Self-Paced Feature Attention Fusion Network for Concealed Object Detection in Millimeter-Wave Image
Self-Paced Feature Attention Fusion Network for Concealed Object Detection in Millimeter-Wave Image
复制标题
用于毫米波图像中隐藏物体检测的自定进度特征注意融合网络
DOI：
10.1109/tcsvt.2021.3058246
复制
发表时间：
2022-01
影响因子：
8.4
通讯作者：
Mao Shasha
中科院分区：
文献类型：
--
作者：
Wang Xinlin;Gou Shuiping;Li Jichao;Zhao Yinghai;Liu Zhen;Jiao Changzhe;Mao Shasha
有源毫米波扫描仪由于其能够探测衣服下的各种物体且对人体无害，近年来被广泛应用于公共场所的人体安全检查。然而，由于固有的成像噪声，未知的目标种类和不确定的位置，它是真正具有挑战性的自动和准确地检测所有隐藏的目标。最近，许多现有的方法，特别是基于深度学习的方法，在隐藏对象检测方面取得了良好的性能。这些方法对于检测几种大的目标效果很好，但是对于弱小的、不完整的硬目标效果不佳。为了解决这个问题，本文提出了一种基于自适应特征注意力融合网络（SPFAFN）的隐藏目标检测模型。具体而言，不同尺度的特征以自顶向下的方式融合，以整合细节和全局语义，从而更好地检测小目标。在融合多尺度特征的过程中，提出了一种由通道注意和空间注意组成的层次金字塔注意机制来感知目标。此外，利用提升自定进度学习来引导模型学习难以检测的硬样本。该方法在两个真实世界的数据集上进行了验证：AMMW数据集和公开可用的被动毫米波（PMMW）数据集。实验结果表明，该方法在两个数据集上均取得了较好的平均精度（AP），优于现有方法的上级性能。
The active millimeter-wave (AMMW) scanner has been widely used for inspecting human security in public places in recent years owing to its ability to detect all kinds of objects under the clothes and be harmless to the body. However, it is really challenging to detect all concealed objects automatically and accurately due to inherent imaging noise, unknown object kind, and uncertain position. Recently, many existing methods, especially deep learning-based, have achieved good performances on concealed object detection. These methods work well for detecting a few kinds of large objects, but fail to perform on dim and incomplete hard objects. To address this task, a concealed object detection model with self-paced feature attention fusion network (SPFAFN) is proposed in this article. To be specific, the features with different scales are fused in a top-down manner to integrate details and global semantics to better detect small objects. During fusing multi-scale features, a hierarchical pyramid attention mechanism composed of channel and spatial attention is developed to perceive the object. Moreover, boosting self-paced learning is exploited to guide the model to learn hard samples that are difficultly detected. The proposed method is validated on two real-world datasets: an AMMW dataset and a publicly available passive millimeter-wave (PMMW) dataset. Experimental results demonstrate that the proposed approach is superior to the state-of-the-art methods, and achieves better performances on the two datasets with Average Precision (AP).