Examination of a tracking and detection method using compressed domain information

Erii Maekawa, Satoshi Goto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

In this paper, we propose a moving object tracking method in the compressed domain. Because video data are large in size, it is usually compressed by H.264/AVC or MPEG for storage or transmission. Most image processing systems track targets in the pixel domain after decoding compressed data. Objects in video data are tracked based on their color and luminance information in the pixel domain. However, tracking methods in the pixel domain have higher computational complexity than in the compressed domain. We propose a method that directly employs moving object tracking in the compressed domain without a decoding process. Tracking algorithms in the compressed domain are usually based on motion information, or motion vectors. However, motion vectors are not generated when objects stop moving, and their accuracy is low. To overcome these problems, we propose a method that uses motion vectors and other information in macroblocks to track moving objects in a compressed H.264/AVC video stream. The proposed method can reduce computational complexity compared to a pixel domain algorithm. In addition, experimental results show that tracking accuracy is improved by the proposed method. Therefore, this method can be effectively used for video surveillance systems.

Original languageEnglish
Title of host publication2013 Picture Coding Symposium, PCS 2013 - Proceedings
PublisherIEEE Computer Society
Pages141-144
Number of pages4
ISBN (Print)9781479902941
DOIs
Publication statusPublished - 2013
Event2013 Picture Coding Symposium, PCS 2013 - San Jose, CA
Duration: 2013 Dec 82013 Dec 11

Other

Other2013 Picture Coding Symposium, PCS 2013
CitySan Jose, CA
Period13/12/813/12/11

Fingerprint

Pixels
Decoding
Computational complexity
Luminance
Image processing
Color

Keywords

  • Motion detection
  • Video compression
  • Video signal processing

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software

Cite this

Maekawa, E., & Goto, S. (2013). Examination of a tracking and detection method using compressed domain information. In 2013 Picture Coding Symposium, PCS 2013 - Proceedings (pp. 141-144). [6737703] IEEE Computer Society. https://doi.org/10.1109/PCS.2013.6737703

Examination of a tracking and detection method using compressed domain information. / Maekawa, Erii; Goto, Satoshi.

2013 Picture Coding Symposium, PCS 2013 - Proceedings. IEEE Computer Society, 2013. p. 141-144 6737703.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Maekawa, E & Goto, S 2013, Examination of a tracking and detection method using compressed domain information. in 2013 Picture Coding Symposium, PCS 2013 - Proceedings., 6737703, IEEE Computer Society, pp. 141-144, 2013 Picture Coding Symposium, PCS 2013, San Jose, CA, 13/12/8. https://doi.org/10.1109/PCS.2013.6737703
Maekawa E, Goto S. Examination of a tracking and detection method using compressed domain information. In 2013 Picture Coding Symposium, PCS 2013 - Proceedings. IEEE Computer Society. 2013. p. 141-144. 6737703 https://doi.org/10.1109/PCS.2013.6737703
Maekawa, Erii ; Goto, Satoshi. / Examination of a tracking and detection method using compressed domain information. 2013 Picture Coding Symposium, PCS 2013 - Proceedings. IEEE Computer Society, 2013. pp. 141-144
@inproceedings{de069f01af014fcca1b7327338443ae4,
title = "Examination of a tracking and detection method using compressed domain information",
abstract = "In this paper, we propose a moving object tracking method in the compressed domain. Because video data are large in size, it is usually compressed by H.264/AVC or MPEG for storage or transmission. Most image processing systems track targets in the pixel domain after decoding compressed data. Objects in video data are tracked based on their color and luminance information in the pixel domain. However, tracking methods in the pixel domain have higher computational complexity than in the compressed domain. We propose a method that directly employs moving object tracking in the compressed domain without a decoding process. Tracking algorithms in the compressed domain are usually based on motion information, or motion vectors. However, motion vectors are not generated when objects stop moving, and their accuracy is low. To overcome these problems, we propose a method that uses motion vectors and other information in macroblocks to track moving objects in a compressed H.264/AVC video stream. The proposed method can reduce computational complexity compared to a pixel domain algorithm. In addition, experimental results show that tracking accuracy is improved by the proposed method. Therefore, this method can be effectively used for video surveillance systems.",
keywords = "Motion detection, Video compression, Video signal processing",
author = "Erii Maekawa and Satoshi Goto",
year = "2013",
doi = "10.1109/PCS.2013.6737703",
language = "English",
isbn = "9781479902941",
pages = "141--144",
booktitle = "2013 Picture Coding Symposium, PCS 2013 - Proceedings",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Examination of a tracking and detection method using compressed domain information

AU - Maekawa, Erii

AU - Goto, Satoshi

PY - 2013

Y1 - 2013

N2 - In this paper, we propose a moving object tracking method in the compressed domain. Because video data are large in size, it is usually compressed by H.264/AVC or MPEG for storage or transmission. Most image processing systems track targets in the pixel domain after decoding compressed data. Objects in video data are tracked based on their color and luminance information in the pixel domain. However, tracking methods in the pixel domain have higher computational complexity than in the compressed domain. We propose a method that directly employs moving object tracking in the compressed domain without a decoding process. Tracking algorithms in the compressed domain are usually based on motion information, or motion vectors. However, motion vectors are not generated when objects stop moving, and their accuracy is low. To overcome these problems, we propose a method that uses motion vectors and other information in macroblocks to track moving objects in a compressed H.264/AVC video stream. The proposed method can reduce computational complexity compared to a pixel domain algorithm. In addition, experimental results show that tracking accuracy is improved by the proposed method. Therefore, this method can be effectively used for video surveillance systems.

AB - In this paper, we propose a moving object tracking method in the compressed domain. Because video data are large in size, it is usually compressed by H.264/AVC or MPEG for storage or transmission. Most image processing systems track targets in the pixel domain after decoding compressed data. Objects in video data are tracked based on their color and luminance information in the pixel domain. However, tracking methods in the pixel domain have higher computational complexity than in the compressed domain. We propose a method that directly employs moving object tracking in the compressed domain without a decoding process. Tracking algorithms in the compressed domain are usually based on motion information, or motion vectors. However, motion vectors are not generated when objects stop moving, and their accuracy is low. To overcome these problems, we propose a method that uses motion vectors and other information in macroblocks to track moving objects in a compressed H.264/AVC video stream. The proposed method can reduce computational complexity compared to a pixel domain algorithm. In addition, experimental results show that tracking accuracy is improved by the proposed method. Therefore, this method can be effectively used for video surveillance systems.

KW - Motion detection

KW - Video compression

KW - Video signal processing

UR - http://www.scopus.com/inward/record.url?scp=84897740615&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897740615&partnerID=8YFLogxK

U2 - 10.1109/PCS.2013.6737703

DO - 10.1109/PCS.2013.6737703

M3 - Conference contribution

SN - 9781479902941

SP - 141

EP - 144

BT - 2013 Picture Coding Symposium, PCS 2013 - Proceedings

PB - IEEE Computer Society

ER -