Detail publikace

Visual Codebooks Survey for Video On-line Processing

Originální název

Visual Codebooks Survey for Video On-line Processing

Anglický název

Visual Codebooks Survey for Video On-line Processing

Jazyk

en

Originální abstrakt

This paper explores techniques in the pipeline of image description based on visual codebooks suitable for video on-line processing. The pipeline components are (i) extraction and description of local image features, (ii) translation of each high-dimensional feature descriptor to several most appropriate visual words selected from the discrete codebook and (iii) combination of visual words into bag-of-words using hard or soft assignment weighting scheme. For each component, several state-of-the-art techniques are analyzed and discussed and their usability for video on-line processing is addressed. The experiments are evaluated on the standard Kentucky and Oxford building datasets using image retrieval framework. The results show the impact loosing the pipeline precision in the price of improving the time cost which is crucial for real-time video processing.

Anglický abstrakt

This paper explores techniques in the pipeline of image description based on visual codebooks suitable for video on-line processing. The pipeline components are (i) extraction and description of local image features, (ii) translation of each high-dimensional feature descriptor to several most appropriate visual words selected from the discrete codebook and (iii) combination of visual words into bag-of-words using hard or soft assignment weighting scheme. For each component, several state-of-the-art techniques are analyzed and discussed and their usability for video on-line processing is addressed. The experiments are evaluated on the standard Kentucky and Oxford building datasets using image retrieval framework. The results show the impact loosing the pipeline precision in the price of improving the time cost which is crucial for real-time video processing.

BibTex


@inproceedings{BUT35523,
  author="Vítězslav {Beran} and Pavel {Zemčík}",
  title="Visual Codebooks Survey for Video On-line Processing",
  annote="This paper explores techniques in the pipeline of image description based on
visual codebooks suitable for video on-line processing. The pipeline components
are (i) extraction and description of local image features, (ii) translation of
each high-dimensional feature descriptor to several most appropriate visual words
selected from the discrete codebook and (iii) combination of visual words into
bag-of-words using hard or soft assignment weighting scheme. For each component,
several state-of-the-art techniques are analyzed and discussed and their
usability for video on-line processing is addressed. The experiments are
evaluated on the standard Kentucky and Oxford building datasets using image
retrieval framework. The results show the impact loosing the pipeline precision
in the price of improving the time cost which is crucial for real-time video
processing.",
  address="Springer Verlag",
  booktitle="Second International Conference, ICCVG 2010, Proceedings Part 1.",
  chapter="35523",
  doi="10.1007/978-3-642-15910-7_1",
  edition="Lecture Notes in Computer Science",
  howpublished="print",
  institution="Springer Verlag",
  number="1",
  year="2010",
  month="november",
  pages="1--10",
  publisher="Springer Verlag",
  type="conference paper"
}