基于Faster R-CNN的航母舰面多尺度目标检测算法

doi:10.12305/j.issn.1001-506X.2022.01.06

摘要/Abstract

摘要：

针对航母舰面复杂的多尺度目标检测环境, 且现有算法对牵引车、人员等小目标检测性能不佳的问题, 提出一种改进快速区域卷积神经网络(faster region convolutional neural netuorks, Faster R-CNN)的舰面多尺度目标检测算法。基于多尺度特征层提取了不同尺度的区域建议网络, 提高了算法对不同尺度目标尤其是对小目标的检测性能。基于K-means聚类算法生成了适合于舰面目标数据集的先验框尺寸, 进一步提升了算法的性能。实验表明, 所提算法有效地提升了不同尺度目标的检测性能，尤其是对小目标的检测效果, 并对所提算法进行了消融实验, 最后与不同算法的性能进行了对比, 所提算法检测准确率取得了最优水平。

关键词: 目标检测, 多尺度特征层, K-means聚类, 航母舰面

Abstract:

Aiming at the complex multi-scale object detection environment on the aircraft carrier surface, and the poor performance of existing algorithms for small objects such as tractors and personnel, an improved faster region convolutional neural netuorks(Faster R-CNN) aircraft carrier surface multi-scale object detection algorithm is proposed. Based on the multi-scale feature layer, the region proposal network of different scales is extracted, which improves the detection performance of the algorithm for objects of different scales, especially small objects. Based on the K-means clustering algorithm, a prior box suitable for the aircraft carrier surface object dataset is generated, which further improves the performance of the algorithm. Experiments show that the proposed algorithm effectively improves the detection performance for different scales of objects, especially the detection effect of small objects, and conducts ablation experiments on the improved algorithm. Finally, the performance of different algorithms is compared, which shows that the detection accuracy of the proposed algorithm achieveds the optimal level.

Key words: object detection, multi-scale feature layer, K-means clustering, aircraft carrier surface

中图分类号:

TP391.41

范加利, 田少兵, 黄葵, 朱兴动. 基于Faster R-CNN的航母舰面多尺度目标检测算法[J]. 系统工程与电子技术, 2022, 44(1): 40-46.

Jiali FAN, Shaobing TIAN, Kui HUANG, Xingdong ZHU. Multi-scale object detection algorithm for aircraft carrier surface based on Faster R-CNN[J]. Systems Engineering and Electronics, 2022, 44(1): 40-46.

