarm event, and the several pieces of disorderly drainage alarm information are used as supporting display information corresponding to the alarm event.

7. The method for automatically monitoring the disorderly discharge of rainwater outlets according to claim 1 is characterized in that: After classifying the illegal drainage alarm information into events and obtaining alarm events, the method further includes: Obtaining the alarm geographical location information of the illegal drainage alarm information in the alarm event; Based on the alarm geographical location information, the nearest geographical distance query is performed on the location of the patrol staff to determine the optimal patrol staff so that the optimal patrol staff can complete the handling of the alarm event.

8. An automatic monitoring device for rainwater discharge disorder, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, so that the at least one processor can execute the method for automatically monitoring disorderly discharge of rainwater outlets according to any one of claims 1-7.

9. A non-volatile computer storage medium, characterized in that: The storage medium is a non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium stores at least one program, each of which includes instructions, and when the instructions are executed by the terminal, the terminal executes the method for automatically monitoring the disorderly discharge of rainwater outlets according to any one of claims 1-7.

Images