Real-Time Multi-Class Object Detection and Analytics using the YOLO26n Architecture

A new benchmark for the efficiency of neural networks was set in January 2026 when the YOLO26 architecture was introduced. This research assesses the performance of the YOLO26n (Nano) model in a real-time environment using a carefully selected subset of the COCO dataset from Kaggle. The research also analyzes the training data to prove the effectiveness of the YOLO26n model, as the trained data reached a peak mAP@50 of 0.5122, thereby validating its suitability for use on consumer-grade hardware. The final solution was integrated with a Streamlit-based dashboard for batch analytics as well as local webcam usage, thereby demonstrating its applicability for smart surveillance and counting purposes.