基于被动式人体安检太赫兹图像的小目标物体检测方法
A Method for Small Object Detection of Passive Terahertz Image in Human Body Security Check—Subtitle as Needed
摘要: 被动式太赫兹成像设备不断应用于人体安检，而在特定安检场合(例如机场)需要快速准确检测出人体安检图像中的小目标违禁品。由于被动式太赫兹图像低分辨率的限制，人体安检对小目标检测精度和速度的需求，传统检测方法和单纯的深度学习算法都难以满足。根据被动式太赫兹图像低分辨率的特性，本文在目标检测前对图像进行预处理。针对小目标检测，我们对SSD算法的网络结构和预选框进行了优化。在小目标检测方面，我们的方法可以提高检测精度到73%。而在一般目标检测方面(包含小目标)我们的方法可以达到76%mAP。
Abstract: Passive terahertz imaging equipment is constantly used in human body security check. In the specific security situation such as airport, it is necessary to detect small object contraband quickly and accurately. Due to the low resolution of passive terahertz image, the traditional detection algorithm and simple deep learning algorithm cannot meet the needs of accuracy for small object detection in human body security check. In this paper, according to the low resolution of passive terahertz image, we preprocess the image before object detection. To improve detection accuracy for small objects, we optimize the architecture and default boxes of SSD model. For small object detection, our method, the optimized SSD with preprocessing, can improve accuracy to 73%. For common object detection, our method can achieve 76% mAp.
文章引用：张骋, 史秀聪, 黄子豪, 符基高. 基于被动式人体安检太赫兹图像的小目标物体检测方法[J]. 计算机科学与应用, 2020, 10(5): 1064-1073. https://doi.org/10.12677/CSA.2020.105111

参考文献

[1] Si, S., H, F. and Gu, Y. (2014) A Gaussian Filtering Algorithm Based on Irregular Region. Computer Science, 41, 313-316.
[2] Huang, T., Yang, G. and Tang, G. (1979) A Fast Two-Dimensional Median Filtering Algorithm. IEEE Transactions on Acoustics, Speech, and Signal Processing, 27, 13-18. [Google Scholar] [CrossRef] 
[3] 赵然, 赵源萌, 张存林. 被动式人体太赫兹图像中的目标辅助识别[J]. 强激光与粒子束, 2014, 26(7): 132-136.
[4] 朱维文, 赵跃进, 朱慧时, 李冰, 孔令琴, 董立泉. 改进的均值滤波算法在太赫兹成像中的应用[J]. 红外与激光工程, 2013, 42(5): 1241-1246.
[5] 朱书进, 李跃华. 基于自适应流形高维滤波的太赫兹图像滤波算法[J]. 太赫兹科学与电子信息学报, 2016, 14(4): 497-501 + 507.
[6] 孙建忠, 章乐, 高飞, 李九生. 太赫兹连续波成像的质量改进与降噪[J]. 光谱学与光谱分析, 2017, 37(11): 3343-3346.
[7] 冯艳平, 王徽. 基于阈值分割和边缘检测的枪支THz图像识别[J]. 红外, 2011, 32(12): 23-26.
[8] 江天, 沈会良, 杨冬晓, 刘建军, 邹哲. 基于模糊局部信息C均值的太赫兹图像目标检测[J]. 激光技术, 2015, 39(3): 289-294.
[9] Xie, L.L., Liu, Y.L., Jin, L.W. and Xie, Z.C. (2019) DeRPN: Taking a Further Step to-ward More General Object Detection.
https://arxiv.org/abs/1811.06700
[10] Lu, X., Li, B., Yue, Y., Li, Q. and Yan, J. (2019) Grid R-CNN. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 16-21 June 2019, 7355-7364. https://arxiv.org/abs/1811.12030 [Google Scholar] [CrossRef] 
[11] Li, J., Wang, C., Wang, Y., Tai, Y., Qian, J., Wang, C., Yang, J., Li, J. and Huang, F. (2019) Dual Shot Face Detector.
https://arxiv.org/abs/1810.10220
[12] Li, Y., Chen, Y., Wang, N. and Zhang, Z. (2019) Scale-Aware Trident Networks for Object Detection.
https://arxiv.org/abs/1901.01892
[13] Zhu, C., He, Y. and Savvides, M. (2019) Feature Selective Anchor-Free Module for Single-Shot Object Detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 16-21 June 2019, 840-849. https://arxiv.org/abs/1903.00621 [Google Scholar] [CrossRef] 
[14] Chen, Y., Yang, T., Zhang, X., Meng, G., Pan, C. and Sun, J. (2019) Neural Architecture Search on Object Detection.
https://arxiv.org/abs/1903.10979
[15] Gupta, A., Dollar, P. and Girshick, R. (2019) Lvis: A Dataset for Large Vocabulary Instance Segmentation. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 16-21 June 2019, 5351-5359. https://arxiv.org/abs/1908.03195 [Google Scholar] [CrossRef] 
[16] Girshick, R., Donahue, J. and Darrell, T. (2014) Rich Feature Hi-erarchies for Accurate Object Detection and Semantic Segmentation. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 23-28 June 2014, 580-587. https://arxiv.org/abs/1905.02285 [Google Scholar] [CrossRef] 
[17] He, K., Zhang, X. and Ren, S. (2015) Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 1904-1916. https://arxiv.org/abs/1406.4729 [Google Scholar] [CrossRef] 
[18] Girshick, R. (2015) Fast R-CNN.
https://arxiv.org/abs/1504.08083
[19] Ren, S., He, K., Grishick, R. and Sun, J. (2016) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intel-ligence, 39, 1137-1149. [Google Scholar] [CrossRef] 
[20] Liu, W., Anguelov, D., Erhan, D., Szegedy, C. and Reed, S. (2015) SSD: Single Shot Multi-Box Detector. European Conference on Computer Vision, Amsterdam, 8-16 October 2015, 21-37. https://arxiv.org/abs/1512.02325 [Google Scholar] [CrossRef] 
[21] Redmon, J., Divvala, S., Girshick, R. and Farhadi, A. (2016) You Only Look Once: Unified, Real-Time Object Detection.
https://arxiv.org/abs/1506.02640
[22] Cai, Z. and Vasconcelos, N. (2017) Cascade R-CNN: Delving into High Quality Object Detection.
https://arxiv.org/abs/1712.00726