Global Mask R-CNN for marine ship instance segmentation

Marine ship instance segmentation by deep neural networks using a global and local attention (GALA) mechanism

“…As to marine ship segmentation, semantic segmentation classifies all ships in an image into one category, by labelling all ships with one color, while instance segmentation detects individual ships and classifies them into different categories. The applications of instance segmentation have been launched successfully in scenarios such as unmanned vehicle development [6,7], human-computer interaction [8,9], bio-medicine development [10][11][12], video surveillance [13][14][15], and marine ship monitoring [16][17][18].…”

“…Instance segmentation of marine ships is capable of providing important information such as the relative location of a ship with respect to other ships or surrounding obstacles, which is crucial for ship travel safety. Nowadays, various types of imaging techniques such as radar and infrared camera, have been equipped on a modern marine ship or an intelligent unmanned ship [16]. The spatial analysis of the ship imaging data can provide accurate environmental information to assist the ships to autonomously avoid crashing with other ships and natural obstacles in the ocean.…”

“…SAR imaging can perform regardless of weather conditions, but SAR images usually contain a large amount of scattering noise and do not have rich spectral information, which is not convenient for subsequent ship segmentation purpose.IR imaging has strong penetration capability and is not easily affected by environmental conditions, but the contrast and signal-to-noise ratio of the obtained IR images are usually not high enough, resulting in a lack of color and texture information of ships. In contrast, VL images have many unique advantages over other types of images such as high resolution, the inclusion of color and texture information, high signal-to-noise ratio, high contrast and of rich details, and thus VL images can be a strong complementary portion to satellite, SAR and IR images [16]. With these merits, VL images can provide clear information of ship features (e.g., shape) that are crucial for subsequent ship detection, segmentation and classification.…”

“…However, so far, there are only a limited number of open-source databases for VL marine ship images. Although two VL image datasets of marine ships were presented by Zhang et al and Sun et al respectively [16,18], these datasets have not been made publicly available, the scale of these datasets is relatively small and the labelling of the datasets in terms of ship categories is not fine enough.…”

“…Zhang et al proposed an integrated ship segmentation method based on discriminators and extractors to reduce the interference factors of complex ocean backgrounds [18]. To preserve the global information of a ship, Sun et al proposed a method using precise RoI pooling and global mask head that could improve the performance of ship instance segmentation [16]. showing that the use of the global and complete appearance information of a ship can increase the performance of instance segmentation.…”