- CONVR 2023 - Proceedings of the 23rd International Conference on Construction Applications of Virtual Reality
- Edited by Pietro Capone, Vito Getuli, Farzad Pour Rahimian, Nashwan Dawood, Alessandro Bruttini, Tommaso Sorbi
Efficient Data Curation Using Active Learning for a Video-Based Fire Detection
- Keyur Joshi
- Angelina Aziz
- Philip Dietrich
- Markus König
- © 2023 Author(s) |
- CC BY-NC 4.0
- DOI: 10.36253/979-12-215-0289-3.60
Video-based fire detection is a crucial object detection problem that relies on accurate and reliable data to detect fires. However, collecting and labeling fire-related data can be time-consuming and expensive, making it difficult to obtain sufficient data for training machine learning models. To address this challenge, uncertainty-based active learning techniques can be used to iteratively select the most informative samples for labeling. This can reduce the amount of labeled data needed to achieve high model performance and has the potential to even prune the training data with fewer informative samples. The traditional sampling-based uncertainty estimation methods are computationally expensive. Hence, an efficient prior network-based ensemble distillation State-of-the-Art approach is evaluated on an internal dataset which still requires relatively higher overhead computation making it difficult for production deployment. A biased softmax differencing-based uncertainty approach and a feature-based hard data mining approach are proposed and compared with the distillation approach. The novel approaches are found to have a very low overhead uncertainty estimation time compared to the ensemble distillation approach and traditional sampling techniques. The methods are evaluated in the context of curating the unlabeled pool data and improving the training data. For completeness, the experiments are performed on three different data sizes, and overall, the frame-wise selection strategy is proved to be better than the sequence-wise querying strategy. The Principal Component Analysis (PCA)-based hard data mining outperformed other methods and improved the model performance by 16.33% with AUC2% metric when compared with the random selection of data. The approach even outperformed the main network trained on full data by 7.33%, henceforth improving the training data by using informative 26.39% data. The results indicate that novel data mining provides efficient training and pool data curation
- Keywords:
- Uncertainty Estimation,
- Active Learning,
- Object Detection,
- Outlier Detection,
- Feature-based cluster analysis,
- Video-based Fire Detection,
Ruhr-University Bochum, Germany
Ruhr-University Bochum, Germany - ORCID: 0000-0001-7853-1395
Bosch Sicherheitssysteme GmbH, Germany
Ruhr-University Bochum, Germany - ORCID: 0000-0002-2729-7743
- Breunig, M. M., Kriegel, H.-P., Ng, R. T., & Sander, J. (2000). LOF: Identifying density-based local outliers. In Proceedings of the 2000 ACM SIGMOD international conference on Management of data (pp. 93-104). DOI: 10.1145/342009.335388
- Campbell, R. (2018). Fire in Industrial or Manufacturing Properties. Technical report, National Fire Protection Association (NFPA). Retrieved July 24, 2023, from NFPA report website: https://www.nfpa.org/News-and-Research/Data-research-and-tools/Building-and-Life-Safety/Fires-in-US-Industrial-and-Manufacturing-Facilities
- Choi, J., Elezi, I., Lee, H.-J., Farabet, C., & Alvarez, J. M. (2021). Active Learning for Deep Object Detection via Probabilistic Modeling. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 10264-10273). DOI: 10.48550/arXiv.2103.16130
- Deepshikha, K., Yelleni, S. H., Srijith, P. K., & Mohan, C. K. (2021). Monte Carlo DropBlock for Modelling Uncertainty in Object Detection. In Computing Research Repository (CoRR). DOI: 10.48550/arXiv.2108.03614
