Nithin Varghese

Smart CCTV Analytics Company

• Led enterprise-scale computer vision projects end-to-end, delivering advanced solutions for:
  - Coal India Video Analytics: Deployed no-PPE detection, fire detection, crowd counting, overmanning, tailgating detection, idle time tracking, zone intrusion detection, and vehicle counting—successfully rolled out to major coal mines across India.
  - HPCL Wagon Tracking & Counting: Reduced human error rates at industrial plants by implementing automated CCTV-based monitoring and analytics.
  - Banking & Retail Sector: Designed complete solution architecture and managed edge-based deployments for mission-critical computer vision models, optimizing real-time video analytics and resource utilization.
  - Facial Recognition Systems: Oversaw full deployment cycle, from model development to on-site rollout, ensuring high accuracy and scalability.
• Spearheaded hardware-specific optimization of deep learning models using TFLite, TensorRT, and OpenVINO for seamless machine learning deployments on Raspberry Pi, CPU, and GPU environments—boosting platform performance and cost efficiency across the organization.
• Developed custom algorithms for specialized computer vision applications, including robust image processing pipelines tailored to diverse client requirements (e.g., steel roll safety checks, exam security, ATM monitoring, medical deep learning).
• Managed high-impact additional projects, such as:
  ArcelorMittal: Implemented automated person-under-steel-roll detection to enhance operational safety.
  Education Examinations: Deployed invigilator movement detection and examination paper tampering detection, and other examination related usecases while scaling to over 10,000 cameras per exam across India.
  ATM Security Use Cases: Introduced helmet and mask detection, intrusion alerts, camera tampering/fault detection, and other advanced video analytics measures—rolled out widely across multiple banking ATMs.
• Boosted innovation and scalability by continuously researching state-of-the-art techniques in computer vision, deep learning architectures, and AI-driven security solutions.

• Created Novel algorithm for camera Tamper detection
• Trained and deployed models for masked face , helmet detection
• Trained and deployed models for crowd detection use case

• Receipt Information Extractor: Developed a computer vision solution that processes an image of a receipt to automatically detect relevant data fields using YOLOv3-based object detection, then seamlessly passes the extracted data through an OCR pipeline to produce a structured CSV output.