How Orbital Insight is harnessing machine vision technology - Interview with James Crawford
summary
Machine vision uses deep learning and traditional computer vision to turn satellite pixels into counts and measurements, not vague examples. The system counts cars in parking lots to infer retail performance, reads oil-tank lids and supertanker locations to estimate inventory flows, and measures lake and crop area to predict shortages. Imagery volume explodes so humans can’t keep up (estimated equivalent of all New Yorkers staring at images), and resolution is ~30 cm per pixel so analysis is aggregate not individual.
AI-written summary · about
chapters (4)
- 0:00Start
- 0:03What Machine Vision Is and How It Relates to or Differs from Deep Learning and Computer Vision
- 1:09Why Is Machine Vision the Appropriate Technology for the Task
- 2:05What Industries Do You Think Will Be Most Impacted the Work You'Re Doing
related talks
21mThe eyes of industry 4.0 - Vision intelligence and machine learning
28mVision, Big Data and AI
27mComputer vision for automated quality inspection
23mComputer Vision Toolbox - Connected Computer Vision & AI Quality Inspection at Scale!
29mApplied Custom Vision
01mWe talk with
14mComputer vision on edge devices
59mThe bold promise of teaching computers to understand the visual world