图/表 10

图1

图2

图3

图4

图5

表1

表2

图6

表3

表4

参考文献 30

1	苏建华, 薛栋娥, 刘传凯, 等. HOG内嵌模板匹配的车门夹人检测算法[J]. 北京交通大学学报, 2019, 43 (2): 64- 71. doi: 10.11860/j.issn.1673-0291.20180079
	SU J H , XUE D E , LIU C K , et al. An algorithm for detecting train door persons based on HOG inline template matching[J]. Journal of Beijing Jiaotong University, 2019, 43 (2): 64- 71. doi: 10.11860/j.issn.1673-0291.20180079
2	郭小兵. 基于贝叶斯网络的目标综合识别方法研究[D]. 长沙: 国防科技大学, 2004.
	GUO X B. A research on the algorithms of target identification fusion with Bayesian networks[D]. Changsha: National University of Defense Technology, 2004.
3	黄洁, 张海. 利用支持向量机的飞机目标检测[J]. 电光与控制, 2008, 15 (9): 6- 9. doi: 10.3969/j.issn.1671-637X.2008.09.002
	HUANG J , ZHANG H . Plane detection based on support vector machine and information fusion[J]. Electronics Optics and Control, 2008, 15 (9): 6- 9. doi: 10.3969/j.issn.1671-637X.2008.09.002
4	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. doi: 10.1109/TPAMI.2015.2389824
5	GIRSHICK R. Fast R-CNN[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 1440-1448.
6	REN S , HE K , GIRSHICK R , et al. Faster R-CNN: towards realtime object detection with region proposal network[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
7	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.
8	REDMON J, FARHADI A. YOLO 9000 better, faster, stronger[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 6517-6525.
9	REDMON J, FARHADI A. YOLO v3 an incremental improvement[EB/OL]. [2018-04-08]. https//arxiv.org/abs/1804.02767.
10	LIU W, ANGUELOY D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proc. of the European Conference on Computer Vision, 2016: 21-37.
11	李晓光, 付陈平, 李晓莉, 等. 面向多尺度目标检测的改进Faster R-CNN算法[J]. 计算机辅助设计与图形学学报, 2019, 31 (7): 1195- 1101.
	LI X G , FU C P , LI X L , et al. Improved Faster R-CNN for multi-scale object detection[J]. Journal of Computer-Aided Design and Computer Graphics, 2019, 31 (7): 1195- 1101.
12	孙皓泽, 常天庆, 王全东, 等. 一种基于分层多尺度卷积特征提取的坦克装甲目标图像检测方法[J]. 兵工学报, 2017, 38 (9): 1681- 1691. doi: 10.3969/j.issn.1000-1093.2017.09.003
	SUN H Z , CHANG T Q , WANG Q D , et al. Image detection method for tank and armored targets based on hierarchical multi-scale convolution feature extraction[J]. Acta Armamentarii, 2017, 38 (9): 1681- 1691. doi: 10.3969/j.issn.1000-1093.2017.09.003
13	黄凤荣, 李杨, 郭兰申, 等. 基于Faster R-CNN的零件表面缺陷检测方法[J]. 计算机辅助设计与图形学学报, 2020, 32 (6): 883- 893.
	HUANG F R , LI Y , GUO L S , et al. Method for detection surface defects of engine parts based on faster R-CNN[J]. Journal of Computer-Aided Design and Computer Graphics, 2020, 32 (6): 883- 893.
14	曹旭, 邹焕新, 成飞, 等. 基于RHTC网络的飞机目标检测与精细识别[J]. 系统工程与电子技术, 2021, 43 (12): 3439- 3451.
	CAO X , ZOU H X , CHENG F , et al. Aircraft target detection and fine-grained recognition based on RHTC network[J]. Systems Engineering and Electronics, 2021, 43 (12): 3439- 3451.
15	孙嘉赤, 邹焕新, 邓志鹏, 等. 基于级联卷积神经网络的港口多方向舰船检测与分类[J]. 系统工程与电子技术, 2020, 42 (9): 1903- 1910.
	SUN J C , ZOU H X , DENG Z P , et al. Oriented inshore ship detection and classification based on cascade RCNN[J]. Systems Engineering and Electronics, 2020, 42 (9): 1903- 1910.
16	LI Y , FU K , SUN H , et al. An aircraft detection framework based on reinforcement learning and convolutional neural networks inremote sensing images[J]. Remote Sensing, 2018, 10 (2): 243. doi: 10.3390/rs10020243
17	CAI Z W , VASCONCELOS N . Cascade R-CNN: high quality target detection and instance segmentation[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2021, 43 (5): 1483- 1498. doi: 10.1109/TPAMI.2019.2956516
18	NAJIBI M, RASTEGARI M, DAVIS L S. G-CNN: an iterative grid based object detector[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 2369-2377.
19	SHRIVASTAVA A, GUPTA A, GIRSHICK R. Training region-based object detectors with online hard example mining[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 761-769.
20	朱兴动, 田少兵, 黄葵, 等. 基于深度卷积神经网络的舰载机目标检测[J]. 计算机应用, 2020, 40 (5): 1529- 1533.
	ZHU X D , TIAN S B , HUANG K , et al. Target detection of carrier-based aircraft based on deep convolutional neural network[J]. Journal of Computer Applications, 2020, 40 (5): 1529- 1533.
21	YANG F, CHOI W, LIN Y Q. Exploit all the layers: fast and accurate CNN object detector with scale dependent pooling and cascaded rejection classifers[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 2129-2137.
22	KONG T, YAO A B, CHEN Y R. HyperNet: towards accurate region proposal generation and joint object detection[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 845-853.
23	CAO C Q , WANG B . An improved faster R-CNN for small object detection[J]. IEEE Access, 2019, 7, 106838- 106846. doi: 10.1109/ACCESS.2019.2932731
24	GIRSHICK R . Region-based convolutional networks for accurate object detection and segmentation[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2015, 38 (1): 142- 158.
25	REN S Q , HE K M , GIRSHICK R , et al. Faster R-CNN: towards realtime object detection with region proposal networks[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
26	DAI J F, LI Y, HE K M. R-FCN: object detection via region-based fully convolutional networks[C]//Proc. of the Advances in Neural Information Processing Systems, 2016: 379-387.
27	周龙, 韦素媛. 基于深度学习的复杂背景雷达图像多目标检测[J]. 系统工程与电子技术, 2019, 41 (6): 1258- 1264.
	ZHOU L , WEI S Y . Multi-objective detection of complex background radar image based on deep learning[J]. Systems Engineering and Electronics, 2019, 41 (6): 1258- 1264.
28	王全东, 常天庆. 基于深度学习算法的坦克装甲目标自动检测与跟踪系统[J]. 系统工程与电子技术, 2018, 40 (9): 2143- 2156.
	WANG Q D , CHANG T Q . Automatic detection and tracking system of tank armored targets based on deep learning algorithm[J]. Systems Engineering and Electronics, 2018, 40 (9): 2143- 2156.
29	李广帅, 苏娟, 李义红. 基于改进Faster R-CNN的SAR图像飞机检测算法[J]. 北京航空航天大学学报, 2021, 47 (1): 159- 168.
	LI G S , SU J , LI Y H . An aircraft detection algorithm in SAR image based on improved Faster R-CNN[J]. Journal of Beijing University of Aeronautics and Astronautics, 2021, 47 (1): 159- 168.
30	张玉燕, 李永保. 基于Faster R-卷积神经网络的金属点阵结构缺陷识别方法[J]. 兵工学报, 2019, 40 (11): 2329- 2335. doi: 10.3969/j.issn.1000-1093.2019.11.018
	ZHANG Y Y , LI Y B . Internal detection of metal three-dimensional multi-layer lattice structure based on Faster R-CNN[J]. Acta Armamentarii, 2019, 40 (11): 2329- 2335. doi: 10.3969/j.issn.1000-1093.2019.11.018

