Intelligent AI muck truck management method and system and medium

Abstract

The invention discloses an intelligent AI slag car management method and system, and a medium. The method comprises the following steps: collecting image data of slag cars on a preset route of the slag cars through an AI camera; preprocessing the image data of the muck truck, calculating the vehicle type and license plate information of the muck truck based on the preprocessed image data, and calculating the driving duration of the muck truck; judging whether the line is overtime or not according to the driving duration of the muck truck and a preset duration; and if the line is overtime, judging that the muck truck does not run according to the preset line, and notifying the model and license plate information of the muck truck to a management terminal to give an alarm. No equipment needs to be installed on the transport vehicle for AI route planning, an enterprise and a law enforcement unit can be automatically warned when illegal operation behaviors are found, a transport duration alarm linkage short message is set, the transport vehicle is prevented from toppling disorderly in an urban area, the management cost of the muck vehicle is reduced, and the management efficiency and the transport safety of the muck vehicle are improved.

Description

Technical Field

[0001] This invention relates to the field of construction waste truck management technology, and in particular to a smart AI construction waste truck management method, system and medium. Background Technology

[0002] In recent years, with the rapid development of urban economy and society and the acceleration of urbanization, the number of heavy-duty trucks carrying construction waste, known as "dump trucks," has increased dramatically. This surge in the number of dump trucks has not only damaged the urban environment but also led to a high incidence of traffic violations and frequent fatal accidents. As is well known, the dump truck problem has always been a key and pressing issue in urban management. Although relevant government departments have been actively taking measures to regulate dump trucks, the results have been less than satisfactory.

[0003] Currently, the management of construction waste trucks is carried out through onboard equipment. However, with fewer construction sites operating now, the vehicles transporting construction waste are not fixed. Repeatedly installing onboard equipment on each vehicle for control is not only costly and prone to equipment failure, but also seriously affects the safety and efficiency of transportation. Summary of the Invention

[0004] The main objective of this invention is to propose a smart AI-powered method, system, and medium for managing construction waste trucks, aiming to reduce the management cost of construction waste trucks and improve management efficiency and transportation safety.

[0005] To achieve the above objectives, the present invention provides a smart AI dump truck management method. The method is applied to a smart AI dump truck management system, which includes AI cameras installed on preset routes of the dump trucks. The method includes the following steps:

[0006] Step S10: Collect image data of dump trucks on the preset route of the dump trucks using the AI ​​camera;

[0007] Step S20: Preprocess the image data of the dump truck, calculate the vehicle type and license plate information of the dump truck based on the preprocessed image data, and calculate the driving time of the dump truck.

[0008] Step S30: Determine whether the route has exceeded the time limit based on the travel time of the dump truck and the preset time limit.

[0009] Step S40: If the route times out, it is determined that the dump truck is not traveling along the preset route, and the vehicle type and license plate information of the dump truck are notified to the management terminal for alarm.

[0010] A further technical solution of the present invention is that step S20, the step of preprocessing the image data of the dump truck, includes:

[0011] Step S201: Perform grayscale conversion and noise reduction processing on the image data;

[0012] The step of performing grayscale processing on the image data includes:

[0013] Each pixel in the image data is converted from the RGB color space to the grayscale space, using the following weighted average formula:

[0014] Gray=0.299×R+0.587×G+0.114×B;

[0015] Where R, G, and B are the red, green, and blue components of the pixel, respectively, and Gray is the grayscale value;

[0016] The step of denoising the image data includes:

[0017] For each pixel in the image, the average value of the surrounding pixels is taken as the new value for that pixel.

[0018] A further technical solution of the present invention is that the step of calculating the license plate information of the dump truck based on the preprocessed image data in step S20 includes:

[0019] Based on template matching, feature extraction, and classification, the license plate characters of the dump truck are identified to obtain the license plate information of the dump truck.

