| Citation: |
WANG Kai, LOU Shuli, WANG Yan. Small object detection algorithm based on improved YOLOv3[J]. Journal of Applied Optics, 2024, 45(4): 732-740. DOI: 10.5768/JAO202445.0402002
|
In order to effectively solve the problem that small objects are difficult to recall and easy to miss detection, an improved YOLOv3 algorithm based on feature fusion and feature enhancement was proposed. To enhance the generalization performance of the model, the Mosaic and Mixup methods were combined for data enhancement during training. Firstly, in order to improve the low recall rate of small object detection, the original feature fusion network was extended to the shallower layer, and the bottom-up feature pyramid was added, so that the details and positioning information of the shallow feature layer could be transmitted to the deep layer. Secondly, a feature enhancement module was proposed to enlarge the receptive field, so that the shallow feature layer could obtain the rich deep semantic information and optimize the expression ability of the feature layer. Finally, the GIoU was used as a regression loss function to reduce the missing rate and achieve more accurate regression. Simulation experiments on Pascal VOC2007 and VOC2012 show that the improved algorithm can improve the mean average precision (mAP) value by 4.4% on the premise of ensuring the detection speed. Experimental results fully prove that the proposed algorithm can effectively improve the performance of small object detection.
| [1] |
耿创, 宋品德, 曹立佳. YOLO 算法在目标检测中的研究进展[J]. 兵器装备工程学报,2022, 43(9): 162-173.
GENG Chuang, SONG Pinde, CAO Lijia. Research progress of YOLO algorithm in object detection [J]. Journal of Ordnance Equipment Engineering,2022, 43(9): 162-173.
|
| [2] |
邵延华, 张铎, 楚红雨, 等. 基于深度学习的YOLO目标检测综述[J]. 电子与信息学报, 2022, 44(10): 3697-3708. doi: 10.11999/JEIT210790
SHAO Yanhua, ZHANG Duo, CHU Hongyu, et al. A review of YOLO object detection based on deep learning[J]. Journal of Electronics & Information Technology, 2022, 44(10): 3697-3708. doi: 10.11999/JEIT210790
|
| [3] |
杜紫薇, 周恒, 李承阳, 等. 面向深度卷积神经网络的小目标检测算法综述[J]. 计算机科学, 2022, 49(12): 205-218. doi: 10.11896/jsjkx.220500260
DU Ziwei, ZHOU Heng, LI Chengyang, et al. A review of small object detection algorithms for deep convolutional neural networks[J]. Computer Science, 2022, 49(12): 205-218. doi: 10.11896/jsjkx.220500260
|
| [4] |
杨茹锦, 商新娜, 李文法. 基于深度学习的小目标检测方法综述[C]//2022年第二十六届网络新技术与应用年会论文集. [S. l. ]: 中国计算机用户协会网络应用分会, 2022: 5.
YANG Rujin, SHANG Xinna, LI Wenfa. A review of small object detection methods based on deep learning [C]//Proceedings of the 26th Annual Conference on New Network Technologies and Applications, 2022.[S. l. ]: Network Computer Users Association, 2022: 5.
|
| [5] |
GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2014: 580-587.
|
| [6] |
GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision. New York: IEEE, 2015: 1440-1448.
|
| [7] |
REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(6): 1137-1149.
|
| [8] |
LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single Shot Multibox Detector[C]//Proceedings of European Conference on Computer Vision. [S.l.]:[s.n.],2016: 21-37.
|
| [9] |
REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR). New York: IEEE, 2016: 779-788.
|
| [10] |
REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR). New York: IEEE, 2017: 7263-7271.
|
| [11] |
董刚, 谢维成, 黄小龙, 等. 深度学习小目标检测算法综述[J]. 计算机工程与应用, 2023, 59(11): 16-27. doi: 10.3778/j.issn.1002-8331.2211-0377
DONG Gang, XIE Weicheng, HUANG Xiaolong, et al. A review of small object detection algorithms in deep learning[J]. Computer Engineering and Applications, 2023, 59(11): 16-27. doi: 10.3778/j.issn.1002-8331.2211-0377
|
| [12] |
LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2017: 2117-2125.
