Name
Abstract | ||
|---|---|---|
Recently, deep learning-based methods have made great improvements in object detection in remote sensing images (RSIs). However, detecting tiny objects in low-resolution images is still challenging. The features of these objects are not distinguishable enough due to their tiny size and confusing backgrounds and can be easily lost as the network deepens or downsamples. To address these issues, we propose an effective Tiny Ship Detector for Low-Resolution RSIs, abbreviated as LR-TSDet, consisting of three key components: a filtered feature aggregation (FFA) module, a hierarchical-atrous spatial pyramid (HASP) module, and an IoU-Joint loss. The FFA module captures long-range dependencies by calculating the similarity matrix so as to strengthen the responses of instances. The HASP module obtains deep semantic information while maintaining the resolution of feature maps by aggregating four parallel hierarchical-atrous convolution blocks of different dilation rates. The IoU-Joint loss is proposed to alleviate the inconsistency between classification and regression tasks, and guides the network to focus on samples that have both high localization accuracy and high confidence. Furthermore, we introduce a new dataset called GF1-LRSD collected from the Gaofen-1 satellite for tiny ship detection in low-resolution RSIs. The resolution of images is 16m and the mean size of objects is about 10.9 pixels, which are much smaller than public RSI datasets. Extensive experiments on GF1-LRSD and DOTA-Ship show that our method outperforms several competitors, proving its effectiveness and generality.</p> |
Year | DOI | Venue |
|---|---|---|
2021 | 10.3390/rs13193890 | REMOTE SENSING |
Keywords | DocType | Volume |
tiny ship detection, remote sensing images (RSIs), convolutional neural network (CNN), self-attention, atrous convolution | Journal | 13 |
Issue | Citations | PageRank |
19 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jixiang Wu | 1 | 0 | 0.34 |
| Zongxu Pan | 2 | 74 | 8.13 |
| Bin Lei | 3 | 11 | 4.73 |
| Yuxin Hu | 4 | 0 | 0.34 |