Logo Logo
deutsch
directory schraeg
Knowledge
Codecs
Hardware
Camcorders· Cinema-Kamera· Computers· Drohnen· GPU· Kamera-Zubehör· Video-DSLR· accessories
Software
Compositing· Color correction· DV Editing
DV-Movies

HowTo
Shooting· Sound
Misc
Forschung· Reviews· Streaming
/// News
Define video masks simply by description using new AI algorithm

Define video masks simply by description using new AI algorithm

[13:21 Wed,1.December 2021   by ]    

This new Deep Learning algorithm from a team in Israel does something very interesting for video editing: based on a simple description of an object in a video in the form of a short sentence, it recognizes the object and exposes it via mask.

TextMask-Example




The description of the desired object can be quite complex and can also describe it by dynamic relations to other objects or its position in space, like "a man in a white T-shirt and blue pants riding a surfboard", "a big monkey playing with a baby monkey", "the zebra in the back on the right standing behind another one looking to the left" or "a person on a motorcycle".

TextMask-Algo


To do this, the AI algorithm performs a whole series of complex tasks from the areas of text and video understanding: first it must "understand" the input text, then it must correctly recognize all the objects in a video, including dynamic relationships, and identify the correct object based on the description given by the user (including its properties, such as its color and relationships to another object, such as "the tennis racket in the hand of the player with the, red shirt").



Then the object must be separated from the background and tracked across all frames in which it appears, forming a dynamic mask from it - even as it changes appearance through movement and perspective changes. This no longer has to be adjusted by hand afterwards. Even dynamic actions that span a video sequence are correctly detected in a longer video, such as "the hand giving the dog a ball."

TextMask-Examples


The new algorithm demonstrates quite vividly the complex tasks that can now be accomplished by combining different Deep Learning methods. It could be used, for example, to find specific objects in a video archive together with their relationship to other objects and to extract them.
As always, the corresponding program code can also be tried out for yourself - assuming the appropriate prior knowledge.

Link more infos at bei github.com

deutsche Version dieser Seite: Videomasken einfach per Beschreibung definieren durch neuen KI-Algorithmus

  

  Vorige News lesen Nächste News lesen 
bildSony stellt wegen Chipmangel die Produktion von Sony Alpha 7 II, Alpha 6100/6400 und PXW-Z190 ein bildSonys professionelle "Alpha"-Drohne Airpeak S1 wird ab 24. Dezember ausgeliefert


related news:1E0New AI automatically perfectly exposes objects from photos 7.August 2022
AI-based grading solution fylm.ai v1.3 learns some context 26.July 2022
Anyone can do art: Meta's new AI acts as a painter at will 19.July 2022
Video stabilization: AI-supported Mercalli V6 SAL introduced 18.July 2022
Is AI Revolutionizing Photography? Object-based editing with the help of DALL-E 2 30.June 2022
DaVinci Resolve 18 Beta 5 - incl. AI stabilizer for gyro metadata and 10 bit preview 25.June 2022
See in the dark by AI with color 22.May 2022
alle Newsmeldungen zum Thema Machine Learning


[nach oben]
















Archiv Newsmeldungen

2022

August - July - June - May - April - March - February - January

2021
December - November - October - September - August - July - June - May - April - March - February - January

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

2003

2002

2001

2000






































deutsche Version dieser Seite: Videomasken einfach per Beschreibung definieren durch neuen KI-Algorithmus



last update : 10.August 2022 - 18:02 - slashCAM is a project by channelunit GmbH- mail : slashcam@--antispam:7465--slashcam.de - deutsche Version