Name
Abstract | ||
|---|---|---|
Accurate multiclass object detection in remote sensing images is a challenging task, especially for small objects. Since the scales of objects in remote sensing images have a great variance, almost all of the advanced detection methods have shortcomings. Consequently, improving the accuracy of multiclass objects detection has always been the direction of researchers' efforts. In this paper, a spatial enhanced-Single Shot MultiBox Detector (SE-SSD) is proposed. First, to enhance the spatial information, we enlarge the input image channels with embedding oriented-gradients feature maps. Second, the multiple output layers in the backbone network are changed to reduce one pooling operation. Finally, we design a context module to enhance the receptive field for feature layer description in SE-SSD framework. Experimental results on DOTA dataset demonstrate that Spatial Enhanced-SSD method reaches a much higher mean average precision (mAP) than Faster R-CNN, SSD and other classic detection network. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/IGARSS.2019.8898526 | IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium |
Keywords | Field | DocType |
Remote Sensing,Deep Learning,Object Detection,Oriented Gradients,Context Module,Receptive Field | Spatial analysis,Object detection,Computer vision,Embedding,Computer science,Remote sensing,Pooling,Communication channel,Artificial intelligence,Deep learning,Backbone network,Detector | Conference |
ISSN | ISBN | Citations |
2153-6996 | 978-1-5386-9155-7 | 0 |
PageRank | References | Authors |
0.34 | 1 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Guanqun Wang | 1 | 0 | 0.34 |
| Yin Zhuang | 2 | 17 | 7.77 |
| Zhiru Wang | 3 | 4 | 0.74 |
| He Chen | 4 | 7 | 2.80 |
| Hao Shi | 5 | 30 | 9.58 |
| L. Chen | 6 | 3 | 2.74 |