Loading...
Please wait, while we are loading the content...
Similar Documents
Sparse Label Assignment for Oriented Object Detection in Aerial Images
| Content Provider | MDPI |
|---|---|
| Author | Ming, Qi Miao, Lingjuan Zhou, Zhiqiang Song, Junjie Yang, Xue |
| Copyright Year | 2021 |
| Description | Object detection in aerial images has received extensive attention in recent years. The current mainstream anchor-based methods directly divide the training samples into positives and negatives according to the intersection-over-unit (IoU) of the preset anchors. This label assignment strategy assigns densely arranged samples for training, which leads to a suboptimal learning process and cause the model to suffer serious duplicate detections and missed detections. In this paper, we propose a sparse label assignment strategy (SLA) to select high-quality sparse anchors based on the posterior IoU of detections. In this way, the inconsistency between classification and regression is alleviated, and better performance can be achieved through balanced training. Next, to accurately detect small and densely arranged objects, we use a position-sensitive feature pyramid network (PS-FPN) with a coordinate attention module to extract position-sensitive features for accurate localization. Finally, the distance rotated IoU loss is proposed to eliminate the inconsistency between the training loss and the evaluation metric for better bounding box regression. Extensive experiments on the DOTA, HRSC2016, and UCAS-AOD datasets demonstrate the superiority of the proposed approach. |
| Starting Page | 2664 |
| e-ISSN | 20724292 |
| DOI | 10.3390/rs13142664 |
| Journal | Remote Sensing |
| Issue Number | 14 |
| Volume Number | 13 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2021-07-07 |
| Access Restriction | Open |
| Subject Keyword | Remote Sensing Imaging Science Aerial Image Oriented Object Detection Label Assignment Convolutional Neural Network |
| Content Type | Text |
| Resource Type | Article |
