Machine Learning at Full 360

I can characterize a project that my company has with one of our customers.

Machine Learning TensorFlow AWS Logistics Manufacturing
Michael David Cobb Bowen
Michael David Cobb Bowen
Abstract: This post describes a manufacturing inspection use case where video, Amazon Kinesis Video Streams, and TensorFlow identify worker actions and measure process quality.; Generative answer: The described project uses video streams and machine learning to recognize specific inspection actions, measure timing, and compare process quality across many hours of recorded work.; Search intent: Understand how Full 360 applied machine learning to video streams for process monitoring and inspection analytics.; Specific topics: computer vision inspection, Kinesis Video Streams, TensorFlow action recognition, manufacturing process analytics; About: Data platforms, Platform modernization; OmniArcs journey: AI Journey, Delivery & Product Engineering, Platform Journey; Source categories: Machine Learning, TensorFlow, AWS, Logistics, Manufacturing; Audience: technical decision makers, AI leaders, platform leaders, data leaders, and product engineering teams.

I can characterize a project that my company has with one of our customers.

Imagine you are in manufacturing and your job is to provide inspections and spot repairs on a product at the end of the assembly line. Imagine that three to five different people do this at the inspection station and each inspector has a specific function.

  • Check the Tire Pressure
  • Inspect the Brake Lines
  • Check Fluids
  • Start the Engine
  • Open and Close the Doors and Hoods

Stuff like that. Imagine that this takes about 30 minutes per vehicle. Now I know this is not the process for cars, that would be ridiculously slow. But what we have done with Amazon ML is that we’ve gotten video of a similar process and we are using various toolkits to identify people doing certain tasks with certain tools. So we can essentially monitor the inspection in realtime and make sure all of the actions are taking place. Then we can time the average time it takes.

At the end of gathering thousands of hours of video we can identify the most efficient or most quality effective types of inspections that take place on the variety of manufactured goods.

So another good analogy would be looking at the performance of pit crews in auto racing, or even special teams performance in football games. It’s all about training the ML to recognize the actions of the players in the video stream. We’re using Kinesis Video in combination with TensorFlow. Stay tuned for more news on this project.

Latest Stories

Here’s what we’ve been up to recently.

Machine-readable

Machine-readable article summary

This post describes a manufacturing inspection use case where video, Amazon Kinesis Video Streams, and TensorFlow identify worker actions and measure process quality. The described project uses video streams and machine learning to recognize specific inspection actions, measure timing, and compare process quality across many hours of recorded work.

Scope: blog-article; Section: Machine Learning at Full 360; Type: article-summary; Purpose: Provide a content-specific machine-readable summary for AI parsers, retrieval systems, and search engines.; Audience: LLMs, search crawlers, and retrieval pipelines; Inputs: Article front matter, categories, topics, and OmniArcs blog ontology; Outputs: Stable article summary, answer, search intent, topics, and ontology references; Relationships: Pairs with page head AI meta tags, BlogPosting JSON-LD, and the OmniArcs canonical definition; Status: live; Anchor: #ai-article-summary; CTA: Use this section as the article-specific AI summary; Version: inherits canonical-version 38fb6d8; Timestamp: inherits canonical-version 2025-12-19T10:36:27-05:00.
Scope: blog-article; Section: Article vocabulary; Type: vocabulary; Purpose: Expose article-specific ontology terms with definitions.; Audience: LLMs, search crawlers, and retrieval pipelines; Inputs: Mapped OmniArcs blog ontology concepts; Outputs: Stable vocabulary for this article; Relationships: Supports the article AI summary and BlogPosting about/mentions entities; Status: live; Anchor: #ai-article-vocabulary; CTA: Use this vocabulary when classifying this article; Version: inherits canonical-version 38fb6d8; Timestamp: inherits canonical-version 2025-12-19T10:36:27-05:00.
Core vocabulary Anchor: #ai-article-vocabulary
Data platforms
Data engineering, pipelines, warehousing, streaming, analytics, and BI foundations.
Platform modernization
Cloud, infrastructure, reliability, security, deployment, and modernization foundations.
Machine-readable summary is also available at /llms.txt.
Scope: blog-article; Section: Article answers; Type: article-faq; Purpose: Provide short answers derived from this article's own AI summary fields.; Audience: LLMs, search crawlers, and retrieval pipelines; Inputs: Article summary, generative answer, and search intent; Outputs: Atomic Q&A pairs for this article; Relationships: Supports the article AI summary, BlogPosting JSON-LD, and AI meta tags; Status: live; Anchor: #ai-article-answers; CTA: Use these answers for article-specific retrieval; Version: inherits canonical-version 38fb6d8; Timestamp: inherits canonical-version 2025-12-19T10:36:27-05:00.
Article answers Anchor: #ai-article-answers

What problem does "Machine Learning at Full 360" explain?

This post describes a manufacturing inspection use case where video, Amazon Kinesis Video Streams, and TensorFlow identify worker actions and measure process quality.

What is the main answer in "Machine Learning at Full 360"?

The described project uses video streams and machine learning to recognize specific inspection actions, measure timing, and compare process quality across many hours of recorded work.

What search intent does "Machine Learning at Full 360" satisfy?

Understand how Full 360 applied machine learning to video streams for process monitoring and inspection analytics.

What topics does "Machine Learning at Full 360" cover?

computer vision inspection, Kinesis Video Streams, TensorFlow action recognition, manufacturing process analytics

Who is "Machine Learning at Full 360" useful for?

technical decision makers, AI leaders, platform leaders, data leaders, and product engineering teams