City appearance environment early warning method and system based on AI intelligent garbage identification

Abstract

The invention discloses a city appearance environment early warning method and system based on AI intelligent garbage identification, and relates to the technical field of artificial intelligence and garbage classification technologies. The method comprises the steps that firstly, garbage classification throwing stations are set; step 2, acquiring and processing image data; step 3, carrying out image frame selection and tracking; 4, setting a threshold value and generating prompt information; 5, scheduling the garbage trucks, connecting the garbage trucks in series according to the uploaded alarm stations, and designing a route; by monitoring the state of the garbage throwing station in real time, the system can timely find the situation that the number of the garbage cans reaches the standard, and automatically generate early warning information, so that an environmental sanitation management department can timely dispatch garbage trucks to carry out clearing and transportation, and environmental pollution and resource waste caused by long-time garbage accumulation are avoided; the dynamic adjustment function of the system ensures that the driving route of the garbage truck can be rapidly updated when the actual situation changes, for example, early warning is newly added, and the garbage treatment efficiency and the response speed are further improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of artificial intelligence and garbage classification, and in particular to a city appearance and environment early warning method and system based on AI intelligent garbage identification. Background Art

[0002] With the acceleration of urbanization and the increase in population density, the amount of urban garbage generated has increased dramatically, bringing huge challenges to urban environment management. Traditional garbage disposal methods often rely on manual inspections and regular cleaning. This method is not only inefficient, but also difficult to respond to garbage accumulation problems in real time, resulting in frequent problems such as overflowing garbage bins, environmental pollution and waste of resources. Therefore, how to efficiently and accurately monitor and manage urban garbage has become a social problem that continues to be solved. In recent years, the development of artificial intelligence technology has provided new possibilities for intelligent garbage identification and management, but the existing artificial intelligence technology solutions still have some limitations, such as noise interference and color distortion in the image acquisition process, which affect the accuracy of identification; lack of effective threshold setting mechanism to distinguish the urgency of different types of garbage; and insufficient optimization of route planning in garbage truck scheduling. Therefore, we propose an urban environment early warning method and system based on AI intelligent garbage identification. Summary of the invention

[0003] The purpose of the present invention is to provide a city environment early warning method and system based on AI intelligent garbage identification. By real-time monitoring the status of garbage delivery stations, the system can promptly discover the situation where the garbage bins are overflowing when the quantity standard is reached, and automatically generate early warning information, which helps the sanitation management department to dispatch garbage trucks for transportation in time, avoid environmental pollution and waste of resources caused by long-term accumulation of garbage, and solve the problem that traditional garbage disposal methods often rely on manual inspections and regular cleaning. This method is not only inefficient, but also difficult to respond to the problem of garbage accumulation in real time, resulting in overflowing garbage bins, environmental pollution and waste of resources.

[0004] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0005] The present invention is a city appearance and environment early warning method and system based on AI intelligent garbage identification, comprising the following steps:

[0006] Step 1: Set up a garbage classification delivery station;

[0007] Step 2: Image data acquisition and processing;

[0008] Step 3: Image selection and tracking;

[0009] Step 4: Set the threshold and generate prompt information;

[0010] Step 5: Dispatch garbage trucks and connect them according to the uploaded alarm sites to design routes.

[0011] Furthermore, in the described method and system for early warning of urban environment based on AI intelligent garbage identification, in step one, site selection planning: garbage disposal stations are rationally arranged in key urban areas such as commercial areas, residential areas and parks, and blind spots for garbage disposal are avoided through scientific site selection analysis, so that each area can easily find the nearest garbage disposal point, ensuring comprehensive coverage and convenience for residents to dispose of garbage; with the development of the city and population changes, the amount of garbage generated will also change. When selecting and planning the site, a certain amount of expansion space and adjustment room should be reserved.

