A Lightweight Model for Real-Time Detection of Vehicle Black Smoke
Abstract
:1. Introduction
2. YOLOv5 Network Framework
3. Lightweight Model Improvements
3.1. Backbone Network Lightweight Optimization
3.2. Neck Network Lightweight Optimization
3.3. MGSNet Model
4. Experimental Preparation
4.1. Experimental Environment and Parameter Configuration
4.2. Custom Dataset
4.3. Evaluation Metrics
5. Experimental Results and Analysis
5.1. Performance Comparison of Lightweight Networks
5.2. Ablation Experiments
5.3. Comparison of Existing Algorithms
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Liao, X.; Zeng, X. Review of target detection algorithm based on deep learning. In Proceedings of the 2020 International Conference on Artificial Intelligence and Communication Technology (AICT), Chongqing, China, 28–29 March 2020; pp. 55–59. [Google Scholar]
- Ge, H.; Dai, Y.; Zhu, Z.; Zang, X. Single-stage underwater target detection based on feature anchor frame double optimization network. Sensors 2022, 22, 7875. [Google Scholar] [CrossRef]
- Ellouze, A.; Ksantini, M.; Delmotte, F.; Karray, M. Multiple object tracking: Case of aircraft detection and tracking. In Proceedings of the 2019 16th International Multi-Conference on Systems, Signals & Devices (SSD 2019), Istanbul, Turkey, 21–24 March 2019; pp. 473–478. [Google Scholar]
- Ellouze, A.; Ksantini, M.; Delmotte, F.; Karray, M. Single object tracking applied to an aircraft. In Proceedings of the 2018 15th International Multi-Conference on Systems, Signals & Devices (SSD 2018), Hammamet, Tunisia, 19–22 March 2018; pp. 1441–1446. [Google Scholar]
- Cao, Y.; Lu, X. Learning spatial-temporal representation for smoke vehicle detection. Multimed. Tools Appl. 2019, 78, 27871–27889. [Google Scholar] [CrossRef]
- Xia, X. Research on Smoke Vehicle Detection Technology Based on Video Image. Master’s Thesis, Southeast University, Nanjing, China, 2019. [Google Scholar]
- Guo, T.; Ren, M. Dual branch network for black smoke and vehicle detection based on attention mechanism. Comput. Digit. Eng. 2022, 50, 147–151. [Google Scholar]
- Zhang, G.; Zhang, D.; LU, X.; Cao, Y. Smoky vehicle detection algorithm based on improved transfer learning. In Proceedings of the 2019 6th International Conference on Systems and Informatics (ICSAI), Shanghai, China, 2–4 November 2019; pp. 155–159. [Google Scholar]
- Zhang, G. Research on Smoke Vehicle Detection Technology Based on Deep Learning. Master’s Thesis, Southeast University, Nanjing, China, 2021. [Google Scholar]
- Isana, F.; Taichi, Y.; Xi, Z.; Masahiro, I. Image adjustment for multi-exposure images based on convolutional neural networks. IEICE Trans. Inf. Syst. 2022, 1, 123–133. [Google Scholar]
- Pelletier, C.; Webb, G.I.; Petitjean, F. Temporal convolutional neural network for the classification of satellite image time series. Remote Sens. 2019, 11, 523. [Google Scholar] [CrossRef]
- Anowar, F.; Sadaoui, S.; Selim, B. Conceptual and empirical comparison of dimensionality reduction algorithms (PCA, KPCA, LDA, MDS, SVD, LLE, ISOMAP, LE, ICA, t-SNE). Comput. Sci. Rev. 2021, 40, 100378. [Google Scholar] [CrossRef]
- Wang, P.; Wang, H.; Yu, F.; Xia, W. A high-precision fast smoky vehicle detection method based on improved Yolov5 network. In Proceedings of the 2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID), Guangzhou, China, 28–30 May 2021; pp. 255–259. [Google Scholar]
- Zhang, Q. Research on Smoky Vehicle Detection Technology Based on Computer Vision. Master’s Thesis, Hebei University of Science and Technology, Shijiazhuang, China, 2021. [Google Scholar]
- Du, C.; Wang, Y.; Liu, S.; Song, X. Granary pest detection model based on RA-YOLOv5s. Comput. Simul. 2023, 40, 486–491. [Google Scholar]
- Zhao, Y.; Wang, Q.; Sha, J.; Guo, Q. Lightweight object detection algorithm for table tennis based on YOLOv5s. J. Comput. Appl. 2023, 43, 229–234. [Google Scholar]
