光电工程, 2019, 46 (4): 180307, 网络出版: 2019-05-04  

面向**目标识别的 DRFCN 深度网络设计及实现

Design and implementation of DRFCN in-depth network for military target identification
作者单位
1 杭州电子科技大学通信信息传输与融合技术国防重点学科实验室, 浙江杭州 310018
2 中国船舶重工集团公司第七一五研究院, 浙江杭州 310023
摘要
自动目标识别(ATR)技术一直是**领域中急需解决的重点和难点。本文设计并实现了一种新的面向**目标识别应用的 DRFCN深度网络。首先, 在 DRPN部分通过卷积模块稠密连接的方式, 复用深度网络模型中每一层的特征, 实现高质量的目标采样区域的提取; 其次, 在 DFCN部分通过融合高低层次特征图语义特征信息, 实现采样区域目标类别和位置信息的预测; 最后, 给出了 DRFCN深度网络模型结构以及参数训练方法。与此同时, 进一步对 DRFCN算法开展了实验分析与讨论: 1) 基于 PASCAL VOC数据集进行对比实验, 结果表明, 由于采用卷积模块稠密连接的方法, 在目标识别平均准确率、实时性和深度网络模型大小方面, DRFCN算法均明显优于已有基于深度学习的目标识别算法; 同时, 验证了 DRFCN算法可以有效解决梯度弥散和梯度膨胀问题。 2) 利用自建**目标数据集进行实验, 结果表明, DRFCN算法在准确率和实时性上满足**目标识别任务。
Abstract
Automatic target recognition (ATR) technology has always been the key and difficult point in the militaryfield. This paper designs and implements a new DRFCN in-depth network for military target identification. Firstly, the part of DRPN is densely connected by the convolution module to reuse the features of each layer in the deep net-work model to extract the high quality goals of sampling area; Secondly, in the DFCN part, we fuse the information of the semantic features of the high and low level feature maps to realize the prediction of target area and location in-formation in the sampling area; Finally, the deep network model structure and the parameter training method of DRFCN are given. Further, we conduct experimental analysis and discussion on the DRFCN algorithm: 1) Based on the PASCAL VOC dataset for comparison experiments, the results show that DRFCN algorithm is obviously superior to the existing algorithm in terms of average accuracy, real-time and model size because of the convolution module dense connection method. At the same time, it is verified that the DRFCN algorithm can effectively solve the problem of gradient dispersion and gradient expansion. 2) Using the self-built military target dataset for experiments, the re-sults show that the DRFCN algorithm implements the military target recognition task in terms of accuracy and real-time.

刘俊, 孟伟秀, 余杰, 李亚辉, 孙乔. 面向**目标识别的 DRFCN 深度网络设计及实现[J]. 光电工程, 2019, 46(4): 180307. Liu Jun, Meng Weixiu, Yu Jie, Li Yahui, Sun Qiao. Design and implementation of DRFCN in-depth network for military target identification[J]. Opto-Electronic Engineering, 2019, 46(4): 180307.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!