改进YOLOv8n的选通图像目标检测算法

doi:10.3778/j.issn.1002-8331.2406-0292

摘要/Abstract

摘要： 激光选通成像技术在复杂环境下表现出色，但选通图像为灰度图像无法提供颜色信息，并且对比度较低，所以在进行小目标和遮挡目标检测时更加困难。为解决以上问题提出了一种改进YOLOv8n的选通图像目标检测算法。在特征提取的主干网络部分，使用大核卷积C2f-DSF更有效地捕获输入数据的全局信息。添加了多头注意力检测头Detect-SEAM模块，增强了特征提取和目标识别的能力。为了获取不同感受野的上下文信息，增强特征提取能力，使用了SPPF-M模块。采用上采样算子Dysample，减少特征信息的损失，从而提高小目标的检测精度。改进的YOLOv8n算法在选通图像数据集上mAP@0.5提高了2.4个百分点，mAP@0.5：0.95提高了1.8个百分点。为了验证改进的YOLOv8n算法的泛化性，选取KITTI数据集实验，相比于YOLOv8n算法改进YOLOv8n的mAP@0.5提高了4.3个百分点，mAP@0.5：0.95提高了3.5个百分点。

关键词: 选通图像, YOLOv8n, 遮挡目标, 小目标, 大卷积核

Abstract: Laser gated imaging technology performs well in complex environments. But gated images cannot provide color information for grayscale images and have low contrast, so it is more difficult to detect small targets and occluded targets. In order to solve the above problems, an improved YOLOv8n gated image target detection algorithm is proposed. Firstly, in the backbone network part of feature extraction, the large kernel convolution C2f-DSF is used to capture the global information of the input data more effectively. Then, the multi-head attention detection head Detect-SEAM module is added to enhance the ability of feature extraction and object recognition. In addition, in order to obtain the context information of different receptive fields and enhance the feature extraction ability, the SPPF-M module is used. The upsampling operator Dysample is used to reduce the loss of feature information, so as to improve the detection accuracy of small objects. The improved YOLOv8n algorithm improves mAP@0.5 by 2.4 percentage points and mAP@0.5：0.95 by 1.8 percentage points on the strobe image dataset. In order to verify the generalization of the improved YOLOv8n algorithm, the KITTI data set experiment is selected. Compared with the YOLOv8n algorithm, the improved YOLOv8n’s mAP@0.5 is increased by 4.3 percentage points, and mAP@0.5：0.95 is increased by 3.5 percentage points.

Key words: gated imaging, YOLOv8n, occluded targets, small targets, large kernel convolution

田青, 王颖, 张正, 羊强. 改进YOLOv8n的选通图像目标检测算法[J]. 计算机工程与应用, 2025, 61(2): 124-134.

TIAN Qing, WANG Ying, ZHANG Zheng, YANG Qiang. Improved YOLOv8n for Gated Imaging Object Detection Algorithm[J]. Computer Engineering and Applications, 2025, 61(2): 124-134.

