Sea-land segmentation data with ground truth
We collected inshore ship images of different ports from GoogleEarth, and manually labeled the images for sea-land segmentation.
Link: https://pan.baidu.com/s/1CBJfkNmiWlQtwAqhGdoINw key: uvq8
Zhihong Pan, Hao Dou, Tian Tian, Zhengquan Chu, and many other fellows in AIA-HUST and CS-CUG.
We appreciate you if our papers can be cited (The manuscript is also included in the file for reference):
[1] Zhengquan Chu, Tian Tian*, Ruyi Feng, Lizhe Wang, Sea-land segmentation with Res-Unet and fully connected CRF. 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2019), 2019, 3840-3843.
[2] Pan, Zhihong, Hao Dou, Jiaxing Mao, Min Dai, and Jinwen Tian. MIFNet: Multi-Information Fusion Network for Sea-Land Segmentation. In Proceedings of the 2nd International Conference on Advances in Image Processing, 2018, 24-29. 2018.
[3] Tian Tian*, Zhihong Pan, Xiangyu Tan, Zhengquan Chu, Arbitrary-oriented inshore ship detection based on multi-scale feature fusion and contextual pooling on rotation region proposals. Remote Sensing, 2020, 12(2), 339. DOI: 10.3390/rs12020339. (https://www.mdpi.com/2072-4292/12/2/339/htm. Ship detection data is available as well.)