基于全局感知机制的地面红外目标检测方法

doi:10.12305/j.issn.1001-506X.2022.05.05

系统工程与电子技术 ›› 2022, Vol. 44 ›› Issue (5): 1461-1467.doi: 10.12305/j.issn.1001-506X.2022.05.05

基于全局感知机制的地面红外目标检测方法

赵晓枫^1,², 徐叶斌^1,^2,*, 吴飞^1,², 牛家辉^1,², 蔡伟^1,², 张志利^1,²

1. 火箭军工程大学导弹工程学院, 陕西西安 710025
2. 兵器发射理论与技术国家重点学科实验室, 陕西西安 710025

收稿日期:2021-04-08 出版日期:2022-05-01 发布日期:2022-05-16
通讯作者: 徐叶斌
作者简介:赵晓枫(1979—), 男, 副教授, 博士, 主要研究方向为兵器发射理论与技术|徐叶斌(1997—), 男, 硕士研究生, 主要研究方向为计算机视觉、红外目标检测|吴飞(1994—), 男, 硕士研究生, 主要研究方向为图像处理、光电隐身伪装与防护|牛家辉(1994—), 男, 硕士研究生, 主要研究方向为图像处理、光电隐身伪装与防护|蔡伟(1974—), 男, 教授, 博士研究生导师, 博士, 主要研究方向为定位定向与光电防护|张志利(1966—), 男, 教授, 博士研究生导师, 博士, 主要研究方向为发射系统总体与仿真
基金资助:
国家自然科学基金(41404022)

Ground infrared target detection method based on global sensing mechanism

Xiaofeng ZHAO^1,², Yebin XU^1,^2,*, Fei WU^1,², Jiahui NIU^1,², Wei CAI^1,², Zhili ZHANG^1,²

1. College of Missile Engineering, Rocket Force Engineering University, Xi'an 710025, China
2. Armament Launch Theory and Technology Key Discipline Laboratory of China, Xi'an 710025, China

Received:2021-04-08 Online:2022-05-01 Published:2022-05-16
Contact: Yebin XU

摘要/Abstract

摘要：

针对地面场景下的红外目标检测易受复杂背景干扰、检测精度不高、易发生误检和漏检的问题, 以车辆红外特征为研究对象, 提出了基于全局感知机制的红外目标检测方法。在以Darknet-53为主干网络的基础上, 结合具有全局信息融合的空间金字塔池化机制, 在增大模型感受域的同时增强了模型的全局信息感知力和抗干扰能力; 设计了平滑焦点损失函数, 解决了图像内因目标相互影响而导致的检测精度不高、易出现误检、漏检等问题。实验表明, 在Infrared-VOC320数据集上, 该算法的平均检测精度为80.1%, 较YOLOv3提高了4.4%, 检测速度达到了56.4 FPS, 有效提高了复杂背景下红外目标的检测精度, 实现了对红外目标的实时检测。

关键词: 红外目标检测, YOLOv3, 深度学习, 损失函数, 空间金字塔池化

Abstract:

Aiming at the problems of infrared target detection in ground scenes, such as complex background interference, low detection accuracy, false detection and missed detection, an infrared target detection method based on global perception mechanism is proposed. Based on Darknet-53 as the backbone network, combined with the spatial pyramid pooling mechanism with global information fusion, the global information perception and anti-interference ability of the model are enhanced while increasing the sensing domain of the model. The smooth focus loss function is designed to solve the problems of low detection accuracy, false detection and missed detection caused by the interaction of targets in the image. Experiments show that on the infrared-voc320 data set, the average detection accuracy of the algorithm is 80.1%, which is 4.4% higher than that of YOLOv3, and the detection speed reaches 56.4 FPS, which effectively improves the detection accuracy of infrared targets under complex background and realizes the real-time detection of infrared targets.

Key words: infrared target detection, YOLOv3, deep learning, loss function, spatial pyramid pooling

中图分类号:

TP391.4

赵晓枫, 徐叶斌, 吴飞, 牛家辉, 蔡伟, 张志利. 基于全局感知机制的地面红外目标检测方法[J]. 系统工程与电子技术, 2022, 44(5): 1461-1467.

Xiaofeng ZHAO, Yebin XU, Fei WU, Jiahui NIU, Wei CAI, Zhili ZHANG. Ground infrared target detection method based on global sensing mechanism[J]. Systems Engineering and Electronics, 2022, 44(5): 1461-1467.

