Comparative Analysis for the Detection of Marine Vessels from Satellite Images Using FCM and Marker-Controlled Watershed
- PDF / 825,271 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 85 Downloads / 162 Views
RESEARCH ARTICLE
Comparative Analysis for the Detection of Marine Vessels from Satellite Images Using FCM and Marker-Controlled Watershed Segmentation Algorithm C. Heltin Genitha1
•
M. Sowmya1 • Tharani Sri1
Received: 12 April 2019 / Accepted: 17 August 2020 / Published online: 25 August 2020 Ó Indian Society of Remote Sensing 2020
Abstract The security of maritime activity is enhanced by the detection of marine vessels. Satellite images are used to detect the marine vessels irrespective of extreme weather conditions. Marine vessels can be detected efficiently using image segmentation algorithms. Many researchers have applied Haar-like classifier, convolution neural network, artificial neural network techniques to detect the marine vessels. In this work two different methodologies such as fuzzy C means (FCM) and marker-controlled watershed segmentation algorithms are developed and demonstrated to detect the marine vessels from satellite images. The marker-controlled watershed algorithm can effectively visualize an image in three dimensions and easily segments three-dimensional images. On the other hand, the number of iterations needed to achieve a specific clustering exercise in FCM is very less. It calculates the distance between the pixels and the cluster centres in the spectral domain to calculate the membership function. Experiments are carried out using IKONOS image of 4-m resolution. The average users accuracy of FCM algorithm and marker-controlled watershed algorithm is 91.29% and 95.79%, respectively. The results obtained show that there is an increase in accuracy for marker-controlled watershed algorithm when compared to FCM algorithm. Keywords Marine vessel Satellite image Fuzzy C means Marker-controlled watershed algorithm
Introduction Marine vessel detection is essential to restrict the vessel traffic and upgrade the safety and security of maritime system. The control of vessel activity in profoundly congested zones has turned into a basic prerequisite for safety and security as vessels carrying dangerous goods and tankers may cause environmental issues. Moreover, the protection of marine vessels is necessary due to the threats from smugglers and intruders. Hence, detection of marine vessels plays a vital role in protecting the maritime security, illegal act and to combat piracy. Marine vessels can be detected effectively by using appropriate image segmentation algorithm. & C. Heltin Genitha [email protected] 1
Department of Information Technology, St. Joseph’s College of Engineering, Old Mahabalipuram Road, Chennai 600119, India
Zhang et al. proposed an approach for combining specific spatial angle clustering and support vector machine (SVM) classification to detect marine vessels in whole image independently. However, the position of the marine vessel was detected using radar which may not suitable for populated areas (Zhang et al. 2017). Kruger et al. used canny edge detector to determine long edges for marine vessels. But, only small boats and ships were detected and tracked
Data Loading...
