Artificial-intelligence image processing method based on intelligent transportation

Abstract

An artificial-intelligence image processing method based on intelligent transportation. The method comprises the steps of image acquisition and preprocessing, feature extraction, construction and training of an artificial intelligence model, intelligent analysis and decision support, intelligent image processing and feedback, result output and application, etc. In the artificial-intelligence image processing method based on intelligent transportation, information obtained by means of feature extraction is used for the establishment of an artificial-intelligence analysis model, thereby significantly enhancing the intelligent analysis capability of an intelligent-transportation management system. In the step of construction and training of an artificial intelligence model, by means of performing mapping calculation on extracted features and historical data, a constructed artificial-intelligence analysis model can learn and recognize a pattern in a transportation image, thereby predicting an optimal processing method. The establishment of such a model enables the intelligent-transportation management system to not only process current image data, but also perform learning and prediction on the basis of the historical data, thereby improving the intelligence level of the system.

Description

An AI-powered image processing method based on intelligent transportation Technical Field

[0001] This invention relates to the field of image processing technology, specifically to an artificial intelligence image processing method based on intelligent transportation. Background Technology

[0002] With the acceleration of urbanization and the continuous increase in the number of vehicles, problems such as traffic congestion and frequent accidents have become increasingly prominent. Traditional traffic management methods can no longer meet the demands of modern society for traffic safety and efficiency. Therefore, intelligent transportation systems have emerged. Intelligent transportation systems utilize advanced image recognition technology to analyze and process images in traffic scenes, enabling the automatic acquisition and processing of information such as traffic flow and traffic violations, thereby improving the efficiency and accuracy of traffic management.

[0003] Although intelligent transportation systems have made some progress in image processing technology, existing image processing methods still have some shortcomings. Existing image processing methods are highly dependent on data and require a large amount of labeled data to train models. This not only increases the cost of data collection and processing, but also limits the generalization ability of models in new scenarios. Existing image processing methods suffer from low efficiency and insufficient accuracy, and have high requirements for the accuracy of image data, which limits the ability to process large amounts of image data and affects the overall work efficiency. Summary of the Invention

[0004] The purpose of this invention is to address the problem that existing image processing methods are highly dependent on data and require a large amount of labeled data to train models. This not only increases the cost of data collection and processing but also limits the generalization ability of models in new scenarios. Existing image processing methods suffer from low efficiency and insufficient accuracy, and have high requirements for the accuracy of image data, which limits the ability to process large amounts of image data and affects the overall work efficiency. Therefore, this invention proposes an artificial intelligence image processing method based on intelligent transportation.

[0005] The objective of this invention can be achieved through the following technical solution: an artificial intelligence image processing method based on intelligent transportation, comprising the following steps:

[0006] Step 1: Image Acquisition and Preprocessing: Collect traffic element images and preprocess the collected traffic element images;

[0007] Step 2: Feature Extraction: Extract useful feature information for identification and classification from the traffic element image after preprocessing in Step 1;

[0008] Step 3: Construction and training of the artificial intelligence model: Based on the traffic element image feature information extracted in Step 2, the traffic image historical data and processing methods in the intelligent traffic management system are mapped and calculated using a big data cloud server and a forward propagation neural network algorithm to construct an artificial intelligence analysis model for traffic images.

[0009] Step 4: Intelligent Analysis and Decision Support: The traffic image artificial intelligence analysis model obtained in Step 3 is called from the big data cloud server to perform intelligent analysis on the traffic element images after the preprocessing in Step 1, and the best processing method is selected.

[0010] Step 5: Intelligent Image Processing and Feedback: Based on the optimal processing method in Step 4, intelligent processing is performed on the traffic element images, and the processing results are fed back to the intelligent traffic management system in real time.

[0011] Step Six: Output and Application of Results: Push the processed image data and analysis results from Step Five to the intelligent transportation management system to provide decision support for the system.

