Research on the Algorithm of Position Correction for High-Speed Moving Express Packages Based on Traditional Vision and AI Vision
The rapid development of the logistics industry poses significant challenges to the sorting work within this sector. The fast and precise identification of moving express parcels holds immense significance for the performance of logistics sorting systems. This paper proposes a motion express parcel...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/3/892 |
| _version_ | 1827354534926614528 |
|---|---|
| author | Ning Dai Zhehao Lu Jingchao Chen Kaixin Xu Xudong Hu Yanhong Yuan |
| author_facet | Ning Dai Zhehao Lu Jingchao Chen Kaixin Xu Xudong Hu Yanhong Yuan |
| author_sort | Ning Dai |
| collection | DOAJ |
| description | The rapid development of the logistics industry poses significant challenges to the sorting work within this sector. The fast and precise identification of moving express parcels holds immense significance for the performance of logistics sorting systems. This paper proposes a motion express parcel positioning algorithm that combines traditional vision and AI-based vision. In the traditional vision aspect, we employ a brightness-based traditional visual parcel detection algorithm. In the AI vision aspect, we introduce a Convolutional Block Attention Module (CBAM) and Focal-EIoU to enhance YOLOv5, improving the model’s recall rate and robustness. Additionally, we adopt an Optimal Transport Assignment (OTA) label assignment strategy to provide a training dataset based on global optimality for the model training phase. Our experimental results demonstrate that our modified AI model surpasses traditional algorithms in both parcel recognition accuracy and inference speed. The combined approach of traditional vision and AI vision in the motion express parcel positioning algorithm proves applicable for practical logistics sorting systems. |
| first_indexed | 2024-03-08T03:48:59Z |
| format | Article |
| id | doaj.art-9e3654019f444953bb721564f86f1a5e |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T03:48:59Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9e3654019f444953bb721564f86f1a5e2024-02-09T15:22:10ZengMDPI AGSensors1424-82202024-01-0124389210.3390/s24030892Research on the Algorithm of Position Correction for High-Speed Moving Express Packages Based on Traditional Vision and AI VisionNing Dai0Zhehao Lu1Jingchao Chen2Kaixin Xu3Xudong Hu4Yanhong Yuan5Key Laboratory of Modern Textile Machinery & Technology of Zhejiang Province, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaKey Laboratory of Modern Textile Machinery & Technology of Zhejiang Province, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaKey Laboratory of Modern Textile Machinery & Technology of Zhejiang Province, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaKey Laboratory of Modern Textile Machinery & Technology of Zhejiang Province, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaKey Laboratory of Modern Textile Machinery & Technology of Zhejiang Province, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaKey Laboratory of Modern Textile Machinery & Technology of Zhejiang Province, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaThe rapid development of the logistics industry poses significant challenges to the sorting work within this sector. The fast and precise identification of moving express parcels holds immense significance for the performance of logistics sorting systems. This paper proposes a motion express parcel positioning algorithm that combines traditional vision and AI-based vision. In the traditional vision aspect, we employ a brightness-based traditional visual parcel detection algorithm. In the AI vision aspect, we introduce a Convolutional Block Attention Module (CBAM) and Focal-EIoU to enhance YOLOv5, improving the model’s recall rate and robustness. Additionally, we adopt an Optimal Transport Assignment (OTA) label assignment strategy to provide a training dataset based on global optimality for the model training phase. Our experimental results demonstrate that our modified AI model surpasses traditional algorithms in both parcel recognition accuracy and inference speed. The combined approach of traditional vision and AI vision in the motion express parcel positioning algorithm proves applicable for practical logistics sorting systems.https://www.mdpi.com/1424-8220/24/3/892package positioningcombination of traditional vision and AI visionYOLOv5label allocation |
| spellingShingle | Ning Dai Zhehao Lu Jingchao Chen Kaixin Xu Xudong Hu Yanhong Yuan Research on the Algorithm of Position Correction for High-Speed Moving Express Packages Based on Traditional Vision and AI Vision Sensors package positioning combination of traditional vision and AI vision YOLOv5 label allocation |
| title | Research on the Algorithm of Position Correction for High-Speed Moving Express Packages Based on Traditional Vision and AI Vision |
| title_full | Research on the Algorithm of Position Correction for High-Speed Moving Express Packages Based on Traditional Vision and AI Vision |
| title_fullStr | Research on the Algorithm of Position Correction for High-Speed Moving Express Packages Based on Traditional Vision and AI Vision |
| title_full_unstemmed | Research on the Algorithm of Position Correction for High-Speed Moving Express Packages Based on Traditional Vision and AI Vision |
| title_short | Research on the Algorithm of Position Correction for High-Speed Moving Express Packages Based on Traditional Vision and AI Vision |
| title_sort | research on the algorithm of position correction for high speed moving express packages based on traditional vision and ai vision |
| topic | package positioning combination of traditional vision and AI vision YOLOv5 label allocation |
| url | https://www.mdpi.com/1424-8220/24/3/892 |
| work_keys_str_mv | AT ningdai researchonthealgorithmofpositioncorrectionforhighspeedmovingexpresspackagesbasedontraditionalvisionandaivision AT zhehaolu researchonthealgorithmofpositioncorrectionforhighspeedmovingexpresspackagesbasedontraditionalvisionandaivision AT jingchaochen researchonthealgorithmofpositioncorrectionforhighspeedmovingexpresspackagesbasedontraditionalvisionandaivision AT kaixinxu researchonthealgorithmofpositioncorrectionforhighspeedmovingexpresspackagesbasedontraditionalvisionandaivision AT xudonghu researchonthealgorithmofpositioncorrectionforhighspeedmovingexpresspackagesbasedontraditionalvisionandaivision AT yanhongyuan researchonthealgorithmofpositioncorrectionforhighspeedmovingexpresspackagesbasedontraditionalvisionandaivision |