|
| [13] |
REDMON J, FARHADI A. YOLOV3: an incremental improvement[EB/OL]. [2020-02-11]. https://pjreddie.com/media/files/papers/YOLOv3.pdf
|
| [14] |
张丽莹, 庞春江, 王新颖, 等. 基于改进YOLOv3的多尺度目标检测算法[J]. 计算机应用, 2022, 42(8): 2423-2431.
ZHANG Liying, PANG Chunjiang, WANG Xinying, et al. Multi-scale object detection algorithm based on improved YOLOv3 [J]. Journal of Computer Applications, 2022, 42(8): 2423-2431.
|
| [15] |
葛录录, 陈厚儒, 杨哲铭,等. 基于特征增强的改进型YOLOv3目标检测算法[C]// 第十五届全国信号和智能信息处理与应用学术会议论文集. [S. l. ]: 中国高科技产业化研究会智能信息处理产业化分会, 2022: 8.
GE Lulu, CHEN Houru, YANG Zheming, et al. An improved YOLOv3 object detection algorithm based on feature enhancement [C]// Proceedings of the 15th National Conference on Signal and Intelligent Information Processing and Application. [S. l. ]:Intelligent Information Processing Industrializaiton Branch of China High-tech Industrialization Society, 2022: 8.
|
| [16] |
陈德海, 孙仕儒, 王昱朝等. 改进SSD算法的小目标检测研究[J]. 传感器与微系统, 2023, 42(3): 65-68.
CHEN Dehai, SUN Shiru, WANG Yuchao et al. Research on small object detection based on improved SSD algorithm[J]. Transducer and Microsystem Technologies, 2023, 42(3): 65-68.
|
| [17] |
吴珊, 周凤. 基于改进SSD算法的小目标检测[J]. 计算机工程, 2023, 49(7): 179-188.
WU Shan, ZHOU Feng. Small object detection based on improved SSD algorithm[J]. Computer Engineering, 2023, 49(7): 179-188.
|
| [18] |
BOCHKOVSKIY A, WANG C Y, LIAO H Y. Yolov4: optimal speed and accuracy of object detection [EB/OL]. [2023-05-20]. https://www.cnblogs.com/hejunlin1992/p/13384782.html.
|
| [19] |
ZHANG H Y, CISSE M, DAUPHIN Y N, et al. Mixup: beyond empirical risk minimization [EB/OL]. [2023-05-20]. https://arxiv.org/abs/1710.09412.
|
| [20] |
REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union: a metric and a loss for bounding box regression[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2019: 658-666.
|
| [21] |
蔡伟, 徐佩伟, 杨志勇, 等. 复杂背景下红外图像弱小目标检测[J]. 应用光学, 2021, 42(4): 643-650. doi: 10.5768/JAO202142.0402002
CAI Wei, XU Peiwei, YANG Zhiyong, et al. Dim and small target detection in infrared image under complex background[J]. Journal of Applied Optics, 2021, 42(4): 643-650. doi: 10.5768/JAO202142.0402002
|
| [22] |
LI C, LI L, JIANG H, et al. YOLOv6: a single-stage object detection framework for industrial applications [EB/OL]. [2023-05-20]. http://arxiv.org/pdf/2209.02976v1.
|
| [23] |
WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2020: 390-391.
|
| [24] |
YU J, JIANG Y, WANG Z, et al. Unitbox: An advanced object detection network[C]// Proceedings of the 24th ACM international conference on Multimedia. [S. l. ]: [s. n. ], 2016: 516-520.
