Optimized vessel detection in marine environment using hybrid adaptive cuckoo search algorithm. (September 2019)

• Record Type: Journal Article
• Authors: S., Iwin Thanakumar Joseph; Sasikala, J.; Juliet, D. Sujitha
• Is Part Of: Computers & electrical engineering. Volume 78(2019)
• Page Start: 482
• Page End: 492
• Publication Date: 2019-09
• Subjects: Cuckoo search algorithm -- Neural network -- Computation model -- Data analysis -- Vessel detection; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2019.08.009
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Detection of vessels in a marine environment is a challenging task due to the complexity of identifying small objects, necessitating a detection algorithm to discriminate between variants in vessel-based geometry. False detection can be an issue due to sea clutter. The huge neural network-based computation models used for data analysis produce results that reflect the changing environment, based on iterations and common computation assumptions. To obtain the best results, the proposed research uses an optimization model with a classifier. This experimental model provides better accuracy than other detection systems, even with thousands of vessel images. This hybrid, adaptive cuckoo search-based optimization model produces the best results in dynamic sea-clutter regions, and outputs show lower false alarms in ports and other coastal surveillance regions.