Hi, I am Vighnesh Budharapu

• Benchmarked YOLOv8, YOLOv12, and Faster R-CNN on a custom 9K-frame cricket ball dataset at 4K and 1080p resolutions, achieving mAP50 of 0.94, 0.87, and 0.92; conducted ablation studies with hue augmentation to evaluate cross-color generalization • Engineered a classical CV pipeline (background subtraction, color-based segmentation, ROI masking, domain heuristics) achieving real-time 30 FPS with detection accuracy comparable to ML models; validated on dynamic umpire-mounted camera footage • Implemented homography-based camera-to-field coordinate projection achieving 98% accuracy; applied Kalman and particle filters for occlusion-robust ball trajectory tracking • Deployed YOLOv8 and classical CV pipelines as a Dockerized FastAPI service on AWS EC2 with Nginx reeverse proxy, SSL, and GitHub Actions CI/CD; automated build, push to ECR, and zero-touch deployment on every commit.