@inproceedings{8f1a1fd01de3496389093167db30ceb6,
title = "Ship Detection from Optical Remote Sensing Image based on Size-Adapted CNN",
abstract = "Due to the diversity of ship sizes, ship detection from optical remote sensing images is still a challenging task. To tackle this problem, this paper proposed a size-adapted framework based on a coarse-to-fine strategy. First, the proposed method generates ship candidates through calculating the convolutional feature maps by three shallow convolutional neural networks (CNN) with different scales, in which the entire images with arbitrary sizes are fed as input; Second, a feature vector with fixed-length is extracted by the spatial pyramid pooling (SPP) layer from the candidates, regardless of the size and aspect ratio of the candidates; Finally, the multi-task learning is employed to classify the candidates using a softmax classifier, as well as to reduce the ship localization error by simple bounding-box regression. The experiments were carried out on various images, and the results demonstrated the effectiveness of the proposed method while dealing with the ships of different sizes.",
keywords = "multi-task learning, ship detection, size-adapted CNN, spatial pyramid pooling (SPP)",
author = "Xin Hou and Qizhi Xu and Yan Ji",
note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 5th International Workshop on Earth Observation and Remote Sensing Applications, EORSA 2018 ; Conference date: 18-06-2018 Through 20-06-2018",
year = "2018",
month = dec,
day = "31",
doi = "10.1109/EORSA.2018.8598601",
language = "English",
series = "5th International Workshop on Earth Observation and Remote Sensing Applications, EORSA 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
editor = "Qihao Weng and Paolo Gamba and Ni-Bin Chang and Guangxing Wang and Wanqiang Yao",
booktitle = "5th International Workshop on Earth Observation and Remote Sensing Applications, EORSA 2018 - Proceedings",
address = "United States",
}