aparsoft/yolo-streamlit-detection-tracking
A real-time computer vision application using YOLO26, YOLO World v2, and Streamlit for object detection, tracking, segmentation, and pose estimation.
Velocity · 7d
+0.4
★ / day
Trend
→steady
star history
This project provides a Streamlit-based interface for running YOLO vision models on video streams and static images. It supports object detection with YOLO26n, instance segmentation, pose estimation with RLE-based keypoints, and open-vocabulary detection via YOLO World v2. Multiple tracking algorithms (ByteTrack, BoSORT) enable multi-object tracking with per-frame and cumulative counting across video streams.