图/表 9

图1

图2

图3

图4

表1

表2

图5

表3

图6

参考文献 30

1	苏呈浩. 复杂背景下红外弱小目标检测和跟踪算法研究[D]. 西安: 西安电子科技学, 2019.
	SU C H. Research on infrared dim small target detection and tracking algorithm in complex background[D]. Xi'an: Xidian University, 2019.
2	BAI X Z , ZHOU F G . Analysis of new top-hat transformation and the application for infrared dim small target detection[J]. Pattern Recognition, 2010, 43 (6): 2145- 2156. doi: 10.1016/j.patcog.2009.12.023
3	HAN J H , MA Y , HUANG J , et al. An infrared small target detecting algorithm based on human visual system[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13 (3): 452- 456.
4	CAO Y , LIU R M , YANG J . Infrared small target detection using PPCA[J]. International Journal of Infrared and Millimeter Waves, 2008, 29 (4): 385- 395. doi: 10.1007/s10762-008-9334-0
5	BUZZI S , LOPS M , VENTURINO L . Track-before-detect procedures for early detection of moving target from airborne radars[J]. IEEE Trans.on Aerospace and Electronic Systems, 2005, 41 (3): 937- 954. doi: 10.1109/TAES.2005.1541440
6	OHLMEYER E J, MENON P K. Applications of the particle filter for multi-object tracking and classification[C]//Proc. of the American Control Conference, 2013: 6181-6186.
7	GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2014: 580-587.
8	GIRSHICK R. Fast R-CNN[C]//Proc. of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
9	REN S , HE K , GIRSHICK R , et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. Advances in Neural Information Processing Systems, 2015, 28, 91- 99.
10	HE K, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[C]//Proc. of the IEEE International Conference on Computer Vision, 2017: 2961-2969.
11	CAI Z, VASCONCELOS N. Cascade R-CNN: delving into high quality object detection[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.
12	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proc. of the European Conference on Computer Vision, 2016: 21-37.
13	JEONG J, PARK H, KWAK N. Enhancement of SSD by concatenating feature maps for object detection[EB/OL]. [2021-04-01]. http://arxivorg/abs/1705.09587v1.
14	LIN T Y , GOYAL P , GIRSHICK R , et al. Focal loss for dense object detection[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2020, 42 (2): 318- 327. doi: 10.1109/TPAMI.2018.2858826
15	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 779-788.
16	REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 7263-7271.
17	REDMON J, FARHADI A. Yolov3: an incremental improvement[EB/OL]. [2021-04-01]. http://arxiv.org/abs/1804.02767.
18	苗壮, 张湧, 陈瑞敏, 等. 基于关键点的快速红外目标检测方法[J]. 光学学报, 2020, 40 (23): 2312006.
	MIAO Z , ZHANG Y , CHEN R M , et al. Method for fast detection of infrared targets based on key points[J]. Acta Optica Sinica, 2020, 40 (23): 2312006.
19	吴双忱, 左峥嵘. 基于深度卷积神经网络的红外小目标检测[J]. 红外与毫米波学报, 2019, 38 (3): 371- 380.
	MU S C , ZUO Z R . Small target detection in infared images using deep convolutional neural networks[J]. Journal of Infrared and Millimeter Waves, 2019, 38 (3): 371- 380.
20	刘俊明, 孟卫华. 融合全卷积神经网络和视觉显著性的红外小目标检测[J]. 光子学报, 2020, 49 (7): 46- 56.
	LIU J M , MENG W H . Infrared small target detection based on fully convolutional neural network and visual saliency[J]. Acta Photonica Sinica, 2020, 49 (7): 46- 56.
21	DONG L L , MA D D , QIN G , et al. Infrared target detection in backlighting maritime environment based on visual attention model[J]. Infrared Physics & Technology, 2019, 99, 193- 200.
22	DU J M , LU H Z , HU M F , et al. CNN-based infrared dim small target detection algorithm using target-oriented shallow-deep features and effective small anchor[J]. IET Image Processing, 2021, 15 (1) doi: 10.1049/ipr2.12001
23	梁杰, 李磊, 任君, 等. 基于深度学习的红外图像遮挡干扰检测方法[J]. 兵工学报, 2019, 40 (7): 1401- 1410.
	LIANG J , LI L , REN J , et al. Infrared image occlusion interference detection method based on deep learning[J]. Acta Armamentarii, 2019, 40 (7): 1401- 1410.
24	HU X , WANG X , YANG X , et al. An infrared target intrusion detection method based on feature fusion and enhancement[J]. Defence Technology, 2020, 16 (3): 737- 746. doi: 10.1016/j.dt.2019.10.005
25	ZHAO X F , XU Y B , WU F , et al. IYOLO: multi-scale infrared target detection method based on bidirectional feature fusion[J]. Journal of Physics: Conference Series, 2021, 1873 (1): 012020.
26	TAN M, PANG R, LE Q V. EfficientDet: scalable and efficient object detection[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.
27	ZHAO H S, SHI J P, QI X J, et al. Pyramid scene parsing network[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2881-2890.
28	LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proc. of the IEEE Confe-rence on Computer Vision and Pattern Recognition, 2017.
29	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016.
30	HE K M , ZHANG X Y , REN S Q , et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2015, 37 (9): 1904- 1916.

