Deep Learning Approach to Key Frame Detection in Human Action Videos

Gawande, Ujwalla; Hajari, Kamal; Golhar, Yogesh

doi:10.5772/intechopen.91188

Cited by 12 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because of the combined elements of human position in movement and the background, detecting representative frames in movies based on human actions is fairly difficult. Gawande et al [2] address the issue and define key frame detection as the process of identifying the video frames that contribute the most to distinguishing the underlying action category from all others. They tested their method on the UCF101 dataset, which is a difficult human action dataset, and found that it can detect critical frames with high accuracy.…”

Section: Literature Reviewmentioning

confidence: 99%

Efficient Indexing of Meta-Data (Extracted From Educational Videos)

Kumbham,

Debnath,

Krothapalli

2023

Preprint

View full text Add to dashboard Cite

Video lectures are becoming more popular and in demand as online classroom teaching is becoming more prevalent. Massive Open Online Courses (MOOCs), such as NPTEL, have been creating high-quality educational content that is freely accessible to students online. A large number of colleges across the country are now using NPTEL videos in their classrooms. So more video lectures are being recorded, maintained, and uploaded. These videos generally contain information about that video before the lecture begins. We generally observe that these educational videos have metadata containing five to six attributes: Institute Name, Publisher Name, Department Name, Professor Name, Subject Name, and Topic Name. It would be easy to maintain these videos if we could organize them according to their categories. The indexing of these videos based on this information is beneficial for students all around the world to efficiently utilise these videos. In this project, we are trying to get the metadata information mentioned above from the video lectures.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Efficient Indexing of Meta-Data (Extracted From Educational Videos)

Kumbham,

Debnath,

Krothapalli

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Researchers have proposed many pedestrian detection frameworks based on deep learning to improve the accuracy of pedestrian detection [30][31][32][33][34][35]. However, the accuracy of pedestrian detectors is affected by complex backgrounds, pedestrian scale changes, object occlusion, and illumination changes.…”

Section: Literature Surveymentioning

confidence: 99%

SIRA: Scale illumination rotation affine invariant mask R-CNN for pedestrian detection

Gawande¹,

Hajari²,

Golhar³

2022

Appl Intell

Self Cite

View full text Add to dashboard Cite

In this paper, we resolve the challenging obstacle of detecting pedestrians with the ubiquity of irregularities in scale, rotation, and the illumination of the natural scene images natively. Pedestrian instances with such obstacles exhibit significantly unique characteristics. Thus, it strongly influences the performance of pedestrian detection techniques. We propose the new robust Scale Illumination Rotation and Affine invariant Mask R-CNN (SIRA M-RCNN) framework for overcoming the predecessor’s difficulties. The first phase of the proposed system deals with illumination variation by histogram analysis. Further, we use the contourlet transformation, and the directional filter bank for the generation of the rotational invariant features. Finally, we use Affine Scale Invariant Feature Transform (ASIFT) to find points that are translation and scale-invariant. Extensive evaluation of the benchmark database will prove the effectiveness of SIRA M-RCNN. The experimental results achieve state-of-the-art performance and show a significant performance improvement in pedestrian detection.

show abstract

“…These pooled frames are used to classify an action. [29] identifies the KFs using CNN and reported precision of 92% in the human action videos. The authors in [30] identify 4 KFs in the sports videos with the help of fully convolutional networks.…”

Section: Motivation and Related Workmentioning

confidence: 99%

An Automated Method for Identification of Key frames in Bharatanatyam Dance Videos

et al. 2021

View full text Add to dashboard Cite

Identifying key frames is the first and necessary step before solving the variety of other Bharatanatyam problems. The paper aims to partition the momentarily stationary frames (key frames) from this dance video's motion frames. The proposed key frames (KFs) localization is novel, simple, and effective compared to the existing dance video analysis methods. It is distinctive from standard KFs detection algorithms as used in other human motion videos. In the dance's basic structure, the occurrence of KFs during performances is often not completely stationary and varies with the dance form and the performer. Hence, it is not easy to decide a global threshold (on the quantum of motion) to work across dancers and performances. The earlier approaches try to compute the threshold iteratively. However, the novelty of the paper is: (a) formulating an adaptive threshold, (b) adopting Machine Learning (ML) approach and, (c) generating the effective feature by combining three frame differencing and bit-plane technique for the KF detection. In ML, we use Support Vector Machine (SVM) and Convolutional Neural Network (CNN) as the classifiers. The proposed approaches are also compared and analyzed with the earlier approaches. Finally, the proposed ML techniques emerge as a winner with around 90% accuracy.

show abstract

Deep Learning Approach to Key Frame Detection in Human Action Videos

Cited by 12 publications

References 27 publications

Efficient Indexing of Meta-Data (Extracted From Educational Videos)

Efficient Indexing of Meta-Data (Extracted From Educational Videos)

SIRA: Scale illumination rotation affine invariant mask R-CNN for pedestrian detection

An Automated Method for Identification of Key frames in Bharatanatyam Dance Videos

Contact Info

Product

Resources

About