[0012] Preferably, in step one, the process of collecting traffic element images includes the following steps:

[0013] S11: Equipment Deployment: Deploy image sensor equipment such as cameras, radar, and laser scanners on traffic roads, facilities, and vehicles;

[0014] S12: Real-time monitoring: Utilize real-time traffic monitoring to capture dynamic changes and ensure the timeliness and accuracy of data;

[0015] S13: Data transmission: The acquired image data needs to be transmitted to the backend via wired or wireless network. Compression and encryption are required during data transmission to ensure transmission efficiency and security.

[0016] S14: After decompressing and decrypting the transmitted image data, store it on the server for subsequent analysis and processing.

[0017] Preferably, traffic element images include the following aspects: vehicles, pedestrians, traffic signs and signals, roads, license plates, and road environment.

[0018] Preferably, in step one, the preprocessing of the traffic element image includes, but is not limited to, image correction, image denoising, image enhancement, image normalization, image cropping, image segmentation, image sharpening, and image fusion.

[0019] Preferably, in step two, the extracted feature information includes, but is not limited to, color features, texture features, shape features, spatial relationship features, semantic features, and optical flow features.

[0020] Preferably, in step three, the construction and training of the artificial intelligence model includes model design, data preparation, model training, and model optimization.

[0021] Preferably, model design involves designing a forward propagation neural network model based on the extracted feature information to learn and recognize patterns in traffic images; data preparation involves collecting and organizing historical traffic image data and processing methods from the intelligent traffic management system to provide a dataset for training the model; model training utilizes the computing power of a big data cloud server to train the model, enabling it to recognize features in traffic images based on historical data and predict the optimal processing method; model optimization involves adjusting model parameters and structure to optimize model performance and improve its accuracy.

[0022] Preferably, in step four, intelligent analysis and decision support includes the following steps:

[0023] S41: Use artificial intelligence models to perform pattern recognition and classification on preprocessed traffic element images;

[0024] S42: Based on the identification results, analyze traffic flow, traffic incidents, and traffic conditions to determine the best traffic management strategy;

[0025] S43: Combine the analysis results with real-time data from the traffic management system to provide real-time decision support and traffic optimization suggestions.

[0026] Preferably, in step five, the intelligent processing and feedback of the image includes the following steps:

[0027] S51: Based on the preferred processing method, further analysis and processing of traffic element images are performed, such as traffic flow control, accident detection and response, traffic signal optimization, etc.

[0028] S52: Display the processing results to traffic management personnel through a visual interface for manual review and intervention;

[0029] S53: Store the processing results and feedback information in the database for further learning and optimization of the model.

[0030] Preferably, in step six, the result output and application include the following steps:

[0031] S61: Format the processed image data and analysis results to facilitate the integration and use of the intelligent transportation management system;

[0032] S62: Push data and results to the intelligent traffic management system via API or other interfaces to achieve automated traffic management;

[0033] S63: Regularly evaluate and update the pushed data and results to ensure that the decision support of the intelligent transportation management system is always up-to-date and accurate.

[0034] Compared with the prior art, the beneficial effects of the present invention are:

[0035] (1) This AI image processing method based on intelligent transportation significantly enhances the intelligent analysis capabilities of the intelligent transportation management system by using the information extracted from features to establish an AI analysis model. In step three, by mapping the extracted features with historical data, the constructed AI analysis model can learn and recognize patterns in traffic images, thereby predicting the optimal processing method. The establishment of this model enables the intelligent transportation management system not only to process current image data but also to learn and predict based on historical data, improving the system's intelligence level. As the image processing data from the optimal processing method in step five is pushed to the intelligent transportation management system, the system accumulates more and more data, which provides a basis for AI analysis. The model provides richer data support. With the accumulation of data and continuous optimization of the model, the analytical capabilities of the intelligent traffic management system will become more powerful, enabling it to more accurately predict and handle various traffic situations, thereby improving the efficiency and safety of traffic management. This method achieves continuous optimization and self-adaptation of the intelligent traffic management system through continuous image processing and data push. As more and more image features of the best processing methods are extracted and used in the artificial intelligence analysis model, the performance of the model will be continuously improved, making the next artificial intelligence analysis model more powerful. This continuous optimization and self-adaptation capability enables the intelligent traffic management system to continuously adapt to changes in traffic conditions over time, improving the accuracy of its prediction and response.

