面向嵌入式平台的光学遥感图像舰船检测识别
Ship Detection and Recognition of Optical Remote Sensing Images for Embedded Platform
何鑫宇 1陆陈鑫 1冯书谊 1欧阳尚荣 1穆文涛1
作者信息
- 1. 上海航天电子技术研究所 上海 201109
- 折叠
摘要
建设海洋强国是我国当前大力发展的战略方向.针对现有基于深度学习的遥感图像舰船目标检测识别算法在嵌入式平台上存在检测分类识别率低、运行速率慢等问题,提出了一种基于寒武纪MLU220嵌入式平台改进的Mix-YOLO网络模型.该模型以YOLOv7-tiny网络为基本框架,首先,引入MobileNet系列网络模块对特征提取网络进行部分替换,减少网络参数量;然后,引入ULSAM注意力机制,以便增强网络学习分类能力,减少虚警率;最后,为了显著提升嵌入式平台检测速率,采用将网络模型大模块拆分为小模块的编写方式.实验结果表明:Mix-YOLO算法在原YOLOv7-tiny网络基础上,参数量和计算量分别下降了39.70％和29.70％,处理帧率由97.27 fps提升至120.88fps,精度提高了7.7％,能够实现对遥感图像中舰船目标的实时检测识别.
Abstract
The construction of a maritime power is a current strategic direction for China's vigorous development.In response to the low detection and classification recognition rate and slow operation speed of existing deep learning-based remote sensing image ship target detection and classification algorithms on embedded platforms,this paper proposes an improved Mix-YOLO network model based on the Cambricon-MLU220 embedded platform.The model is based on the YOLOv7-tiny network as the basic framework.Firstly,the MobileNet series network module is introduced to replace the feature extraction network partially,reduc-ing the network parameter volume.Then,the ULSAM attention mechanism is introduced to enhance the network's learning and classification ability,reducing the false alarm rate.Finally,in order to make the detection speed improvement effect more obvious on the embedded platform,the network model is programmed by splitting the large module into small modules.Experimental re-sults show that the Mix-YOLO algorithm reduces the parameter volume and calculation by 39.70％and 29.70％,respectively,on the basis of the original YOLOv7-tiny network.The processing frame rate is increased from 97.27 fps to 120.88 fps,and the ac-curacy is improved by 7.7％.It can achieve real-time detection and recognition of ship targets in remote sensing images.
关键词
光学遥感图像/舰船检测/轻量级网络/注意力机制/嵌入式平台Key words
Optical remote sensing image/Ship detection/Lightweight network/Attention mechanism/Embedded platform引用本文复制引用
出版年
2024
NETL
NSTL
万方数据