Intro

Stereo Depth from Disparity

~8 mincode completion

Implement stereo_depth(f, B, disparity) returning .

Examples

f=2, B=10, d=4 gives Z=5

Input
stereo_depth(2, 10, 4)
Output
5

The same rig, a quarter of the disparity, is four times farther

Input
stereo_depth(2, 10, 1)
Output
20

A long focal length and a small disparity: Z = 240

Input
stereo_depth(100, 0.12, 0.05)
Output
240

Hints

Hint 1

Convert the input with before doing elementwise work.

Hint 2

A common slip here: multiplied by disparity instead of dividing.

Requirements

  • f: focal length

  • B: baseline

  • disparity: scalar or array of x_L - x_R

  • Return depth, same shape as disparity

Constraints

  • Allowed library: NumPy only

  • Time limit: 200 ms, Memory: 64 MB

Try similar problems(4)
Intro
Pinhole Projection

Calculus, 3D Vision, and Depth · ~10 min

Intro
Image Gradient Magnitude

Calculus, 3D Vision, and Depth · ~12 min

Intro
Gradient Orientation

Calculus, 3D Vision, and Depth · ~8 min

Intro
Back-Project a Pixel

Calculus, 3D Vision, and Depth · ~10 min

Where this shows up

~8 min

8 employers weight this skill

4 autonomy companies, 1 defense company, 1 health and bio company, 1 enterprise vendor, 1 AI product company. Top match scores 93.

Python
import numpy as np


def stereo_depth(f, B, disparity):
    """
    Depth from a rectified stereo pair.

    Args:
        f:          focal length
        B:          baseline
        disparity:  scalar or array of x_L - x_R

    Returns:
        depth, same shape as disparity
    """
    # YOUR CODE HERE
    pass
Loading docs…

The AI Mentor needs an account

It reads your code and the failing tests and nudges you toward the fix without handing you the answer. Free accounts get it on every problem you're working on today.