[0036] (2) This intelligent transportation-based artificial intelligence image processing method achieves a comprehensive improvement in the level of intelligent traffic management through the close cooperation of six steps. First, in step one, by deploying image sensor equipment and monitoring traffic conditions in real time, real-time acquisition and preprocessing of traffic element images are achieved, providing a high-quality data foundation for subsequent intelligent analysis. In step two, feature extraction further extracts key information from the preprocessed images. In step three, the artificial intelligence model constructed using big data cloud servers and forward propagation neural network algorithms can learn from historical data and identify patterns in traffic images, providing a powerful intelligent analysis tool for traffic management. The intelligent analysis and decision support, as well as the intelligent image processing and feedback in steps four and five, enable the traffic management system to respond to traffic conditions in real time and make rapid decisions, such as traffic flow control and accident response. This greatly reduces the need for human intervention and improves the automation level and response speed of traffic management. Finally, the result output and application in step six pushes the processed image data and analysis results to the intelligent traffic management system, providing real-time decision support for traffic management departments and helping to formulate more effective traffic management strategies. Overall, the coordination of these six steps realizes full-process intelligentization from data collection to decision support, greatly improving the efficiency and effectiveness of traffic management.

[0037] (3) The AI ​​image processing method based on intelligent transportation first extracts features from the collected images, then uses these features to map and calculate with the data of the intelligent transportation management system to establish an AI analysis model, and finally uses the model to intelligently analyze and obtain the best processing method to process the collected images. This achieves high efficiency and high accuracy in image processing. In step two, the feature extraction is fast and has low requirements, which helps to quickly process a large amount of image data and improve overall work efficiency. In step five, the best processing method is used to intelligently process the images again, making the processing results more accurate and better meeting the needs of intelligent transportation management. This two-stage image processing process can provide high-quality image processing results while maintaining high efficiency. This is especially important for traffic management systems that require rapid response. For example, in traffic congestion or accident detection, it can quickly identify problems and take action while ensuring the accuracy of identification and avoiding false alarms or missed alarms. Attached Figure Description

[0038] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0039] Figure 1 is a flowchart of the processing method of the present invention. Detailed Implementation

[0040] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] Please refer to Figure 1, which illustrates an AI-based image processing method for intelligent transportation, comprising the following steps:

[0042] Step 1: Image Acquisition and Preprocessing: Collect traffic element images and preprocess the collected traffic element images;

[0043] Step 2: Feature Extraction: Extract useful feature information for identification and classification from the traffic element image after preprocessing in Step 1;

[0044] Step 3: Construction and training of the artificial intelligence model: Based on the traffic element image feature information extracted in Step 2, the traffic image historical data and processing methods in the intelligent traffic management system are mapped and calculated using a big data cloud server and a forward propagation neural network algorithm to construct an artificial intelligence analysis model for traffic images.

[0045] Step 4: Intelligent Analysis and Decision Support: The traffic image artificial intelligence analysis model obtained in Step 3 is called from the big data cloud server to perform intelligent analysis on the traffic element images after the preprocessing in Step 1, and the best processing method is selected.

[0046] Step 5: Intelligent Image Processing and Feedback: Based on the optimal processing method in Step 4, intelligent processing is performed on the traffic element images, and the processing results are fed back to the intelligent traffic management system in real time.

[0047] Step Six: Output and Application of Results: Push the processed image data and analysis results from Step Five to the intelligent transportation management system to provide decision support for the system.