[0012] Facility configuration: High-definition cameras installed around the site can monitor garbage disposal in real time, including residents' disposal behavior, overflowing status of garbage bins, and sanitation conditions of the surrounding environment; these cameras should have night vision functions and waterproof and dustproof properties to ensure that they can work normally under different weather and light conditions; according to different monitoring needs, various types of sensors can be installed, such as weight sensors for monitoring weight changes of garbage in garbage bins; gas sensors for monitoring the concentration of harmful gases generated by garbage. These sensors can collect data in real time and upload it to cloud servers for processing and analysis; in order to realize remote transmission and processing of data, each garbage disposal station needs to be equipped with stable network transmission equipment, which can be Wi-Fi, 4G / 5G modules or other wireless communication equipment.

[0013] Classification setting: According to local garbage classification standards, four types of garbage bins are set up for recyclables, hazardous waste, wet garbage (kitchen waste) and dry garbage (other garbage). Each type of garbage bin should have sufficient capacity to meet daily needs and be made of materials that are easy to clean and maintain. The recyclables bin is blue, the hazardous waste bin is red, the wet garbage bin is green, and the dry garbage bin is gray. To ensure the normal use and neat appearance of the classified garbage bins, the garbage bins need to be cleaned, disinfected and damaged parts replaced regularly. At the same time, damaged or lost garbage bins should be replenished and replaced in time.

[0014] Smart prompts: Guide residents to sort and dispose of garbage through electronic screens or voice prompts. Set up electronic screens at the entrance of garbage disposal stations or in conspicuous locations to play garbage sorting guides, promotional videos or animation content in a loop. The electronic screens should have the characteristics of high-definition display, waterproof and dustproof, and durability. By installing voice prompt equipment and using infrared sensors, garbage sorting prompts or slogans will be automatically played when residents approach the garbage cans. The voice prompts should be concise, clear and easy to understand, and should be available in multiple languages ​​to meet the needs of different residents. In addition, the volume adjustment function can be set as needed to adapt to different environmental noise levels.

[0015] Furthermore, in the described method and system for early warning of urban environment based on AI intelligent garbage identification, in step 2, real-time collection: in order to ensure that the image data of the garbage disposal station area can be captured in a timely and accurate manner, by utilizing high-definition cameras installed in the site, these cameras have high resolution and wide-angle field of view, and can monitor the disposal station area uninterruptedly around the clock. Whether it is day or night, whether it is sunny or rainy, the cameras can operate stably and collect image data in real time.

[0016] De-noising: During the image acquisition process, due to the influence of uncontrollable factors such as ambient light changes and weather factors, the collected images often have certain noise. In order to reduce the impact of these noises on subsequent recognition results, we perform denoising on the collected images; by using the following denoising formula;

[0017]

[0018] Among them, G(x,y) is the pixel value after filtering, I(x,y) is the pixel value of the original image, and H(i,j) is the Gaussian kernel function;

[0019] The above formula can effectively remove noise points in the image and make the image clearer.

[0020] Color correction: In order to ensure that the color information in the image can truly reflect the actual scene, by adjusting the color balance of the image, we can make the colors in the image more vivid, natural, and closer to the real scene.

[0021] Furthermore, in the described urban environment early warning method and system based on AI intelligent garbage identification, in step three, area selection: using the AI ​​algorithm, first select a specific area, and place the full trash can in this area. After the trash can is placed in the area, the system will automatically identify the number of trash cans in the current area. Through precise area division, it can ensure that the status of each trash can is independently monitored and recorded.

[0022] Target detection: Based on the camera installed at the delivery station, the trash can target is automatically detected in the framed image through image acquisition. The image acquisition data is obtained by collecting a large number of trash can image samples, including trash can pictures of various categories and colors, and manually annotating them. Then, these annotated samples are used to train the AI. The AI ​​parameters are optimized through repeated iterations until the AI ​​reaches a satisfactory accuracy rate and can quickly and accurately identify trash cans of different types and sizes. The number of trash cans in this area is limited. When trash cans that exceed the area are placed, the excess information of the overflowing trash cans is uploaded.

