Stereo Disparity Depth Calculator
Calculate ideal rectified stereo depth and first-order depth uncertainty from focal length in pixels, baseline and disparity.
YOUR CALCULATION
Result
—
Calculation steps
Work through one step at a time or reveal the complete calculation. The steps use your current inputs.
How to calculate
Use a calibrated parallel rectified camera model, with principal-point disparity offsets already corrected.
Depth=focal pixels×baseline/disparity; u(depth)=focal×baseline×u(disparity)/disparity²
Worked example
1000 px focal length, 0.1 m baseline and 20 px disparity give depth 5 m. A 0.5 px disparity uncertainty gives first-order depth uncertainty 0.125 m.
Assumptions and input details
Positive depth/disparity and uncertainty ≤20% of disparity for the local linear approximation. No image matching, lens distortion, rectification, occlusion or measurement calibration is performed. Baseline/focal uncertainties are excluded.
Unit definitions
Unit selection is independent of language. Each selector contains only units for its physical quantity. Calculations use defined base units internally.
Choose from 23 length definitions, including explicitly labelled regional measures. Area conversions square the length factor; geometric volumes cube it.
Regional measures are not interchangeable merely because their names look similar. This is a documented selection, not a claim to include every historical unit.
NIST measurement tables · Japanese traditional units · Mainland China and Hong Kong unit distinctions
Using this calculator
Can I enter my own problem?
Yes. Replace the example values with your own inputs. The result, calculation steps, tables and applicable diagrams update from those inputs. Blank or invalid values clear the result; example values are never silently substituted for missing inputs.
Are the results exact?
Results use floating-point arithmetic and displayed rounding. Read the formula, assumptions and any stated data precision before interpreting the result.
Is my input uploaded?
The calculation runs in your browser. No account, file upload or external AI service is required. Inputs are not saved between page reloads.
Calculate horizontal, vertical and diagonal field angles and scene coverage from sensor dimensions, focal length and subject-plane distance.
Propagate independent standard uncertainties through a sum, difference, product or quotient using first-order sensitivities.
Reflect, rotate or translate a point in the coordinate plane. Keep exact fractional coordinates and compare the original point with its image on equal-scale axes.
Reserved advertising space.