[0048] Preferably, in step one, the process of collecting traffic element images includes the following steps:

[0049] S11: Equipment Deployment: Deploy image sensor equipment such as cameras, radar, and laser scanners on traffic roads, facilities, and vehicles;

[0050] S12: Real-time monitoring: Utilize real-time traffic monitoring to capture dynamic changes and ensure the timeliness and accuracy of data;

[0051] S13: Data transmission: The acquired image data needs to be transmitted to the backend via wired or wireless network. Compression and encryption are required during data transmission to ensure transmission efficiency and security.

[0052] S14: After decompressing and decrypting the transmitted image data, store it on the server for subsequent analysis and processing.

[0053] Preferably, the traffic element image includes the following aspects: vehicles, pedestrians, traffic signs and signals, roads, license plates, and road environment. Among them, vehicles include various types of vehicles, such as cars, trucks, buses, and motorcycles; traffic signs and signals include traffic lights, traffic signs, and roadblocks; roads include lane lines, road surface conditions, and road boundaries; and the road environment includes buildings, green belts, and traffic facilities around the road.

[0054] Preferably, in step one, the preprocessing of the traffic element image includes, but is not limited to, image correction, image denoising, image enhancement, image normalization, image cropping, image segmentation, image sharpening, and image fusion. Image correction employs perspective transformation and geometric correction techniques to correct image tilt and distortion caused by the shooting angle, thereby improving the geometric accuracy of the image and providing accurate image data for subsequent feature extraction and analysis. Image denoising uses mean filtering, median filtering, and Gaussian filtering methods to eliminate unnecessary noise in the image, improve image quality, restore image clarity and detail information, making the image more realistic, natural, and easier to analyze and process. Image enhancement employs histogram equalization and contrast enhancement techniques to improve the image's contrast, brightness, and color, making it more realistic and natural. Easier to observe and analyze, improving the visual effect of images, making target features more prominent, and facilitating subsequent recognition and analysis. Image normalization scales the pixel values ​​of an image to a small, specified range to eliminate the influence of dimensions, which can accelerate model training speed, improve model accuracy, reduce the impact of geometric transformations, and improve the model's generalization ability. Image cropping removes uninteresting regions from an image, retaining only key features or regions of interest, reducing unnecessary calculations, improving processing speed, and making the image more focused and highlighting the subject. Image segmentation uses threshold segmentation, region growing, and deep learning methods to divide the image into different regions or objects, helping to identify and locate objects in the image and facilitating subsequent target recognition and analysis. Image sharpening uses Unsharp Masking and Laplacian sharpening techniques to enhance the edges and details of the image, improve image clarity, make edges more obvious, and improve image quality. Image fusion uses pixel-level, feature-level, or decision-level fusion to combine information from multiple images, improving the visual effect and information content of the image, and enhancing the accuracy and reliability of target detection and recognition.

[0055] Preferably, in step two, the extracted feature information includes, but is not limited to, color features, texture features, shape features, spatial relationship features, semantic features, and optical flow features. Color features are extracted by color space transformation (e.g., RGB to HSV) and color histogram calculation, which can distinguish different traffic signs and vehicle types, improving recognition accuracy. Texture features use methods such as Gray-Level Co-occurrence Matrix (GLCM) or Local Binary Pattern (LBP) to describe the texture information of the image. Texture features can effectively capture the local structural information of the image, which is very useful for distinguishing different types of road conditions and traffic signs. Shape features extract the shape information of objects in the image through edge detection (e.g., Sobel, Canny operators) and contour tracking techniques, which is crucial for recognizing the contours and poses of traffic participants such as vehicles and pedestrians. Spatial relationship features... Image features analyze the relative positions and distances between different objects in an image, such as using clustering algorithms or graphical models. Spatial relationship features help understand traffic flow patterns and interactions between traffic participants. Semantic features utilize deep learning models (such as CNNs) to automatically learn high-level semantic information from images. Semantic features provide rich contextual information, helping to improve the depth and accuracy of traffic scene understanding. Optical flow features are extracted by calculating the motion vectors of pixels in an image sequence. Optical flow features are important for analyzing dynamic changes in traffic flow and detecting vehicle motion states. By extracting image features, the dimensionality of data can be reduced, processing speed and efficiency can be improved, and the recognition and prediction accuracy of the model can be enhanced. By selecting the most representative features, the risk of model overfitting can be reduced, making the model's decision-making process more transparent and interpretable.