[0020] A further technical solution of the present invention is that the step of obtaining the license plate information of the dump truck by recognizing the license plate characters of the dump truck based on template matching, feature extraction and classification includes:

[0021] The similarity between the character image to be identified and the template character image is calculated using the normalized cross-correlation algorithm formula, where the normalized cross-correlation algorithm formula is:

[0022]

[0023] Where R(x,y) represents the similarity. These are the average values ​​of I and T, respectively;

[0024] The image is divided into small cell units, and the gradient direction histogram of each cell unit is calculated. These histograms are then combined into a feature vector. For a pixel (x, y), its gradient magnitude is:

[0025]

[0026] gradient direction

[0027] A further technical solution of the present invention is that the step of calculating the vehicle type information of the dump truck based on the preprocessed image data in S20 includes:

[0028] The vehicle type information of the dump truck is calculated based on feature extraction methods and deep learning methods;

[0029] The steps for calculating the vehicle type information of the dump truck based on feature extraction and deep learning methods include:

[0030] Based on scale-invariant feature transformation, keypoints are detected in different scale spaces, and the orientation and descriptor of the keypoints are calculated: for a pixel x in the image, its response in the scale space (L, X, O) is obtained by convolving the image I(x) with a Gaussian kernel G(X, O), i.e., L(x,σ)=G(x,σ)*I(z), where

[0031] The gradient direction histogram of a local region of the image is calculated as a feature. When calculating the gradient direction histogram, the gradient magnitude and direction are calculated by the difference between the image pixels. Then, the image is divided into multiple cells, and the gradient direction histogram in each cell is counted. Finally, the histograms of all cells are concatenated to form the gradient direction histogram feature vector.

[0032] In the convolutional layer of a convolutional network, the feature map F is obtained by performing a convolution operation between the input image I and the convolution kernel K, with the formula F(x,y)=∑ i ∑ j I(x+i,y+j)K(i,j).

[0033] A further technical solution of the present invention is that the method further includes:

[0034] The amount of construction waste is calculated based on the vehicle model information, and the fee is automatically deducted from the company to which the construction waste truck belongs, based on the license plate information.

[0035] A further technical solution of the present invention is that the system further includes an AI camera installed at the city exit, and the method further includes:

[0036] When the AI ​​camera set up at the city exit detects a dump truck, an alarm is triggered on the management terminal.

[0037] A further technical solution of the present invention is that, after step S40, it further includes:

[0038] Step S50: Based on the alarm information, link the violation assessment of the transport driver of the dump truck.

[0039] To achieve the above objectives, the present invention also proposes a smart AI dump truck management system, the system including AI cameras installed on the preset routes of dump trucks and at the city exits, as well as a memory, a processor, and a smart AI dump truck management program stored on the processor. The smart AI dump truck management program is executed by the processor to perform the steps of the method described above.

[0040] To achieve the above objectives, the present invention also proposes a computer-readable storage medium storing a smart AI dump truck management program, wherein the smart AI dump truck management program is executed by a processor to perform the steps of the method described above.

[0041] The beneficial effects of the intelligent AI-powered method, system, and medium for managing construction waste trucks in this invention are:

[0042] This invention, through the aforementioned technical solution, uses AI cameras to collect image data of dump trucks along a preset route; preprocesses the image data, calculates the truck model and license plate information based on the preprocessed image data, and calculates the truck's travel time; determines whether the route has exceeded the time limit based on the travel time; if the route exceeds the time limit, it is determined that the dump truck is not traveling according to the preset route, and the truck model and license plate information are notified to the management terminal for alarm. No equipment needs to be installed on the transport vehicles for AI route planning. It can automatically warn enterprises and law enforcement units when illegal calculation behavior is detected, and can set up SMS alerts linked to travel time alarms to prevent illegal dumping in urban areas, thereby reducing the management cost of dump trucks and improving management efficiency and transportation safety. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0044] Figure 1 This is a flowchart illustrating a preferred embodiment of the intelligent AI dump truck management method of the present invention;

[0045] Figure 2 This is a hardware architecture diagram of the intelligent AI dump truck management system of this invention.

[0046] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0047] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0048] This invention proposes a smart AI dump truck management method, which is applied to a smart AI dump truck management system. The system includes AI cameras installed on preset routes of the dump trucks.

[0049] The following section first describes the intelligent AI dump truck management system involved in the intelligent AI dump truck management method of the present invention.

