Detect ships using saliency in infrared images with sea-sky background

Abstract

Nowadays, ship detection in sea-sky background is not only useful in maritime visual surveillance, but also helpful in maritime search and rescue. Since ships are salient objects in infrared images with sea-sky background, we present a novel and effective algorithm based on saliency for ship detection in this situation. Our algorithm adopts global saliency, local saliency and background prior to generate saliency maps. Ships are finally segmented in saliency maps. Our algorithm is compared with four classic salient object detection algorithms. And experimental results show our algorithm outperforms the other four algorithms in qualitative and quantitative terms.

Enhanced YOLOv8 Ship Detection Empower UnmannedSurface Vehicles for Advanced Maritime Surveillance

“…Complementing these advancements, [11] presents a real-time semantic segmentation model for USVs , streamlining obstacle mapping. In the realm of vessel detection, [12] and [13] explore efficient algorithms for analyzing both aerial and infrared sea-sky imagery, emphasizing their flexibility under diverse environmental conditions. Comprehensively, [14] brings to light a multi-sensor surveillance system adept at tracking a variety of vessels, effectively adapting to changing visual environments.…”

Water Region Extraction in Thermal and RGB Sequences Using Spatiotemporally-Oriented Energy Features

“…Consequently, such methods can primarily deal with simple scenarios, where there are only sea and sky regions in the captured scene. Besides this, there are several methods that do not attempt to find the ROI at all [8][9][10][11][12][13][14]. Such methods try to model the background (which is mostly the water itself) and then extract the target object directly by background subtraction.…”