scispace - formally typeset
Proceedings ArticleDOI

Towards automated post-production and semantic annotation of films

Reads0
Chats0
TLDR
This paper provides an overview of the relevant computer vision technologies which could be used to automate the more time intensive parts of these tasks, provided their performance reaches the high quality standards of the film industry, and semantically annotate the films.
Abstract
Film post-production nowadays can be, and most often is, done in the digital domain using computers. There are plenty of tools available for 3D CGI effects, 2D image manipulation of individual frames, color correction and grading, audio-visual synchronization and video editing. Every task, however, still requires a considerable amount of human interaction. In this paper, we will provide an overview of the relevant computer vision technologies which could be used to automate the more time intensive parts of these tasks, provided their performance reaches the high quality standards of the film industry, and semantically annotate the films.

read more

Citations
More filters
Patent

Method and system of identifying non-distinctive images/objects in a digital video and tracking such images/objects using temporal and spatial queues

TL;DR: In this article, a method and system to identify and locate images/objects which may be characterized as non-distinctive or featureless and which would be difficult to locate by conventional means comprises a plurality of steps including identifying first and second frame markers, increasing granularity between the frame marker, identifying at least one dominant object between the marker, normalizing its shape and identifying its edges, dissecting the dominant object into at least two equally sized sections, identifying shape and characteristics of the dominant objects, applying geometric modeling such that section data from the analyzed section is used to determine overall
Journal ArticleDOI

The Digitalization of Motion Picture Production and Its Value Chain Implications

TL;DR: An international two-stage Delphi study suggested a more frequent use of smartphones as cameras, the emergence of full digital film sets and digital star avatars, as well as advancements in VR-based and interactive movies.
References
More filters
Proceedings ArticleDOI

Histograms of oriented gradients for human detection

TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Journal ArticleDOI

Robust Real-Time Face Detection

TL;DR: In this paper, a face detection framework that is capable of processing images extremely rapidly while achieving high detection rates is described. But the detection performance is limited to 15 frames per second.
Proceedings ArticleDOI

Robust real-time face detection

TL;DR: A new image representation called the “Integral Image” is introduced which allows the features used by the detector to be computed very quickly and a method for combining classifiers in a “cascade” which allows background regions of the image to be quickly discarded while spending more computation on promising face-like regions.
Journal ArticleDOI

Face recognition: A literature survey

TL;DR: In this paper, the authors provide an up-to-date critical survey of still-and video-based face recognition research, and provide some insights into the studies of machine recognition of faces.
Journal ArticleDOI

A survey of advances in vision-based human motion capture and analysis

TL;DR: This survey reviews recent trends in video-based human capture and analysis, as well as discussing open problems for future research to achieve automatic visual analysis of human movement.
Related Papers (5)