基于改进Faster R-CNN的垃圾检测与分类方法

doi:10.19678/j.issn.1000-3428.0058258

摘要/Abstract

摘要： 针对人工分拣垃圾环境差、任务繁重且分拣效率低的问题，为提高垃圾识别与分类的精确度，同时克服垃圾体积小及图像分辨率较低的难题，基于现有深度卷积神经网络模型，提出改进的Faster R-CNN目标检测模型与VGG16及ResNet50卷积神经网络相结合的方法。根据卷积网络的特性，修改Faster R-CNN网络结构，提升小目标检测任务精度，采用Soft-NMS算法替代传统的非极大值抑制算法，并对参数进行敏感分析，确定其参数范围为0.4~0.7。实验结果表明，与传统Faster R-CNN算法相比，该方法平均精确度提高8.26个百分点，综合识别率达到81.77%，且能够减少图像处理时间。

关键词: 垃圾识别, 分类, 目标检测, 深度学习, 非极大值抑制

Abstract: Traditional garbage sorting is implemented manually. Workers have to suffer from the poor environment and intensive tasks, which reduce their efficiency. Neural network can help automate the process, and thus free workers from the heavy labor. This paper proposes a neural network-based method to improve the accuracy of garbage identification and classification, especially for the small-sized garbage and low-resolution images. The method combines the improved Faster R-CNN target detection model, VGG16 and Resnet50. According to the features of the convolutional network, the structure of Faster R-CNN is modified to improve the accuracy of small target detection. The Soft-NMS algorithm is used to replace the traditional non-maximum suppression algorithm, and conduct sensitive analysis of the parameters to determine the parameter ranging within 0.4~0.7. Experimental results show that compared with the traditional Faster R-CNN algorithm, the method increases the average accuracy by 8.26 percentage points, and provides a comprehensive recognition rate of up to 81.77%. It also reduces the image processing time.

Key words: garbage identification, classification, target detection, deep learning, non-maximum suppression

中图分类号:

TP391

马雯, 于炯, 王潇, 陈嘉颖. 基于改进Faster R-CNN的垃圾检测与分类方法[J]. 计算机工程, 2021, 47(8): 294-300.

MA Wen, YU Jiong, WANG Xiao, CHEN Jiaying. Garbage Detection and Classification Method Based on Improved Faster R-CNN[J]. Computer Engineering, 2021, 47(8): 294-300.

