

浏览全部资源
扫码关注微信
上海理工大学 健康科学与工程学院, 上海 200093
Received:28 December 2025,
Revised:2026-01-23,
Published:05 February 2026
移动端阅览
CHEN Yucong, HE Hong, LI Zexu, et al. MLC-YOLO based key object detection method for origami action[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(2): 240-252.
CHEN Yucong, HE Hong, LI Zexu, et al. MLC-YOLO based key object detection method for origami action[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(2): 240-252. DOI: 10.37188/CJLCD.2025-0255. CSTR: 32172.14.CJLCD.2025-0255.
由于简易精神状态检查(CMMSE)量表中“三步指令”的人工评分存在评分者间及自身内部差异,且过程耗时,提出一种基于MLC-YOLO的目标检测方法,旨在实现该动作的自动精准检测。首先,对人体关键部位和纸张进行多级分类目标检测,采用同类极大置信度选择简化后处理,保证同类目标的唯一性;其次,设计自适应空间信道解耦模块,实现高效降采样;然后,在C3中引入幽灵卷积和小波变换,提升多尺度特征提取的效率与能力;最后,针对小目标检测层,引入空间和通道协同注意力,提高复杂场景下的准确率与召回率。实验结果表明:该方法的mAP95达61.8%,较原模型提升5.6%,参数量减少51.52%,证明了方法的有效性,为目标唯一和多级分类的目标检测问题提供了新思路,为MMSE中的“三步指令”的自动评分提供有效的目标检测方法。
To address the inter-rater and intra-rater variability, as well as the time-consuming nature of manual scoring for the “three-step command” in the Mini-Mental State Examination(MMSE), an object detection method based on MLC-YOLO is proposed to achieve automatic and precise detection of this action. First, multi-level classification object detection is performed on key human body parts and paper, and a same-class maximum confidence selection strategy is adopted to simplify post-processing and ensure the uniqueness of targets of the same class. Second, an adaptive spatial-channel decoupling module is designed to achieve efficient downsampling. Then, Ghost convolution and wavelet transform are introduced into the C3 module to enhance the efficiency and capability of multi-scale feature extraction. Finally, for the small object detection layer, spatial and channel collaborative attention is introduced to improve precision and recall in complex scenes.Experimental results indicate that the mAP95 of the proposed method reaches 61.8%, an increase of 5.6% compared to the original model, while the parameter count is reduced by 51.52%. It proves the effectiveness of the method, offering a new approach for object detection problems involving unique targets and multi-level classification, and providing an effective object detection method for the automatic scoring of the “three-step command” in MMSE.
王廉源 , 杨毅 , 丛慧文 , 等 . 不同MMSE评分下阿尔兹海默病发病风险因素的贝叶斯分位数回归联合模型分析 [J]. 吉林大学学报(医学版) , 2023 , 49 ( 2 ): 395 - 401 .
WANG L Y , YANG Y , CONG H W , et al . Bayesian quantile regression joint model analysis on risk factors of Alzheimer's disease in people with different MMSE scores [J]. Journal of Jilin University (Medicine Edition) , 2023 , 49 ( 2 ): 395 - 401 . (in Chinese)
ANNADANAM A , KAHANA E , ANDREWS C , et al . Comparison of machine and human expert evaluation of capsulorrhexis creation performance through analysis of surgical video recordings [J]. Clinical Ophthalmology , 2024 , 18 : 943 - 950 . doi: 10.2147/opth.s444201 http://dx.doi.org/10.2147/opth.s444201
WANG Y T , SHEN X , HU S X , et al . Self-supervised transformers for unsupervised object discovery using normalized cut [C]// Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans : IEEE , 2022 : 14543 - 14553 . doi: 10.1109/cvpr52688.2022.01414 http://dx.doi.org/10.1109/cvpr52688.2022.01414
MAO W A , GE Y T , SHEN C H , et al . TFPose: direct human pose estimation with transformers [J/OL]. arXiv , 2021 : 2103 . 15320 . doi: 10.1007/978-3-031-20068-7_5 http://dx.doi.org/10.1007/978-3-031-20068-7_5
吕情深 . 基于目标检测的中国手语识别研究 [D]. 乌鲁木齐 : 新疆大学 , 2020 .
