Dual efficient self-attention network for multi-target detection in aerial imagery
文献类型：会议论文
| 作者 | Wang SK(王思奎)1,2,4 ; Liu YP(刘云鹏)2,3,4,5; Lin ZY(林智远)1,2,4; Zhang ZY(张钟毓)1,2,4
|
| 出版日期 | 2019 |
| 会议日期 | August 28-30, 2019 |
| 会议地点 | Shenyang, China |
| 关键词 | Target detection Self-attention block Deconvolutional module Semantic features Hard examples mining |
| 页码 | 1-7 |
| 英文摘要 | Aerial imagery target detection has been widely used in the military and economic fields. However, it still faces a variety of challenges. In this paper, we proposed several efficiency improvements based on YOLO v3 framework for getting a better small target detection precision. Firstly, a dual self-attention (DAN) block is embedded in Darknet-53's ResNet units to refine the feature map adaptively. Furthermore, the deep semantic features are cascaded with the shallow outline features in a feedforward deconvolutional module to obtain context details of small targets. Finally, introducing online hard examples mining and combining Focal Loss to enhance the discriminating ability between classes. The experimental results on the VEDAI aerial dataset show that the proposed algorithm is significantly improved in accuracy compared to the original network and achieves better performance than two-stage algorithms. |
| 源文献作者 | Chinese Society for Optical Engineering |
| 产权排序 | 1 |
| 会议录 | Second Target Recognition and Artificial Intelligence Summit Forum
 |
| 会议录出版者 | SPIE |
| 会议录出版地 | Bellingham, USA |
| 语种 | 英语 |
| ISSN号 | 0277-786X |
| ISBN号 | 978-1-5106-3631-6 |
| WOS记录号 | WOS:000546230500012 |
| 源URL | [http://ir.sia.cn/handle/173321/26421]  |
| 专题 | 沈阳自动化研究所_光电信息技术研究室 |
| 通讯作者 | Wang SK(王思奎) |
| 作者单位 | 1.University of Chinese Academy of Sciences, Beijing, China 2.Key Laboratory of Opto-Electronic Information Processing, CAS, Shenyang, China 3.Key Lab of Image Understanding and Computer Vision, Shenyang, China 4.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China 5.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China |
| 推荐引用方式 GB/T 7714 | Wang SK,Liu YP,Lin ZY,et al. Dual efficient self-attention network for multi-target detection in aerial imagery[C]. 见:. Shenyang, China. August 28-30, 2019. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。