YOLO11-LG：结合边界增强方法的玻璃器皿检测

doi:10.3778/j.issn.1002-8331.2503-0090

摘要/Abstract

摘要： 玻璃器皿的精确检测是实现实验室无人化的基础和关键，但由于玻璃器皿的特殊光学属性和内部纹理微弱，使得识别工作面临较大挑战。现有的检测网络缺乏对玻璃器皿的针对性，难以兼顾准确与效率。为了应对这些挑战，研究设计了一种基于YOLO11的高效玻璃器皿检测网络——YOLO11-LG。为了增强对玻璃器皿边界特征的提取，提出边界加强模块，内置了独创性的通道-空间联合注意力机制，通过多维协同处理方式，从通道特征响应与空间结构分布两个层面，显著增强对特征图中高频细节信息的解析能力，精准定位玻璃器皿的边缘拓扑特征，深度强化目标与背景的语义对比度，提升算法在复杂场景中的目标检测精度与泛化能力。此外，还提出了高效融合模块，对原有颈部结构进行了优化，以增强特征融合能力，有效减少了存在遮挡的目标和远处小目标的漏检。实验结果表明，YOLO11-LG网络在检测玻璃器皿时具有出色的性能和实时性，与基准模型相比，所有指标均实现了提升，其准确率、mAP50和mAP50?95分别提高了0.030、0.021和0.034，检测速度为145 FPS，具有良好的实时性。

关键词: 玻璃器皿检测, YOLO, YOLO11-LG, 边界增强

Abstract: The precise detection of glassware is the basis and key to achieving unmanned laboratories. However, due to the special optical properties and weak internal textures of glassware, the identification work faces considerable challenges. The existing detection network lacks specificity for glassware and is difficult to balance accuracy and efficiency. To address these challenges, the research has designed an efficient glassware detection network YOLO11-LG based on YOLO11. To enhance the extraction of the boundary features of glassware, a boundary enhancement module is proposed, which is equipped with an original channel-space joint attention mechanism. Through a multi-dimensional collaborative processing method, from the two levels of channel feature response and spatial structure distribution, the analytical ability of high-frequency detail information in the feature map is significantly enhanced, and the edge topological features of glassware are accurately located. It deeply enhances the semantic contrast between the target and the background to improve the target detection accuracy and generalization ability of the algorithm in complex scenes. In addition, an efficient fusion module is proposed to optimize the original neck structure to enhance the feature fusion ability and effectively reduce the missed detection of occluded targets and distant small targets. The experimental results show that the YOLO11-LG network has excellent performance and real-time performance when detecting glassware. Compared with the benchmark model, all indicators have been improved. Among them, the accuracy rates, mAP50 and mAP50-95 have increased by 0.030、0.021and 0.034 respectively, and the detection speed is 145 FPS, demonstrating good real-time performance.

Key words: glassware detection, YOLO, YOLO11-LG, boundary enhancemen

张泽鸣, 孟祥印, 王孜洲, 周志伟, 刘桓龙. YOLO11-LG：结合边界增强方法的玻璃器皿检测[J]. 计算机工程与应用, 2025, 61(17): 136-146.

ZHANG Zeming, MENG Xiangyin, WANG Zizhou, ZHOU Zhiwei, LIU Huanlong. YOLO11-LG： Glassware Detection Combined with Boundary Enhancement Methodology[J]. Computer Engineering and Applications, 2025, 61(17): 136-146.

