Tensor-Based Shot Boundary Detection in Video Streams

Bogusław Cyganek,Michał Woźniak

doi:10.1007/s00354-017-0024-0

Bogusław Cyganek, Michał Woźniak

Open Access

https://doi.org/10.1007/s00354-017-0024-0

Copy DOI

Abstract

This paper presents a method for content change detection in multidimensional video signals. Video frames are represented as tensors of order consistent with signal dimensions. The method operates on unprocessed signals and no special feature extraction is assumed. The dynamic tensor analysis method is used to build a tensor model from the stream. Each new datum in the stream is then compared to the model with the proposed concept drift detector. If it fits, then a model is updated. Otherwise, a model is rebuilt, starting from that datum, and the signal shot is recorded. The proposed fast tensor decomposition algorithm allows efficient operation compared to the standard tensor decomposition method. Experimental results show many useful properties of the method, as well as its potential further extensions and applications.

Highlights

Increasing amounts of visual information raise the needs for the development of automatic data analysis methods
It was shown that tensor-based methods frequently offer many benefits, such as in the case of the tensorfaces, as well as view synthesis proposed by Vasilescu and Terzopoulos [48,49,50], or data dimensionality reduction by Wang and Ahuja [51, 52], handwritten digits recognition proposed by Savas and Elden [42] or road signs recognition by Cyganek [9], to name a few
The model is continuously updated by the frames in the stream if they fit to the model based on the proposed fitness function

Summary

Introduction

Increasing amounts of visual information raise the needs for the development of automatic data analysis methods. (2017) 35:311–340 improve efficacy of video cataloging, indexing, archiving, information search, data compression, to name a few [47] These methods, in turn, rely on efficient algorithms of boundary detection in the visual streams. A key step in these methods is to track a video stream and recognize regions of sufficiently abrupt change in the visual content Such generally stated task is subjective and depends on specific video content which manifests with different segmentations done in human-made experiments. Video surveillance, hyperspectral images, sensor networks, to name a few Their processing with the standard vectorbased methods is usually not sufficient due to the loss of important information contained in internal structure and relations among data. Further information can be found in many publications, such as, for instance, [5, 10, 11, 24, 25, 32, 48]

Methods

Results

Conclusion