Visual Odometry Quiz

Answers and explanations appear as you take the quiz.

1. What does visual odometry primarily estimate?
   • The camera's incremental motion (rotation and translation) over time
   • The color temperature of the scene
   • The number of objects in view
   • The camera's manufacturer
2. What is 'drift' in visual odometry?
   • The camera physically sliding on a surface
   • A sudden loss of all image data
   • Accumulation of small per-frame errors that grow over the trajectory
   • The intentional rotation of the lens
3. Why is absolute scale ambiguous in ordinary monocular visual odometry without a metric reference?
   • A color sensor cannot detect image features
   • The image geometry can support differently scaled scenes and translations that project alike
   • Every monocular camera records absolute depth directly
   • A single-camera sequence has no rotation information at all
4. How does visual-inertial odometry improve robustness?
   • By adding more cameras of the same type only
   • By reducing the frame rate
   • By converting images to text
   • By fusing camera data with IMU (accelerometer/gyroscope) measurements
5. How does plain visual odometry differ from full visual SLAM?
   • VO builds a global map with loop closure; SLAM only tracks local motion
   • They are exactly the same thing
   • VO focuses on local frame-to-frame motion, while SLAM also builds and maintains a global map with loop closure
   • SLAM does not use cameras at all
6. What do direct methods of visual odometry minimize, instead of matching explicit features?
   • Photometric (pixel intensity) error between frames
   • The number of pixels in the image
   • The camera's battery consumption
   • The text labels in the scene
7. What physical quantity gives a calibrated stereo visual-odometry system a metric reference?
   • The number of letters in the camera brand
   • The chosen image file extension
   • The scene's average pixel brightness alone
   • The known separation, or baseline, between the two cameras
8. Why can a moving vehicle in view interfere with a static-scene visual-odometry estimate?
   • Every tracked pixel must belong to a fixed background point
   • Its image motion includes object movement that is not explained by camera movement alone
   • Moving objects reveal the camera's manufacturer automatically
   • Object motion changes only the file's compressed byte count