###Smart City Planning: Automated Visual Pollution Classification

This project aims to establish a new field of automated visual pollution classification by utilizing convolutional neural networks (CNNs) to simulate the human learning experience in the context of picture identification for the classification of visual pollutants. The project will use a large-scale dataset that features the raw sensor camera inputs as perceived by a fleet of multiple vehicles in a restricted geographic area in KSA. The goal is to build and optimize algorithms based on this dataset to classify visual pollution types such as graffiti, faded signage, potholes, garbage, construction road, broken signage, bad streetlight, bad billboard, sand on roads, cluttered sidewalks, and unkept facade.

The project will involve preprocessing the dataset by splitting it into training, validation and test sets. Then, a pre-trained CNN model will be fine-tuned on the dataset and trained using the training set. Its performance will be evaluated using the validation set. Once the model's performance is satisfactory, it will be used to classify images in the test set. Finally, various evaluation metrics such as accuracy, precision, recall, and F1-score will be used to evaluate the model's overall performance on the test set.

If successful, this project will make a significant contribution towards stimulating further development in city planning and empowering communities around the world by providing a "visual pollution score/index" for urban areas that might produce a new "metric" or "indicator" in the discipline of urban environmental management.