[0056] Preferably, in step three, the construction and training of the artificial intelligence model includes model design, data preparation, model training, and model optimization.

[0057] Preferably, the model design involves designing a forward propagation neural network model based on the extracted feature information to learn and recognize patterns in traffic images. Deep learning techniques, especially convolutional neural networks, are employed. Image features are extracted through convolutional layers, with the output of each layer serving as the input to the next, thus abstracting and extracting image features layer by layer. This also includes pre-training the model on an image dataset to initialize network parameters and improve convergence speed. Data preparation involves collecting and organizing historical traffic image data and processing methods from the intelligent traffic management system to provide a dataset for training the model. This includes manually collecting data from multiple sources, constructing single-modal and multi-modal traffic datasets, and employing histogram equalization, etc. Image resizing is used to preprocess the data to ensure the consistency and quality of the model input. Model training utilizes the computing power of big data cloud servers to train the model. During training, the model is iteratively trained using the training set data, enabling it to identify features in traffic images based on historical data and predict the optimal processing method. Data augmentation techniques, including rotation, translation, shearing, and scaling, are employed during training to expand the training dataset and improve the model's generalization ability. Model optimization involves adjusting model parameters and structure to improve model performance and accuracy. This includes using Dropout layers to prevent overfitting and configuring appropriate learning rates and optimizers to improve training stability and convergence speed.

[0058] Preferably, in step four, intelligent analysis and decision support includes the following steps:

[0059] S41: Use artificial intelligence models to perform pattern recognition and classification on preprocessed traffic element images;

[0060] S42: Based on the identification results, analyze traffic flow, traffic incidents, and traffic conditions to determine the best traffic management strategy;

[0061] S43: Combine the analysis results with real-time data from the traffic management system to provide real-time decision support and traffic optimization suggestions.

[0062] Preferably, in step five, the intelligent processing and feedback of the image includes the following steps:

[0063] S51: Based on the preferred processing method, further analysis and processing of traffic element images are performed, such as traffic flow control, accident detection and response, traffic signal optimization, etc.

[0064] S52: Display the processing results to traffic management personnel through a visual interface for manual review and intervention;

[0065] S53: Store the processing results and feedback information in the database for further learning and optimization of the model.

[0066] Preferably, in step six, the result output and application include the following steps:

[0067] S61: Format the processed image data and analysis results to facilitate the integration and use of the intelligent transportation management system;

[0068] S62: Push data and results to the intelligent traffic management system via API or other interfaces to achieve automated traffic management;

[0069] S63: Regularly evaluate and update the pushed data and results to ensure that the decision support of the intelligent transportation management system is always up-to-date and accurate.

[0070] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. An artificial intelligence image processing method based on intelligent transportation, characterized in that, Includes the following steps: Step 1: Image Acquisition and Preprocessing: Collect traffic element images and preprocess the collected traffic element images; Step 2: Feature Extraction: Extract useful feature information for identification and classification from the traffic element image after preprocessing in Step 1; Step 3: Construction and training of the artificial intelligence model: Based on the traffic element image feature information extracted in Step 2, the traffic image historical data and processing methods in the intelligent traffic management system are mapped and calculated using a big data cloud server and a forward propagation neural network algorithm to construct an artificial intelligence analysis model for traffic images. Step 4: Intelligent Analysis and Decision Support: The traffic image artificial intelligence analysis model obtained in Step 3 is called from the big data cloud server to perform intelligent analysis on the traffic element images after the preprocessing in Step 1, and the best processing method is selected. Step 5: Intelligent Image Processing and Feedback: Based on the optimal processing method in Step 4, intelligent processing is performed on the traffic element images, and the processing results are fed back to the intelligent traffic management system in real time. Step Six: Output and Application of Results: Push the processed image data and analysis results from Step Five to the intelligent transportation management system to provide decision support for the system.

