| 一种基于深度学习的高速无人艇视觉检测实时算法 |
| |
| 引用本文： | 周治国,刘开元,郑翼鹏,屈崇,王黎明.一种基于深度学习的高速无人艇视觉检测实时算法[J].北京理工大学学报,2021,41(7):758-764. |
| |
| 作者姓名： | 周治国 刘开元 郑翼鹏 屈崇 王黎明 |
| |
| 作者单位： | 北京理工大学信息与电子学院,北京 100081;北京理工大学信息与电子学院,北京 100081;中国船舶重工集团公司第七一一研究所,上海 201108;中国人民解放军海军工程大学,湖北,武汉 430032 |
| |
| 摘 要： | 针对高速无人艇自主航行时对视觉检测的实时性以及由于水面场景变化和波浪反射等干扰的鲁棒性需求，提出一种基于深度学习的高速无人艇视觉检测实时算法.采用基于MobileNet的神经网络快速提取全图特征，设计SSD结构的检测网络融合各层特征图的结果以完成快速多尺度检测，并在嵌入式GPU NVIDIA Jetson TX2硬件平台上将算法实现并验证.结果表明，该算法能够实时检测多类水上特定目标，具有鲁棒性强、多尺度的特点，单帧视频的检测时间可以控制在50 ms以内.
|
| 关 键 词： | 高速无人艇 深度学习 视觉检测 实时 |
| 收稿时间： | 2020/7/30 0:00:00 |
A Real-Time Algorithm for Visual Detection of High-Speed Unmanned Surface Vehicle Based on Deep Learning |
| |
| ZHOU Zhiguo,LIU Kaiyuan,ZHENG Yipeng,QU Chong,WANG Liming.A Real-Time Algorithm for Visual Detection of High-Speed Unmanned Surface Vehicle Based on Deep Learning[J].Journal of Beijing Institute of Technology(Natural Science Edition),2021,41(7):758-764. |
| |
| Authors: | ZHOU Zhiguo LIU Kaiyuan ZHENG Yipeng QU Chong WANG Liming |
| |
| Affiliation: | 1. School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China;2. Shanghai Marine Diesel Engine Research Institute, Shanghai 201108, China;3. Naval University of Engineering, PLA, Wuhan, Hubei 430032, China |
| |
| Abstract: | In order to solve the problem of high real-time, and robustness to disturbances such as scene changes and wave reflections during visual detection in unmanned surface vehicle(USV) autonomous navigation, a real-time algorithm for visual detection of high-speed USV based on deep learning was proposed. First, a neural network MobileNet was arranged to quickly extract the full-image features. Then, a detection network based on SSD was used to fuse feature maps of each layer and achieve fast and multi-scale detection. Finally, the algorithm was implemented and validated on a hardware platform embedded GPU NVIDIA Jetson TX2. The results show that the proposed algorithm can quickly detect multiple types of specific obstacle on the water with strong robustness and multi-scale detection ability, and the detection speed of single-frame video within 50 ms. |
| |
| Keywords: | high-speed unmanned surface vehicle deep learning visual detection real-time |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《北京理工大学学报》浏览原始摘要信息 |
|
点击此处可从《北京理工大学学报》下载全文 |
|
