Visual analysis of corrupted video data in video event data recorders

Youngbin Pyo; Choongin Lee; Heejo Lee

doi:10.1109/DESEC.2017.8073828

Visual analysis of corrupted video data in video event data recorders

Youngbin Pyo, Choongin Lee, Heejo Lee

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

With the rapid proliferation of video event data recorders (VEDRs), video file data from VEDRs are often used as the primary evidence in many fields, such as law enforcement. In this paper, we propose a method for reconstructing corrupted video files and capturing key events recorded in the video file for use as valid evidence. The method first extracts image features from each video frame and constructs a multidimensional vector. Subsequently, dimension reduction of these vectors is performed for visualization in low-dimensional space. The proper sequence of the video frames is restored by using a curve fitting technique for the low-dimensional vectors. Then, we calculate the change in the slope of the curve-fitted model to detect key events in video files. The proposed method generates significant results not provided by existing file recovery techniques.

Original language	English
Title of host publication	2017 IEEE Conference on Dependable and Secure Computing
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	453-458
Number of pages	6
ISBN (Electronic)	9781509055692
DOIs	https://doi.org/10.1109/DESEC.2017.8073828
Publication status	Published - 2017 Oct 18
Event	2017 IEEE Conference on Dependable and Secure Computing - Taipei, Taiwan, Province of China Duration: 2017 Aug 7 → 2017 Aug 10

Publication series

Name	2017 IEEE Conference on Dependable and Secure Computing

Other

Other	2017 IEEE Conference on Dependable and Secure Computing
Country/Territory	Taiwan, Province of China
City	Taipei
Period	17/8/7 → 17/8/10

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

Keywords

Digital forensics
Video event detection
Video sequence reconstruction
Visualization

ASJC Scopus subject areas

Computer Networks and Communications
Safety, Risk, Reliability and Quality
Software

Access to Document

10.1109/DESEC.2017.8073828

Cite this

Visual analysis of corrupted video data in video event data recorders. / Pyo, Youngbin; Lee, Choongin; Lee, Heejo.
2017 IEEE Conference on Dependable and Secure Computing. Institute of Electrical and Electronics Engineers Inc., 2017. p. 453-458 8073828 (2017 IEEE Conference on Dependable and Secure Computing).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Pyo, Y, Lee, C & Lee, H 2017, Visual analysis of corrupted video data in video event data recorders. in 2017 IEEE Conference on Dependable and Secure Computing., 8073828, 2017 IEEE Conference on Dependable and Secure Computing, Institute of Electrical and Electronics Engineers Inc., pp. 453-458, 2017 IEEE Conference on Dependable and Secure Computing, Taipei, Taiwan, Province of China, 17/8/7. https://doi.org/10.1109/DESEC.2017.8073828

@inproceedings{61a4fe3e9c404cadada2fcf8ce211230,

title = "Visual analysis of corrupted video data in video event data recorders",

abstract = "With the rapid proliferation of video event data recorders (VEDRs), video file data from VEDRs are often used as the primary evidence in many fields, such as law enforcement. In this paper, we propose a method for reconstructing corrupted video files and capturing key events recorded in the video file for use as valid evidence. The method first extracts image features from each video frame and constructs a multidimensional vector. Subsequently, dimension reduction of these vectors is performed for visualization in low-dimensional space. The proper sequence of the video frames is restored by using a curve fitting technique for the low-dimensional vectors. Then, we calculate the change in the slope of the curve-fitted model to detect key events in video files. The proposed method generates significant results not provided by existing file recovery techniques.",

keywords = "Digital forensics, Video event detection, Video sequence reconstruction, Visualization",

author = "Youngbin Pyo and Choongin Lee and Heejo Lee",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 IEEE Conference on Dependable and Secure Computing ; Conference date: 07-08-2017 Through 10-08-2017",

year = "2017",

month = oct,

day = "18",

doi = "10.1109/DESEC.2017.8073828",

language = "English",

series = "2017 IEEE Conference on Dependable and Secure Computing",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "453--458",

booktitle = "2017 IEEE Conference on Dependable and Secure Computing",

}

TY - GEN

T1 - Visual analysis of corrupted video data in video event data recorders

AU - Pyo, Youngbin

AU - Lee, Choongin

AU - Lee, Heejo

PY - 2017/10/18

Y1 - 2017/10/18

N2 - With the rapid proliferation of video event data recorders (VEDRs), video file data from VEDRs are often used as the primary evidence in many fields, such as law enforcement. In this paper, we propose a method for reconstructing corrupted video files and capturing key events recorded in the video file for use as valid evidence. The method first extracts image features from each video frame and constructs a multidimensional vector. Subsequently, dimension reduction of these vectors is performed for visualization in low-dimensional space. The proper sequence of the video frames is restored by using a curve fitting technique for the low-dimensional vectors. Then, we calculate the change in the slope of the curve-fitted model to detect key events in video files. The proposed method generates significant results not provided by existing file recovery techniques.

AB - With the rapid proliferation of video event data recorders (VEDRs), video file data from VEDRs are often used as the primary evidence in many fields, such as law enforcement. In this paper, we propose a method for reconstructing corrupted video files and capturing key events recorded in the video file for use as valid evidence. The method first extracts image features from each video frame and constructs a multidimensional vector. Subsequently, dimension reduction of these vectors is performed for visualization in low-dimensional space. The proper sequence of the video frames is restored by using a curve fitting technique for the low-dimensional vectors. Then, we calculate the change in the slope of the curve-fitted model to detect key events in video files. The proposed method generates significant results not provided by existing file recovery techniques.

KW - Digital forensics

KW - Video event detection

KW - Video sequence reconstruction

KW - Visualization

UR - http://www.scopus.com/inward/record.url?scp=85039897776&partnerID=8YFLogxK

U2 - 10.1109/DESEC.2017.8073828

DO - 10.1109/DESEC.2017.8073828

M3 - Conference contribution

AN - SCOPUS:85039897776

T3 - 2017 IEEE Conference on Dependable and Secure Computing

SP - 453

EP - 458

BT - 2017 IEEE Conference on Dependable and Secure Computing

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 IEEE Conference on Dependable and Secure Computing

Y2 - 7 August 2017 through 10 August 2017

ER -

Visual analysis of corrupted video data in video event data recorders

Abstract

Publication series

Other

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this