Potholes are irregular-shaped depressions on road surfaces and represent a pervasive threat to road safety worldwide. Potholes pose significant risks to road users, contributing to accidents, vehicle damage, and fatalities. Statistical data from the Ministry of Road Transport & Highways (MoRTH), India, reveal a staggering toll of incidents, with thousands of fatalities and injuries resulting from pothole-related accidents annually. Moreover, the negative impacts of potholes extend beyond safety concerns, affecting traffic flow, vehicle efficiency, and economic productivity. They are known to cause traffic jams, increase fuel consumption, and degrade vehicle components, leading to decreased fuel economy and heightened maintenance costs. Road transport is like the heart and arteries of a nation when it comes to moving people and things around. Road upkeep is a difficult task in nations like India. The rising number of potholes is causing an annual increase in the number of accidents. Considering these challenges, our research leverages a computer vision system centered around the YOLOv5 algorithm's capabilities to detect potholes efficiently and accurately. By employing deep learning techniques, we aim to develop a robust pothole detection system capable of identifying these hazards in real time. Such a system holds promise for enhancing road safety, reducing accident rates, and mitigating the economic burdens associated with pothole-related incidents. Through this case study, we demonstrate the potential of YOLOv5 as a tool for proactive pothole detection and pave the way for future advancements in road maintenance and safety protocols.