botsort

BoxMOT: Pluggable Python and C++ SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes

🔥 CVPR 2025 (Nashville TN, USA) - The 4th Anti-UAV Workshop & Challenge 🥉

juxtapose: Multi-Person Pose Tracking Inference SDK with RTMDet, YOLOv8, GDino, RTMPose (ONNX) & Trackers (ByteTrack & BotSORT) & Tapnet with custom ROIs + FastAPI GPU exe

Automated football tactical analysis system using Deep Learning and Object Tracking to extract real-time player stats, heatmaps, and passing networks directly from video.

Real-time YOLO detection, multi-object tracking, and interactive object locking with TensorRT—optimized for NVIDIA Jetson (ARGUS via GStreamer) and GPUs.

Robust Player Tracking & Behavior Analysis pipeline for SoccerNet Benchmark. Features YOLO11x, BoT-SORT (GMC), and Adaptive Field Masking. Artificial Vision Project 2025/26 @ Unisa.

📹 [Video] Real-time multi-face tracking using MTCNN and BoxMot

Multi-object tracking system for retail environments using YOLOv12, BoT-SORT, and homography-based cross-camera re-identification. Features post-processing heuristics and spatiotemporal matching for robust visitor trajectory generation.

In computer vision, this project meticulously constructs a dataset for precise 'Shoe' tracking using YOLOv8 models. Emphasizing detailed data organization, advanced training, and nuanced evaluation, it provides comprehensive insights. A final project for the Computer Vision cousre on Ottawa Master's in (2023).

Computer vision pipeline for underwater object detection (mines, UUVs, divers) — custom YOLOv8 training with physics-based synthetic data generation and iterative hard-negative mining.

A project to track dancers in video and maintain stable IDs through crossings, occlusions, re-entries, and temporary tracking loss. Frame-to-frame tracking preserves continuity, while periodic face recognition corrects identities, even with similar outfits. YOLO , BotSort , insightface

Real-time C++ multi-object tracker (BoTSORT + YOLOv8 kmodel) running natively on Kendryte K230 at 22 FPS under RTOS

Modular multi-camera person tracking pipeline: YOLO26 + BoT-SORT detection/tracking, clothes-agnostic Re-ID (C2DResNet50 + CAL) and a global movement graph with an interactive Streamlit dashboard. Validated on the MEVID benchmark.

Real-time soccer player tracking & re-identification with YOLOv11, plus a benchmarked comparison of ByteTrack, BoT-SORT, DeepSORT, and Norfair on 720p/4K footage. Python · OpenCV · Ultralytics.

Real-time object detection and tracking system with YOLO11 and BoT-SORT

Offline fall detection pipeline using YOLOv8-Pose + BoT-SORT/ByteTrack. Dual detection methods (pose geometry & trajectory scoring), polygon zone filtering, webcam/video/RTSP support, annotated video & JSON output.

Real time vehicle compliance monitoring , seatbelt , mobile phone use , and license plate recognition using YOLO11 and BotSort

Computer vision system for clamp detection and stable fixed-ID tracking using YOLO11m, BoT-SORT, and circular motion modeling.

YOLO11 and BoT-SORT people-flow analytics for escalator direction counting.

Defense-Grade AI C4ISR Perception, Multi-Model WBF Consensus, ReAct AI Copilot & Persistent 3D Target Tracking Platform.