[0050] The intelligent AI-powered construction waste truck management system includes AI cameras installed along preset routes and at city exits to identify truck types and license plates. The system also includes AI cameras at city exits that trigger an alarm when a truck is detected entering or leaving the city, notifying the corresponding driver and law enforcement agencies. Once a construction waste truck is linked to the system, the company can set up a prepaid account. Each truck can be linked to several construction sites for hauling earth, with automatic route planning, automatic payment deductions, and automatic site count tracking. When a truck's route exceeds the time limit, it will be linked to the driver's violation assessment. Furthermore, through this system, law enforcement inspectors can set daily inspection plans to check for illegal construction activities at construction sites at night.

[0051] This intelligent AI-powered construction waste truck management system automatically calculates the volume of construction waste at construction sites without requiring any AI route planning equipment on transport vehicles. It automatically alerts companies and law enforcement agencies when illegal calculations are detected, sets up SMS alerts for transport duration to prevent illegal dumping within urban areas, integrates a pre-payment system for companies to automatically deduct fees and calculate earthwork volume, and sets up out-of-town alerts to link with companies and law enforcement agencies to prevent vehicles from dumping construction waste outside the city. Adding or removing construction waste trucks is as simple as automatically adding and binding them to the transport sites on the platform. Previous construction waste truck management systems relied on onboard equipment. However, with fewer construction sites and less fixed transport vehicles, repeatedly installing onboard equipment for control on each vehicle led to frequent equipment malfunctions, severely impacting transport safety and efficiency. This intelligent AI-powered construction waste truck management system, strongly integrated with business operations, effectively saves significant labor costs, automatically charges fees, automatically maps data, and uses AI for route planning, reducing the cost of equipment installation on vehicles.

[0052] like Figure 1As shown, a preferred embodiment of the intelligent AI-powered muck truck management method of the present invention includes the following steps:

[0053] Step S10: Collect image data of dump trucks on the preset route using an AI camera.

[0054] In this embodiment, an AI camera is installed on the pre-set route for the dump truck. If the AI ​​camera does not capture the dump truck, or if it does capture the dump truck but subsequent calculations show that the truck's travel time exceeds the preset time, i.e., the route has exceeded the time limit, then it is determined that the dump truck may have violated the rules by not traveling along the preset route.

[0055] It should be noted that this intelligent AI dump truck management system can set up timeout warnings for vehicle transportation routes in the background. For example, if the time limit for the route from construction site A to dump site B is set to 30 minutes, and the dump truck departs from construction site A and is not detected entering dump site B after 30 minutes, or if the dump truck is detected but the time exceeds 30 minutes, it will be judged as a route timeout and an alarm will be triggered to remind the vehicle of the timeout.

[0056] Step S20: Preprocess the image data of the dump truck, calculate the vehicle type and license plate information of the dump truck based on the preprocessed image data, and calculate the driving time of the dump truck.

[0057] In this embodiment, the license plate information of the dump truck is bound to the intelligent AI dump truck management system and the corresponding enterprise. When the license plate information is identified, the corresponding enterprise information and vehicle driver information can be queried.

[0058] Step S30: Determine whether the route has exceeded the time limit based on the travel time of the dump truck and the preset time limit.

[0059] In step S40, if the route times out, it is determined that the dump truck is not traveling along the preset route, and the dump truck's model and license plate information are notified to the management terminal to issue an alarm.

[0060] In this embodiment, after calculating the travel time of the dump truck, the travel time is compared with a preset time. If the travel time exceeds the preset time, it is determined that the route has exceeded the time limit, indicating that the dump truck has not traveled along the preset route. At this time, the management terminal is notified to issue an alarm. The management terminal can be, for example, an enforcement terminal.

[0061] Specifically, in this embodiment, step S20, the step of preprocessing the image data of the dump truck, includes:

[0062] Step S201: Perform grayscale conversion and noise reduction on the image data.

[0063] The specific steps for converting image data to grayscale include:

[0064] The weighted average method used to convert each pixel in the image data from the RGB color space to the grayscale space is as follows:

[0065] Gray=0.299×R+0.587×G+0.114×B;

[0066] Where R, G, and B are the red, green, and blue components of a pixel, respectively, and the values ​​of R, G, and B range from (0, 255). Gray is the grayscale value, and the value range is also (0, 255).