模型	准确率/ %	帧数/ (Frame·s^－1)	平均精度/ @0.5/%
Faster R-CNN	80.3	7	75.6
SSD300	76.5	44	70.4
YOLOv3	80.28	58.8	75.7
Infrared-YOLO	82.7	56.4	80.1

基准模型	S-FL	全局感知池化金字塔机制	精度@0.5/%		平均精度@0.5/%
基准模型	S-FL	全局感知池化金字塔机制	小汽车	公交车	平均精度@0.5/%
√	-	-	77.8	73.6	75.7
√	√	-	78.1	77.3	77.7
√	-	√	79.0	78.5	78.8
√	√	√	81.4	78.9	80.1

基准模型	空间金字塔机制	全局感知空间金字塔机制	空间复杂度	参数/Mb	平均精度@0.5/%
√	-	-	155.1	58.67	75.7
√	√	-	155.9	59.68	76.5
√	-	√	189.1	46.71	78.8

[1]	韩啸, 陈世文, 陈蒙, 杨锦程. 基于互易点学习的LPI信号开集识别[J]. 系统工程与电子技术, 2022, 44(9): 2752-2759.
[2]	张立民, 谭凯文, 闫文君, 张聿远. 基于多级跳线残差网络的雷达辐射源识别[J]. 系统工程与电子技术, 2022, 44(7): 2148-2156.
[3]	金国栋, 薛远亮, 谭力宁, 许剑锟. 基于孪生神经网络的目标跟踪算法进展研究[J]. 系统工程与电子技术, 2022, 44(6): 1805-1822.
[4]	邹虹, 白陈阳, 何鹏, 崔亚平, 王汝言, 吴大鹏. 基于分布式深度学习的边缘服务放置策略[J]. 系统工程与电子技术, 2022, 44(5): 1728-1737.
[5]	陈冬, 句彦伟. 基于语义分割实现的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2022, 44(4): 1195-1201.
[6]	孙晶明, 虞盛康, 孙俊. 基于深度学习的HRRP识别姿态敏感性分析[J]. 系统工程与电子技术, 2022, 44(3): 802-807.
[7]	姚云翔, 陈莹. 注意力机制下双模态交互融合的目标跟踪网络[J]. 系统工程与电子技术, 2022, 44(2): 410-419.
[8]	高涌荇, 王旭东, 汪玲, 朱岱寅, 郭军, 孟凡旺. 基于RCNN的双极化气象雷达天气信号检测[J]. 系统工程与电子技术, 2022, 44(11): 3380-3387.
[9]	周毅恒, 杨军, 夏赛强, 吕明久. 闪烁现象下旋翼目标微动参数估计方法[J]. 系统工程与电子技术, 2022, 44(1): 54-63.
[10]	付蓉, 黄天耀, 刘一民. 基于深度学习的捷变相参雷达1-Bit块稀疏重构[J]. 系统工程与电子技术, 2022, 44(1): 70-75.
[11]	张聿远, 张立民, 闫文君. 基于互相关特征图和扩张稠密卷积网络的SFBC-OFDM识别方法[J]. 系统工程与电子技术, 2021, 43(9): 2657-2664.
[12]	王彩云, 李阳雨, 李晓飞, 王佳宁, 魏文怡. 基于稀疏性深度学习的航拍图像超分辨重构[J]. 系统工程与电子技术, 2021, 43(8): 2045-2050.
[13]	黄月平, 李小锋, 杨小冈, 齐乃新, 卢瑞涛, 张胜修. 基于相关滤波的视觉目标跟踪算法新进展[J]. 系统工程与电子技术, 2021, 43(8): 2051-2065.
[14]	王彬, 王国宇. 基于改进的深度学习网络的SAR图像瞬时海岸线自动提取算法[J]. 系统工程与电子技术, 2021, 43(8): 2108-2115.
[15]	谢春思, 刘志赢, 桑雨. 基于特征匹配的舰载对陆导弹目标识别模型[J]. 系统工程与电子技术, 2021, 43(8): 2244-2253.

基于全局感知机制的地面红外目标检测方法

Ground infrared target detection method based on global sensing mechanism

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 30

相关文章 15

编辑推荐

Metrics

本文评价