改进YOLOv7-tiny的轻量级红外车辆目标检测算法

doi:10.3778/j.issn.1002-8331.2305-0312

摘要/Abstract

摘要： 为了解决红外场景下车辆检测算法参数量与计算量大、识别精度低、小目标检测难度大的问题，提出了一种改进YOLOv7-tiny的轻量级红外车辆目标检测算法：KD-YOLO-DW。通过融合深度可分离卷积提出了ELAN-DW模块，极大地降低了网络参数量与计算量。通过在特征融合层引入GhostNet V2模块，提高了不同尺度特征的融合能力。采用动态非单调FM的WIoU损失函数，解决了红外数据集难易样本不平衡的问题，提高了轻量级算法对红外弱小目标的检测能力。联合残差思想提出跨尺度融合策略，提高了轻量级算法对不同尺度目标的检测效果，降低了小目标的漏检率。通过知识蒸馏对轻量化模型再次浓缩，进一步提高了模型对检测红外目标的准确性。实验结果表明，KD-YOLO-DW模型在参数量与计算量方面分别较YOLOv7-tiny模型下降了24.6%和16.7%，模型大小仅为9.2 MB，mAP分别提高了3.27和3.15个百分点，拥有更小的模型体积与更好的检测效果。

关键词: 红外目标检测, 轻量级, 知识蒸馏, 损失函数, YOLOv7-tiny, GhostNet V2

Abstract: In order to solve the problems of large number of parameters and computation, low recognition accuracy, and difficult small target detection in infrared scene, a lightweight infrared vehicle target detection algorithm with improved YOLOv7-tiny is proposed: KD-YOLO-DW. Firstly, the ELAN-DW module is proposed by merging deep separable convolution, which greatly reduces the number of network parameters and the amount of computation. Secondly, by introducing GhostNet V2 module in the feature fusion layer, the fusion ability of different scale features is improved. The WIoU loss function of dynamic non-monotone FM is used to solve the problem of imbalanced samples in the infrared data set, and the detection ability of the lightweight algorithm is improved. Then, a cross-scale fusion strategy is proposed in combination with residual idea, which improves the detection effect of lightweight algorithm on different scale targets and reduces the missing rate of small targets. Finally, the lightweight model is reconcentrated by knowledge distillation, which further improves the accuracy of the model for detecting infrared targets. The experimental results show that compared with the YOLOv7-tiny model, KD-YOLO-DW model has 24.6% and 16.7% fewer parameters and 16.7% less computation, the model size is only 9.2 MB, and mAP is increased by 3.27 and 3.15 percentage points, respectively, with smaller model volume and better detection effect.

Key words: infrared target detection, lightweight, knowledge distillation, loss function, YOLOv7-tiny, GhostNet V2

许晓阳, 高重阳. 改进YOLOv7-tiny的轻量级红外车辆目标检测算法[J]. 计算机工程与应用, 2024, 60(1): 74-83.

XU Xiaoyang, GAO Chongyang. Improved YOLOv7-tiny Lightweight Infrared Vehicle Target Detection Algorithm[J]. Computer Engineering and Applications, 2024, 60(1): 74-83.

参考文献

[1] 聂光涛, 黄华. 光学遥感图像目标检测算法综述[J]. 自动化学报, 2021, 47(8): 1749-1768.
NIE G T, HUANG H. A survey of object detection in optical remote sensing images [J]. Acta Automatica Sinica, 2021, 47(8): 1749-1768.
[2] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), 2005: 886-893.
[3] FELZENZWALB P, MCALLESTER D, RAMANAN D. A discriminatively trained, multiscale, deformable part model[C]//2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008: 1-8.
[4] HE K, ZHANG X, REN S, 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.
[5] GIESHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
[6] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//European Conference on Computer Vision. Cham: Springer, 2016: 21-37.
[7] 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.
[8] REDMON J, FARHADI A. Yolov3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[9] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. Yolov4: optimal speedand accuracy of object detection[J]. arXiv:2004.10934, 2020.
[10] 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.
[11] 李北明, 金荣璐, 徐召飞, 等. 基于特征蒸馏的改进Ghost-YOLOv5红外目标检测算法[J]. 郑州大学学报(工学版), 2022, 43(1): 20-26.
LI B M, JIN R L, XU Z F, et al. An improved Ghost-YOLOv5 infrared target detection algorithm based on feature distillation[J]. Journal of Zhengzhou University (Engineering Science), 2022, 43(1): 20-26.
[12] 胡皓, 郭放, 刘钊. 改进YOLOX-S模型的施工场景目标检测[J]. 计算机科学与探索, 2023, 17(5): 1089-1101.
HU H, GUO F, LIU Z. Object detection based on improved YOLOX-S model in construction sites[J]. Journal of Frontiers of Computer Science & Technology, 2023, 17(5): 1089-1101.
[13] 贾天豪, 彭力, 戴菲菲. 引入残差学习与多尺度特征增强的目标检测器[J]. 计算机科学与探索, 2023, 17(5): 1102-1111.
JIA T H, PENG L, DAI F F. Object detector with residual learning and multi-scale feature enhancement[J]. Journal of Frontiers of Computer Science & Technology, 2023, 17(5): 1102-1111.
[14] 赵明, 张浩然. 一种基于跨域融合网络的红外目标检测方法[J]. 光子学报, 2021, 50(11): 339-349.
ZHAO M, ZHANG H R. An infrared object detection method based on cross-domain fusion network[J]. Acta Photonica Sinica, 2021, 50(11): 339-349.
[15] 黄磊, 杨媛, 杨成煜, 等. FS-YOLOv5: 轻量化红外目标检测方法[J]. 计算机工程与应用, 2023, 59(9): 215-224.
HUANG L, YANG Y, YANG C Y, et al. FS-YOLOv5: lightweight infrared rode target detection method[J]. Computer Engineering and Applications, 2023, 59(9): 215-224.
[16] ZHENG Z, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 12993-13000.
[17] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[J]. arXiv:2207.02696, 2022.
[18] TANG Y, HAN K, GUO J, et al. Gho-stNetV2: enhance cheap operation with long-range attention[J]. arXiv:2211. 12905, 2022.
[19] TONG Z, CHEN Y, XU Z, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[J]. arXiv:2301.10051, 2023.
[20] CHEN G, CHOI W, YU X, et al. Learning efficient object detection models with knowledge distillation[C]//Advances in Neural Information Processing Systems, 2017.
[21] JOCHER G, STOKEN A, BOROVEC J, et al. ultralytics/yolov5: v3.0[Z]. Zenodo, 2020.
[22] 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.
[23] WANG Y, LIAO H Y M, YEH I H. Designing network design strategies through gradient path analysis[J]. arXiv:2211.04800, 2022.
[24] KAISER L, GOMEZ A N, CHOLLET F. Depthwise separable convolutions for neural machine translation[J]. arXiv:1706.03059, 2017.
[25] ZHANG Y F, REN W, ZHANG Z, et al. Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing, 2022, 506: 146-157.
[26] HE J, ERFANI S, MA X, et al. Alpha-IoU: a family of power intersection over union losses for bounding box regression[C]//Advances in Neural Information Processing Systems, 2021: 20230-20242.