改进YOLOv8的轻量级军事飞机检测算法

doi:10.3778/j.issn.1002-8331.2404-0058

摘要/Abstract

摘要： 遥感图像军事飞机检测在侦察预警、情报分析等领域具有重要意义。为使军事飞机检测模型能在算力受限的设备上高效运行，从网络设计与模型压缩两个方面对YOLOv8n进行轻量化改进。在网络设计方面，使用FAS_C2f替换原始主干网络中的C2f模块，减少计算冗余并加快网络特征提取的速度；根据军事飞机目标的尺度特征对网络结构进行优化，缓解因过度下采样导致的小目标信息丢失问题；使用Inner-SIoU作为新的定位回归损失函数，提升对小目标样本的学习能力并加快回归边界框的收敛。在模型压缩方面，使用基于LAMP分数的通道剪枝对重设计后的模型进行压缩，进一步减少参数和模型大小；并利用通道级知识蒸馏（channel-wise knowledge distillation，CWD）将模型精度恢复到接近剪枝前的水平。实验结果表明，在公开军用飞机数据集MAR20上，轻量化后的模型mAP为97.2%，体积仅有0.7 MB，较原始模型缩小了88.3%，FPS提高了14帧/s，满足军事飞机目标检测的实时性要求。

关键词: 目标检测, 军事飞机, YOLOv8, 模型剪枝, 知识蒸馏

Abstract: Military aircraft detection with remote sensing images is of great significance in the fields of reconnaissance and early warning, intelligence analysis and so on. In order to make the military aircraft inspection model run efficiently on the equipment with limited computing power, the lightweight improvement of YOLOv8n is carried out from two aspects: network design and model compression. In the aspect of network design, firstly, FAS_C2f is used to replace the C2f module in the original backbone network, which reduces the computational redundancy and speeds up the network feature extraction. Secondly, the network structure is optimized according to the scale characteristics of military aircraft targets to alleviate the problem of small target information loss caused by excessive downsampling. Thirdly, Inner-SIoU is used as a new localization regression loss function to improve the learning ability of small target samples and accelerate the convergence of regression bounding box. In terms of model compression, channel pruning based on LAMP fraction is used to compress the redesigned model to further reduce parameters and model size. With channel-wise knowledge distillation (CWD), the accuracy of the model is restored to the level close to that before pruning. The experimental results show that on the open military aircraft data set MAR20, the mAP of the lightweight model is 97.2%, the volume is only 0.7 MB, which is 88.3% smaller than the original model, and the FPS is increased by 14 frames per second, which meets the real-time requirements of military aircraft target detection.

Key words: object detection, military aircraft, YOLOv8, model pruning, knowledge distillation

刘丽, 张硕, 白宇昂, 李宇健, 张初夏. 改进YOLOv8的轻量级军事飞机检测算法[J]. 计算机工程与应用, 2024, 60(18): 114-125.

LIU Li, ZHANG Shuo, BAI Yu’ang, LI Yujian, ZHANG Chuxia. Improved Lightweight Military Aircraft Detection Algorithm of YOLOv8[J]. Computer Engineering and Applications, 2024, 60(18): 114-125.

