利用截面序列多级特征全局关联性的毫米波图像隐匿物检测  

Concealed Object Detection in Millimeter Wave Image Based on Global Correlation of Multi-level Features in Cross-section Sequence

作　　者：何婉婷 张铂 王斌[1,2] 孙晓玮[3] 杨明辉[3] 吴晓峰[1,2] HE Wan-Ting;ZHANG Bo;WANG Bin;SUN Xiao-Wei;YANG Ming-Hui;WU Xiao-Feng(Key Laboratory for Information Science of Electromagnetic Waves(MoE),Fudan University,Shanghai 200433,China;Research Center of Smart Networks and Systems,School of Information Science and Technology,Fudan University,Shanghai 200433,China;Key Laboratory of Terahertz Technology,Shanghai Institute of Microsystem and Information Technology,Shanghai 200050,China)

机构地区：[1]复旦大学电磁波信息科学教育部重点实验室,上海200433 [2]复旦大学信息学院智慧网络与系统研究中心,上海200433 [3]中国科学院上海微系统与信息技术研究所中科院太赫兹固态技术重点实验室,上海200050

出　　处：《红外与毫米波学报》2021年第6期738-748,共11页Journal of Infrared and Millimeter Waves

基　　金：国家自然科学基金(61731021)。

摘　　要：基于毫米波图像的隐匿物检测技术在无接触式人体安检中具有重要意义。目前,毫米波设备已实现三维成像,但隐匿物检测算法通常将其简单压缩为二维图像进行目标检测,未能充分利用图像深度方向的信息。针对这一问题,提出一种毫米波图像隐匿物检测框架,将三维图像视为截面序列并充分利用其截面内特征沿序列(即深度方向)的内在逻辑关系。该框架由卷积神经网络与长短时记忆网络构成,前者用于提取截面的粗细粒度特征,后者用于提取上述特征沿深度方向的全局关联性,实现特征级信息融合,从而提高隐匿物二维定位准确率。实验结果表明,与现有主流毫米波图像隐匿物检测方法相比,所提模型能大幅提高检测精度。The concealed object detection in millimeter wave(MMW)image is of great significance in non-contact body inspection.At present,MMW radar has been able to obtain 3D images,which are simply compressed into 2D images in current methods in general.However,such a rough processing does not take the information along the depth direction into account which results in a bottleneck of detection accuracy.To address this issue,a novel framework for MMW image concealed object detection is proposed,in which a 3D image is regarded as a sequence of 2D cross-sectional images and the most of the internal logic relations of features in the cross-sectional images can be explored along the sequential direction,i.e.the depth direction of the 3D image.The framework consists of a Convolutional Neural Network(CNN)and a Long Short-Term Memory(LSTM)network.The former is used to extract the multiscale features in each 2D cross-sectional image while the latter is used to explore the global correlation of the above features along the depth direction to achieve feature-level information fusion and improve the accuracy of 2D location prediction.Experimental results show that the proposed method achieves remarkable results comparing to the known detection method based on 2D MMW images.

关 键 词：毫米波图像 三维图像 目标检测 深度学习 卷积神经网络 长短时记忆网络 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]