Spatiotemporal Video Synchronisation by Visual Matching
نویسندگان
چکیده
The media coverage of live events can be turned into a more immersive experience if content from multiple sources, e.g., professional and user generated content, are combined. We have implemented a visual matching approach to establish or improve temporal and visual synchronisation of such heterogeneous content. The approach is based on matching of SIFT descriptors and is implemented on the GPU. In order to visualise and explore the matching results, we have implemented a web-based viewer for the aligned content. ACM Classification
منابع مشابه
Multimedia Content Understanding : Bringing Context to Content
In this paper, we propose a framework to extendsemantic labeling of images to video shot sequences and achieveefficient and semantic-aware spatiotemporal video segmentation.This task faces two major challenges, namely the temporal vari-ations within a video sequence which affect image segmentationand labeling, and the computational cost of region labeling.Guided by these...
متن کاملReal-time Action Recognition by Spatiotemporal Semantic and Structural Forests
This paper presents a novel real-time action recogniser by utilising both local appearance and structural information. Our method is able to recognise actions continuously in real-time while achieving comparably high accuracy over state-of-the-arts. Run-time speed is of vital importance in real-world action recognition systems, but existing methods seldom take computational complexity into full...
متن کاملAn fMRI study of human visual cortex in response to spatiotemporal properties of visual stimuli
ABSTRACT Background: The brain response to temporal frequencies (TF) has been already reported, but with no study reported for different TF with respect to various spatial frequencies (SF). Materials and Methods: fMRI was performed by 1.5T GE-system in 14 volunteers during checkerboard, with TFs of 4, 6, 8 and 10Hz in low and high SFs of 0.5 and 8cpd. Results: Average percentage BOLD signa...
متن کاملAn Enhanced Spatiotemporal Visual Attention Model for Sports Video Analysis
Inspired by the human visual system, visual attention (VA) models seem to provide solutions to problems of semantic image understanding by selecting only a small but representative fraction of visual input to process. Having proposed a spatiotemporal VA model for video processing in the past, we propose considerable enhancements in this paper, including the use of steerable filters for 3D orien...
متن کاملJRS at Synchronization of Multi-user Event Media Task
The event synchronisation task addresses the problem of aligning media (i.e., photo and video) streams (“galleries”) from different users temporally and identifying coherent events in the streams. Our approach uses the visual similarity of image/key frame pairs based on full matching of SIFT descriptors with geometric verification. Based on the visual similarity and the given time information, ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2015