Stuck on an issue?

Lightrun Answers was designed to reduce the constant googling that comes with debugging 3rd party libraries. It collects links to all the places you might be looking at while hunting down a tough bug.

And, if you’re still stuck at the end, we’re happy to hop on a call to see how we can help out.

Disparity Confidence Threshold

See original GitHub issue

Background: Currently we hard-code in firmware the disparity confidence threshold to be 200 out of a configurable range of 0 to 255.

Improvement: Allow this to be set from the host as a parameter in the depth entry in config: https://github.com/luxonis/depthai/blob/0611eb701fffbcd743644e4f0d2c7b92e60b7cd9/depthai.py#L382

Issue Analytics

State:
Created 3 years ago
Comments:9

Top GitHub Comments

1reaction

ConnorChristiecommented, May 27, 2020

@Luxonis-Brandon It was more about curiosity and that I am also looking for other ways to communicate with the depthai board instead of using USB. Mainly so I can transition to utilizing a microcontroller instead of a raspberry PI for example.

When you say “hence why we made a fully-open-source API on the host and will be doing the same for I2C, SPI, and UART interface” does this mean you are adding those additional communication protocols in addition to USB? Or is this something that is already functional?

Also, this doesn’t really have anything to do with the Github issue so if you want, we can take this elsewhere but I just didn’t know where to start the convo.

0reactions

Luxonis-Brandoncommented, Jul 8, 2020

Merged to master today.

Top Results From Across the Web

StereoDepth - DepthAI documentation - Luxonis

For the final disparity map, a filtering is applied based on the confidence threshold value: the pixels that have their confidence score larger...

On the confidence of stereo matching in a deep-learning era

Abstract—Stereo matching is one of the most popular techniques to estimate dense depth maps by finding the disparity between matching pixels on two, ......

DEEP STEREO CONFIDENCE PREDICTION FOR DEPTH ...

In this step, predicting the confidence of an estimated disparity is one of the most important issues. Conventionally, the left-right consistency check or...

a novel confidence measure for disparity maps by pixel-wise ...

A NOVEL CONFIDENCE MEASURE FOR DISPARITY MAPS BY PIXEL-WISE COST ... In this paper, we introduce a novel confidence measure ... higher than...

Learning a confidence measure in the disparity domain from O ...

for confidence estimation based on features computed in the disparity domain, making our proposal ... The error threshold is set to τ =...