- Desai, S. V., Chandra, A. L., Guo, W., Ninomiya, S., & Balasubramanian, V. N. (2019, October). An Adaptive Supervision Framework for Active Learning in Object Detection. In Proceedings of the British Machine Vision Conference. https://api.semanticscholar.org/CorpusID:199472921
- Gal, Y., & Ghahramani, Z. (2016). Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. In International conference on machine learning, PMLR (pp. 1050-1059). https://proceedings.mlr.press/v48/gal16.html
- Gal, Y., Islam, R., & Ghahramani, Z. (2017). Deep Bayesian Active Learning with Image Data. In International conference on machine learning, PMLR (pp. 1183-1192). DOI: 10.48550/arXiv.1703.02910
- Jolliffe, I. T., & Cadima, J. (2016). Principal component analysis: A review and recent developments. Philosophical transactions of the royal society A: Mathematical, Physical and Engineering Sciences, 374(2065), 20150202. DOI: 10.1098/rsta.2015.0202
- Kendall, A., & Gal, Y. (2017). What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? Advances in neural information processing systems, 30. DOI: 10.5555/3295222.3295309
- Lakshminarayanan, B., Pritzel, A., & Blundell, C. (2017). Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles. Advances in neural information processing systems, 30. https://api.semanticscholar.org/CorpusID:6294674
- Malinin, A., & Gales, M. (2018). Predictive Uncertainty Estimation via Prior Networks. Advances in neural information processing systems, 31. DOI: 10.48550/arXiv.1802.10501
- Malinin, A., Mlodozeniec, B., & Gales, M. (2019). Ensemble Distribution Distillation. In 8th International Conference on Learning Representations. DOI: 10.48550/arXiv.1905.00076
- Manivannan, I. (2020). A Comparative Study of Uncertainty Estimation Methods in Deep Learning Based Classification Models. Technical report, Hochschule Bonn-Rhein-Sieg University of Applied Sciences, Department of Computer Science. DOI: 10.18418/978-3-96043-085-8
- Nguyen, V.-L., Shaker, M. H., & Hüllermeier, E. (2022). How to measure uncertainty in uncertainty sampling for active learning. Machine Learning, 111(1), 89-122, DOI: 10.1007/s10994-021-06003-9
- Schorn, C., & Gauerhof, L. (2020). FACER: A Universal Framework for Detecting Anomalous Operation of Deep Neural Networks. In 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (pp. 1-6). DOI: 10.1109/ITSC45102.2020.9294226
- Sousa, M. J., Moutinho, A., & Almeida, M. (2020). Thermal Infrared Sensing for Near Real-Time Data-Driven Fire Detection and Monitoring Systems. Sensors (Basel, Switzerland), 20(23), 6803. DOI: 10.3390/s20236803
- Streiner, D. L., & Cairney, J. (2007). What’s under the ROC? An introduction to receiver operating characteristics curves. The Canadian Journal of Psychiatry, 52(2), 121-128. DOI: 10.1177/070674370705200210
- Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Rabinovich, A. (2015). Going Deeper with Convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1-9). DOI: 10.1109/CVPR.2015.7298594
Chapter Information
Chapter Title
Efficient Data Curation Using Active Learning for a Video-Based Fire Detection
Authors
Keyur Joshi, Angelina Aziz, Philip Dietrich, Markus König
DOI
10.36253/979-12-215-0289-3.60
Peer Reviewed
Publication Year
2023
Copyright Information
© 2023 Author(s)
Content License
Metadata License
Bibliographic Information
Book Title
CONVR 2023 - Proceedings of the 23rd International Conference on Construction Applications of Virtual Reality
Book Subtitle
Managing the Digital Transformation of Construction Industry
Editors
Pietro Capone, Vito Getuli, Farzad Pour Rahimian, Nashwan Dawood, Alessandro Bruttini, Tommaso Sorbi
Peer Reviewed
Publication Year
2023
Copyright Information
© 2023 Author(s)
Content License
Metadata License
Publisher Name
Firenze University Press
DOI
10.36253/979-12-215-0289-3
eISBN (pdf)
979-12-215-0289-3
eISBN (xml)
979-12-215-0257-2
Series Title
Proceedings e report
Series ISSN
2704-601X
Series E-ISSN
2704-5846