[0067] The specific steps for denoising image data include:

[0068] For each pixel in the image, the average value of the surrounding pixels is taken as the new value for that pixel.

[0069] Furthermore, in this embodiment, the step S20, which calculates the license plate information of the dump truck based on the preprocessed image data, includes:

[0070] Based on template matching, feature extraction, and classification, the license plate characters of the dump trucks are identified to obtain the license plate information of the dump trucks.

[0071] The specific steps for obtaining license plate information of dump trucks based on template matching, feature extraction, and classification to identify license plate characters include:

[0072] The similarity between the character image to be identified and the template character image is calculated using the normalized cross-correlation algorithm formula, where the normalized cross-correlation algorithm formula is:

[0073]

[0074] Where R(x,y) represents the similarity. These are the average gray values ​​of I and T, respectively. (x, y) represents the coordinates of the character image I to be recognized relative to the template character image T during the matching process, used to iterate through the matching results at different positions on the image; I(i+x, j+y) is the gray value of the pixel at coordinates (i+x, j+y) in the character image I to be recognized; T(i, j) is the gray value of the pixel at coordinates (i, j) in the template character image T. R(x, y) is the similarity value between the character image I to be recognized and the template character image T at position (x, y), generally ranging from [-1, 1], with a value closer to 1 indicating a higher similarity.

[0075] The image is divided into small cell units, and the gradient direction histogram of each cell unit is calculated. These histograms are then combined into a feature vector. For a pixel (x, y), its gradient magnitude is:

[0076]

[0077] gradient direction

[0078] Where (x,y) represents the coordinates of the current pixel in the image; I(x+1,y), I(x-1,y), I(x,y+1), and I(x,y-1) are the gray values ​​of the pixels adjacent to the current pixel (x,y) in the horizontal and vertical directions, respectively; m(x,y) is the gradient magnitude of the current pixel (x,y), reflecting the intensity of the gray-level change at that pixel; and θ(x,y) is the gradient direction of the current pixel (x,y), representing the direction of the gray-level change at that pixel.

[0079] In this embodiment, the step of calculating the vehicle type information of the dump truck based on the preprocessed image data in S20 includes:

[0080] The vehicle type information of the dump truck is calculated based on feature extraction and deep learning methods.

[0081] The specific steps for calculating the vehicle type information of dump trucks based on feature extraction methods and deep learning methods include:

[0082] Based on scale-invariant feature transformation, keypoints are detected in different scale spaces, and the orientation and descriptor of the keypoints are calculated: for a pixel x in the image, its response in the scale space (L, X, O) is obtained by convolving the image I(x) with a Gaussian kernel G(X, O), i.e., L(x,σ)=G(x,σ)*I(z), where

[0083] Where (x) represents the coordinates of a pixel in the image, which can be understood as a two-dimensional vector containing the coordinates of (x) and (y). σ is the scale space factor, a real number greater than 0, used to control the scale of the Gaussian kernel; different values ​​of σ correspond to different scales of image representation. L(x,σ) is the scale space response value of pixel x at scale σ, reflecting the feature intensity of the pixel at the corresponding scale. G(x,σ) is the two-dimensional Gaussian kernel function used to smooth the image to construct the scale space. I(x) is the original gray value of pixel (x) in the image.

[0084] The gradient orientation histogram of a local region of the image is calculated as a feature. When calculating the gradient orientation histogram, the gradient magnitude and direction are calculated by the difference between the image pixels. Then, the image is divided into multiple cells, and the gradient orientation histogram in each cell is counted. Finally, the histograms of all cells are concatenated to form the gradient orientation histogram feature vector.

[0085] In the convolutional layer of a convolutional network, the feature map F is obtained by performing a convolution operation between the input image I and the convolution kernel K, with the formula F(x,y)=∑ i ∑ j I(x)+i,y+j)K(i,j).

[0086] Where (x,y) is the coordinate position of the current pixel on feature map F, (i,j) is the coordinate position of the pixel on convolution kernel K, and I(x+i,y+j) is the gray value of the pixel at the corresponding position in input image I corresponding to convolution kernel K, which corresponds to different positions as convolution kernel K slides on the input image. K(i,j) is the weight value of the pixel at coordinate (i,j) in convolution kernel K. F(x,y) is the value of the pixel at coordinate (x,y) on feature map F after the convolution operation, reflecting the feature information extracted at that position.

