A Review of Moving Object Detection Techniques for Night Time

Moving Object Detection in low light conditions is a challenging task due to limited visibility and the presence of noise and objects in the captured images, low contrast, low brightness, low appearance information, and low Signal to Noise Ratio. The majority of night surveillance models suffer from lack of adaptability for different scenes and separation between detection and tracking. This review paper provides a comprehensive survey of recent advancements in Moving Object Detection Techniques for night-time situations. It presents an overview of various approaches proposed in the literature, including traditional and deep learning-based methods, and discusses their strengths and limitations. Moreover, the paper highlights evaluation metrics commonly used in the literature, the datasets they have been evaluated upon, along with a comparative analysis of the performance metrics & various limitations of different methods. Finally, the paper identifies the key research challenges and future directions for Moving Object Detection in Night Time viz. dim-lit environments, such as the need for more robust and efficient algorithms that can handle diverse environmental conditions and real-time applications.