| 大会名称 |
| 2018年 総合大会 |
| 大会コ－ド |
| 2018G |
| 開催年 |
|
2018
|
| 発行日 |
|
|
| セッション番号 |
|
D-12A
|
| セッション名 |
|
パターン認識・メディア理解A
|
| 講演日 |
|
2018/3/21
|
| 講演場所(会議室等) |
|
２号館 9Ｆ 2903教室
|
| 講演番号 |
|
D-12-17
|
| タイトル |
|
Comparative Study of Feature Extraction Approaches for Ship Classification in Moderate-Resolution SAR Imagery
|
| 著者名 |
|
◎Shreya Sharma, Kenta Senzaki, Hirofumi Aoki,
|
| キーワード |
|
feature extraction, moderate resolution, deep learning, synthetic aperture radar, ship classification
|
| 抄録 |
|
In maritime surveillance applications, ship classification is one of key functionalities because it provides important information about marine traffic. Synthetic Aperture Radar (SAR) is an effective tool due to its all-weather and day-and-night acquisition capability. A number of studies have reported that feature extraction based ship classification methods efficiently work with high-resolution SAR images. However, the spatial resolution of practical SAR images for applications in maritime surveillance is limited to achieve wide-area coverage. Therefore, in this paper, we present comparative study on the effectiveness of major feature extraction methods to the ship classification in moderate-resolution SAR imagery, and select a promising method for practical SAR images.
|
| 本文pdf |
|
PDF download
|
