High-Speed Classification and Location Algorithm for Logistics Parcels
Author Information
Author(s): Lu Zhehao, Dai Ning, Hu Xudong, Xu Kaixin, Yuan Yanhong
Primary Institution: Zhejiang Sci-Tech University
Hypothesis
This study aims to address the limitations of traditional light curtain positioning methods in logistics sorting workshops amidst high-speed upgrades.
Conclusion
The proposed algorithm significantly reduces the parcel error rate and average parcel supply time compared to traditional methods.
Supporting Evidence
- The algorithm combines traditional visual processing methods with an enhanced version of the lightweight YOLOv5 object detection algorithm.
- Experimental results demonstrate that this model exhibits outstanding performance on a customized logistics parcel dataset.
- The intelligent classification and positioning algorithm significantly reduces both the parcel error rate and average parcel supply time.
Takeaway
This study created a smart system that helps sort packages quickly and accurately using a camera, making it easier for delivery companies to handle lots of parcels.
Methodology
The study utilized a monocular camera and an enhanced YOLOv5 object detection algorithm to classify and locate logistics parcels.
Limitations
Some positioning errors may arise due to the inability to determine the height of parcels, and pre-sorting of taller parcels is essential.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website