Depth Estimation: Understanding 3D Space

Why Depth Matters for Drones

A standard camera captures a flat 2D image — it loses all distance information. Depth estimation recovers the 3D structure of the scene, which is critical for obstacle avoidance, terrain following, 3D mapping, and landing on uneven surfaces.

Stereo Triangulation Mathematics

Stereo vision uses two cameras separated by a known baseline. The depth is calculated from the disparity (horizontal pixel difference) between the two images.

Depth Map Visualization

Depth maps encode distance as colors. Common visualizations:

Hands-On Project: Simple Stereo Depth

Key Takeaways

• Depth estimation recovers 3D structure from 2D images
• Stereo vision uses triangulation from two cameras (needs calibration)
• Structured light projects patterns for indoor/short-range depth
• ToF cameras directly measure distance using light travel time
• Depth maps encode distance as color for visualization
• Disparity = horizontal pixel shift between left/right images
• Z = (baseline × focal_length) / disparity