This master thesis presents a comprehensive review of various activity detection methods that can be used in surveillance systems to capture relevant footage. The review encompasses twenty articles, covering a wide range of intelligent video system approaches. The key methodologies examined include background subtraction, optical flow, machine learning techniques such as Support Vector Machines, and deep learning techniques including You Only Look Once, Convolutional Neural Networks, and Faster Region-based Convolutional Neural Networks. Each method is thoroughly explained, with an emphasis on their respective strengths and weaknesses. The analysis provides insights into the current state of the art and identifies potential areas for future research and development in surveillance systems.