https://www.ecice06.com/CN/Y2021/V47/I8/294

图/表 11

20210819202610

20210819202614

20210819202618

20210819202622

20210819202626

20210819202630

20210819202634

20210819202638

20210819202643

20210819202647

20210819202651

参考文献

[1] 魏潇潇, 王小铭, 李蕾, 等. 1979年-2015年中国城市生活垃圾产生和处理时空特征[J]. 中国环境科学, 2018, 38(10): 3833-3843. WEI X X, WANG X M, LI L, et al. Temporal and spatial characteristics of municipal solid waste generation and treatment in China from 1979 to 2016[J]. China Environmental Science, 2018, 38(10): 3833-3843.(in Chinese)
[2] 薛之昕, 郑英豪, 肖建, 等. 基于多尺度卷积神经网络的交通标志识别[J]. 计算机工程, 2020, 46(3): 261-266. XUE Z X, ZHENG Y H, XIAO J, et al. Traffic sign recognition based on multi-scale convolutional neural network[J]. Computer Engineering, 2020, 46(3): 261-266.(in Chinese)
[3] 赵亚男, 吴黎明, 陈琦.基于多尺度融合SSD的小目标检测算法[J]. 计算机工程, 2020, 46(1): 247-254. ZHAO Y N, WU L M, CHEN Q.Small object detection algorithm based on multi-scale fusion SSD[J]. Computer Engineering, 2020, 46(1): 247-254.(in Chinese)
[4] SIMONYAN K, ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL]. [2020-04-01]. https://arXivpreprint arXiv:1409.1556.
[5] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas, USA:IEEE Computer Society, 2016:770-778.
[6] LKRIZHEVSKY A, SUTSKEVER I, HINTON G E.ImageNet classification with deep convolutional neural networks[C]//Proceedings of NIPS'12.Cambridge, USA:MIT Press, 2012:1097-1105.
[7] 曹明宇, 杨志豪, 罗凌, 邓.基于神经网络的药物实体与关系联合抽取[J]. 计算机研究与发展, 2019, 56(7): 1432-1440. CAO M Y, YANG Z H, LUO L, et al. Joint drug entities and relations extraction based on neural networks[J]. Journal of Computer Research and Developmen, 2019, 56(7): 1432-1440.(in Chinese)
[8] GIRSHICK R, DONAHUE J, DARRELL T, et al. Region-based convolutional networks for accurate object detection and segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(1): 142-158.
[9] HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visuall recognition[C]//Proceedings of IEEE ECCV'14.Washington D.C., USA:IEEE Press, 2014:269-278.
[10] SERMANET P, EIGEN D, ZHANG X, et al. OverFeat:Integrated recognition, localization and detection using convolutional networks[EB/OL]. [2020-04-01]. https://arxiv.org/pdf/1312.6229.pdf.
[11] KRIZHEVSKY A, SUTSKEVER I, HINTON G E.ImageNet classification with deep convolutional neural networks[J]. Neural Computing & Applications, 2012, 25:1097-1105.
[12] JOACHIMS T.Making large-scale SVM learning practical[D]. Dortmund, Germany:University of Dortmund, 1998.
[13] GIRSHICK R.Faster R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Computer Society, 2015:1440-1448.
[14] 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.
[15] ZEILER M D, FERGUS R.Visualizing and understanding convolutional networks[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2014:818-833.
[16] LIN T Y.Microsoft COCO:common objects in context[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2014:740-755.
[17] EVERINGHAM M, VAN GOOL L, WILLIAMS C K I, et al. The pascal visual object classes challenge[J]. International Journal of Computer Vision, 2009, 88(2): 303-338.
[18] 龚格格, 吴珊, 郭湘南.人脸检测算法的优化[J]. 计算机技术与发展, 2019, 29(6): 47-51. GONG G G, WU S, GUO X N.Optimization of face detection algorithm[J]. Computer Technology and Development, 2019, 29(6): 47-51.(in Chinese)
[19] 钟志权, 袁进, 唐晓颖.基于卷积神经网络的左右眼识别[J]. 计算机研究与发展, 2018, 55(8): 1667-1673. ZHONG Z Q, YUAN J, TANG X Y.Left-vs-right eye discrimination based on convolutional neural network[J]. Journal of Computer Research and Development, 2018, 55(8): 1667-1673.(in Chinese)
[20] 谢娟英, 侯琦, 史颖欢, 等. 蝴蝶种类自动识别研究[J]. 计算机研究与发展, 2018, 55(8): 1609-1618. XIE J Y, HOU Q, SHI Y H, et al. The automatic identification of butterfly species[J]. Journal of Computer Research and Development, 2018, 55(8): 1609-1618.(in Chinese)
[21] 柯岩, 林小竹, 廖蕊, 等. 卷积神经网络层级分解研究[J]. 计算机工程, 2019, 45(11): 191-197. KE Y, LIN X Z, LIAO R, et al. Research on hierarchical decomposition of convolutional neural network[J]. Computer Engineering, 2019, 45(11): 191-197.(in Chinese)
[22] LIN T Y, DOLLAR P, GIRSHICK O, et al. Feature pyramid networks for object detection[EB/OL]. [2020-04-01]. https://arxiv.org/abs/1612.03144.
[23] REDMON J, FARHADI A.YOLOv3:an incremental improvement[EB/OL]. [2020-04-01]. https://arxiv.org/abs/1804.02767.
[24] BODLA N, SINGH B, CHELLAPPA R, et al. Soft-NMS improving object detection with one line of code[EB/OL]. [2020-04-01]. https://arxiv.org/abs/1704.04503.
[25] 冶忠林, 赵海兴, 张科, 等. 基于邻节点和关系模型优化的网络表示学习[J]. 计算机研究与发展, 2019, 56(12): 2562-2577. YE Z L, ZHAO H X, ZHANG K, et al. Network representation learning using the optimizations of neighboring vertices and relation model[J]. Journal of Computer Research and Development, 2019, 56(12): 2562-2577.(in Chinese)
[26] WANG C, YANG J F, XIE L H, et al. Kervolutional neural networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:31-40.
[27] 黄继鹏, 史颖欢, 高阳.面向小目标的多尺度Faster-RCNN检测算法[J]. 计算机研究与发展, 2019, 56(2): 319-327. HUANG J P, SHI Y H, GAO Y.Multi-scale faster-RCNN algorithm for small object detection[J]. Journal of Computer Research and Development, 2019, 56(2): 319-327.(in Chinese)
[28] 柯鹏飞, 蔡茂国, 吴涛.基于改进卷积神经网络与集成学习的人脸识别算法[J]. 计算机工程, 2020, 46(2): 262-267, 273. KE P F, CAI M G, WU T.Face recognition algorithm based on improved convolutional neural network and ensemble learning[J]. Computer Engineering, 2020, 46(2): 262-267, 273.(in Chinese)

选择文件类型/文献管理软件名称

选择包含的内容