|
| [25] |
EVERINGHAM M, GOOL L VAN, WILLIAMS C K I, et al. The PASCAL visual object classes challenge[J]. International Journal of Computer Vision, 2010, 88(2): 303-338. doi: 10.1007/s11263-009-0275-4
|
| [1] | HE Wenfan, XU Junqi, LI Yang. Effects of different preparation parameters on optical properties of porous TiO2 thin films[J]. Journal of Applied Optics, 2024, 45(6): 1277-1283. DOI: 10.5768/JAO202445.0605002 |
| [2] | ZHANG Yaoyuan, WANG Rui, JIANG Ruitao, DU Kunyang, LI Yuanyang. Performance evaluation method of silicon-based optical phased array[J]. Journal of Applied Optics, 2021, 42(2): 242-246. DOI: 10.5768/JAO202142.0201006 |
| [3] | LI Qiantao, XIONG Changxin, YANG Changcheng. Research on chemical strengthening technology for K9 optical glass[J]. Journal of Applied Optics, 2021, 42(1): 188-193. DOI: 10.5768/JAO202142.0105002 |
| [4] | SHI Yunyun, XU Junqi, SU Junhong. Optical, electrical and mechanical properties and applications of multicomponent composite films[J]. Journal of Applied Optics, 2020, 41(2): 405-420. DOI: 10.5768/JAO202041.0205005 |
| [5] | Yi Siqi, Ding Haolin, Long Zhiqiang. Optimal design of supersonic gaseous film cooling optical performance[J]. Journal of Applied Optics, 2017, 38(4): 549-554. DOI: 10.5768/JAO201738.0401006 |
| [6] | PAN Yong-qiang, BAI Tao, TIAN Yu-jun. Influence of UV irradiation on optical property of TiO2 thin film[J]. Journal of Applied Optics, 2013, 34(1): 128-132. |
| [7] | LIAO Zhi-bo, JIAO Wen-chun-FU Rui-min, . Thermal optics property simulation of optical window for remote sensing[J]. Journal of Applied Optics, 2011, 32(3): 407-410. |
| [8] | XU Liang, LI Chuang, FAN Xue-wu. Deformation of optical window and its influence on collimator’s optical performance[J]. Journal of Applied Optics, 2010, 31(6): 914-917. |
| [9] | ZHU Hai-feng, ZHANG Ya-ping, LI Shu-guang, HUANG Liu-bin, LIU Yan-min. Aspherical IOLs design and influence of pupil on optical performance of AIOL[J]. Journal of Applied Optics, 2010, 31(4): 557-561. |
| [10] | PIAO Yong, LIANG Hong jun, GAO Peng, DING Wan-yu, LU Wen-qi, MA Tengcai, XU Jun. The influence of deposition parameters on chemical structure and optical properties of silicon carbonitride film[J]. Journal of Applied Optics, 2006, 27(4): 274-280. |
| 1. |
黄富瑜，李刚，史云胜，张晓良，邹昌帆，禹烨. 多光谱多光轴平行性检测方案设计与误差分析. 光电工程. 2019(02): 12-20 .
| |
| 2. |
杨雪，陈文红，张玺，初华，钱琨，张珊，方洁，孙宁，张勇，郭延龙，欧阳艳蓉. 宽光谱光电系统多光轴平行性工程化测试方法研究. 激光与红外. 2019(08): 978-982 .
| |
| 3. |
张磊，邱伟，张凯. 基于双五棱镜组件的大间距光轴平行性检测方法. 红外与激光工程. 2018(07): 176-180 .
| |
| 4. |
应家驹，陈玉丹，武东生，刘杰. 双目光轴平行性检校仪检测精度分析. 激光与红外. 2018(06): 750-755 .
| |
| 5. |
张磊，崔启胤，张凯. 适应大温差变化的多光轴一致性测试系统. 长春理工大学学报(自然科学版). 2017(04): 10-13 .
|
WeChat
You are the 2900341th visitor, Welcome!
Address: No.9, west section of No.3 electronic road, Xi'an Post Code: 710065 Tel: 029-88288172
Copyright © Editorial Department of Journal of Applied Optics
陕公网安备 61011302001501号 
DownLoad: