The imperative task of identifying and promptly detecting cracks in concrete bridges is crucial for preserving their structural health and ensuring the safety of users. Traditional bridge inspection methods heavily rely on human eyes and additional tools, demanding extensive training for inspectors and resulting in time-consuming processes. The increasing demand for Unmanned Aerial Vehicles (UAVs) has provided a transformative solution to access hard-to-reach areas efficiently. This research explores the integration of deep learning algorithms, including CNN, RCNN, Fast RCNN, Faster RCNN, and YOLO, to enhance the accuracy and efficiency of UAV-based crack detection systems. Experimental results affirm the effectiveness of these algorithms in addressing challenges such as lighting variations and small crack detection. The study aims to contribute to structural health monitoring, improving maintenance practices, and enhancing safety. © 2023, Chulalongkorn University, Faculty of Fine and Applied Arts. All rights reserved.