舰载机	直升机1	直升机2	牵引车	人员
3 236	3 125	3 058	3 241	3 310

算法	AP/%					mAP/%	Fps(frame·s^-1)
算法	舰载机	直升机1	直升机2	牵引车	人员	mAP/%	Fps(frame·s^-1)
改进前	95.6	91.7	90.3	85.6	81.4	88.97	9
改进后	97.3	94.8	94.6	92.1	88.5	93.46	8

方案	AP					mAP
方案	舰载机	直升机1	直升机2	牵引车	人员	mAP
a	95.6	91.7	90.3	85.6	81.4	88.97
b	96.4	92.9	93.1	90.8	87.9	92.22
c	97.0	93.6	93.0	90.3	87.7	92.32
d	97.3	94.8	94.6	92.1	88.5	93.46

算法	mAP/%	Fps/(frame·s^-1)
YOLO v3	83.64	22
SSD	81.90	20
本文	93.46	8

[1]	宋爽, 张悦, 张琳娜, 岑翼刚, 李浥东. 基于深度学习的轻量化目标检测算法[J]. 系统工程与电子技术, 2022, 44(9): 2716-2725.
[2]	肖宇, 邓正宏, 张展. 基于双阶段互信息准则的多目标检测波形设计[J]. 系统工程与电子技术, 2022, 44(9): 2736-2742.
[3]	刘祥, 黄天耀, 刘一民. 频率捷变雷达的扩展目标检测[J]. 系统工程与电子技术, 2022, 44(6): 1833-1838.
[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.
[5]	魏文晓, 刘洁瑜, 沈强, 李成. 基于人眼视点图的特征融合小目标检测算法[J]. 系统工程与电子技术, 2022, 44(4): 1120-1127.
[6]	李洪瑶, 李小强, 韩心中, 谢学立, 席建祥. 基于决策融合的多无人机协同目标检测识别算法[J]. 系统工程与电子技术, 2022, 44(3): 746-754.
[7]	潘超凡, 李润生, 许岩, 胡庆, 牛朝阳, 刘伟. 基于感知向量的光学遥感图像舰船检测[J]. 系统工程与电子技术, 2022, 44(12): 3631-3640.
[8]	贾晓雅, 汪洪桥, 杨亚聃, 崔忠马, 熊斌. 基于YOLO框架的无锚框SAR图像舰船目标检测[J]. 系统工程与电子技术, 2022, 44(12): 3703-3709.
[9]	薛春岭, 曹菲, 孙庆, 秦建强, 冯晓伟. 基于多特征信息融合的海面微弱目标检测[J]. 系统工程与电子技术, 2022, 44(11): 3338-3345.
[10]	李永刚, 朱卫纲, 黄琼男, 李云涛, 何永华. 复杂背景下SAR图像近岸舰船目标检测[J]. 系统工程与电子技术, 2022, 44(10): 3096-3103.
[11]	龚树凤, 龙伟军, 贲德, 潘明海. 组网雷达自适应模糊CFAR检测融合算法[J]. 系统工程与电子技术, 2022, 44(1): 100-107.
[12]	杨威, 刘永祥, 付耀文, 黎湘. 基于连续信任函数理论的鲁棒雷达目标检测方法[J]. 系统工程与电子技术, 2021, 43(9): 2463-2469.
[13]	吕跃, 杨爱武, 李战武, 奚之飞. 空战决策知识构建方法研究[J]. 系统工程与电子技术, 2021, 43(7): 1866-1874.
[14]	张佳琦, 陶海红, 张修社. 量测点迹空间聚类的多传感器多帧检测算法[J]. 系统工程与电子技术, 2021, 43(6): 1533-1540.
[15]	时艳玲, 刘子鹏, 张学良, 顾为亮. 基于EMD能量占比的海面漂浮小目标特征检测[J]. 系统工程与电子技术, 2021, 43(2): 300-310.