LYU Q S . Research on Chinese sign language recognition based on object detection [D]. Urumqi : Xinjiang University , 2020 . (in Chinese)
杨锋 , 丁之桐 , 邢蒙蒙 , 等 . 深度学习的目标检测算法改进综述 [J]. 计算机工程与应用 , 2023 , 59 ( 11 ): 1 - 15 . doi: 10.3778/j.issn.1002-8331.2209-0312 http://dx.doi.org/10.3778/j.issn.1002-8331.2209-0312
YANG F , DING Z T , XING M M , et al . Review of object detection algorithm improvement in deep learning [J]. Computer Engineering and Applications , 2023 , 59 ( 11 ): 1 - 15 . (in Chinese) . doi: 10.3778/j.issn.1002-8331.2209-0312 http://dx.doi.org/10.3778/j.issn.1002-8331.2209-0312
汤伟 , 王锦韫 , 张龙 . 基于改进Faster R-CNN的纸病检测算法 [J]. 包装工程 , 2023 , 44 ( 21 ): 260 - 266 .
TANG W , WANG J Y , ZHANG L . Paper defect detection algorithm based on improved Faster R-CNN [J]. Packaging Engineering , 2023 , 44 ( 21 ): 260 - 266 . (in Chinese)
JIA P , TIAN D P , WANG Y T , et al . Airborne optical imaging technology: a road map in CIOMP [J]. Light: Science & Applications , 2025 , 14 ( 1 ): 119 . doi: 10.1038/s41377-025-01776-3 http://dx.doi.org/10.1038/s41377-025-01776-3
王琳毅 , 白静 , 李文静 , 等 . YOLO系列目标检测算法研究进展 [J]. 计算机工程与应用 , 2023 , 59 ( 14 ): 15 - 29 .
WANG L Y , BAI J , LI W J , et al . Research progress of YOLO series target detection algorithms [J]. Computer Engineering and Applications , 2023 , 59 ( 14 ): 15 - 29 . (in Chinese)
WONG A , FAMUORI M , SHAFIEE M J , et al . YOLO Nano: a highly compact you only look once convolutional neural network for object detection [C]// Proceedings of 2019 Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing-NeurIPS Edition (EMC2-NIPS) . Vancouver : IEEE , 2019 : 22 - 25 . doi: 10.1109/emc2-nips53020.2019.00013 http://dx.doi.org/10.1109/emc2-nips53020.2019.00013
KHOKHLOV I , DAVYDENKO E , OSOKIN I , et al . Tiny-YOLO object detection supplemented with geometrical data [C]// Proceedings of 2020 IEEE 91st Vehicular Technology Conference . Antwerp : IEEE , 2020 : 1 - 5 . doi: 10.1109/vtc2020-spring48590.2020.9128749 http://dx.doi.org/10.1109/vtc2020-spring48590.2020.9128749
陈仁祥 , 邱天然 , 杨黎霞 , 等 . 改进YOLOv7的服务机器人密集遮挡目标识别 [J]. 光学 精密工程 , 2024 , 32 ( 10 ): 1595 - 1605 . doi: 10.37188/ope.20243210.1595 http://dx.doi.org/10.37188/ope.20243210.1595
CHEN R X , QIU T R , YANG L X , et al . A method for dense occlusion target recognition of service robots based on improved YOLOv7 [J]. Optics and Precision Engineering , 2024 , 32 ( 10 ): 1595 - 1605 . (in Chinese) . doi: 10.37188/ope.20243210.1595 http://dx.doi.org/10.37188/ope.20243210.1595
林珊玲 , 张雪 , 陈燕 , 等 . 融合全局信息与双域注意力机制的光学遥感飞机目标检测 [J]. 光学 精密工程 , 2024 , 32 ( 20 ): 3085 - 3098 . doi: 10.37188/ope.20243220.3085 http://dx.doi.org/10.37188/ope.20243220.3085
LIN S L , ZHANG X , CHEN Y , et al . Integrating global information and dual-domain attention mechanism for optical remote sensing aircraft target detection [J]. Optics and Precision Engineering , 2024 , 32 ( 20 ): 3085 - 3098 . (in Chinese) . doi: 10.37188/ope.20243220.3085 http://dx.doi.org/10.37188/ope.20243220.3085
吕学涵 , 李富 , 祁铭瑞 , 等 . 基于改进YOLOv11s的无人机小目标检测算法 [J]. 液晶与显示 , 2025 , 40 ( 11 ): 1744 - 1756 . doi: 10.37188/cjlcd.2025-0193 http://dx.doi.org/10.37188/cjlcd.2025-0193
LÜ X H , LI F , QI M R , et al . Target detection algorithm based on improved YOLOv11s UAV aerial image [J]. Chinese Journal of Liquid Crystals and Displays , 2025 , 40 ( 11 ): 1744 - 1756 . (in Chinese) . doi: 10.37188/cjlcd.2025-0193 http://dx.doi.org/10.37188/cjlcd.2025-0193
陈怡 . 健康医疗数据共享与个人信息保护研究 [J]. 情报杂志 , 2023 , 42 ( 5 ): 192 - 199 .
