This paper provides a comprehensive overview of uncertainty estimation in deep neural networks (DNNs), highlighting recent advances, current challenges, and potential research opportunities. It emphasizes the importance of uncertainty estimation for safe decision-making in high-risk applications and the need for reliable calibration of DNN predictions. The paper discusses various sources of uncertainty, including model uncertainty and data uncertainty, and reviews different approaches to quantify and model these uncertainties. These approaches include Bayesian neural networks, ensemble methods, test-time data augmentation, and single deterministic networks. The paper also explores practical applications in fields such as medical image analysis, robotics, and earth observation, and addresses the limitations and practical limitations of current uncertainty quantification methods. Finally, it outlines future research directions and the broader implications for mission- and safety-critical real-world applications.This paper provides a comprehensive overview of uncertainty estimation in deep neural networks (DNNs), highlighting recent advances, current challenges, and potential research opportunities. It emphasizes the importance of uncertainty estimation for safe decision-making in high-risk applications and the need for reliable calibration of DNN predictions. The paper discusses various sources of uncertainty, including model uncertainty and data uncertainty, and reviews different approaches to quantify and model these uncertainties. These approaches include Bayesian neural networks, ensemble methods, test-time data augmentation, and single deterministic networks. The paper also explores practical applications in fields such as medical image analysis, robotics, and earth observation, and addresses the limitations and practical limitations of current uncertainty quantification methods. Finally, it outlines future research directions and the broader implications for mission- and safety-critical real-world applications.