[0023] Furthermore, in the method and system for early warning of urban environment based on AI intelligent garbage identification, in step four; threshold setting: reasonable early warning thresholds are set according to factors such as garbage type, quantity, and accumulation speed. The setting of these thresholds is based on historical data analysis, on-site investigations, and expert advice to ensure that the actual situation of garbage accumulation can be accurately reflected. For example, for perishable kitchen waste, a lower threshold may need to be set to prevent odor and hygiene problems, and recycling needs to be given priority. For recyclables, since there will be no problem of deterioration, they do not need to be given priority for recycling in the subsequent garbage truck scheduling, and a higher threshold can be set to make full use of storage space.

[0024] Real-time monitoring: Continuously monitor the status of garbage targets. When the warning threshold is reached or exceeded, the warning mechanism is triggered. Through the high-definition cameras installed in the delivery station and AI model image processing technology, the system can monitor the number of garbage bins 24 / 7. Once the system finds that the number of full garbage bins in the selected area reaches the predetermined number, the system will immediately start the warning process and report to the background to ensure timely response and measures.

[0025] Generation of early warning information: Generate early warning information containing detailed information on garbage type, quantity, location, and time. This information will be pushed to managers via email, SMS or mobile applications, allowing them to understand the specific situation and make decisions at the first time. At the same time, these data will also be recorded in the system for subsequent analysis and optimization of operational management strategies.

[0026] Multi-level warning: According to the severity of garbage accumulation, different levels of warnings (such as yellow, orange, and red) are set so that the management department can take corresponding measures. The yellow warning means that the number of recyclable garbage bins has reached and needs attention and preparation for cleaning; the orange warning means that the dry garbage bin has reached the critical point and should be arranged for removal as soon as possible; the red warning indicates that the non-recyclable garbage bin has reached the critical point and should be arranged for removal as the top priority; in this way, the management department can reasonably allocate resources according to different warning levels and give priority to the most urgent situations.

[0027] Furthermore, in the described urban environment early warning method and system based on AI intelligent garbage identification, in step five; receiving early warnings: the sanitation management department receives early warning information from each delivery station in real time. This information includes detailed data such as the type, quantity, location, and time of garbage, providing a basis for subsequent scheduling and transportation work.

[0028] Route planning: After receiving the warning message, the system will comprehensively consider the location of the garbage station, traffic conditions and the capacity of the garbage truck, and use algorithms to optimize the driving route of the garbage truck. This includes calculating the shortest path, avoiding congested sections, and reasonably arranging the order of loading and unloading points to ensure that the garbage truck can complete the collection task efficiently.

[0029] Dynamic adjustment: Since the actual situation may change (such as new warnings, changes in road conditions, etc.), the system has a dynamic adjustment function. When there is a new warning or road condition changes, the system will immediately recalculate and update the garbage truck's dispatch plan and driving route to ensure that the garbage truck can respond in time and complete the task.

[0030] The present invention has the following beneficial effects:

[0031] 1. By real-time monitoring of the status of garbage delivery stations, the present invention can timely discover the overflow of garbage bins that have reached the quantity standard and automatically generate early warning information, which helps the sanitation management department to dispatch garbage trucks for timely removal and avoid environmental pollution and waste of resources caused by long-term accumulation of garbage. At the same time, the dynamic adjustment function of the system ensures that when the actual situation changes, such as new warnings or changes in road conditions, the driving route of the garbage truck can be quickly updated, further improving the efficiency and response speed of garbage disposal and improving the efficiency of garbage cleaning.

[0032] 2. The city appearance and environment early warning method and system based on AI intelligent garbage identification of the present invention can accurately distinguish different types of garbage and set reasonable early warning thresholds according to their accumulation speed and quantity. This allows the sanitation management department to reasonably allocate resources according to the actual situation of the garbage, such as giving priority to cleaning perishable kitchen waste to reduce odor and hygiene problems, and setting higher thresholds for recyclables to make full use of storage space. This refined management not only improves the utilization efficiency of resources, but also reduces management costs.

