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

Mizher, Manar Abduljabbar Ahmad; Ang, Mei Choo; Abdullah, Siti Norul Huda Sheikh; Ng, Kok Weng

doi:10.1007/978-3-319-70010-6_34

Cited by 8 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

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%

“…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%

“…The introduction of self-adaptive threshold namely AOF_ST can only support video shots duration for not more than 30 seconds. Later, Mizher et al (2017a) overcame AOF_ST algorithm limitation by proposing an action key frames extraction algorithm based on L1-norm and accumulative optical flow for compact video shot summarisation.…”

Section: Introductionmentioning

confidence: 99%

“…Xia et al (2017) claimed that the L1-norm and L2-norm are not sparse as much as necessary to select one key frame from a sequence of very similar frames. The L1-norm was applied by (Mizher et al, 2017a) in calculating the sum of the absolute differences between each two optical flow frames to return motion sparsity information about these frames. Consequently, this action key frame extraction algorithm achieved a high compression ratio in the KTH dataset with action appearance accuracy between 91% and 100%.…”

Section: Introductionmentioning

confidence: 99%

“…Several environments and camera conditions were experimented using key frames extraction algorithms. Grey colour with a static camera and static background video shots (Mizher et al, 2017a;Sheena & Narayanan, 2015), colour video shots with moving camera and dynamic background (Mizher et al, 2017b;Paul et al, 2017) Paul, Bhattacharya, and Gupta, 2017 extracted the key frames by formulating the dissimilarity between the video shot frames based on changes in object orientations and steerable filtering.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

An Improved Action Key Frames Extraction Algorithm for Complex Colour Video Shot Summarization

Mizher

Choo

Abdullah

et al. 2019

JICT

View full text Add to dashboard Cite

Key frame extraction is one of the critical techniques in computer vision fields such as video search, video identification and video forgeries detection. The extracted key frames should be sufficient key frames that preserve main actions in a video with compact representation. The objective of this work is to improve our previous action key frames extraction algorithm (AKF) by adapting a threshold which selects action key frames as final key frames. The threshold adaptation was achieved by using the mean value, the standard deviation, and the L1norm instead of the comparison of user summaries evaluation method to obtain a fully automatic video summarisation algorithm, and by eliminating the conditions in selecting the final key frames to reduce the complexity of the algorithm. We have validated our proposed Improved AKF on complex colour video shots instead of the simple grey level video shots.144 frames, reduce processing complexity, and preserve sufficient information about the main actions in a video shot. We then evaluated the Improved AKF algorithm with the-state-of-theart algorithms in terms of compression ratio using Paul videos and Shih-Tang dataset. The evaluation results showed that the Improved AKF algorithm achieved better compression ratio and retained sufficient information in the extracted action key frames under different testing video shots. Therefore, the improved AKF algorithm is a suitable technique for applications in computer vision fields such as passive object-based video authentication systems.

show abstract

Section: Improved Action Key Frames Extraction Algorithmmentioning

confidence: 99%

Section: Improved Action Key Frames Extraction Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An Improved Action Key Frames Extraction Algorithm for Complex Colour Video Shot Summarization

Mizher

Choo

Abdullah

et al. 2019

JICT

View full text Add to dashboard Cite

show abstract

A novel keyframe extraction method for video classification using deep neural networks

Kızıltepe

Gan

Escobar

2021

Neural Comput & Applic

View full text Add to dashboard Cite

Combining convolutional neural networks (CNNs) and recurrent neural networks (RNNs) produces a powerful architecture for video classification problems as spatial–temporal information can be processed simultaneously and effectively. Using transfer learning, this paper presents a comparative study to investigate how temporal information can be utilized to improve the performance of video classification when CNNs and RNNs are combined in various architectures. To enhance the performance of the identified architecture for effective combination of CNN and RNN, a novel action template-based keyframe extraction method is proposed by identifying the informative region of each frame and selecting keyframes based on the similarity between those regions. Extensive experiments on KTH and UCF-101 datasets with ConvLSTM-based video classifiers have been conducted. Experimental results are evaluated using one-way analysis of variance, which reveals the effectiveness of the proposed keyframe extraction method in the sense that it can significantly improve video classification accuracy.

show abstract

A Novel gray wolf optimization-based key frame extraction method for video classification using ConvLSTM

Gawande,

Hajari,

Golhar

et al. 2024

Neural Comput & Applic

View full text Add to dashboard Cite

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

Cited by 8 publications

References 17 publications

An Improved Action Key Frames Extraction Algorithm for Complex Colour Video Shot Summarization

An Improved Action Key Frames Extraction Algorithm for Complex Colour Video Shot Summarization

A novel keyframe extraction method for video classification using deep neural networks

A Novel gray wolf optimization-based key frame extraction method for video classification using ConvLSTM

Contact Info

Product

Resources

About