参考文献

[1] 禹文奇, 程塨, 王美君，等. MAR20: 遥感图像军用飞机目标识别数据集[J]. 遥感学报, 2023, 27 (12): 2688-2696.
YU W Q, CHENG G, WANG M J, et al. MAR20: a benchmark for military aircraft recogntion in remote sensing images[J]. National Remote Sensing Bulletin, 2023, 27(12): 2688-2696.
[2] REN S Q, HE K M, 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, 2017, 39(6): 1137-1149.
[3] HE K M, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2017: 2961-2969.
[4] CAI Z W, VASCONCELOS N. Cascade R-CNN: delving into high quality object detection[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 6154-6162.
[5] DAI J F, LI Y, HE K M, et al. R-FCN: object detection via region-based fully convolutional networks[C]//Advances in Neural Information Processing Systems, 2016.
[6] TERVEN J, CORDOVA-ESPARZA D. A comprehensive review of YOLO: from YOLOv1 to YOLOv8 and beyond[J]. arXiv:2304.00501, 2023.
[7] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the IEEE Conference on Computer Vision, 2016.
[8] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE Conference on Computer Vision, 2017: 2980-2988.
[9] ZHOU X Y, WANG D Q, KR?HENBüHL P, et al. Objects as points[J].?arXiv:1904.07850, 2019.
[10] TAN M X, PANG R, LE Q V. EfficientDet: scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 10778-10787.
[11] CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers[J]. arXiv:2005.12872, 2020.
[12] 苗茹, 岳明, 周珂, 等. 基于改进YOLOv7的遥感图像小目标检测方法[J]. 计算机工程与应用, 2024, 60(10): 246-255.
MIAO R, YUE M, ZHOU K. Small target detection method in remote sensing images based on improved YOLOv7[J]. Computer Engineering and Applications, 2024, 60(10): 246-255.
[13] 梁燕, 饶星晨. 改进YOLOX的遥感图像目标检测算法[J]. 计算机工程与应用, 2024, 60(12):181-188.
LIANG Y, RAO X C. Remote sensing image object detection algorithm with improved YOLOX[J]. Computer Engineering and Applications, 2024, 60(12):181-188.
[14] 张秀再, 沈涛, 许岱. 改进YOLOv8算法的遥感图像目标检测[J]. 激光与光电子学进展, 2024, 61(10): 1028001.
ZHANG X Z, SHEN T, XU D. Remote-sensing image object detection based on improved YOLOv8 algorithm[J]. Laser & Optoelectronics Progress, 2024, 61(10): 1028001.
[15] 张天骏, 刘玉怀, 李苏晨. 基于改进YOLOv4的遥感影像飞机目标检测[J]. 电光与控制, 2022, 29(12): 101-105.
ZHANG T J, LIU Y H, LI S C. Detection of aircrafts in remote sensing images based on improved YOLOv4[J]. Electronics Optics & Control, 2022, 29(12): 101-105.
[16] 王成龙, 赵倩, 赵琰, 等. 基于结构化剪枝的遥感飞机检测算法[J]. 电光与控制, 2022, 29(6): 37-41.
WANG C L, ZHAO Q, ZHAO Y, et al. Remote sensing aircraft detection algorithm based on structural pruning[J]. Electronics Optics & Control, 2022, 29(6): 37-41.
[17] 吴杰, 高策, 余毅, 等. 改进LDS_YOLO网络的遥感飞机检测算法研究[J]. 计算机工程与应用, 2022, 58(15): 210-219.
WU J, GAO C, YU Y, et al. Research on improved LDS_ YOLO network remote sensing aircraft detection algorithm[J]. Computer Engineering and Applications, 2022, 58(15): 210-219.
[18] 党玉龙, 叶成绪. 基于Faster R-CNN的轻量化遥感图像军用飞机检测模型[J/OL]. 激光杂志: 1-8[2024-02-04].http://kns.cnki.net/kcms/detail/50.1085.TN.20230920.0924.002.html.
DANG Y L, YE C X. A lightweight remote sensing image military aircraft detection model based on Faster R-CNN[J/OL]. Laser Journal: 1-8[2024-02-04]. http://kns.cnki.net/kcms/detail/50.1085.TN.20230920.0924.002.html.
[19] 王杰, 张上, 张岳, 等. 改进YOLOv5的军事飞机检测算法[J]. 无线电工程, 2024, 54(3): 589-596.
WANG J, ZHANG S, ZHANG Y, et al. Improved YOLOv5’s military aircraft detection algorithm[J]. Radio Engineering, 2024, 54(3): 589-596.
[20] CHEN J, KAO S, HE H, et al. Run, don’t walk: chasing higher FLOPS for faster neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 12021-12031.
[21] GEVORGYAN Z. SIoU loss: more powerful learning for bounding box regression[J]. arXiv:2205.12740, 2022.
[22] ZHANG H, XU C, ZHANG S J. Inner-IoU: more effective intersection over union loss with auxiliary bounding box[J]. arXiv:2311.02877, 2023.
[23] LEE J, PARK S, MO S, et al. Layer-adaptive sparsity for the magnitude-based pruning[C]//Proceedings of the International Conference on Learning Representations, 2020.
[24] SHU C Y, LIU W F, GAO J F, et al. Channel-wise knowledge distillation for dense prediction[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 5291-5300.
[25] SANDLER M, HOWARD A, ZHU M, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 4510-4520.
[26] HOWARD A, SANDLER M, CHU G, et al. Searching for MobileNetV3[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019: 1314-1324.
[27] HAN K, WANG Y, TIAN Q, et al. GhostNet: more features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 1580-1589.
[28] MA N N, ZHANG X Y, ZHENG H T, et al. ShuffleNet V2: practical guidelines for efficient CNN architecture design[C]//Proceedings of the European Conference on Computer Vision, 2018.
[29] LIU X Y, PENG H W, ZHENG N X, et al. EfficientViT: memory efficient vision transformer with cascaded group attention[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 14420-14430.
[30] 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/CVF Conference on Computer Vision and Pattern Recognition, 2019: 658-666.
[31] ZHENG Z, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[C]//Proceedings of the 2020 AAAI Conference on Artificial Intelligence, 2020: 12993-13000.
[32] ZHANG Y F, REN W Q, ZHANG Z, et al. Focal and efficient IOU loss for accurate bounding box regression[J]. arXiv:2101.08158, 2021.
[33] SELVARAJU R R, COGSWELL M, DAS A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision, 2017: 618-626.