- Peng, C.; Zhang, Q.; Tang, Z.; Gui, W. Research on mask wearing detection method based on YOLOv5 enhancement model. Comput. Eng. 2022, 48, 39–49. [Google Scholar]
- Lindenheim-Locher, W.; Świtoński, A.; Krzeszowski, T.; Paleta, G.; Hasiec, P.; Josiński, H.; Paszkuta, M.; Wojciechowski, K.; Rosner, J. YOLOv5 drone detection using multimodal data registered by the vicon system. Sensors 2023, 23, 6396. [Google Scholar] [CrossRef]
- Tang, H.; Liang, S.; Yao, D.; Qiao, Y. A visual defect detection for optics lens based on the YOLOv5-C3CA-SPPF network model. Opt. Express 2023, 31, 2628–2643. [Google Scholar] [CrossRef]
- Yi, X.; Qian, C.; Wu, P.; Maponde, B.T.; Jiang, T.; Ge, W. Research on fine-grained image recognition of birds based on improved YOLOv5. Sensors 2023, 23, 8204. [Google Scholar] [CrossRef]
- Dong, W.; Pan, L.; Zhang, Q.; Zhang, W. Athlete target detection method in dynamic scenario based on nonlinear filtering and YOLOv5. Alex. Eng. J. 2023, 82, 208–217. [Google Scholar] [CrossRef]
- Yar, H.; Khan, Z.; Ullah, F.; Ullah, W.; Baik, S. A modified YOLOv5 architecture for efficient fire detection in smart cities. Expert Syst. Appl. 2023, 231, 120465. [Google Scholar] [CrossRef]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 2015, 37, 1904–1916. [Google Scholar] [CrossRef] [PubMed]
- Yang, J.; Fu, X.; Hu, Y.; Huang, Y.; Ding, X.; Paisley, J. PanNet: A deep network architecture for pan-sharpening. In Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Honolulu, HI, USA, 21–26 July 2017; pp. 1753–1761. [Google Scholar]
- Liu, M.; Wan, L.; Wang, B.; Wang, T. SE-YOLOv4: Shuffle expansion YOLOv4 for pedestrian detection based on PixelShuffle. Appl. Intell. 2023, 53, 18171–18188. [Google Scholar] [CrossRef]
- Philippe, M.; Isaac, R. Shuffle polygraphic resolutions for operads. J. Lond. Math. Soc. 2022, 107, 61–122. [Google Scholar]
- Guha, R.; Nassir, N.; Christian, W. Recalibrating fully convolutional networks with spatial and channel “squeeze and excitation” blocks. IEEE Trans. Med. Imaging 2019, 38, 540–549. [Google Scholar]
- Jiang, H.; Ma, L.; Wang, X.; Zhang, J.; Liu, Y.; Wang, D.; Wu, P.; Han, W. Focus prediction of medical microscopic images based on lightweight densely connected with squeeze-and-excitation network. Front. Neurosci. 2023, 17, 1213176. [Google Scholar] [CrossRef]
- Liu, J.; Song, S.; Wang, J.; Balaiti, M.; Song, N.; Li, S. Flatness prediction of cold rolled strip based on deep neural network with improved activation function. Sensors 2022, 22, 656. [Google Scholar] [CrossRef]
- Zheng, H.; Liu, H.; Qi, W.; Xie, H. Little-YOLOv4: A Lightweight pedestrian detection network based on YOLOv4 and GhostNet. Wirel. Commun. Mob. Comput. 2022, 2022, 5155970. [Google Scholar] [CrossRef]
- Yang, Y.; Wang, L.; Huang, M.; Zhu, Q.; Wang, R. Polarization imaging based bruise detection of nectarine by using ResNet-18 and ghost bottleneck. Postharvest Biol. Technol. 2022, 189, 111916. [Google Scholar] [CrossRef]
- Yu, M.; Wan, Q.; Tian, S.; Hou, Y.; Wang, Y.; Zhao, J. Equipment identification and localization method based on improved YOLOv5s model for production line. Sensors 2022, 22, 10011. [Google Scholar] [CrossRef] [PubMed]
- Liu, P.; Wang, Q.; Zhang, H.; Mi, J.; Liu, Y. A lightweight object detection algorithm for remote sensing images based on attention mechanism and YOLOv5s. Remote Sens. 2023, 15, 2429. [Google Scholar] [CrossRef]
- Wang, J.; Li, Q.; Fang, Z.; Zhou, X.; Tang, Z.; Han, Y.; Ma, Z. YOLOv6-ESG: A lightweight seafood detection method. J. Mar. Sci. Eng. 2023, 11, 1623. [Google Scholar] [CrossRef]
- Cengil, E.; Çınar, A.; Yıldırım, M. An efficient and fast lightweight-model with ShuffleNetv2 based on YOLOv5 for detection of hardhat-wearing. Rev. Comput. Eng. Stud. 2022, 9, 116–123. [Google Scholar] [CrossRef]
- Howard, A.; Sandler, M.; Chu, G.; Chen, L.; Chen, B.; Tan, M.; Wang, W.; Zhu, Y.; Pang, R.; Vasudenvan, V.; et al. Searching for MobileNetV3. IEICE Trans. Fundam. Electron. Commun. Comput. Sci. 2019, 1905, 02244. [Google Scholar]
