跳到主要内容Skip to main content

机器视觉Computer Vision

Computer Vision

  • 图像语音视频Image, speech & video
  • 第二站 · 上手Station 2 · Hands On
解决什么问题What problem it solves

让摄像头「看懂」画面——识别人、物体、文字、动作。Lets a camera "see" — recognise people, objects, text and actions.

这是什么What it is

让计算机从图像和视频中提取并理解信息的技术。

Technology that extracts and understands information from images and video.

为什么需要知道Why it matters

它是自动驾驶、安防、医疗影像的技术基础。它与多模态大模型是同一方向的两个阶段。The technical foundation of autonomous driving, security and medical imaging — two stages along the same direction as multimodal models.

出处Sources
  • 斯坦福 CS231n 计算机视觉课程Stanford CS231n: Deep Learning for Computer Vision ↗
  • AlexNet 论文(ImageNet)ImageNet Classification with Deep CNNs ↗