CHEN Y . Research on healthcare data sharing and personal information protection [J]. Journal of Intelligence , 2023 , 42 ( 5 ): 192 - 199 . (in Chinese)
WANG C Y , YEH I H , LIAO H Y M . YOLOv9: Learning what you want to learn using programmable gradient information [C]// Proceedings of the 18th European Conference Computer Vision . Milan : Springer , 2025 : 1 - 21 . doi: 10.1007/978-3-031-72751-1_1 http://dx.doi.org/10.1007/978-3-031-72751-1_1
WANG A , CHEN H , LIU L H , et al . YOLOv10: Real-time end-to-end object detection [C]// Proceedings of the 38th International Conference on Neural Information Processing Systems . Vancouver : Curran Associates Inc. , 2024 : 3429 . doi: 10.52202/079017-3429 http://dx.doi.org/10.52202/079017-3429
HAN K , WANG Y H , TIAN Q , et al . GhostNet: more features from cheap operations [C]// Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle : IEEE , 2020 . doi: 10.1109/cvpr42600.2020.00165 http://dx.doi.org/10.1109/cvpr42600.2020.00165
TULI S , DASGUPTA I , GRANT E , et al . Are convolutional neural networks or transformers more like human vision? [C]// Proceedings of the 43rd Annual Meeting of the Cognitive Science Society . Online : Cognitive Science Society.org , 2021 .
FINDER S E , AMOYAL R , TREISTER E , et al . Wavelet convolutions for large receptive fields [C]// Proceedings of the 18th European Conference Computer Vision . Milan : Springer , 2025 : 363 - 380 . doi: 10.1007/978-3-031-72949-2_21 http://dx.doi.org/10.1007/978-3-031-72949-2_21
SI Y Z , XU H Y , ZHU X Z , et al . SCSA: exploring the synergistic effects between spatial and channel attention [J]. Neurocomputing , 2025 , 634 : 129866 . doi: 10.1016/j.neucom.2025.129866 http://dx.doi.org/10.1016/j.neucom.2025.129866
倪广兴 , 徐华 , 王超 . 融合改进YOLOv5及Mediapipe的手势识别研究 [J]. 计算机工程与应用 , 2024 , 60 ( 7 ): 108 - 118 .
NI G X , XU H , WANG C . Research on gesture recognition based on improved YOLOv5 and Mediapipe [J]. Computer Engineering and Applications , 2024 , 60 ( 7 ): 108 - 118 . (in Chinese)
ZAIDI S S A , ANSARI M S , ASLAM A , et al . A survey of modern deep learning based object detection models [J]. Digital Signal Processing , 2022 , 126 : 103514 . doi: 10.1016/j.dsp.2022.103514 http://dx.doi.org/10.1016/j.dsp.2022.103514
FU R G , HU Q Y , DONG X H , et al . Axiom-based Grad-CAM: towards accurate visualization and explanation of CNNs [C]// Proceedings of the 31st British Machine Vision Conference . Online : BMVA Press , 2020 . doi: 10.5244/c.34.146 http://dx.doi.org/10.5244/c.34.146
0
Views
331
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621