Detecting cargo vehicles, such as trucks and lorries, plays a critical role in optimizing traffic flow, ensuring road safety, and enhancing logistics management in urban environments. Their identification is also vital for monitoring freight movement and improving operational efficiency in sectors such as transportation and security. This study provides a comparative analysis of two widely used object detection algorithms, Faster R-CNN and YOLOv8, focused on detecting these large vehicles. Accurate and fast identification is essential across various industries, including traffic management and logistics. In this research, both algorithms are evaluated in two distinct environments: traffic flow and parking lots. Their detection capability is assessed using key performance metrics. The results indicate that despite being a single-stage detector, YOLOv8 significantly outperforms the two-stage Faster R-CNN in both scenarios, particularly excelling in real-time detection with precision and mAP scores of 0.877 and 0.854, respectively. This establishes YOLOv8 as a more effective model for applications that demand high accuracy and efficiency in vehicle detection.