LearnViz CompSci
Home / Learn / Graphics, Vision & Media / Stereo Vision

Advanced Topic 43 of 49 Graphics, Vision & Media

Stereo Vision

Recovering depth from two viewpoints.

How it works

Stereo vision recovers depth from two images taken by cameras at slightly different positions, like human eyes. After calibration and rectification, which aligns the images so corresponding points lie on the same row, the system finds the horizontal disparity between matching points; depth is then inversely proportional to disparity: Z equals focal length times baseline divided by disparity. Matching uses block matching, semi-global matching or deep networks, producing a disparity map that can be converted into a 3D point cloud.

Where it is used

Robot navigation, autonomous vehicles, depth cameras, 3D reconstruction, augmented reality and industrial measurement use stereo vision.

Common pitfall

Textureless areas, repeated patterns, occlusions and reflective surfaces make matching ambiguous. Depth accuracy falls with distance and depends on baseline and resolution. Poor calibration gives large errors, and cameras must be synchronized. Use calibrated rigs, appropriate baselines, confidence checks and consistency filtering, or combine with other sensors such as lidar.

Where it fits in the course

Stereo Vision is topic 43 of 49 in Graphics, Vision & Media, rated Advanced. It follows Optical Flow. The next topic is Structure from Motion.

Practice and explore

How to study this topic

  1. Read the explanation above and restate the definition in your own words.
  2. Open the interactive lesson and answer its mini quiz.
  3. Read the common pitfall, then write a short example that avoids it.
  4. Check your understanding in the Graphics, Vision & Media quiz, and revisit the topic if you miss a question.

Frequently asked questions

What is Stereo Vision?
Recovering depth from two viewpoints. It belongs to Graphics, Vision & Media and is an advanced-level topic.
Where do people use Stereo Vision?
Robot navigation, autonomous vehicles, depth cameras, 3D reconstruction, augmented reality and industrial measurement use stereo vision.
What is the most common mistake with Stereo Vision?
Textureless areas, repeated patterns, occlusions and reflective surfaces make matching ambiguous.
What should I learn before this topic?
Start with Optical Flow, the topic just before it in Graphics, Vision & Media.
How can I practice it?
Answer the mini quiz in the interactive lesson, then take the Graphics, Vision & Media quiz.
Is Stereo Vision hard to learn?
It is an Advanced topic. Expect to read the explanation more than once and to connect it with earlier topics. Working through a small example by hand helps most.
How long does it take to learn Stereo Vision?
Most learners can read the explanation and finish the interactive lesson in under an hour. Fluency comes from applying the idea, so plan a few short practice sessions with the quiz.
Which topics are related to Stereo Vision?
Optical Flow, Structure from Motion, Image Classification are closely connected. The full list is in the related topics section of this page.
What should I study after Stereo Vision?
Continue with Structure from Motion, the next topic in Graphics, Vision & Media.

Related topics