Project Description We are looking for an experienced Computer Vision engineer to develop a high-performance real-time object tracking system running on Linux. The system will allow a user to select a target within a live video stream and maintain robust tracking under dynamic conditions. This is not a basic OpenCV demo project. We require a stable, production-oriented architecture with strong tracking persistence under motion, scale variation, partial occlusion, and illumination changes. Core Functional Requirements • Linux-based implementation (Ubuntu preferred) • Real-time video stream processing (USB / CSI / RTSP compatible) • User-initiated ROI selection (click-to-track) • Persistent target tracking at minimum 30 FPS (hardware dependent) • Continuous output of: • Bounding box • Target centroid (X,Y) • Confidence metric (if applicable) Performance Expectations The tracker must: • Handle rapid target motion • Adapt to scale and orientation changes • Maintain lock under partial occlusion • Recover gracefully if tracking confidence drops • Avoid drift over time A re-detection or hybrid tracking strategy is preferred if it improves robustness. Technical Requirements Preferred stack: • Python + OpenCV OR C++ + OpenCV • Modular architecture • Hardware acceleration support (CUDA / TensorRT) is a strong plus • Experience with: • Siamese-based trackers • DeepSORT-like approaches • Hybrid detection + tracking pipelines Clean, well-documented code is mandatory. Deliverables 1. Fully functional Linux application 2. Source code repository 3. Setup instructions + dependency list 4. Short demo video 5. Optional: performance benchmark report (latency / FPS)