天津工业大学学报2026，Vol.45Issue(2)：94-100,7.DOI:10.3969/j.issn.1671-024x.2026.02.012
基于混合CNN-Transformer的堆垛纸箱检测方法
Stacked carton detection method based on hybrid CNN-Transformer
摘要
Abstract
In response to the problems of insufficient spatial information processing and lack of global contextual information caused by multi-layer convolution and pooling operations in convolutional neural networks(CNN),a multi-scale densely stacked carton detection method based on CNN and Transformer is proposed.A feature extraction and fu-sion module is designed,combined with a window self-attention mechanism,to enhance the model's ability to model global features.Cross-scale connections are introduced to fuse more semantic information at different lev-els,and the model has a larger receptive field and better feature fusion ability.A BoxIoU loss function is proposed for bounding box regression,which evaluates the similarity of bounding boxes by calculating the minimum point distance and aspect ratio of bounding boxes,improving the accuracy of the model.Experimental results show that on the SCD dataset of densely stacked cartons,the method achieves an mAP50 of 99.36%and an mAP50-95 of 95.09%,with good detection performance and generalization ability.关键词
深度学习/堆垛纸箱/目标检测/自注意力机制Key words
deep learning/stacked cartons/object detection/self-attention mechanism分类
信息技术与安全科学引用本文复制引用
肖志涛,王宇..基于混合CNN-Transformer的堆垛纸箱检测方法[J].天津工业大学学报,2026,45(2):94-100,7.基金项目
京津冀基础研究合作专项项目(21JCZXJC00170) （21JCZXJC00170）