[0033] 3. By setting up electronic screens and voice prompt devices at garbage disposal stations, the present invention can guide residents to correctly classify and dispose of garbage, and provide garbage classification guides, promotional videos and other content. This not only helps to enhance residents' environmental awareness and garbage classification capabilities, but also improves the living environment and reduces pollution and inconvenience caused by littering. At the same time, the system's real-time monitoring and early warning functions also enable residents to have a clearer understanding of garbage disposal, enhancing their trust and satisfaction with urban environmental sanitation management.

[0034] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0036] Figure 1The present invention is a flowchart of a city appearance and environment early warning method and system based on AI intelligent garbage identification. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0038] See also Figure 1 As shown, the present invention is a city appearance and environment early warning method and system based on AI intelligent garbage identification, comprising the following steps:

[0039] Step 1: Set up a garbage classification delivery station;

[0040] Step 2: Image data acquisition and processing;

[0041] Step 3: Image selection and tracking;

[0042] Step 4: Set the threshold and generate prompt information;

[0043] Step 5: Dispatch garbage trucks and connect them according to the uploaded alarm sites to design routes.

[0044] A city appearance and environment early warning method and system based on AI intelligent garbage identification, in step one, site planning: reasonably arrange garbage disposal stations in key urban areas such as commercial areas, residential areas and parks, avoid blind spots for garbage disposal through scientific site selection analysis, so that each area can easily find the nearest garbage disposal point, ensuring comprehensive coverage and convenience for residents to dispose of garbage; with urban development and population changes, the amount of garbage generated will also change. When selecting and planning the site, a certain amount of expansion space and adjustment room should be reserved.

[0045] Facility configuration: High-definition cameras installed around the site can monitor garbage disposal in real time, including residents' disposal behavior, overflowing status of garbage bins, and sanitation conditions of the surrounding environment; these cameras should have night vision functions and waterproof and dustproof properties to ensure that they can work normally under different weather and light conditions; according to different monitoring needs, various types of sensors can be installed, such as weight sensors for monitoring weight changes of garbage in garbage bins; gas sensors for monitoring the concentration of harmful gases generated by garbage. These sensors can collect data in real time and upload it to cloud servers for processing and analysis; in order to realize remote transmission and processing of data, each garbage disposal station needs to be equipped with stable network transmission equipment, which can be Wi-Fi, 4G / 5G modules or other wireless communication equipment.

[0046] Classification setting: According to local garbage classification standards, four types of garbage bins are set up for recyclables, hazardous waste, wet garbage (kitchen waste) and dry garbage (other garbage). Each type of garbage bin should have sufficient capacity to meet daily needs and be made of materials that are easy to clean and maintain. The recyclables bin is blue, the hazardous waste bin is red, the wet garbage bin is green, and the dry garbage bin is gray. To ensure the normal use and neat appearance of the classified garbage bins, the garbage bins need to be cleaned, disinfected and damaged parts replaced regularly. At the same time, damaged or lost garbage bins should be replenished and replaced in time.

[0047] Smart prompts: Guide residents to sort and dispose of garbage through electronic screens or voice prompts. Set up electronic screens at the entrance of garbage disposal stations or in conspicuous locations to play garbage sorting guides, promotional videos or animation content in a loop. The electronic screens should have the characteristics of high-definition display, waterproof and dustproof, and durability. By installing voice prompt equipment and using infrared sensors, garbage sorting prompts or slogans will be automatically played when residents approach the garbage cans. The voice prompts should be concise, clear and easy to understand, and should be available in multiple languages ​​to meet the needs of different residents. In addition, the volume adjustment function can be set as needed to adapt to different environmental noise levels.

[0048] A city environment early warning method and system based on AI intelligent garbage identification. In step 2, real-time collection: In order to ensure that the image data of the garbage disposal station area can be captured in a timely and accurate manner, high-definition cameras installed in the site are used. These cameras have high resolution and wide-angle field of view, and can monitor the disposal station area uninterruptedly around the clock. Whether it is day or night, whether it is sunny or rainy, the cameras can operate stably and collect image data in real time.