[0087] Furthermore, in this embodiment, the intelligent AI-powered method for managing construction waste trucks also includes:

[0088] The amount of construction waste is calculated based on the vehicle model information, and the fee is automatically deducted from the company to which the construction waste truck belongs, based on the license plate information.

[0089] It should be noted that in this embodiment, once the vehicle model information of the dump truck is identified, the amount of construction waste transported by the dump truck each time can be calculated based on the vehicle model information, and then the amount of construction waste can be calculated. The fee is then automatically deducted from the company to which the dump truck belongs, based on the license plate information of the dump truck.

[0090] Furthermore, in this embodiment, the intelligent AI dump truck management system also includes an AI camera installed at the city exit, and the method further includes:

[0091] When the AI ​​camera set up at the city exit detects a dump truck, an alarm is triggered on the management terminal.

[0092] In this embodiment, an AI license plate recognition camera is installed at the city exit. When a dump truck leaving the city is detected, an alarm is triggered, and the alarm information is notified to the corresponding driver and law enforcement unit.

[0093] Furthermore, in this embodiment, the intelligent AI-powered method for managing construction waste trucks also includes:

[0094] Step S50: Based on the alarm information, link the violation assessment of the dump truck driver.

[0095] This embodiment can effectively supervise drivers by linking alarm information to the violation assessment of dump truck drivers, thereby preventing them from deviating from the preset route and improving the operational safety of dump trucks.

[0096] In summary, this invention, through the aforementioned technical solution, uses AI cameras to collect image data of dump trucks along a preset route; preprocesses the image data, calculates the truck model and license plate information based on the preprocessed image data, and calculates the truck's travel time; determines whether the route has exceeded the time limit based on the travel time; if the route exceeds the time limit, it is determined that the dump truck is not traveling along the preset route, and the truck model and license plate information are notified to the management terminal for alarm. No equipment needs to be installed on the transport vehicles for AI route planning. It can automatically warn enterprises and law enforcement units when illegal calculation behavior is detected, and sets up a travel time alarm linkage SMS to prevent transport vehicles from dumping illegally in urban areas, thereby reducing the management cost of dump trucks and improving the management efficiency and transportation safety of dump trucks.

[0097] To achieve the above objectives, this invention also proposes a smart AI-powered dump truck management system, such as... Figure 2 As shown, the system includes AI cameras installed on the preset routes of dump trucks and at the city exits, a processor 1001, a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002, and a smart AI dump truck management program stored on the processor. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard. Optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed RAM or a stable, non-volatile memory, such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0098] Those skilled in the art will understand that Figure 2 The system structure shown does not constitute a limitation on the system and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0099] like Figure 2 As shown, the memory 1005, which serves as a computer storage medium, may include an operating device, a network communication module, a user interface module, and a smart AI dump truck management program.

[0100] exist Figure 2In the system shown, the network interface 1004 is mainly used to connect to the network server and communicate with the network server; the user interface 1003 is mainly used to interact with the user terminal and receive user input instructions; and the processor 1001 can be used to call the intelligent AI dump truck management program stored in the memory 1005.

[0101] To achieve the above objectives, the present invention also proposes a computer-readable storage medium storing a smart AI dump truck management program, wherein the smart AI dump truck management program, when run by a processor, executes the steps of the method described above, which will not be repeated here.

[0102] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. All equivalent structural transformations made under the concept of the present invention using the contents of the present invention specification and drawings, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A smart AI-powered method for managing construction waste trucks, characterized in that: The method is applied to a smart AI-powered construction waste truck management system, which includes AI cameras installed on preset routes for construction waste trucks. The method includes the following steps: Step S10: Collect image data of dump trucks on the preset route of the dump trucks using the AI ​​camera; Step S20: Preprocess the image data of the dump truck, calculate the vehicle type and license plate information of the dump truck based on the preprocessed image data, and calculate the driving time of the dump truck. Step S30: Determine whether the route has exceeded the time limit based on the travel time of the dump truck and the preset time limit. Step S40: If the route times out, it is determined that the dump truck is not traveling along the preset route, and the vehicle type and license plate information of the dump truck are notified to the management terminal for alarm.

