Big Data Analysis in UAV Surveillance for Wildfire Prevention and Management
While wildfires continue to ravage our world, big data analysis aspires to provide solutions to complex problems such as the prevention and management of natural disasters. In this study, we illustrate a state-of-the-art approach towards an enhancement of UAV (Unmanned Aerial Vehicle) surveillance for wildfire prevention and management through big data analysis. Its novelty lies in the instant delivery of images taken from UAVs and the (near) real-time big-data oriented image analysis. Instead of relying on stand-alone computers and time-consuming post-processing of the images, a big data cluster is used and a MapReduce algorithm is applied to identify images from wildfire burning areas. Experiments identified a significant gain regarding the time needed to analyze the data, while the execution time of the image analysis is not affected by the size of the pictures gathered by the UAVs. The integration of UAVs, Big Data components and image analysis provides the means for wildfire prevention and management authorities to follow the proposed methodology to organize their wildfire management plan in a reliable and timely manner. The proposed methodology highlights the role of Geospatial Big Data and is expected to contribute towards a more state-of-the-art knowledge transfer between wildfire confrontation operation centers and firefighting units in the field.
KeywordsGeospatial Big Data Wildfire prevention UAV surveillance
This work has been partially conducted within the framework of the Greek State Scholarship Foundation (IKY) Scholarship Programs funded by the “Strengthening Post-Doctoral Research” Act from the resources of the OP “Human Resources Development and Lifelong Learning” priority axes 6, 8, 9, and co-financed by the European Social Fund (ESF) and the Greek Government.
- 6.Villars, R.L., Olofson, C.W., Eastwood, M.: Big data: what it is and why you should care. White Paper, IDC, 14 (2011)Google Scholar
- 10.Nardi, D.: Intelligent systems for emergency response (invited talk). In: Fourth International Workshop on Synthetic Simulation and Robotics to Mitigate Earthquake Disaster (SRMED 2009) (2009)Google Scholar
- 17.Nguyen, D.T., Ofli, F., Imran, M., Mitra, P.: Damage assessment from social media imagery data during disasters. In: Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, pp. 569–576. ACM (2017)Google Scholar
- 19.Athanasis, N., Themistocleous, M., Kalabokidis, K., Papakonstantinou, A., Soulakellis, N., Palaiologou, P.: The emergence of social media for natural disasters management: a big data perspective. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci. XLII-3/W4, 75–82 (2018). https://doi.org/10.5194/isprs-archives-XLII-3-W4-75-2018
- 20.Codella, N.C., Hua, G., Natsev, A., Smith, J.R.: Towards large scale land-cover recognition of satellite images. In: 2011 8th International Conference on Information, Communications and Signal Processing (ICICS), pp. 1–5. IEEE (2011)Google Scholar
- 22.Hadjisophocleous, G.V., Fu, Z.: Literature review of fire risk assessment methodologies. Int. J. Eng. Perform.-Based Fire Codes 6(1), 28–45 (2004)Google Scholar
- 23.Çelik, T., Ozkaramanlt, H., Demirel, H.: Fire pixel classification using fuzzy logic and statistical color model. In: 2007 IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP 2007, vol. 1, pp. I–1205. IEEE (2007)Google Scholar
- 24.Yuan, C., Liu, Z., Zhang, Y.: UAV-based forest fire detection and tracking using image processing techniques. In: 2015 International Conference on Unmanned Aircraft Systems (ICUAS), pp. 639–643. IEEE (2015)Google Scholar
- 25.Yuan, C., Liu, Z., Zhang, Y.: Vision-based forest fire detection in aerial images for firefighting using UAVs. In: 2016 International Conference on Unmanned Aircraft Systems (ICUAS), pp. 1200–1205. IEEE (2016)Google Scholar
- 26.Sweeney, C., Liu, L., Arietta, S., Lawrence, J.: HIPI: a Hadoop image processing interface for image-based mapreduce tasks. University of Virginia, Chris (2011)Google Scholar