参考文献

[1] BENJAMIN G, LUTZMANN P. Review on short-wavelength infrared laser gated-viewing at Fraunhofer IOSB[J]. Optical Engineering, 2017, 56(3): 031203.
[2] 王寿增, 孙峰, 张鑫. 激光照明距离选通成像技术研究进展[J]. 红外与激光工程, 2008, 37(3): 95-99.
WANG S Z, SUN F, ZHANG X. Development of laser illuminating range-gated imaging technique[J]. Infrared and Laser Engineering, 2008, 37(3): 95-99.
[3] 王书宇, 艾磊, 陶声祥, 等. 便携式远距离激光选通成像系统研究[J]. 兵器装备工程学报, 2018, 39(9): 166-170.
WANG S Y, AI L, TAO S X, et al. Research on portable long range laser range gated imaging system[J]. Journal of Ordnance Equipment Engineering, 2018, 39(9): 166-170.
[4] REN W Z, QIN H B, YIN Z J, et al. Design and implementation of portable rang-gated camera for seeing through the fire[C]//Proceedings of the 8th Symposium on Novel Photoelectronic Detection Technology and Applications, 2022: 1597-1601.
[5] GIRSHICK R, DONAHUE J, DARRELL T, et al. Richfeature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014: 580-587.
[6] HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916.
[7] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
[8] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real- time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems, 2015: 91-99.
[9] HE K, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2017: 2980-2988.
[10] 赵珊, 郑爱玲, 刘子路, 等. 通道分离双注意力机制的目标检测算法[J]. 计算机科学与探索, 2023, 17(5): 1112-1125. ZHAO S, ZHENG A L, LIU Z L, et al. Object detection algorithm based on channel separation dual attention mechanism[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(5): 1112-1125.
[11] 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, 2016: 779-788.
[12] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the European Conference on Computer Vision, 2016: 21-37.
[13] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[14] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934, 2020.
[15] JOCHER G, STOKEN A, BOROVEC J, et al. YOLOv5: V3.1-bug fixes and performance improvements[EB/OL]. (2020)[2024-01-12]. doi:10.5281/zenodo.4154370, 2020.
[16] 张艳, 孙晶雪, 孙叶美, 等. 基于分割注意力与线性变换的轻量化目标检测[J]. 浙江大学学报(工学版), 2023, 57(6): 1195-1204.
ZHANG Y, SUN J X, SUN Y M, et al. Lightweight object detection based on split attention and linear transformation[J]. Journal of Zhejiang University(Engineering Science), 2023, 57(6): 1195-1204.
[17] VARGHESE R,SAMBATH M. YOLOv8: a novel object detection algorithm with enhanced performance and robustness[C]//Proceedings of the 2024 International Conference on Data Engineering and Intelligent Computing Systems, 2024: 1-6.
[18] 张正, 白佳华, 田青. 基于单级特征金字塔的图像旋转目标检测[J]. 计算机工程与应用, 2023, 59(15): 235-242.
ZHANG Z, BAI J H, TIAN Q. Image rotating objects detection based on single level feature pyramid[J]. Computer Engineering and Applications, 2023, 59(15): 235-242.
[19] 卫策, 吕进, 曲晨阳. 改进YOLOv5s的复杂交通场景下目标检测算法[J]. 电子测量技术,2024, 47(2): 121-130.
WEI C, LV J, QU C Y. Improved object detection algorithm for complex traffic scenes in YOLOv5s[J]. Electronic Measurement Technology, 2024, 47(2): 121-130.
[20] 刘辉, 刘鑫满, 刘大东. 面向复杂道路目标检测的YOLOv5算法优化研究[J]. 计算机工程与应用, 2023, 59(18): 207-217.
LIU H, LIU X M, LIU D D. Research on optimization of YOLOv5 detection algorithm for object in complex road[J]. Computer Engineering and Applications, 2023, 59(18): 207-217.
[21] 袁磊, 唐海, 陈彦蓉, 等. 改进YOLOv5的复杂环境道路目标检测方法[J]. 计算机工程与应用, 2023, 59(16): 212-222.
YUAN L, TANG H, CHEN Y R, et al. Improved YOLOv5 for road target detection in complex environments[J]. Computer Engineering and Applications, 2023, 59(16): 212-222.
[22] 胡淼, 姜麟, 陶友凤, 等. 改进YOLOv7的自动驾驶目标检测算法[J]. 计算机工程与应用, 2024, 60(11): 165-172.
HU M, JIANG L, TAO Y F, et al. Improved YOLOv7 automatic driving object detection algorithm[J]. Computer Engineering and Applications, 2024, 60(11): 165-172.
[23] DING X H, ZHANG Y Y, GE Y X, et al. UniRepLKNet: a universal perception large-kernel ConvNet for audio video point cloud time-series and image recognition[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024: 5513-5524.
[24] YU Z P, HUANG H B, CHEN W J, et al. YOLO-FaceV2: a scale and occlusion aware face detector[J]. Pattern Recognition, 2024, 155: 110714.
[25] 肖进胜, 赵陶, 周剑, 等. 基于上下文增强和特征提纯的小目标检测网络[J]. 计算机研究与发展, 2023, 60(2): 465-474.
XIAO J S, ZHAO T, ZHOU J, et al. Context augmentation and feature refinement network for tiny object detection[J]. Journal of Computer Research and Development, 2023, 60(2): 465-474.
[26] LIU W Z, LU H, FU H T, et al. Learning to upsample by learning to sample[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023: 6027-6037.
[27] GEIGER A, LENZ P, STILLER C, et al. Vision meets robotics: the KITTI dataset[J]. The International Journal of Robotics Research, 2013, 32(11): 1231-1237.