Abstract
With the substantial improvement of people’s living standards, the amount of domestic garbage is increasing rapidly, and intelligent waste classification has become an urgent need in modern society. In this paper, we propose a real-time garbage detection model based on the improved YOLOv5 (you only look once version 5) algorithm. Firstly, mosaic data enhancement is introduced to enrich the background of the detection object and improve the robustness of the network. Secondly, Distance-IOU Non-Maximum Suppression is used to replace the traditional Non-Maximum Suppression to improve the suppression effect of prediction boxes. Finally, the network is further optimized from the aspect of activation function. The experimental results show that among the four versions of YOLOv5, their mean average precision(mAP) all reach more than 84%, The improved YOLOv5x has the best recognition effect, whose mAP reaches 89.4%, which is 2.1% higher than that of YOLOv5x and 5.3% higher than that of YOLOv5s.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 25, 1097–1105 (2012)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Buvana, M., Muthumayil, K., Kumar, S.S., Nebhen, J., Alshamrani, S.S.: Deep optimal vgg16 based covid-19 diagnosis model. Comput., Mater. Continua 70(1), 43–58 (2022)
Huang, G., Liu, Z., Maaten, L.V.D.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
He, K., Zhang, X., Ren, S.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Jeslin, T., Linsely, J.A.: Agwo-cnn classification for computer-assisted diagnosis of brain tumors. Comput., Mater. Continua 71(1), 171–182 (2022)
Ke, H., Chen, D., Li, X.: Towards brain big data classification: Epileptic EEG identification with a lightweight VGGNet on global MIC. IEEE Access 6, 14722–14733 (2018)
Budhiman, A., Suyanto, S., Arifianto, A.: Melanoma cancer classification using ResNet with data augmentation. In: 2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), IEEE, pp. 17–20 (2019)
Girshick, R., Donahue, J., Darrell, T.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Ren, S., He, K., Girshick, R.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing systems vol. 28, pp. 91–99 (2015)
Ushasukhanya, S., Karthikeyan, M.: Automatic human detection using reinforced faster-rcnn for electricity conservation system. Intell. Autom. Soft Comput. 32(2), 1261–1275 (2022)
Liu, W., Anguelov, D., Erhan, D.: Single shot multibox detector. In: European Conference on Computer Vision. Springer, Cham, pp. 21–37 (2016)
Redmon, J., Divvala, S., Girshick, R.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263–7271 (2017)
Murthy, C.B., Hashmi, M.F., Muhammad, G., Alqahtani, S.A.: Yolov2pd: an efficient pedes-trian detection algorithm using improved yolov2 model. Comput., Mater. Continua 69(3), 3015–3031 (2021)
Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Wang, Y.M., Jia, K.B., Liu, P.Y.: Impolite pedestrian detection by using enhanced YOLOv3-Tiny. J. Artif. Intell. 2(3), 113–124 (2020)
Liu, Q., Lu, S., Lan, L.: Yolov3 attention face detector with high accuracy and efficiency. Comput. Syst. Sci. Eng. 37(2), 283–295 (2021)
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)
Liu, J., Zhang, Y., Li, Z., Zhao, Y., Ran, X., Cui, Z., Niu, M.: Head detection based on rdm-yolov3. Laser & Optoelectronics Progress, 1–15 (2021)
Li, W., Yang, C., Jiang, L., Zhao, Y.: Indoor scene target detection based on improved yolov4 algorithm. Laser & Optoelectronics Progress, 1–19 (2021)
Wei, Z., Xiaohui, Y., Zhongbin, R.L., Cong, W., Hefeng, W.: Chao: Real time detection method of key components of yolov4 transmission line based on improvement. Sci., Technol. Eng. 21(24), 10393–10400 (2021)
He, G., Hu, W., Tang, H.: Study on the headgear and seat of the thangka image based on the improved yolov4 algorithm. In: 2020 5th International Conference on Information Science, pp. 153–157 (2020)
Adedeji, O., Wang, Z.: Intelligent waste classification system using deep learning convolutional neural network. Procedia Manuf. 35, 607–612 (2019)
Bircanog˘lu, C., Atay, M., Bes¸er, F.: RecycleNet: intelligent waste sorting using deep neural networks. In: 2018 Innovations in Intelligent Systems and Applications (INISTA), IEEE, pp. 1–7 (2018)
Ning, K., Dongbo, Z., Yin, F.: Garbage detection and classification of intelligent sweeping robot based on visual perception. Chin. J. Image Graph 24(8), 1358–1368 (2019)
Liu, Y., Ge, Z., Lv, G.: Research on automatic garbage detection system based on deep learning and narrowband internet of things. J. Phys: Conf. Ser. 1069, 12032 (2018)
Zipei, W.: Recognition and classification system of bottles for garbage classification. M.S. dissertation, Hebei University of Engineering (2020)
Wang, Y., Zhang, X.: Autonomous garbage detection for intelligent urban management. In: MATEC Web of Conferences, EDP Sciences, vol. 232, p. 01056 (2018)
Ma, N., Zhang, X., Liu, M.: Activate or not: learning customized activation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8032–8042 (2021)
Biswas, K., Kumar, S., Banerjee, S.: SAU: Smooth activation function using convolution with approximate identities. arXiv preprint arXiv:2109.13210 (2021)
Acknowledgement
This work was supported by “Automatic Garbage Classification System Based on DenseNet” in National training program of innovation and entrepreneurship for undergraduates.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kan, S., Fang, W., Wu, J., Sheng, V.S. (2022). Real-Time Domestic Garbage Detection Method Based on Improved YOLOv5. In: Sun, X., Zhang, X., Xia, Z., Bertino, E. (eds) Advances in Artificial Intelligence and Security. ICAIS 2022. Communications in Computer and Information Science, vol 1586. Springer, Cham. https://doi.org/10.1007/978-3-031-06767-9_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-06767-9_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06766-2
Online ISBN: 978-3-031-06767-9
eBook Packages: Computer ScienceComputer Science (R0)