{
  "id": 9161143,
  "title": "How Tata Elxsi detects industrial safety risks in seconds on AWS",
  "url": "https://urgent.news/2026/09/22/how-tata-elxsi-detects-industrial-safety-risks-in-seconds-on-aws",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-22T15:19:54.000Z",
  "source": {
    "name": "AWS Machine Learning",
    "slug": "aws-machine-learning",
    "url": "https://aws.amazon.com/blogs/machine-learning/how-tata-elxsi-detects-industrial-safety-risks-in-seconds-on-aws/"
  },
  "original_language": "en",
  "account": "Tata Elxsi developed IRIS, a real-time industrial safety platform built on AWS, to detect safety risks in seconds instead of minutes. This platform aims to transform passive recording systems into continuous, automated monitoring solutions that scale with the number of cameras. IRIS operates in the Asia Pacific (Mumbai) AWS Region to meet data-residency requirements and provide low-latency access to customer facilities in India. The solution follows a serverless, event-driven architecture that includes edge acquisition and processing, real-time event streaming, context analysis, alert generation, compliance storage, and continuous learning.\n\nAt the edge, Tata Elxsi uses AWS IoT Greengrass on industrial-grade, GPU-equipped servers to process video frames and extract relevant metadata. Frames containing people, vehicles, or equipment are uploaded to Amazon S3, while the streaming layer only carries structured event data with minimal information. This design reduces the amount of video sent to the cloud by 70-80%, significantly lowering monitoring costs. The real-time event stream, managed by Amazon Kinesis Data Streams, serves as the backbone of the platform, facilitating fast transmission of safety-relevant metadata.\n\nIRIS analyzes the video content at the edge, applying first-pass models to identify frames containing relevant objects and then running more comprehensive models on selected frames. This approach ensures that the cloud-based models have access to the necessary visual data while minimizing the amount of data transmitted. The system generates actionable alerts based on the detected safety risks, ensuring compliance and enabling proactive measures to enhance workplace safety.",
  "summary": "Learn how Tata Elxsi built IRIS, a real-time industrial safety platform on AWS. IRIS filters camera video at the edge, streams metadata through Amazon Kinesis, runs computer vision on Amazon SageMaker AI, and correlates detections into high-confidence alerts, detecting unsafe conditions in seconds instead of minutes.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}