Abstract
Increasing the demands of digital video by developing the Internet market and the multimedia technologies, video indexing technique such as scene change detection is required to manage the data efficiently. In conventional methods, scene change is detected by comparing the value of current detected measure with the fixed threshold induced from preceding experiments. However, this can not guarantee the best performances on all various video sequences, due to their own specific characteristics. To solve this problem, a novel adaptive threshold decision method is proposed. First, histogram of scene change detection measure induced from preceding experiments is derived. Then this is modeled with log-normal distributed pdf and the model parameters are estimated. Consequently, experimental results obtained from this pdf model and estimated parameters demonstrate better performance of the proposed method comparing with conventional methods.
| Original language | English |
|---|---|
| Title of host publication | Proceedings 2013 IEEE 3rd International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2013 |
| Publisher | IEEE Computer Society |
| Pages | 75-78 |
| Number of pages | 4 |
| ISBN (Print) | 9781479914128 |
| DOIs | |
| Publication status | Published - 2013 Jan 1 |
| Event | 2013 IEEE 3rd International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2013 - Berlin, Germany Duration: 2013 Sep 8 → 2013 Sep 11 |
Publication series
| Name | Proceedings 2013 IEEE 3rd International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2013 |
|---|
Other
| Other | 2013 IEEE 3rd International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2013 |
|---|---|
| Country | Germany |
| City | Berlin |
| Period | 13/9/8 → 13/9/11 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Electrical and Electronic Engineering
Cite this
}
Adaptive thresholding for scene change detection. / Hong, Soongi; Cho, Beobkeun; Choe, Yoonsik.
Proceedings 2013 IEEE 3rd International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2013. IEEE Computer Society, 2013. p. 75-78 6698056 (Proceedings 2013 IEEE 3rd International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2013).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Adaptive thresholding for scene change detection
AU - Hong, Soongi
AU - Cho, Beobkeun
AU - Choe, Yoonsik
PY - 2013/1/1
Y1 - 2013/1/1
N2 - Increasing the demands of digital video by developing the Internet market and the multimedia technologies, video indexing technique such as scene change detection is required to manage the data efficiently. In conventional methods, scene change is detected by comparing the value of current detected measure with the fixed threshold induced from preceding experiments. However, this can not guarantee the best performances on all various video sequences, due to their own specific characteristics. To solve this problem, a novel adaptive threshold decision method is proposed. First, histogram of scene change detection measure induced from preceding experiments is derived. Then this is modeled with log-normal distributed pdf and the model parameters are estimated. Consequently, experimental results obtained from this pdf model and estimated parameters demonstrate better performance of the proposed method comparing with conventional methods.
AB - Increasing the demands of digital video by developing the Internet market and the multimedia technologies, video indexing technique such as scene change detection is required to manage the data efficiently. In conventional methods, scene change is detected by comparing the value of current detected measure with the fixed threshold induced from preceding experiments. However, this can not guarantee the best performances on all various video sequences, due to their own specific characteristics. To solve this problem, a novel adaptive threshold decision method is proposed. First, histogram of scene change detection measure induced from preceding experiments is derived. Then this is modeled with log-normal distributed pdf and the model parameters are estimated. Consequently, experimental results obtained from this pdf model and estimated parameters demonstrate better performance of the proposed method comparing with conventional methods.
UR - http://www.scopus.com/inward/record.url?scp=84893629565&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84893629565&partnerID=8YFLogxK
U2 - 10.1109/ICCE-Berlin.2013.6698056
DO - 10.1109/ICCE-Berlin.2013.6698056
M3 - Conference contribution
AN - SCOPUS:84893629565
SN - 9781479914128
T3 - Proceedings 2013 IEEE 3rd International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2013
SP - 75
EP - 78
BT - Proceedings 2013 IEEE 3rd International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2013
PB - IEEE Computer Society
ER -