参考文献

[1] MENG X Y, WEN J, LI Y, et al. DFNet-Trans: an end-to-end multibranching network for depth estimation for transparent objects[J]. Computer Vision and Image Understanding, 2024, 240: 103914.
[2] 李安达, 吴瑞明, 李旭东. 改进YOLOv7的小目标检测算法研究[J]. 计算机工程与应用, 2024, 60(1): 122-134.
LI A D, WU R M, LI X D. Research on improving YOLOv7’s small target detection algorithm[J]. Computer Engineering and Applications, 2024, 60(1): 122-134.
[3] VIOLA P, JONES M. Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2001: 511-518.
[4] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2005 : 886-893.
[5] LOWE D G. Object recognition from local scale-invariant features[C]//Proceedings of the Seventh IEEE International Conference on Computer Vision. Piscataway: IEEE, 1999: 1150-1157.
[6] YU H, KIM S. SVM tutorial: classification, regression, and ranking[M]. Cham: Springer , 2012.
[7] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 580-587.
[8] LAI P J, FUH C S. Transparent object detection using regions with convolutional neural network[C]//Proceedings of the 1st International Conference on Big Data Analysis and Deep Learning, 2019: 86-93.
[9] KHAING M P, MASAYUKI M. Transparent object detection using convolutional neural network[C]//Proceedings of the Big Data Analysis and Deep Learning Applications, 2019: 86-93.
[10] XIE E Z, WANG W J, WANG W H, et al. Segmenting transparent objects in the wild[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 696-711.
[11] HE H, LI X T, CHENG G L, et al. Enhanced boundary learning for glass-like object segmentation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 15839-15848.
[12] XIE E, WANG W, WANG W, et al. Segmenting transparent object in the wild with transformer[J]. arXiv:2101.08461, 2021.
[13] ZHANG J M, YANG K L, CONSTANTINESCU A, et al. Trans4Trans: efficient transformer for transparent object segmentation to help visually impaired people navigate in the real world[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. Piscataway: IEEE, 2021: 1760-1770.
[14] 张涛, 谢探阳, 李玉梅, 等. 基于改进YOLOv4算法的玻璃杯缺陷识别方法研究[J]. 电子测量技术, 2024, 46(2): 46-51.
ZHANG T, XIE T Y, LI Y M, et al. Research on glass defect recognition method based on improved YOLOv4[J]. Electronic Measurement Technology, 2024, 46(2): 46-51.
[15] ALI M, JAVAID M, NOMAN M, et al. COSNet: a novel semantic segmentation network using enhanced boundaries in cluttered scenes[J]. arXiv:2410.24139, 2024.
[16] SAJJAN S, MOORE M, PAN M K, et al. Clear grasp: 3D shape estimation of transparent objects for manipulation[C]//Proceedings of the IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 2020: 3634-3642.
[17] SUN T Y, ZHANG G D, YANG W M, et al. TROSD: a new RGB-D dataset for transparent and reflective object segmentation in practice[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33(10): 5721-5733.
[18] KALRA A, TAAMAZYAN V, RAO S K, et al. Deep polarization cues for transparent object segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 8599-8608.
[19] YU R N, REN W Y, ZHAO M, et al. Transparent objects segmentation based on polarization imaging and deep learning[J]. Optics Communications, 2024, 555: 130246.
[20] HUO D, WANG J, QIAN Y M, et al. Glass segmentation with RGB-thermal image pairs[J]. IEEE Transactions on Image Processing, 2023, 32: 1911-1926.
[21] 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.
[22] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer International Publishing, 2014: 740-755.
[23] LIU C. Sebica: lightweight spatial and efficient bidirectional channel attention super resolution network[J]. arXiv:2410. 20546, 2024.
[24] CHEN J, MAI H S, LUO L B, et al. Effective feature fusion network in BIFPN for small object detection[C]//Proceedings of the IEEE International Conference on Image Processing. Piscataway: IEEE, 2021: 699-703.
[25] XU H P, WANG Y R, EPPEL S, et al. Seeing glass: joint point cloud and depth completion for transparent objects[C]//Proceedings of the 5th Conference on Robot Learning, 2021: 827-838.
[26] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6): 1137-1149.
[27] FU C Y, LIU W, RANGA A, et al. DSSD: deconvolutional single shot detector[J]. arXiv:1701.06659, 2017.
[28] TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 10778-10787.
[29] ZHANG S F, WEN L Y, BIAN X, et al. Single-shot refinement neural network for object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 4203-4212.
[30] WANG C Y, YEH I H, MARK LIAO H Y. YOLOv9: learning what you want toLearn using programmable gradient information[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer International Publishing, 2025: 1-21.
[31] WANG, A, CHEN H, LIU L H, et al. YOLOv10: real-time end-to-end object detection[J]. arXiv:2405.14458, 2024.
[32] ZHAO Y A, LYU W Y, XU S L, et al. DETRs beat YOLOs on real-time object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2024: 16965-16974.
[33] SELVARAJU R R, COGSWELL M, DAS A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[J]. International Journal of Computer Vision, 2020, 128(2): 336-359.