An Efficient and Adaptive Method for Collision Probability of Ships, Icebergs Using CNN and DBSCAN Clustering Algorithm
Collision between ships and icebergs is a major problem in glacial area, where large to small icebergs becomes a threat to cargo ships, tankers, fishing ships etc. In this paper, we have devised a new approach for the detection of icebergs and movement of ships to predict their probability of collision. In this proposed work, an adaptive method is used to detect the presence of icebergs and the velocity of ships, followed by integrating the obtained data and applying the Bayesian algorithm we have successfully computed the collision probability. This work exhibits effective results against reduced visibility due to fog. Besides, we have acquired all the foreground authentic data from valid resources. So, the results will help in marking the safe and unsafe zones in the form of clusters by using DBSCAN algorithm.
KeywordsShips Icebergs Convolution neural network Collision probability Cluster
- 1.Khan, A.A.: Why would sea-level rise for global warming and polar ice-melt, China University of Geosciences (Beijing and Peking University), Elsevier B.V. http://doi.org/10.1016/j.jsf.2018.01.008
- 2.Li, Y., Han, J., Yang. J.: Clustering moving objects, Department of Computer Science University of Illinois UrbanaChampaign. ACM (2004). 1-58113-888-1/04/0008Google Scholar
- 3.Wesche, C., Dierking, W.: From ice shelves to icebergs: classification of calving fronts, iceberg monitoring and drift simulation. In: 2014 IEEE Geoscience and Remote Sensing Symposium (2014). https://doi.org/10.1109/igarss.2014.6946410
- 6.Phung, S.L., Bouzerdoum, A.: Matlab library for convolutional neural networks (2009)Google Scholar
- 8.Soman, K.P., Diwakar, S., Ajay, V.: Insight into data mining. PHI Publication (2009)Google Scholar