采用动态样本分配的特征融合目标检测算法

doi:10.3778/j.issn.1002-8331.2305-0254

摘要/Abstract

摘要： 针对轻量级目标检测算法SSD-Lite检测精度低、对小目标预测能力差等问题，提出了一种采用动态样本分配策略的多尺度特征融合目标检测算法。在轻量级目标检测算法SSD-Lite的颈部网络引入特征金字塔结构（feature pyramid network，FPN），并对其进行轻量化设计，同时引入残差特征增强模块（residual feature augmentation，RFA），采用残差分支注入不同空间的上下文信息来改善高层特征的特征表达，以提升网络对小目标的检测能力；在特征金字塔结构中插入轻量级注意力机制ECA模块，提升网络对重要特征的关注能力；针对网络训练过程中采用的固定交并比（intersection-over-union，IOU）阈值的样本分配策略导致的正负样本分配适应性差、难以选出高质量正样本等问题，设计了一种动态样本分配策略，取消锚框的预设置，采用中心点采样的方式，同时结合样本均值、标准差作为筛选阈值，减少人工先验的影响，在不改变网络结构的情况下提升算法性能。算法在Pascal VOC数据集上测试，实验结果表明：该算法整体预测精度相较于基准算法提升1.9个百分点，对小目标检测能力提升3.3个百分点，算法推理时延仅增加2.32%；实验证明了该算法可以以较小的性能代价，显著提升算法的预测精度。

关键词: 特征金字塔结构, 残差特征增强模块, 轻量级注意力机制, 动态样本分配策略

Abstract: A multi-scale feature fusion target detection algorithm with dynamic sample allocation strategy is proposed to address the problems of low detection accuracy and poor prediction ability of small targets in the lightweight target detection algorithm SSD-Lite. Firstly, the feature pyramid network (FPN) is introduced in the neck network of the lightweight target detection algorithm SSD-Lite and designed to be lightweight, while the residual feature augmentation (RFA) module is introduced, which uses residual branches to inject different. Then, this paper inserts a lightweight attention mechanism ECA module into the feature pyramid structure to improve the ability of network to focus on important features. Finally, to address the problems of poor adaptability of positive and negative sample assignment and difficulty in selecting high-quality positive samples caused by the fixed Intersection-over-Union (IOU) threshold sample assignment strategy used in the network training process, this paper designs a dynamic sample assignment strategy, which eliminates the pre-setting of anchor frames and adopts the centroid sampling method, while combining the sample mean and standard deviation as screening thresholds to reduce the influence of artificial a priori and improve the algorithm performance without changing the network structure. The algorithm is tested on Pascal VOC dataset, and the experimental results show that the overall prediction accuracy of the algorithm is improved by 1.9 percentage points compared with the benchmark algorithm, the detection ability of small targets is improved by 3.3 percentage points, and the inference delay of the algorithm is increased by only 2.32%. The experiments demonstrate that the algorithm can significantly improve the prediction accuracy of the algorithm with a small performance cost.

Key words: feature pyramid structure, residual feature augmentatione module, lightweight attention mechanism, dynamic sample assignment strategy

牛文涛, 王鹏, 陈遵田, 李晓艳, 郜辉, 孙梦宇. 采用动态样本分配的特征融合目标检测算法[J]. 计算机工程与应用, 2024, 60(15): 211-220.

NIU Wentao, WANG Peng, CHEN Zuntian, LI Xiaoyan, GAO Hui, SUN Mengyu. Feature Fusion Target Detection Algorithm Using Dynamic Sample Assignment[J]. Computer Engineering and Applications, 2024, 60(15): 211-220.

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] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
[3] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems, 2015.
[4] HE K, GKIOXARI G, DOLLáR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2017: 2961-2969.
[5] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//European Conference on Computer Vision. Cham: Springer, 2016: 21-37.
[6] 符惠桐, 王鹏, 李晓艳, 等. 面向移动目标识别的轻量化网络模型[J]. 西安交通大学学报, 2021, 55(7): 124-131.
FU H T, WANG P, LI X Y, et al. Lightweight network model for moving object recognition[J]. Journal of Xi’an Jiaotong University, 2021, 55(7): 124-131.
[7] 张灵灵, 王鹏, 李晓艳, 等. 基于优化SSD的低空无人机检测方法[J]. 计算机工程与应用, 2022, 58(16): 204-212.
ZHANG L L, WANG P, LI X Y, et al. Low-altitude UAV detection method based on optimized SSD[J]. Computer Engineering and Applications, 2022, 58(16): 204-212.
[8] LI Z, ZHOU F. FSSD: feature fusion single shot multibox detector[J]. arXiv:1712.00960, 2017.
[9] LIU S, HUANG D. Receptive field block net for accurate and fast object detection[C]//Proceedings of the European Conference on Computer Vision (ECCV), 2018: 385-400.
[10] JEONG J, PARK H, KWAK N. Enhancement of SSD by concatenating feature maps for object detection[J]. arXiv:1705.09587, 2017.
[11] 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 and Technology, 2023, 17(5): 1102-1111.
[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 and Technology, 2023, 17(5): 1089-1101.
[13] TIAN Z, SHEN C, CHEN H, et al. FCOS: fully convolutional one-stage object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019: 9627-9636.
[14] SANDLER M, HOWARD A, ZHU M, et al. MobileNetv2: inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 4510-4520.
[15] GUO C, FAN B, ZHANG Q, et al. AugFPN: improving multi-scale feature learning for object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 12595-12604.
[16] 李晓艳, 符惠桐, 牛文涛, 等. 基于深度学习的多模态行人检测算法[J]. 西安交通大学学报, 2022, 56(10): 61-70.
LI X Y, FU H T, NIU W T, et al. Multi-modal pedestrian detection algorithm based on deep learning[J]. Journal of Xi’an Jiaotong University, 2022, 56(10): 61-70.
[17] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 7132-7141.
[18] ZHANG S, CHI C, YAO Y, et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 9759-9768.
[19] KIM K, LEE H S. Probabilistic anchor assignment with IOU prediction for object detection[C]//European Conference on Computer Vision. Cham: Springer, 2020: 355-371.
[20] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[C]//13th European Conference on Computer Vision, Zurich, Switzerland, September 6-12, 2014: 740-755.
[21] ZHOU B, KHOSLA A, LAPEDRIZA A, et al. Learning deep features for discriminative localization[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 2921-2929.
[22] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision, 2017: 2980-2988.
[23] 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.