# Stereo Depth Perception gone wrong
**URL:** https://forum.opencv.org/t/stereo-depth-perception-gone-wrong/2457
**Category:** C++
**Tags:** calib3d
**Created:** [March 29, 2021, 2:26pm UTC](https://forum.opencv.org/t/stereo-depth-perception-gone-wrong/2457 "2021-03-29T14:26:00Z")
**Posts on this page:** 2
**Page:** 1
### Author:  [@alpi](https://forum.opencv.org/u/alpi)
#### Post date: [March 29, 2021, 2:26pm UTC](https://forum.opencv.org/t/stereo-depth-perception-gone-wrong/2457/1 "2021-03-29T14:26:00Z")
I’ve build a system with 2 cameras (not webcams, something with a good mounting plate) I have them mounted on a 3d printed plate to keep them parallel in yaw and on a single plane in roll. Having a plate with known dimensions gives me the exact distance between cameras. The goal is to get a distance (x,y,z components) to a known object in a scene. I calibrated both cameras separately using chessboard pattern to get a camera matrix.
Here is the overview of the steps I take:
1. grab a frame from both cameras and remove distortions
2. run yolo on a left image to get a bounding box of an object in a scene
3. create a pattern using prev calculated bounding box and run pattern match on a right image
4. triangulate using a single pixel(box center in the left image and matched area center in the right) with the following formula
Z\_component = distance\_between\_cams\_mm \* horizontal\_focal\_distance\_from\_camera\_matrx /
(offset\_from\_the\_optical\_center\_in\_left\_image - offset\_from\_the\_optical\_center\_in\_right\_image)
**Question: horizontal\_focal\_distance\_from\_camera\_matrx \<— which cam should I use left/right??? they have the same lenses but focal distances from cal are slightly different**
5. Now that we have a distance between an object plane and a camera plane we can calculate horizontal and vertical distance components relative to the left camera:
// X = offset\_from\_center\_x \* Z\_component / focal\_x
// Y = offset\_from\_center\_y \* Z\_component / focal\_y
After all this work accuracy isn’t there, +/- 30 cm when an object is 2 meters away and I’m looking to get distance calculation on objects 8-10 metes away. Things need to improve.
**Now the questions:**
**1. How accurate do these systems get from your experience?**
**2. Is there anything obvious that I might be doing wrong? Any steps that I’m missing? I found a stereo calibrate function in the opencv api, docs say it translates an image from left to right camera, not sure why would I need to do it.**
I know this might be a vouge question, but I have no one else to ask these questions besides this forum.
PS\>Please don’t point me to the Disparity Calculation tutorial on the opencv, it shows a trivial sample image and does not go into details on how to tune a disparity map. Plus I don’t need to get the depths of everything just a single object in the scene.
---
### Author:  [@laurent.berger](https://forum.opencv.org/u/laurent.berger)
#### Post date: [March 29, 2021, 3:46pm UTC](https://forum.opencv.org/t/stereo-depth-perception-gone-wrong/2457/2 "2021-03-29T15:46:16Z")
Hi,
A book : [Multiple View Geometry in Computer Vision](https://www.cambridge.org/core/books/multiple-view-geometry-in-computer-vision/0B6F289C78B2B23F596CAA76D3D43F7A)