K-HOG Unsupervised Keyframe Identifier (K-HUKI): Extracting action-rich frames with HOG Features and Unsupervised Learning
Preprint
- 5 May 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
This Report proposes a pioneering method for keyframe identification in activity interpretation. It seamlessly integrates HOG features for informative representation and the flexibility of unsupervised learning through K-means clustering. This approach, named K-HUKI, is further empowered by a robust architecture combining 3D-CNNs for capturing temporal and spatial information and GRUs for handling perpetual dependencies. Extensive evaluation on the UCF101 dataset demonstrates a remarkable improvement in accuracy. By identifying action-rich frames at exceptional speed (almost 5-fold) compared to CNN based approach's and achieving unparalleled accuracy, K-HUKI establishes itself as a groundbreaking advancement in keyframe detection.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Advancing skeleton-based human behavior recognition: multi-stream fusion spatiotemporal graph convolutional networksComplex & Intelligent Systems, 2024
- Identifying the key frames: An attention-aware sampling method for action recognitionPattern Recognition, 2022
- A novel keyframe extraction method for video classification using deep neural networksNeural Computing and Applications, 2021
- Deep learning in multi-object detection and tracking: state of the artApplied Intelligence, 2021
- A comparison among keyframe extraction techniques for CNN classification based on video periocular imagesMultimedia Tools and Applications, 2021
- A survey on deep learning techniques for image and video semantic segmentationApplied Soft Computing, 2018
- A performance evaluation of gradient field HOG descriptor for sketch based image retrievalComputer Vision and Image Understanding, 2013
- Principal component analysisWIREs Computational Statistics, 2010
- Keyframe-based video summarization using Delaunay clusteringInternational Journal on Digital Libraries, 2006
- Euclidean distance mappingComputer Graphics and Image Processing, 1980