A Two-Stage Automatic Container Code Recognition Method Considering Environmental Interference
Source abstract
Abstract
Automatic Container Code Recognition (ACCR) is critical for enhancing the efficiency of container terminals. However, existing ACCR methods frequently fail to achieve satisfactory performance in complex environments at port gates. In this paper, we propose an approach for accurate, fast, and compact container code recognition by utilizing YOLOv4 for container region localization and Deeplabv3+ for character recognition. To enhance the recognition speed and accuracy of YOLOv4 and Deeplabv3+, and to facilitate their deployment at gate entrances, we introduce several improvements. First, we optimize the feature-extraction process of YOLOv4 and Deeplabv3+ to reduce their computational complexity. Second, we enhance the multi-scale recognition and loss functions of YOLOv4 to improve the accuracy and speed of container region localization. Furthermore, we adjust the dilated convolution rates of the ASPP module in Deeplabv3+. Finally, we replace two upsampling structures in the decoder of Deeplabv3+ with transposed convolution upsampling and sub-pixel convolution upsampling. Experimental results on our custom dataset demonstrate that our proposed method, C-YOLOv4, achieves a container region localization accuracy of 99.76% at a speed of 56.7 frames per second (FPS), while C-Deeplabv3+ achieves an average pixel classification accuracy (MPA) of 99.88% and an FPS of 11.4. The overall recognition success rate and recognition speed of our approach are 99.51% and 2.3 ms per frame, respectively. Moreover, C-YOLOv4 and C-Deeplabv3+ outperform existing methods in complex scenarios.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Malware Detection Techniques · Algorithms and Data Compression · Advanced Data Storage Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Transportation and Logistics Engineering, Wuhan University of Technology, Wuhan 430063, China
China Ocean Shipping Agency Tianjin Co., Ltd., Tianjin 300456, China
Qingdao New Qianwan Container Terminal Co., Ltd., Qingdao 266000, China
Funding
National Key R&D Program of China · National Natural Science Foundation of China
References (29)
Show source-provided references
1. Optimization on Combination of Transport Routes and Modes on Dynamic Programming for a Container Multimodal Transport System10.1016/j.proeng.2016.01.272 ↗
2. United Nations Conference on Trade and Development (UNCTAD) (2021). Review of Maritime Transport 2021, UNCTAD.
3. Gate Automation System Evaluation: A Case of a Container Number Recognition System in Port Terminals10.1108/MABR-09-2016-0022 ↗
4. PDD: Partitioning DAG-Topology DNNs for Streaming Tasks10.1109/JIOT.2023.3323520 ↗
5. Simulation Study on Terminal Layout in Automated Container Terminals from Efficiency, Economic and Environment Perspectives10.1016/j.ocecoaman.2021.105882 ↗
6. A Novel Container ISO-Code Recognition Method Using Texture Clustering with a Spatial Structure Window
7. Han, Y., Li, T., Zuo, Y., Tian, Y., Cao, Y., and Philip Chen, C.L. (2018, January 14–17). Application of Broad Learning System for Container Number Identification. Proceedings of the 2018 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC), Jinan, China.10.1109/SPAC46244.2018.8965520 ↗
8. Accurate Detection and Recognition of Dirty Vehicle Plate Numbers for High-Speed Applications10.1109/TITS.2016.2586520 ↗
9. Automatic Container Code Recognition System Based on Geometrical Clustering and Spatial Structure Template Matching10.1007/978-981-10-6571-2_268 ↗
10. Container Number Recognition Method Based on SSD_MobileNet and SVM
11. Wang, Q., Zhang, Q., Liang, X., Wang, Y., Zhou, C., and Mikulovich, V.I. (2021). Traffic Lights Detection and Recognition Method Based on the Improved YOLOv4 Algorithm. Sensors, 22.10.3390/s22010200 ↗
12. Real-Time License Plate Detection and Recognition Using Deep Convolutional Neural Networks10.1016/j.jvcir.2020.102773 ↗
13. Chen, S., Qiu, C., Yang, W., and Zhang, Z. (2022). Combining Edge Guidance and Feature Pyramid for Medical Image Segmentation. Biomed. Signal Process. Control, 78.10.1016/j.bspc.2022.103960 ↗
14. Zhiming, W., Wuxi, W., and Yuxiang, X. (2019, January 19–22). Automatic Container Code Recognition via Faster-RCNN. Proceedings of the 2019 5th International Conference on Control, Automation and Robotics (ICCAR), Beijing, China.10.1109/ICCAR.2019.8813401 ↗
15. Feng, X., Wang, Z., and Liu, T. (2020, January 26–28). Port Container Number Recognition System Based on Improved YOLO and CRNN Algorithm. Proceedings of the 2020 International Conference on Artificial Intelligence and Electromechanical Automation (AIEA), Tianjin, China.10.1109/AIEA51086.2020.00022 ↗
16. Automatic Container Code Recognition from Multiple Views
17. Mei, L., Guo, J., Liu, Q., and Lu, P. (2016, January 3–4). A Novel Framework for Container Code-Character Recognition Based on Deep Learning and Template Matching. Proceedings of the 2016 International Conference on Industrial Informatics-Computing Technology, Intelligent Technology, Industrial Information Integration (ICIICII), Wuhan, China.10.1109/ICIICII.2016.0030 ↗
18. Roeksukrungrueang, C., Kusonthammrat, T., Kunapronsujarit, N., Aruwong, T.N., and Chivapreecha, S. (2018, January 7–9). An Implementation of Automatic Container Number Recognition System. Proceedings of the 2018 International Workshop on Advanced Image Technology (IWAIT), Chiang Mai, Thailand.10.1109/IWAIT.2018.8369807 ↗
19. Key Methods of Recognizing Container Number Automatically Using Video Stream in Intelligent Tally10.1007/978-981-32-9686-2_2 ↗
20. An Adaptive Deep Learning Framework for Shipping Container Code Localization and Recognition
21. A Port Container Code Recognition Algorithm under Natural Conditions10.2112/SI103-170.1 ↗
22. Port Container Number Detection Based on Improved EAST Algorithm10.1088/1742-6596/1651/1/012088 ↗
23. Wan, Z., Liu, Q., and Liu, T. (2021, January 22–24). Multichannel Real-Time Video Container Numbers Recogntion in Container Yard. Proceedings of the 2021 China Automation Congress (CAC), Beijing, China.10.1109/CAC53003.2021.9728242 ↗
24. Towards End-to-End Container Code Recognition10.1007/s11042-022-12477-z ↗
25. Towards Sustainable Agricultural Systems: A Lightweight Deep Learning Model for Plant Disease Detection10.32604/csse.2023.037992 ↗
26. Quadbox: Quadrilateral Bounding Box Based Scene Text Detection Using Vector Regression10.1109/ACCESS.2021.3063030 ↗
27. Container-Code Recognition System Based on Computer Vision and Deep Neural Networks10.1063/1.5033782 ↗
28. A Modified YOLOv5 Architecture for Efficient Fire Detection in Smart Cities10.1016/j.eswa.2023.120465 ↗
29. Singh, A., Bhambhu, Y., Buckchash, H., Gupta, D.K., and Prasad, D.K. (2023). Latent Graph Attention for Enhanced Spatial Context. arXiv.