I implemented object detection using YOLOv3 with OpenCV and Python by integrating pre-trained YOLO weights and configuration files for real-time detection. The system processes images through deep learning models to identify multiple objects and applies bounding boxes, confidence scores, and class labels for visualization. To optimize accuracy, Non-Maximum Suppression (NMS) was used to minimize overlapping detections, ensuring cleaner outputs. This project demonstrates practical computer vision skills by successfully generating labeled outputs and showcases my ability to work with deep learning frameworks, image processing, and object detection pipelines effectively.