[0049] De-noising: During the image acquisition process, due to the influence of uncontrollable factors such as ambient light changes and weather factors, the collected images often have certain noise. In order to reduce the impact of these noises on subsequent recognition results, we perform denoising on the collected images; by using the following denoising formula;

[0050]

[0051] Among them, G(x, y) is the pixel value after filtering, I(x, y) is the pixel value of the original image, and H(i, j) is the Gaussian kernel function;

[0052] The above formula can effectively remove noise points in the image and make the image clearer.

[0053] Color correction: In order to ensure that the color information in the image can truly reflect the actual scene, by adjusting the color balance of the image, we can make the colors in the image more vivid, natural, and closer to the real scene.

[0054] A city environment early warning method and system based on AI intelligent garbage identification. In step three, area selection: using AI algorithm, first select a specific area and place the full garbage can in this area. After the garbage can is placed in the area, the system will automatically identify the number of garbage cans in the current area. Through precise area division, it can ensure that the status of each garbage can is independently monitored and recorded.

[0055] Target detection: Based on the camera installed at the delivery station, the trash can target is automatically detected in the framed image through image acquisition. The image acquisition data is obtained by collecting a large number of trash can image samples, including trash can pictures of various categories and colors, and manually annotating them. Then, these annotated samples are used to train the AI. The AI ​​parameters are optimized through repeated iterations until the AI ​​reaches a satisfactory accuracy rate and can quickly and accurately identify trash cans of different types and sizes. The number of trash cans in this area is limited. When trash cans that exceed the area are placed, the excess information of the overflowing trash cans is uploaded.

[0056] A city appearance and environment early warning method and system based on AI intelligent garbage identification, in step 4; threshold setting: according to the type, quantity and accumulation speed of garbage, reasonable early warning thresholds are set. The setting of these thresholds is based on historical data analysis, on-site investigation and expert advice to ensure that the actual situation of garbage accumulation can be accurately reflected. For example, for perishable kitchen waste, a lower threshold may need to be set to prevent odor and hygiene problems, and recycling needs to be given priority; for recyclables, since there will be no problem of deterioration, they do not need to be given priority in subsequent garbage truck scheduling, and higher thresholds can be set to make full use of storage space.

[0057] Real-time monitoring: Continuously monitor the status of garbage targets. When the warning threshold is reached or exceeded, the warning mechanism is triggered. Through the high-definition cameras installed in the delivery station and AI model image processing technology, the system can monitor the number of garbage bins 24 / 7. Once the system finds that the number of full garbage bins in the selected area reaches the predetermined number, the system will immediately start the warning process and report to the background to ensure timely response and measures.

[0058] Generation of early warning information: Generate early warning information containing detailed information on garbage type, quantity, location, and time. This information will be pushed to managers via email, SMS or mobile applications, allowing them to understand the specific situation and make decisions at the first time. At the same time, these data will also be recorded in the system for subsequent analysis and optimization of operational management strategies.

[0059] Multi-level warning: According to the severity of garbage accumulation, different levels of warnings (such as yellow, orange, and red) are set so that the management department can take corresponding measures. The yellow warning means that the number of recyclable garbage bins has reached and needs attention and preparation for cleaning; the orange warning means that the dry garbage bin has reached the critical point and should be arranged for removal as soon as possible; the red warning indicates that the non-recyclable garbage bin has reached the critical point and should be arranged for removal as the top priority; in this way, the management department can reasonably allocate resources according to different warning levels and give priority to the most urgent situations.

[0060] A city environment early warning method and system based on AI intelligent garbage identification, step five; receiving early warning: the sanitation management department receives early warning information from each delivery station in real time. This information includes detailed data such as garbage type, quantity, location, and time, providing a basis for subsequent scheduling and transportation work.

[0061] Route planning: After receiving the warning message, the system will comprehensively consider the location of the garbage station, traffic conditions and the capacity of the garbage truck, and use algorithms to optimize the driving route of the garbage truck. This includes calculating the shortest path, avoiding congested sections, and reasonably arranging the order of loading and unloading points to ensure that the garbage truck can complete the collection task efficiently.

