SIAVC: Semi-Supervised Framework for Industrial Accident Video Classification
- 4 November 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (3) , 2603-2615
Abstract
Semi-supervised learning suffers from the imbalance of labeled and unlabeled training data in the video surveillance scenario. In this paper, we propose a new semi-supervised learning method called SIAVC for industrial accident video classification. Specifically, we design a video augmentation module called the Super Augmentation Block (SAB). SAB adds Gaussian noise and randomly masks video frames according to historical loss on the unlabeled data for model optimization. Then, we propose a Video Cross-set Augmentation Module (VCAM) to generate diverse pseudo-label samples from the high-confidence unlabeled samples, which alleviates the mismatch of sampling experience and provides high-quality training data. Additionally, we construct a new industrial accident surveillance video dataset with frame-level annotation, namely ECA9, to evaluate our proposed method. Compared with the state-of-the-art semi-supervised learning based methods, SIAVC demonstrates outstanding video classification performance, achieving 88.76% and 89.13% accuracy on ECA9 and Fire Detection datasets, respectively. The source code and the constructed dataset ECA9 will be released in https://github.com/AlchemyEmperor/SIAVC.Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2022YFC3302200)
- National Natural Science Foundation of China (62471207, 62276146)
- Natural Science Foundation of Fujian Province (2024J02029)
- Key Project of Colleges and Universities of Henan Province (23A52002)
This publication has 25 references indexed in Scilit:
- FireMatch: A semi-supervised video fire detection network based on consistency and distribution alignmentExpert Systems with Applications, 2024
- SimMatch: Semi-supervised Learning with Similarity Matching2022
- MViTv2: Improved Multiscale Vision Transformers for Classification and Detection2022
- Video Swin Transformer2022
- Anomaly detection in video sequences: A benchmark and computational modelIET Image Processing, 2021
- Few-Shot Video Classification via Temporal Alignment2020
- Randaugment: Practical automated data augmentation with a reduced search space2020
- Video Classification With Channel-Separated Convolutional Networks2019
- Semi-Supervised Learning by Augmented Distribution Alignment2019
- Improving Fire Detection Reliability by a Combination of Videoanalytics2014