Giter VIP home page Giter VIP logo

Comments (6)

Alonmeytal avatar Alonmeytal commented on June 16, 2024

@nesnes @adujardin

from zed-python-api.

nesnes avatar nesnes commented on June 16, 2024

You can save the color image and the depth one in a file, using OpenCV for example, but we won't recommend this solution.

The ZED SDK offers the SVO file format to record a sequence from the ZED. After recording one you can play it back in the SDK to fully simulate a ZED.
You can record a sequence from the ZED Explorer tool, or from the SDK.
To play it back, just specify its path in the initParameters: https://github.com/stereolabs/zed-python/blob/master/examples/read_svo.py#L42

from zed-python-api.

Alonmeytal avatar Alonmeytal commented on June 16, 2024

@nesnes thanks for the response, but I think you didn't understand my use case:
My app provides a view & record functionality (just like the Zed Viewer), as my users would like to watch their subject "live". We'd also like to use the frames coming on the go for some ML processing, further complicating matters.

from zed-python-api.

nesnes avatar nesnes commented on June 16, 2024

From what you said, you will generate many sequences with the ZED, extract the images and the depth, save them on your hard drive, and give them as an input to your machine learning algorithm.

In these conditions, using an SVO file that requires being opened by the ZED SDK won't be the best solution.
I'll suggest you to take a look at the SVO Export sample that turns SVOs into image and depth sequences in 16-bit png format. It uses OpenCV.
https://github.com/stereolabs/zed-examples/tree/master/svo%20recording/export

This should be a great tool to generate an ML dataset from your SVO files.

from zed-python-api.

Alonmeytal avatar Alonmeytal commented on June 16, 2024

@nesnes if you could answer 2 "follow-up questions":

  1. In the ZED Viewer: How do you retrieve the image for preview (on-screen) while also recording it to SVO?
  2. I understand that saving the video stream from both cameras allow the SDK to create the depth reading from the saved data (as if it was "fresh" data coming in), but is there any transformation that would allow me to keep the result of this calculation? Will using depth.get_data() get me a matrix of depth values aligned to one of the cameras?

Thanks!

from zed-python-api.

github-actions avatar github-actions commented on June 16, 2024

This issue is stale because it has been open 30 days with no activity. Remove stale label or comment otherwise it will be automatically closed in 5 days

from zed-python-api.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    πŸ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. πŸ“ŠπŸ“ˆπŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❀️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.