Web-Based Anomaly Detection for Smart Urban Living: Drone Photography and Videography

Abstract

Smart cities aim to enhance the quality of life for urban dwellers through technological advancements. Machine Learning (ML) plays a crucial role in various domains of Smart X, including education, transportation, healthcare, environment, and living. However, integrating ML into daily life poses challenges. This paper presents a web-based ML application prototype that effectively augments the daily quality of life for communities. It specifically explores the advantages of web-based photography-videography-enabled drones for citizen needs and city inspections. The application utilizes ML to detect anomalies and identify normal objects, addressing the common challenge of distinguishing normalcy from abnormality. Examples include assessing the structural integrity of house components, analyzing medical images, and evaluating the quality of fruits or hydroponic plants. The study employs exploratory and experimental methods, utilizing teachable machine learning and the Python-based Streamlit application. Experimental results demonstrate that web-based photo and video analysis expedites the detection of normal and abnormal images and videos, surpassing the limitations of visual examination with the naked eye. This research contributes to advancing ML applications in smart living for urban communities.