Fahim Faisal Niloy
- Research Assistant, CCDS
PhD Student
University of California Riverside
Research Interests
Machine Learning
Conference Paper2021Cited by 15
A Novel Disaster Image Data-set and Characteristics Analysis using Attention Model
Fahim Faisal Niloy, Arif, Abu Bakar Siddik Nayem, Anis Sarker, Ovi Paul, M Ashraful Amin, Amin Ahsan Ali, Moinul Islam Zaber, AKM Mahbubur Rahman
2020 25th International Conference on Pattern Recognition (ICPR)
IEEE, pp. 6116-6122
Abstract
The advancement of deep learning technology has enabled us to develop systems that outperform any other classification technique. However, success of any empirical system depends on the quality and diversity of the data available to train the proposed system. In this research, we have carefully accumulated a relatively challenging dataset that contains images collected from various sources for three different disasters: fire, water and land. Besides this, we have also collected images for various damaged infrastructure due to natural or man made calamities and damaged human due to war or accidents. We have also accumulated image data for a class named non-damage that contains images with no such disaster or sign of damage in them. There are 13,720 manually annotated images in this dataset, each image is annotated by three individuals. We are also providing discriminating image class information annotated manually with bounding box for a set of 200 test images. Images are collected from different news portals, social media, and standard datasets made available by other researchers. A three layer attention model (TLAM) is trained and average five fold validation accuracy of 95.88% is achieved. Moreover, on the 200 unseen test images this accuracy is 96.48%. We also generate and compare attention maps for these test images to determine the characteristics of the trained attention model.
Keywords
Minimum bounding boxImage (mathematics)Set (abstract data type)Test setClass (philosophy)Bounding overwatchData setPattern recognition (psychology)Deep learning
CCDS Authors
Abu Bakar Siddik Nayem
- Research Assistant, CCDS
Lead ML Engineer
Acme AI
Research Interests
Machine Learning
Anis Sarker
- Research Assistant, CCDS
AI Engineer
AinoviQ
Research Interests
Machine Learning
Ovi Paul
- Research Assistant, CCDS
PhD Student
University of Houston
Research Interests
Machine Learning, Geosensing System Engineering
M Ashraful Amin, PhD
- Founder Director, CCDS
- Director, AI/ML, HCI & DS Wings
Research Interests
Machine Learning, Cognitive & Vision Science, Cybernetics, Surveillance & Security, ICT in Education, Health, & Agriculture, Human-Computer Interaction, Internet of Things, Robotics
Amin Ahsan Ali, PhD
- Director, AI/ML Wing
Professor
Department of Computer Science and Engineering
Independent University, Bangladesh
Research Interests
Artificial Intelligence, Machine Learning
AKM Mahbubur Rahman, PhD
- Director, DS & IPT Wings
Associate Professor
Department of Computer Science and Engineering
Independent University, Bangladesh
References
- 1.Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei. (2009). ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition, 248–255[10.1109/cvpr.2009.5206848]
- 2.Mark Everingham, Luc Van Gool, Christopher K. I. Williams, John Winn, Andrew Zisserman. (2009). The Pascal Visual Object Classes (VOC) Challenge. International Journal of Computer Vision, 88(2), 303–338[10.1007/s11263-009-0275-4]
- 3.Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba. (2016). Learning Deep Features for Discriminative Localization. , 2921–2929[10.1109/cvpr.2016.319]
- 4.Aditya Chattopadhay, Anirban Sarkar, Prantik Howlader, Vineeth N Balasubramanian. (2018). Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks. , 839–847[10.1109/wacv.2018.00097]
- 5.Khan Muhammad, Jamil Ahmad, Sung Wook Baik. (2017). Early fire detection using convolutional neural networks during surveillance for effective disaster management. Neurocomputing, 288, 30–42[10.1016/j.neucom.2017.04.083]
- 6.Turgay Çelik, Hasan Demirel. (2008). Fire detection in video sequences using a generic color model. Fire Safety Journal, 44(2), 147–158[10.1016/j.firesaf.2008.05.005]
- 7.Pasquale Foggia, Alessia Saggese, Mario Vento. (2015). Real-Time Fire Detection for Video-Surveillance Applications Using a Combination of Experts Based on Color, Shape, and Motion. IEEE Transactions on Circuits and Systems for Video Technology, 25(9), 1545–1556[10.1109/tcsvt.2015.2392531]
- 8.Dat T. Nguyen, Ferda Ofli, Muhammad Imran, Prasenjit Mitra. (2017). Damage Assessment from Social Media Imagery Data During Disasters. , 569–576[10.1145/3110025.3110109]
- 9.Byoung Chul Ko, Sun Jae Ham, Jae Yeal Nam. (2011). Modeling and Formalization of Fuzzy Finite Automata for Detection of Irregular Fire Flames. IEEE Transactions on Circuits and Systems for Video Technology, 21(12), 1903–1912[10.1109/tcsvt.2011.2157190]
