In the growth of the Human-Machine Interaction (HMI) discipline, it is essential to assess the human experience to intervene with the given task for autonomously navigated machines such as unmanned aerial vehicles (UAVs). Object detection is a fundamental computer vision task involving identifying and localizing objects within images or videos. It is critical in various fields, such as object detection, tracking, and counting. In this work, we aim to implement the YOLOv7, a popular object detection framework, to count specific object categories, including Cars, Buses, Motorcycles, and People. By capitalizing on the high accuracy and processing capabilities of YOLOv7, we have developed an efficient counting system that can analyze images and provide object counts for each category. We have evaluated the system’s performance on diverse images taken from various angles, considering challenging scenarios such as occlusions and varying scales. The outcomes demonstrate the effectiveness and reliability of YOLOv7 in precisely counting instances of the specified object classes, even during nighttime and on crowded roads and highways from high distances. A drone can potentially use this methodology to detect and count in an aerial photography view.