2017
DOI: 10.1007/978-3-319-70010-6_34
|View full text |Cite
|
Sign up to set email alerts
|

Action Key Frames Extraction Using L1-Norm and Accumulative Optical Flow for Compact Video Shot Summarisation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
8
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 8 publications
(8 citation statements)
references
References 17 publications
0
8
0
Order By: Relevance
“…Schindler and Gool (2008) defined basic action as a unit in which human behaviour shall be classified. Therefore, we attempt to improve the action key frames extraction algorithm (AKF) (Mizher et al, 2017a) which mainly focuses on key frames extraction under KTH dataset. Since KTH dataset was captured using a static camera and static background, and it has video shots in grey level with one basic action in each video shot, we focused on making improvement on AKF algorithm that is suitable for colour video shots with more actions such as one or more moving objects in video shot consisting of dynamic background or moving camera.…”
Section: Improved Action Key Frames Extraction Algorithmmentioning
confidence: 99%
See 4 more Smart Citations
“…Schindler and Gool (2008) defined basic action as a unit in which human behaviour shall be classified. Therefore, we attempt to improve the action key frames extraction algorithm (AKF) (Mizher et al, 2017a) which mainly focuses on key frames extraction under KTH dataset. Since KTH dataset was captured using a static camera and static background, and it has video shots in grey level with one basic action in each video shot, we focused on making improvement on AKF algorithm that is suitable for colour video shots with more actions such as one or more moving objects in video shot consisting of dynamic background or moving camera.…”
Section: Improved Action Key Frames Extraction Algorithmmentioning
confidence: 99%
“…Figure 1 illustrates step-1 until step-7 of the action key frames extraction algorithm (Mizher et al, 2017a) to select the initial key frames based on L1-norm and optical flow with window size W. Hence, we improve step-4 in AKF algorithm (Mizher et al, 2017a) by picking up the action frames (AFs) as final key frames with adaptation of the threshold based on Equations (1), (2) and (3). The AKF algorithm (Mizher et al, 2017a) has used the threshold value in step-4 with L1-norm equals to a fixed value of 4600 based on the comparison of user summaries (CUS) evaluation method in selecting AFs. In order to evaluate the performance of the Improved AKF algorithm, compactness measure (CR) and image fidelity measure (IFM) is used.…”
Section: Improved Action Key Frames Extraction Algorithmmentioning
confidence: 99%
See 3 more Smart Citations