Published Paper Details:

The ability of computer vision technology to recognize objects and impediments, especially in inclement weather, is essential for improving Autonomous Vehicles' (AVs') environmental perception in intelligent transportation systems. Object-detecting systems, which are crucial to modern safety protocols, monitoring infrastructure, and intelligent transportation, face significant challenges under adverse weather conditions. AVs rely mostly on image processing algorithms for guidance and decision-making, which make use of a variety of onboard visual sensors. Even in bad weather, it is crucial to make sure that important components like cars, pedestrians, and road lanes are consistently identified. In addition to offering a thorough analysis of the literature on Object Detection (OD) in inclement weather, this paper explores the constantly changing field of AV architecture, the difficulties faced by automated vehicles in inclement weather, the fundamentals of OD, and the landscape of conventional and deep learning (DL) approaches for OD within the context of AVs. These methods are crucial for improving AVs' ability to identify and react to items in their environment. By successfully connecting these approaches with the developing area of AVs, this study explores earlier studies that used both standard and DL methodologies for the detection of cars, pedestrians, and road lanes. Additionally, this study provides a thorough examination of the datasets frequently used in AV research, emphasizing the identification of critical components in many environmental situations before summarizing the evaluation matrix. We anticipate that this review will aid researchers in better understanding this field of study.