Journal
SENSORS
Volume 21, Issue 13, Pages -Publisher
MDPI
DOI: 10.3390/s21134612
Keywords
character recognition; DETR (detection with transformers); split-attention; multi-scale location coding
Funding
- National Natural Science Foundation of China [51874022]
- Na-tional Key R&D Program of China [2018YFB0704304]
- Beijing Science and Technology Plan Project [Z201100006720004]
Ask authors/readers for more resources
An improved DETR object detection framework is proposed, which uses ResNeSt backbone network and multi-scale location encoding to increase the accuracy of detection and recognition of characters on shipping containers, achieving an overall accuracy of 98.6%.
An improved DETR (detection with transformers) object detection framework is proposed to realize accurate detection and recognition of characters on shipping containers. ResneSt is used as a backbone network with split attention to extract features of different dimensions by multi-channel weight convolution operation, thus increasing the overall feature acquisition ability of the backbone. In addition, multi-scale location encoding is introduced on the basis of the original sinusoidal position encoding model, improving the sensitivity of input position information for the transformer structure. Compared with the original DETR framework, our model has higher confidence regarding accurate detection, with detection accuracy being improved by 2.6%. In a test of character detection and recognition with a self-built dataset, the overall accuracy can reach 98.6%, which meets the requirements of logistics information identification acquisition.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available