复杂场景下基于增强YOLOv3的舰面多目标检测

doi:10.3778/j.issn.1002-8331.2012-0411

摘要/Abstract

摘要： 针对舰面场景复杂、目标相互遮挡导致检测率较低等问题，在YOLOv3算法基础上提出了适用于舰面目标检测的增强YOLOv3算法。在输入网络中加入融合的数据增强策略对图像进行色域变换、裁剪、遮挡等操作，设计了多种类图片选取、变换及组合方式来丰富样本信息；针对舰面目标尺寸的特点，利用K-means算法重新设计与检测目标相匹配的先验锚框并分配至对应的预测尺度，以加速模型收敛；在输出网络中通过线性函数对Soft-NMS算法的高斯软阈值函数参数设定进行了改进，以适应不同密集度下的抑制需要，提高网络检测能力。通过将增强的目标检测算法在目标数据集上进行实验对比，其结果显示，在5类舰面目标识别的精确率和召回率分别提高了1.4%和10.3%，平均准确率值（mAP）达到了95.24%，检测速度达到21.5?frame/s，有效解决了复杂场景下的舰面多目标检测问题。

关键词: YOLOv3算法, K-means, 非极大抑制, 密集目标检测, 数据增强

Abstract: Aiming at the low detection rate caused by complex shipboard scenes and mutual occlusion of targets, an enhanced YOLOv3 algorithm suitable for shipboard target detection is proposed based on the YOLOv3 algorithm. The integrated data augmentation strategy is added to the input network to carry out gamut transformation, clipping, shielding and other operations on the image, and then a variety of image selection, transformation and combination methods are designed to enrich the sample information. According to the characteristics of the target size on ship surface, K-means algorithm is used to redesign the prior box matching the detection target and allocate it to the corresponding prediction scale. In the output network, the parameter setting of Gauss soft threshold function of Soft-NMS algorithm is improved by linear function to meet the need of suppression under different densities. Through enhanced detection algorithm in the target data set on experimental comparison, the results show that five types of ship surface target are identified, and precision rate and recall rate are increased by 1.4% and 10.3% respectively, and the average accuracy value（mAP） reaches 95.24%, and then detection speed is 21.5 frame/s, which effectively solves the complicated situations of ship surface much target detection problem.

Key words: YOLOv3 algorithm, K-means, non-maximum suppression（NMS）, dense target detection, data augmentation

朱兴动, 汪丁, 范加利, 王正, 黄葵. 复杂场景下基于增强YOLOv3的舰面多目标检测[J]. 计算机工程与应用, 2022, 58(13): 177-184.

ZHU Xingdong, WANG Ding, FAN Jiali, WANG Zheng, HUANG Kui. Multitarget Detection Based on Enhanced YOLOv3 in Complex Scenarios[J]. Computer Engineering and Applications, 2022, 58(13): 177-184.

参考文献

[1] 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 Computer Applications，2020，40（5）：1529-1533.
[2] 刘广，颜世伟，李海旭，等.国外航母航空保障技术发展现状[J].航空科学技术，2020，31（2）：1-11.
LIU G，YAN S W，LI H X，et al.Aviation support technology development for foreign aircraft carrier[J].Aeronautical Science and Technology，202，31（2）：1-11.
[3] 寇大磊，权冀川，张仲伟.基于深度学习的目标检测框架进展研究[J].计算机工程与应用，2019，55（11）：25-34.
KOU D L，QUAN J C，ZHANG Z W.Research on progress of object detection framework based on deep learning[J].Computer Engineering and Applications，2019，55（11）：25-34.
[4] REDMON J，FARHADI A.YOLOv3：An incremental Improvement[J].arXiv：1804.02767，2018.
[5] ZHAO L，LI S.Object detection algorithm based on improved YOLOv3[J].Electronics，2020，9（3）：537.
[6] LUO Z，YU H，ZHANG Y.Pine cone detection using boundary equilibrium generative adversarial networks and improved YOLOv3 model[J].Sensors，2020，20：4430.
[7] 王兵，李文璟，唐欢.改进YOLO v3算法及其在安全帽检测中的应用[J].计算机工程与应用，2020，56（9）：33-40.
WANG B，LI W J，TANG H.Improved YOLO v3 algorithm and its application in helmet detection[J].Computer Engineering and Applications，2020，56（9）：33-40.
[8] LI Y，GUO J，GUO X，et al.A novel target detection method of the unmanned surface vehicle under all-weather conditions with an improved YOLOV3[J].Sensors，2020，20：4885.
[9] BUSLAEV A， PARINOV A， KHVEDCHENYA E，et al.Albumentations：Fast and flexible image augmentations[J].arXiv：1809.06839，2018.
[10] XIALI L，MANJUN T，SHIHAN K，et al.A modified YOLOv3 detection method for vision-based water surface garbage capture robot[J].International Journal of Advanced Robotic Systems，2020，17（3）：1-11.
[11] JAIN A K.Data clustering：50 years beyond K-means[J].Pattern Recognition Letters，2010，31（8）：651-666.
[12] ZHAO L，LI S.Object detection algorithm based on improved YOLOv3[J].Electronics，2020，9（3）：537.
[13] LIU J，ZHANG D.Research on vehicle object detection algorithm based on improved YOLOv3 algorithm[J].Journal of Physics（Conference Series），2020，1575：12150.
[14] BAI J，ZHU J，ZHAO R，et al.Area-based non-maximum suppression algorithm for multi-object fault detection[J].Frontiers of Optoelectronics，2020（4）：425-432.
[15] NEUBECK A，GOOL L.Efficient non-maximum suppression[C]//Proceedings of International Conference on Pattern Recognition，2006.
[16] BODLA N，SINGH B，CHELLAPPA R，et al.Improving object detection with one line of code[J].arXiv：1704.
04503，2017.
[17] LIU S，HUANG D，WANG Y.Adaptive NMS：Refining pedestrian detection in a crowd[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2020.
[18] 赵永强，饶元，董世鹏，等.深度学习目标检测方法综述[J].中国图象图形学报，2020，25（4）：629-654.
ZHAO Y Q，RAO Y，DONG S P，et al.Survey on deep learning object detection[J].Journal of Image and Graphics，2020，25（4）：629-654.