An improved object detection algorithm based on depthwise separable convolutions
文献类型：会议论文
| 作者 | Yu, Xiuyuan1,2,3; Bao, Qiliang1,2,3; Jia, Haolong1,2,3; Li, Yu1,2,3; Qin, Rui4 |
| 出版日期 | 2020-07-12 |
| 会议日期 | August 28, 2019 - August 30, 2019 |
| 会议地点 | Shenyang, China |
| 关键词 | Object Detection Depthwise Separable Convolutions Inverted Residuals Feature Pyramid Network Lightweight Network |
| 卷号 | 11427 |
| DOI | 10.1117/12.2552710 |
| 页码 | 114272T |
| 英文摘要 | Aiming at small objects detection such as unmanned aerial vehicle (UAV), this paper proposes a fast object detection algorithm based on depth wise separable convolutions. Firstly, the inverted residuals units based on depth wise convolutions and pointwise convolutions are used to construct a lightweight feature extraction network to improve the network's speed. Secondly, the feature pyramid network is used to detect the five scale feature maps to improve the detection performance of small objects. Otherwise, we make an UAV dataset based on the urban background for training and testing of our experiments. The experimental results show that the improved method proposed in this paper can effectively improve the detection accuracy and real-time performance of UAVs in complex urban backgrounds, and the computation of network is greatly reduced, thereby making it possible to achieve object detection on embedded systems. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only. |
| 会议录 | Proceedings of SPIE 11427 - Second Target Recognition and Artificial Intelligence Summit Forum
 |
| 会议录出版者 | SPIE-INT SOC OPTICAL ENGINEERING |
| 文献子类 | 会议论文 |
| 会议录出版地 | BELLINGHAM |
| 语种 | 英语 |
| ISSN号 | 0277-786X |
| WOS研究方向 | Computer Science ; Optics |
| WOS记录号 | WOS:000546230500098 |
| 源URL | [http://ir.ioe.ac.cn/handle/181551/9895]  |
| 专题 | 光电技术研究所_光电工程总体研究室（一室） |
| 作者单位 | 1.University of Chinese Academy of Sciences, Beijing; 100049, China; 2.Key Laboratory of Optical Engineering, Chinese Academy of Sciences, Chengdu; 610209, China; 3.Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu; 610209, China; 4.Boltzmann Technology, Chengdu; 610041, China |
| 推荐引用方式 GB/T 7714 | Yu, Xiuyuan,Bao, Qiliang,Jia, Haolong,et al. An improved object detection algorithm based on depthwise separable convolutions[C]. 见:. Shenyang, China. August 28, 2019 - August 30, 2019. |
入库方式： OAI收割
来源：光电技术研究所
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。