A Novel Hybrid Keypoint Detection Algorithm for Gradual Shot Boundary Detection

Karpagavalli, S.; Balamurugan, V.; Kumar, Sankaran Ramesh

doi:10.1109/ic-etite47903.2020.343

Cited by 4 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, a unique hybrid crucial point core requirement for SBD is suggested, and it is tested with multiple different custom video inputs, as described by Shunmugam Karpagavalli et al [6]. In regards to the average number of important focusing on the importance and precision, the outcomes of the experiments demonstrate that the Hybrid Key point Recognition system outshines some other reference methodologies such as Min Eigen Value, Corner Detectors, and Features from Accelerated Segment Test, Speed up Robust Features, Maximally Stable Extremal Region, and Binary Robust Invariant Scalable Key points.…”

Section: Related Workmentioning

confidence: 99%

Enriching Shot Boundary Detection through DT-DWT and Deep Learning Models

Kumar¹

2023

Preprint

View full text Add to dashboard Cite

Numerous techniques exist for detecting shot or scene boundaries, typically relying on visual characteristics of frames and contrasting said features among adjacent frames to identify shot boundaries. Shot Boundary Detection can utilize a range of visual characteristics such as edge feature, gray intensity, motion vector, and color histogram. The accuracy of Shot Boundary identification methods that currently exist has demonstrated a relatively high level of effectiveness. It is imperative to adapt current techniques to accommodate diverse video content types, as contemporary video productions employ a wider range of video creation methods than their predecessors. The presented approach in this methodology examines the different techniques fr the purpose of achieving the shot boundary detection. The Dual Tree – Discrete Wavelet Transformation approach has been contrasted with the deep learning approaches such as Artificial Neural Network and Convolutional Neural Network. The video is given as input on which frame extraction, feature extraction through Entropy Calculation and Mean Log Estimation is realized with the Deep learning methodologies. The outcomes of the shot boundary identification have been effectively compared with one another to determine performance which is displayed in the later sections of this research article.

show abstract

Section: Related Workmentioning

confidence: 99%