2. The artificial intelligence image processing method based on intelligent transportation according to claim 1, characterized in that, Step one, the process of collecting traffic element images includes the following steps: S11: Equipment Deployment: Deploy image sensor equipment such as cameras, radar, and laser scanners on traffic roads, facilities, and vehicles; S12: Real-time monitoring: Utilize real-time traffic monitoring to capture dynamic changes and ensure the timeliness and accuracy of data; S13: Data transmission: The acquired image data needs to be transmitted to the backend via wired or wireless network. Compression and encryption are required during data transmission to ensure transmission efficiency and security. S14: After decompressing and decrypting the transmitted image data, store it on the server for subsequent analysis and processing.

3. The artificial intelligence image processing method based on intelligent transportation according to claim 2, characterized in that, Traffic element images include the following aspects: vehicles, pedestrians, traffic signs and signals, roads, license plates, and road environment.

4. The artificial intelligence image processing method based on intelligent transportation according to claim 1, characterized in that, In step one, the preprocessing of traffic element images includes, but is not limited to, image correction, image denoising, image enhancement, image normalization, image cropping, image segmentation, image sharpening, and image fusion.

5. The artificial intelligence image processing method based on intelligent transportation according to claim 1, characterized in that, In step two, the extracted feature information includes, but is not limited to, color features, texture features, shape features, spatial relationship features, semantic features, and optical flow features.

6. The artificial intelligence image processing method based on intelligent transportation according to claim 1, characterized in that, Step three involves the construction and training of the artificial intelligence model, including model design, data preparation, model training, and model optimization.

7. The artificial intelligence image processing method based on intelligent transportation according to claim 6, characterized in that, Model design involves designing a forward propagation neural network model based on extracted feature information to learn and recognize patterns in traffic images. Data preparation involves collecting and organizing historical traffic image data and processing methods from the intelligent traffic management system to provide a dataset for training the model. Model training utilizes the computing power of big data cloud servers to train the model, enabling it to recognize features in traffic images based on historical data and predict the optimal processing method. Model optimization involves adjusting model parameters and structure to improve model performance and accuracy.

8. The artificial intelligence image processing method based on intelligent transportation according to claim 1, characterized in that, Step four, intelligent analysis and decision support includes the following steps: S41: Use artificial intelligence models to perform pattern recognition and classification on preprocessed traffic element images; S42: Based on the identification results, analyze traffic flow, traffic incidents, and traffic conditions to determine the best traffic management strategy; S43: Combine the analysis results with real-time data from the traffic management system to provide real-time decision support and traffic optimization suggestions.

9. The artificial intelligence image processing method based on intelligent transportation according to claim 1, characterized in that, Step five, the intelligent processing and feedback of the image includes the following steps: S51: Based on the preferred processing method, further analysis and processing of traffic element images are performed, such as traffic flow control, accident detection and response, traffic signal optimization, etc. S52: Display the processing results to traffic management personnel through a visual interface for manual review and intervention; S53: Store the processing results and feedback information in the database for further learning and optimization of the model.

10. The artificial intelligence image processing method based on intelligent transportation according to claim 1, characterized in that, Step six, the output and application of results, includes the following steps: S61: Format the processed image data and analysis results to facilitate the integration and use of the intelligent transportation management system; S62: Push data and results to the intelligent traffic management system via API or other interfaces to achieve automated traffic management; S63: Regularly evaluate and update the pushed data and results to ensure that the decision support of the intelligent transportation management system is always up-to-date and accurate.

Images