[0062] Dynamic adjustment: Since the actual situation may change (such as new warnings, changes in road conditions, etc.), the system has a dynamic adjustment function. When there is a new warning or road condition changes, the system will immediately recalculate and update the garbage truck's dispatch plan and driving route to ensure that the garbage truck can respond in time and complete the task.

[0063] In the description of this specification, the description of reference terms such as "one embodiment", "example", "specific example" and the like means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the contents of this specification. This specification selects and describes these embodiments in detail in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A city appearance and environment early warning method and system based on AI intelligent garbage identification, characterized by: The steps include: Step 1: Set up a garbage classification delivery station; Step 2: Image data acquisition and processing; Step 3: Image selection and tracking; Step 4: Set the threshold and generate prompt information; Step 5: Dispatch garbage trucks and connect them according to the uploaded alarm sites to design routes.

2. According to claim 1, a city appearance and environment early warning method and system based on AI intelligent garbage identification is characterized in that: In step one, site selection and planning: rationally arrange garbage disposal stations in key urban areas such as commercial areas, residential areas and parks. Through scientific site selection analysis, avoid blind spots in garbage disposal, so that each area can easily find the nearest garbage disposal point, ensuring comprehensive coverage and convenience for residents. With the development of the city and population changes, the amount of garbage generated will also change. When selecting sites for planning, a certain amount of expansion space and adjustment room should be reserved. Facilities: HD cameras installed around the site can monitor garbage disposal in real time, including residents’ disposal behavior, overflow status of garbage bins, and surrounding environmental sanitation conditions; These cameras should have night vision capabilities and be waterproof and dustproof to ensure that they can work normally under different weather and lighting conditions; according to different monitoring needs, various types of sensors can be installed, such as weight sensors used to monitor the weight changes of garbage in the trash can; gas sensors are used to monitor the concentration of harmful gases generated by garbage. These sensors can collect data in real time and upload it to the cloud server for processing and analysis; in order to realize remote transmission and processing of data, each garbage disposal station needs to be equipped with stable network transmission equipment, which can be Wi-Fi, 4G / 5G modules or other wireless communication equipment. Classification setting: According to local garbage classification standards, four types of garbage bins are set up for recyclables, hazardous waste, wet garbage (kitchen waste) and dry garbage (other garbage). Each type of garbage bin should have sufficient capacity to meet daily needs and be made of materials that are easy to clean and maintain. The recyclables bin is blue, the hazardous waste bin is red, the wet garbage bin is green, and the dry garbage bin is gray. To ensure the normal use and neat appearance of the classified garbage bins, the garbage bins need to be cleaned, disinfected and damaged parts replaced regularly. At the same time, damaged or lost garbage bins should be replenished and replaced in time. Smart prompts: Guide residents to sort and dispose of garbage through electronic screens or voice prompts. Set up electronic screens at the entrance of garbage disposal stations or in conspicuous locations to play garbage sorting guides, promotional videos or animation content in a loop. The electronic screens should have the characteristics of high-definition display, waterproof and dustproof, and durability. By installing voice prompt equipment and using infrared sensors, garbage sorting prompts or slogans will be automatically played when residents approach the garbage cans. The voice prompts should be concise, clear and easy to understand, and should be available in multiple languages ​​to meet the needs of different residents. In addition, the volume adjustment function can be set as needed to adapt to different environmental noise levels.

3. According to claim 1, a city appearance and environment early warning method and system based on AI intelligent garbage identification is characterized in that: In step 2, real-time data collection: In order to ensure that the image data of the garbage disposal station area can be captured in a timely and accurate manner, high-definition cameras installed in the site are used. These cameras have high resolution and wide-angle field of view, and can monitor the disposal station area uninterruptedly around the clock. Whether it is day or night, whether it is sunny or rainy, the cameras can operate stably and collect image data in real time. De-noising: During the image acquisition process, due to the influence of uncontrollable factors such as ambient light changes and weather factors, the collected images often contain certain noise. In order to reduce the impact of these noises on subsequent recognition results, we perform denoising on the collected images; By adopting the following denoising formula; Among them, G(x,y) is the pixel value after filtering, I(x,y) is the pixel value of the original image, and H(i,j) is the Gaussian kernel function; The above formula can effectively remove noise points in the image and make the image clearer. Color correction: In order to ensure that the color information in the image can truly reflect the actual scene, by adjusting the color balance of the image, we can make the colors in the image more vivid, natural, and closer to the real scene.

