改进RetinaNet的轻量化工件检测算法研究

doi:10.3778/j.issn.1002-8331.2104-0424

摘要/Abstract

摘要： 针对传统目标检测模型参数量巨大，制约算法部署与模型推理实时性的问题，提出一种基于改进RetinaNet检测模型的轻量化实时目标检测网络。使用MobileNet-V2代替RetinaNet模型中的ResNet骨干网络，降低整体模型的参数量；设计锚框引导采样机制，基于特征金字塔输出特征层生成感兴趣区域掩码，减少背景区域冗余锚框，降低后处理过程中的计算复杂度；引入GFocalLossV2损失函数统计预测边框分布特征，优化预测边框质量以及提升分类准确度。该模型在自制多类别工件数据集WP和Pascal VOC公开数据集上进行验证实验，改进模型的检测准确率分别达到99.5%、80.5%，检测速度分别达到39.8?FPS、38.3?FPS。实验结果表明，该轻量级目标检测模型能够实现实时检测，同时保证了检测精度。

关键词: RetinaNet, MobileNet-V2, 引导采样, GFocalLossV2

Abstract: Aiming at the problem that the traditional object detection model has a huge amount of parameters, which restricts the deployment of algorithms and the real-time performance of model inference, this paper proposes a lightweight real-time object detection network based on the improved RetinaNet detection model. Use MobileNet-V2 to replace the ResNet backbone network in the RetinaNet model to reduce the amount of parameters of the overall model. Design an anchor frame guided sampling mechanism, generate a region of interest mask based on the feature pyramid output feature layer, decrease redundant anchor frames in the background area, and reduce computational complexity in the postprocessing. Introduce GFocalLossV2 loss function to calculate the distribution characteristics of the prediction frame, optimize the quality of the prediction frame and improve the classification accuracy. The model in this paper is validated on the self-made multi-category workpiece datasets WP and Pascal VOC public datasets. The detection accuracy of the improved model reaches 99.5% and 80.5%, and the detection speed reaches 39.8 FPS and 38.3 FPS respectively. Experimental results show that the lightweight target detection model proposed in this paper can achieve real-time detection while ensuring detection accuracy.

Key words: RetinaNet, MobileNet-V2, guided sampling, GFocalLossV2

梅菠萍, 赵皓, 阳珊, 李林静, 张静, 张华. 改进RetinaNet的轻量化工件检测算法研究[J]. 计算机工程与应用, 2022, 58(22): 172-178.

MEI Boping, ZHAO Hao, YANG Shan, LI Linjing, ZHANG Jing, ZHANG Hua. Research on Lightweight Workpiece Detection by Improved RetinaNet[J]. Computer Engineering and Applications, 2022, 58(22): 172-178.

参考文献

[1] DOLLAR P，WOJEK C，SCHIELE B，et al.Pedestrian detection：a benchmark[C]//2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition，2009：304-311.
[2] YURTSEVER E，LAMBERT J，CARBALLO A，et al.A survey of autonomous driving：common practices and emergingtechnologies[J].IEEE Access，2020，8：58443-58469.
[3] 沈新烽，姜平，周根荣.改进SSD算法在零部件检测中的应用研究[J].计算机工程与应用，2021，57（7）：257-262.
SHEN X F，JIANG P，ZHOU G R.Application of improved SSD algorithm in parts detection[J].Computer Engineering and Application，2021，57（7）：257-262.
[4] UIJLINGS J R R，VAN DE SANDE K E A，GEVERS T，et al.Selective search for object recognition[J].International Journal of Computer Vision，2013，104（2）：154-171.
[5] VEDALDI A，GULSHAN V，VARMA M，et al.Multiple kernels for object detection[C]//2009 IEEE 12th International Conference on Computer Vision，2009：606-613.
[6] YU Y，ZHANG J，HUANG Y，et al.Object detection by context and boosted HOG-LBP[C]//Visual Recognition Challange Workshop，2010.
[7] 刘信君，林浒，郑飂默，等.深度学习技术在工件自动检测中的应用[J].小型微型计算机系统，2020，41（4）：710-714.
LIU X J，LIN H，ZHENG L M，et al.Application of deep learning in workpieces’ automatic detection[J].Journal of Chinese Computer Systems，2020，41（4）：710-714.
[8] 雷毅.基于深度学习的工件检测与双机械臂协作分拣研究[D].广州：华南理工大学，2020.
LEI Y.Research on workpiece detection based on deep learning and collaborative sorting with dual manipulators[D].Guangzhou：South China University of Technology，2020.
[9] 洪奔奔.基于深度学习的扁平工件智能化检测技术研究[D].西安：西安工程大学，2019.
HONG B B.Research on intelligent detection technology of flat workpiece based on deep learning[D].Xi’an：Xi’an Polytechnic University，2019.
[10] REDMON J，FARHADI A.YOLO9000：better，faster，stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition，2017：7263-7271.
[11] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//14th European Conference on Computer Vision.Cham：Springer，2016：21-37.
[12] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition，2014：580-587.
[13] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition，2016：779-788.
[14] TIAN Z，SHEN C，CHEN H，et al.FCOS：fully convolutional one-stage object detection[C]//2019 IEEE/CVF International Conference on Computer Vision，2019：9627-9636.
[15] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[C]//2017 IEEE International Conference on Computer Vision，2017：2980-2988.
[16] SANDLER M，HOWARD A，ZHU M，et al.MobileNetv2：inverted residuals and linear bottlenecks[C]//2018 IEEE Conference on Computer Vision and Pattern Recognition，2018：4510-4520.
[17] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[18] LI X，WANG W，HU X，et al.Generalized FocalLossV2：learning reliable localization quality estimation for dense object detection[J].arXiv：2011.12885，2020.
[19] LIN T Y，DOLLáR P，GIRSHICK R，et al.Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition，2017：2117-2125.
[20] HOWARD A G，ZHU M，CHEN B，et al.MobileNets：efficient convolutional neural networks for mobile vision applications[J].arXiv：1704.04861，2017.
[21] REDMON J，FARHADI A.Yolov3：an incremental improvement[J].arXiv：1804.02767，2018.
[22] ZHANG S，CHI C，YAO Y，et al.Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：9759-9768.
[23] TAN M，PANG R，LE Q V.EfficientDet：scalable and efficient object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：10781-10790.