How does a Kinect sensor generate a depth map?

• A. It projects IR light into the room and reads the distortion in the IR pattern to translate it into a depth map.
• B. It uses visible color cameras to estimate depth from shading.
• C. It relies on ultrasonic waves to measure distance.
• D. It computes depth from stereo vision using two visible cameras.

Answer: (A)

Depth sensing with structured light works by projecting a known infrared pattern and watching how that pattern is distorted by the scene. In the original Kinect, an IR projector emits this pattern and an IR camera records the reflected pattern from the room. By comparing what the camera sees to the known reference pattern, the system determines how much each portion of the pattern has shifted. That shift is interpreted through triangulation to yield a distance for every pixel, producing a depth map.

This approach is different from using shading with visible light, ultrasonic distance measurements, or stereo vision from two visible cameras. Structured light gives dense, per-pixel depth information in real time, which is why it’s used to generate the Kinect’s depth map.