Ship Landmark: An Informative Ship Image Annotation and Its Applications

MingXin Zhang1, Qian Zhang1, Ran Song1*, Paul L. Rosin2, Wei Zhang1
1 School of Control Science and Engineering, Shandong University 2 School of Computer Science and Informatics, Cardiff University


Visual perception of ships has been attracting increasing attention in the fields of computer vision and ocean engineering. Despite the extensive work related to landmark detection of common objects, the role of landmark in ship perception has been overlooked. In this paper, we aim to fill this gap by focusing on ship landmarks. Specifically, we give a comprehensive analysis of both physical structure and deep features of ships, which finds that highlighted areas in feature maps correspond with structurally significant parts of ships. By summarizing the locations of such areas in ships, we define 20 ship landmarks and build the Ship Landmark Dataset (SLAD), the first ship dataset with landmark annotations. We also provide a benchmark for ship landmark detection by evaluating state-of-the-art landmark detection methods on the newly built SLAD. Moreover, we showcased several applications of ship landmarks, including ship recognition, ship image generation, key area detection for ships, and ship detection. Code and Datasets Available Here


Structure-Based Ship Generation

Qualitative results during training

Generated Results

Landmark-based key area detection for ships

Landmark-based Ship Detection

Distribution of the number of ships in different categories in the SLAD

Three annotated visualisations of the SLAD

Visualisation of different values of β

Ship classification results on the data generated with different values of β

Performance of training models with different values of β

CAM image visualisation of ship images using "the ship" as CLIP input text