- Hai, K.; Wang, Y.; Tian, Q.; Guo, J.; Xu, C.; Xu, C. GhostNet: More feature from cheap operations. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 14–19 June 2020; pp. 1577–1586. [Google Scholar]
- Zhang, M.; Gao, F.; Yang, W.; Zhang, H. Wildlife object detection method applying segmentation gradient flow and feature dimensionality reduction. Electronics 2023, 12, 377. [Google Scholar] [CrossRef]
- Zheng, H.; Duan, J.; Dong, Y.; Liu, Y. Real-time fire detection algorithms running on small embedded devices based on MobileNetV3 and YOLOv4. Fire Ecol. 2023, 19, 31. [Google Scholar] [CrossRef]
- Abd Elaziz, M.; Dahou, A.; Alsaleh, N.A.; Elsheikh, A.H.; Saba, A.I.; Ahmadein, M. Boosting COVID-19 image classification using MobileNetV3 and aquila optimizer algorithm. Entropy 2021, 23, 1383. [Google Scholar] [CrossRef]
- Howard, A.; Zhu, M.; Chen, B.; Kalenichenko, D.; Wang, W.; Weyand, T.; Andreetto, M.; Adam, H. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv 2017, arXiv:1704.04861. [Google Scholar]
- Sandler, M.; Howard, A.; Zhu, M.; Zhmoginov, A.; Chen, L. MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of the 2018 Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, 18–21 June 2018; pp. 4510–4520. [Google Scholar]
- Lang, J.; Liu, Y. LCCF-Net: Lightweight contextual and channel fusion network for medical image segmentation. Biomed. Signal Process. Control 2023, 86, 105134. [Google Scholar] [CrossRef]
- Wei, J.; Zhang, X.; Zhuo, Z.; Ji, Z.; Wei, Z.; Li, J.; Li, Q. Leader population learning rate schedule. Inf. Sci. 2023, 623, 455–468. [Google Scholar] [CrossRef]
- Yang, Y.; Ahmadipour, P.; Shanechi, M. Adaptive latent state modeling of brain network dynamics with real-time learning rate optimization. J. Neural Eng. 2021, 18, 036013. [Google Scholar] [CrossRef]
- Fan, L.; Zhang, T.; Zhao, X.; Wang, H.; Zheng, M. Deep topology network: A framework based on feedback adjustment learning rate for image classification. Adv. Eng. Inform. 2019, 42, 100935. [Google Scholar] [CrossRef]
- Kaavya, K.; Lakshmi, G. A new 3D convolutional neural network (3D-CNN) framework for multimedia event detection. Signal Image Video Process. 2020, 15, 779–787. [Google Scholar]
- Arora, A.; Grover, A.; Chugh, R.; Reka, S. Real time multi object detection for blind using single shot multibox detector. Wirel. Pers. Commun. 2019, 107, 651–661. [Google Scholar] [CrossRef]
Name | Version Model |
---|---|
Operating system | Windows10 |
CPU | Intel(R) Core (TM) i5-11400F @2.60 GHz |
GPU | NVIDIA GeForce GTX 1650 |
Programming language | Python3.8.13 |
Deep learning framework | Pytorch1.13.0, CUDA11.7 |
Model | P (%) | R (%) | mAP (%) | F1_Score (%) | Parameters (M) | FPS |
---|---|---|---|---|---|---|
YOLOv5s | 0.967 | 0.968 | 0.983 | 0.97 | 7012822 | 25.7 |
YOLOv5s-S | 0.955 | 0.947 | 0.955 | 0.94 | 842358 | 52.0 |
YOLOv5s-M | 0.978 | 0.935 | 0.967 | 0.96 | 1354454 | 37.6 |
YOLOv5s-G | 0.969 | 0.988 | 0.987 | 0.98 | 5078974 | 31.5 |
Model | P (%) | R (%) | mAP (%) | F1_Score (%) | Parameters (M) | FPS |
---|---|---|---|---|---|---|
YOLOv5s-GS-CBS | 0.963 | 0.962 | 0.981 | 0.97 | 6905846 | 27.0 |
YOLOv5s-GS-C3 | 0.958 | 0.960 | 0.980 | 0.96 | 6825896 | 27.6 |
YOLOv5s-GS | 0.961 | 0.959 | 0.978 | 0.96 | 6764322 | 28.5 |
MGSNet | 0.957 | 0.947 | 0.954 | 0.95 | 1280204 | 44.6 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Chen, K.; Wang, H.; Zhai, Y. A Lightweight Model for Real-Time Detection of Vehicle Black Smoke. Sensors 2023, 23, 9492. https://doi.org/10.3390/s23239492
Chen K, Wang H, Zhai Y. A Lightweight Model for Real-Time Detection of Vehicle Black Smoke. Sensors. 2023; 23(23):9492. https://doi.org/10.3390/s23239492
Chicago/Turabian StyleChen, Ke, Han Wang, and Yingchao Zhai. 2023. "A Lightweight Model for Real-Time Detection of Vehicle Black Smoke" Sensors 23, no. 23: 9492. https://doi.org/10.3390/s23239492