4. The city appearance and environment early warning method and system based on AI intelligent garbage identification according to claim 1 is characterized in that: In step three, area selection: use the AI ​​algorithm to first select a specific area and place the full trash can in this area. After the trash can is placed in the area, the system will automatically identify the number of trash cans in the current area. Through precise area division, it can ensure that the status of each trash can is independently monitored and recorded. Target detection: Based on the camera installed at the delivery station, the trash can target is automatically detected in the framed image through image acquisition. The image acquisition data is obtained by collecting a large number of trash can image samples, including trash can pictures of various categories and colors, and manually annotating them. Then, these annotated samples are used to train the AI. The AI ​​parameters are optimized through repeated iterations until the AI ​​reaches a satisfactory accuracy rate and can quickly and accurately identify trash cans of different types and sizes. The number of trash cans in this area is limited. When trash cans that exceed the area are placed, the excess information of the overflowing trash cans is uploaded.

5. The city appearance and environment early warning method and system based on AI intelligent garbage identification according to claim 1 is characterized in that: In step 4; threshold setting: according to the type, quantity and accumulation speed of garbage, set reasonable warning thresholds. These thresholds are set based on historical data analysis, on-site surveys and expert advice to ensure that they can accurately reflect the actual situation of garbage accumulation. For example, for perishable kitchen waste, a lower threshold may need to be set to prevent odor and hygiene problems, and recycling needs to be given priority; for recyclables, since there will be no problem of deterioration, they do not need to be given priority in the subsequent garbage truck dispatch, and a higher threshold can be set to make full use of storage space. Real-time monitoring: Continuously monitor the status of garbage targets. When the warning threshold is reached or exceeded, the warning mechanism is triggered. Through the high-definition cameras installed in the delivery station and AI model image processing technology, the system can monitor the number of garbage bins 24 / 7. Once the system finds that the number of full garbage bins in the selected area reaches the predetermined number, the system will immediately start the warning process and report to the background to ensure timely response and measures. Generation of early warning information: Generate early warning information containing detailed information on garbage type, quantity, location, and time. This information will be pushed to managers via email, SMS or mobile applications, allowing them to understand the specific situation and make decisions at the first time. At the same time, these data will also be recorded in the system for subsequent analysis and optimization of operational management strategies. Multi-level warning: According to the severity of garbage accumulation, different levels of warnings (such as yellow, orange, and red) are set so that the management department can take corresponding measures. The yellow warning means that the number of recyclable garbage bins has reached and needs attention and preparation for cleaning; the orange warning means that the dry garbage bin has reached the critical point and should be arranged for removal as soon as possible; the red warning indicates that the non-recyclable garbage bin has reached the critical point and should be arranged for removal as the top priority; in this way, the management department can reasonably allocate resources according to different warning levels and give priority to the most urgent situations.

6. The city appearance and environment early warning method and system based on AI intelligent garbage identification according to claim 1 is characterized in that: Step 5: Receive early warnings: The sanitation management department receives early warning information from each garbage disposal station in real time. This information includes detailed data such as the type, quantity, location, and time of garbage, providing a basis for subsequent scheduling and transportation work. Route planning: After receiving the warning message, the system will comprehensively consider the location of the garbage station, traffic conditions and the capacity of the garbage truck, and use algorithms to optimize the driving route of the garbage truck. This includes calculating the shortest path, avoiding congested sections, and reasonably arranging the order of loading and unloading points to ensure that the garbage truck can complete the collection task efficiently. Dynamic adjustment: Since the actual situation may change (such as new warnings, changes in road conditions, etc.), the system has a dynamic adjustment function. When there is a new warning or road condition changes, the system will immediately recalculate and update the garbage truck's dispatch plan and driving route to ensure that the garbage truck can respond in time and complete the task.

Images