Sage Journals: Discover world-class research

Abstract

The manual sorting of recyclable garbage has caused several issues such as the wastage of human resources and low resource utilization. To solve this problem, an improved Single Shot Multibox Detector (SSD) deep learning approach has been developed for recyclable garbage detection. To reduce the number of parameters and make the model easier to deploy and apply, a lightweight network called RepVGG has been chosen to replace the VGG16 network in the SSD. Additionally, the auxiliary convolutional layer structure of the SSD has been modified to further reduce the number of parameters. Additionally, the SK module has been integrated to adaptively adjust the size of the receptive field and enhance the detection accuracy. Experimental results of Waste Classification data set from Kaggle website have demonstrated that the improved SSD model has better detection accuracy and real-time performance, with an accuracy of 95.23%, which is 4.33 percentage points higher than the original SSD, and a detection speed of up to 64 FPS. This algorithm can be better applied in industry.

Keywords

Recyclable garbage detection SSD algorithm structure re-parameterization deep learning

Get full access to this article

View all access options for this article.

References

Bochkovskiy,

C.Y.

Wang and

Liao, Yolov4: Optimal speed and accuracy of object detection, 2020, arXiv:2004.10934.

Cui,

Zhang,

Green et al., Yolov3-darknet with adaptive clustering anchor box for garbage detection in intelligent sanitation, in: Proceedings of the 2019 3rd International Conference on Electronic Information Technology and Computer Engineering, 2019.

Ding,

Guo,

Ding et al., ACNet: Strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks, in: Proceedings of the IEEE/CVF international Conference on Computer Vision, 2019, pp. 1911–1920.

Ding,

Zhang,

Ma et al., RepVGG: Making VGGstyle convnets great again, 2021, arXiv:2101.03697.

Girshick, Faster R-CNN, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1440–1448.

Girshick,

Donahue,

Darrell et al., Rich feature hierarchies for accurate object detection and semantic segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 580–587.

F.X.

Gong,

Shao,

L.Y.

Wang et al., Problems and countermeasures in the implementation of “Regulations of Shanghai municipality on domestic wastemanagement”, Economic Research Guide 34 (2020), 104–106. doi:10.3969/j.issn.1673-291X.2020.34.041.

K.M.

He,

X.Y.

Zhang,

S.Q.

Ren et al., Spatial pyramid pooling in deep convolutional networks for visual recognition, IEEE Transactions On Pattern Analysis And Machine Intelligence 37(9) (2015), 1904–1916. doi:10.1109/TPAMI.2015.2389824.

A.G.

Howard,

Zhu,

Chen et al., Mobilenets: Efficient convolutional neural networks for mobile vision applications, 2017, arXiv:1704.04861.

10.

Jie,

Li and

Gang, Squeeze-and-excitation networks, in: Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (Cvpr), 2018, pp. 7132–7141.

11.

Kaggle, https://www.kaggle.com/techsash/waste-classification-data.

12.

Li,

Wang,

Hu et al., Selective kernel networks, in: Proceedings of the IEEE/CVF Conference on Computervision and Pattern Recognition, 2019, pp. 510–519.

13.

E.Q.

Liu, Classification and detection of domestic wastebased on deep learning, Shanxi University, Taiyuan, China, 2020.

14.

Liu,

Huang and

Wang, Receptive field blocknet for accurate and fast object detection, 2017, arXiv:1711.07767.

15.

Liu,

Anguelov,

Erhan et al., Ssd: Single Shotmultibox Detector. European Conference on Computervision, Springer, Cham, 2016, pp. 21–37.

16.

Liu,

Ge,

Lv et al., Research on automatic garbage detection system based on deep learning and narrowband internet of things, Journal Of Physics: Conference Series 1069 (2018), 012032.

17.

Ning,

D.B.

Zhang,

Yin et al., Garbage detection and classification of intelligent sweeping robot based on visual perception, Journal Of Image And Graphics 24(8) (2019), 1358–1368.

18.

Redmon and

Farhadi, YOLO9000: Better faster stronger, 25 Dec 2016, https://pjreddie.com/darknet/yolo/, arXiv:1612.08242v1 [cs.CV].

19.

Redmon and

Farhadi, Yolov3: An incremental improvement, 2018, arXiv:1804.02767.

20.

Ren,

He,

Girshick et al., Faster R-CNN: Towards real-time object detection with region proposal networks, IEEE Transactions On Pattern Analysis & Machine Intelligence 39(6) (2017), 1137–1149. doi:10.1109/TPAMI.2016.2577031.

21.

Sandler,

Howard et al., MobileNetV2: Inverted residuals and linear bottlenecks, 21 Mar 2019, https://arxiv.org/pdf/1801.04381.pdf, arXiv:1801.04381v4 [cs.CV].

22.

Simonyan and

Zisserman, Very deep convolutional networks for large-scale image recognition, 2014, arXiv:1409.1556.

23.

Szegedy,

Liu,

Jia et al., Going deeper with convolutions, in: 2015 IEEE Conference on Computervision and Pattern Recognition, 2015.

24.

Woo,

Park et al., CBAM: Convolutional block attention module, 2018, arXiv:1807.06521 [cs.CV]. doi:10.48550/arXiv.1807.06521.

25.

Zou,

Shi,

Guo et al., Object detection in 20 years: A survey, 2019, arXiv:1905.05055.

Improving resource recycling based on deep learning

Abstract

Keywords

Get full access to this article

References