2. The intelligent AI-powered method for managing construction waste trucks according to claim 1, characterized in that, Step S20, the step of preprocessing the image data of the dump truck, includes: Step S201: Perform grayscale conversion and noise reduction processing on the image data; The step of performing grayscale processing on the image data includes: Each pixel in the image data is converted from the RGB color space to the grayscale space, using the following weighted average formula: Gray=0.299×R+0.587×G+0.114×B; Where R, G, and B are the red, green, and blue components of the pixel, respectively, and Gray is the grayscale value; The step of denoising the image data includes: For each pixel in the image, the average value of the surrounding pixels is taken as the new value for that pixel.

3. The intelligent AI-powered method for managing construction waste trucks according to claim 1, characterized in that, The step S20, which involves calculating the license plate information of the dump truck based on the preprocessed image data, includes: Based on template matching, feature extraction, and classification, the license plate characters of the dump truck are identified to obtain the license plate information of the dump truck.

4. The intelligent AI-powered method for managing construction waste trucks according to claim 3, characterized in that, The steps for identifying the license plate characters of the dump truck based on template matching, feature extraction, and classification to obtain the license plate information of the dump truck include: The similarity between the character image to be identified and the template character image is calculated using the normalized cross-correlation algorithm formula, where the normalized cross-correlation algorithm formula is: Where R(x,y) represents the similarity. These are the average values ​​of I and T, respectively; The image is divided into small cell units, and the gradient direction histogram of each cell unit is calculated. These histograms are then combined into a feature vector. For a pixel (x, y), its gradient magnitude is: gradient direction 5. The intelligent AI-powered method for managing construction waste trucks according to claim 1, characterized in that, The step in S20 of calculating the vehicle type information of the dump truck based on the preprocessed image data includes: The vehicle type information of the dump truck is calculated based on feature extraction methods and deep learning methods; The steps for calculating the vehicle type information of the dump truck based on feature extraction and deep learning methods include: Based on scale-invariant feature transformation, keypoints are detected in different scale spaces, and the orientation and descriptor of the keypoints are calculated: for a pixel x in the image, its response in the scale space (L, X, O) is obtained by convolving the image I(x) with a Gaussian kernel G(X, O), i.e., L(x,σ)=G(x,σ)*I(z), where The gradient direction histogram of a local region of the image is calculated as a feature. When calculating the gradient direction histogram, the gradient magnitude and direction are calculated by the difference between the image pixels. Then, the image is divided into multiple cells, and the gradient direction histogram in each cell is counted. Finally, the histograms of all cells are concatenated to form the gradient direction histogram feature vector. In the convolutional layer of a convolutional network, the feature map F is obtained by performing a convolution operation between the input image I and the convolution kernel K, with the formula F(x,y)=∑ i ∑ j I(x+i,y+j)K(i,j).

6. The intelligent AI-powered method for managing construction waste trucks according to claim 1, characterized in that, The method further includes: The amount of construction waste is calculated based on the vehicle model information, and the fee is automatically deducted from the company to which the construction waste truck belongs, based on the license plate information.

7. The intelligent AI-powered method for managing construction waste trucks according to claim 1, characterized in that, The system also includes an AI camera installed at the city exit, and the method further includes: When the AI ​​camera set up at the city exit detects a dump truck, an alarm is triggered on the management terminal.

8. The intelligent AI-powered method for managing construction waste trucks according to any one of claims 1 to 7, characterized in that, The process following step S40 also includes: Step S50: Based on the alarm information, link the violation assessment of the transport driver of the dump truck.

9. A smart AI-powered dump truck management system, characterized in that, The system includes AI cameras installed on the preset routes of dump trucks and at the city exits, as well as a memory, a processor, and a smart AI dump truck management program stored on the processor. The smart AI dump truck management program is executed by the processor to perform the steps of the method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a smart AI dump truck management program, which, when executed by a processor, performs the steps of the method as described in any one of claims 1 to 8.

Images