- 10.Yara Rizk, Hadi Samer Jomaa, Mariette Awad, Carlos Castillo. (2019). A computationally efficient multi-modal classification approach of disaster-related Twitter images. , 2050–2059[10.1145/3297280.3297481]
- 11.Steven Verstockt, Tarek Beji, Pieterjan De Potter, Sofie Van Hoecke, Bart Sette, Bart Merci, Rik Van de Walle. (2012). Video driven fire spread forecasting (f) using multi-modal LWIR and visual flame and smoke data. Pattern Recognition Letters, 34(1), 62–69[10.1016/j.patrec.2012.07.018]
- 12.Panagiotis Giannakeris, Konstantinos Avgerinakis, Anastasios Karakostas, Stefanos Vrochidis, Ioannis Kompatsiaris. (2018). People and Vehicles in Danger - A Fire and Flood Detection System in Social Media. , 1–5[10.1109/ivmspw.2018.8448732]
- 13.Arif, Abdullah Omar, Sabah Ashraf, A. K. M. Mahbubur Rahman, M. Ashraful Amin, Amin Ahsan Ali. (2020). A Comparative Study on Disaster Detection from Social Media Images Using Deep Learning. Advances in intelligent systems and computing, 485–499[10.1007/978-981-15-2188-1_38]
Cited By
- 1.Kibitok Abraham, Moataz Abdelwahab, Mohammed Abo-Zahhad. (2023). Classification and detection of natural disasters using machine learning and deep learning techniques: A review. Earth Science Informatics, 17(2), 869–891[10.1007/s12145-023-01205-2]
- 2.Zhihao Ma, Mengke Yuan, Jiaming Gu, Weiliang Meng, Shibiao Xu, Xiaopeng Zhang. (2022). Triple-strip attention mechanism-based natural disaster images classification and segmentation. The Visual Computer, 38(9-10), 3163–3173[10.1007/s00371-022-02535-w]
- 3.Payal Bhadra, Avijit Balabantaray, Ajit Kumar Pasayat. (2023). MFEMANet: an effective disaster image classification approach for practical risk assessment. Machine Vision and Applications, 34(5)[10.1007/s00138-023-01430-1]
- 4.Yikun Zhao, Lei Feng, Fanqin Zhou, Wenjing Li, Zehui Xiong, Hongyang Du, Celimuge Wu, Song Guo, Tony Q. S. Quek, Zhu Han. (2025). Energy-Efficient Over-the-Air Computation for Federated Generative Model Fine-Tuning in Unmanned Vehicle-Assisted Disaster Relief. IEEE Transactions on Cognitive Communications and Networking, 12, 56–73[10.1109/tccn.2025.3553315]
- 5.Kibitok Abraham, Mohammed Abo-Zahhad, Moataz Abdelwahab. (2024). Natural disaster damage analysis using lightweight spatial feature aggregated deep learning model. Earth Science Informatics, 17(4), 3149–3161[10.1007/s12145-024-01325-3]
- 6.Tanu Gupta, Sudip Roy. (2024). DisasterRes-Net: A framework for analyzing social media images in disaster response. International Journal of Disaster Risk Reduction, 116, 105119[10.1016/j.ijdrr.2024.105119]
- 7.Hao Liu, Jiancheng An, Qian Ma, Lu Gan, Mehdi Bennis, Mérouane Debbah, Tie Jun Cui. (2025). A Novel Hybrid Optical-Electronic Neural Network Approach to Task-Oriented Semantic Communications. , 2418–2423[10.1109/icc52391.2025.11160907]
- 8.Sohail Abbas, Manar Abu Talib, Qasim Nasir, Omar Belal, Mohammed Emad Al-Haidary, Ibtihal Ahmed. (2025). A survey of disaster management datasets. Journal of Information and Telecommunication, 9(4), 574–596[10.1080/24751839.2025.2509452]
- 9.Kunshan Yang, Wenwei Luo, Yuguo Hu, Jiafu Yan, Mengmeng Jing, Lin Zuo. (2025). A Semantic-Enhanced Heterogeneous Graph Learning Method for Flexible Objects Recognition. , 1–6[10.1109/icme59968.2025.11210079]
- 10.Jieli Chen, Hanyue Xu, Li Minn Ang, Kah Phooi Seng. (2025). Distributed Situation Awareness System Using Vision Transformer with Attention Maps for Natural Disasters. , 1–4[10.1109/icest66328.2025.11098198]
- 11.Gao Yu Lee, Tanmoy Dam, Md. Meftahul Ferdaus, Daniel Puiu Poenar, Vu Duong. (2026). Enhancing Few-Shot Classification of Disaster Imagery with ABHFA-Net. SN Computer Science, 7(6)[10.1007/s42979-026-05262-4]
- 12.Yachun He, Jidong Wu, Lili Wang, Yingjun Xu, Youtian Yang, Wei Wu, Wei Jiang. (2026). ViGeo-Fuse: A multimodal framework integrating computer vision and geospatial ML for post-earthquake building damage classification. Developments in the Built Environment, 27, 101001[10.1016/j.dibe.2026.101001]
- 13.Samiksha Bharti, Bappaditya Das. (2026). Explainable Quantum-Optimized Efficient Net Framework For Multi-Class Disaster Image Classification. International Journal of Innovations in Science Engineering and Management., 198–208[10.69968/ijisem.2026v5i1198-208]
- 14.Masao KUBO, Quyet Thanh NGUYEN, Hiroshi SATO, Akihiro YAMAGUCHI. (2026). Disaster Related Image Detection on an IoT Device Using Vision-language Technology. Transactions of the Society of Instrument and Control Engineers, 62(2), 59–68[10.9746/sicetr.62.59]
- 15.Alain Patrick Ndigande, Josiah Wiggins, Sedat Ozer. (2026). Survey on Disaster Management Datasets for Remote Sensing-Based Emergency Applications. IEEE Transactions on Geoscience and Remote Sensing, 64, 4705121[10.1109/tgrs.2026.3692760]