Real-time multi-object tracker using YOLOv7 and StrongSORT with OSNet
-
Updated
May 28, 2024 - Python
Real-time multi-object tracker using YOLOv7 and StrongSORT with OSNet
OpenVINO Training Extensions Object Re-identification
Vehicle Re-Identification (ReID) dataset contains over 55,000 images for training and validation of the vehicle re-identification model
Multi-camera people tracking with cross-camera ReID association and bird's-eye-view spatial mapping. YOLOv8m + StrongSort + OSNet on EPFL Laboratory dataset — CMC@3: 90.0%
A production-ready, locally-hosted Retrieval-Augmented Generation (RAG) system for chatting with your documents.
Detect, track and count different classes of objects.
AI-powered retail analytics platform for footfall tracking, heatmaps, zone analytics, demographics, and cross-camera ReID.
C++ pipeline for cross-camera person tracking: YOLO person detection + BYTETrack/IoU in-process or NvDCF via DeepStream, OSNet ReID + Hungarian global ID assignment
AI-powered PPE compliance monitoring system using YOLO, ByteTrack, Flask and OpenCV.
Track video objects with YOLOv8 and StrongSORT, using appearance embeddings and MOT metrics for reliable multi-object tracking
AI-powered multi-camera surveillance system for real-time weapon detection, human activity recognition, person tracking, Re-ID, evidence logging, and heatmap analysis.
Successfully developed a real-time soccer player re-identification and tracking system using YOLOv11 and Deep SORT with TorchreID-based embeddings.
Implementing and training an AI model for Person Re-Identification task
Adaptive motion-feature fusion for robust multi-object tracking · 面向复杂交通场景的自适应运动特征融合多目标跟踪
Advanced multi-object tracking pipeline — YOLOv8m + StrongSORT with OSNet appearance embeddings on MOT17. HOTA 41.6 | MOTA 38.1 | IDF1 50.8. Benchmarked against ByteTrack baseline with TrackEval.
Multi-camera persistent-ID person tracking with a live bird's-eye-view map. Zero-training geometric late fusion (YOLO11 + OSNet), with measured failure analysis on WILDTRACK.
FoundYou — Multi-Camera Person Re-Identification
Scalable Flask API powering the Badminton AI Analyser. Orchestrates a concurrent multi-model pipeline (YOLO, StrongSORT, TrackNet, SlowFast) on Google Cloud Platform to process high-speed match footage.
Hard hat violation detection on video with YOLO11, OSNet re-id for repeat violators, Flask UI
A novel implementation of Multi-Object Tracking in fixed frame setting
To associate your repository with the osnet topic, visit your repo's landing page and select "manage topics."