基于动静结合互学习的预制梁工序检测方法

doi:10.19678/j.issn.1000-3428.0069033

摘要/Abstract

摘要：

针对预制梁场位置偏远、场景复杂、光线不足, 导致数据采集困难、背景干扰、画质受损等问题, 提出一种基于动静结合互学习的预制梁工序检测方法。在单阶段目标检测模型上建立互学习框架, 分别使用数据扩增技术在空间和时间上对样本干扰的能力, 构造动静结合的双分支子网络, 在网络中引入基于归一化的注意力通道子模块动态地调整通道权重, 以适应真实场景下的环境光照复杂性和噪声干扰随机性。为充分发挥两支子网络各自的优势, 利用目标检测模型真实值的预测边界框不唯一的特性, 提出正样本对齐策略, 实现边界框数量及表征分布的双重对齐。构建一个基于真实场景的预制梁工序数据集, 在自制数据集上的实验结果表明, 该方法的精确率和均值平均精度分别达到了97.2%和97.7%, 推理速度达到了78帧/s, 在满足工业落地应用需求的同时, 为预制梁工序检测识别问题提供了一种有效且可靠的解决方案。

关键词: 动静结合, 候选框互学习, 正样本对齐, 工序检测识别, 目标检测

Abstract:

The remote location of precast beam yards, complex scenes, difficulties in data collection due to poor lighting, background interference, and degraded image quality, all create challenges for precast beam processing. This study proposes a dynamic-static mutual learning detection method for precast beam processing. The study establishes a mutual learning framework on a single-stage object-detection model. It uses data augmentation techniques to enhance the ability of a model to manage sample spatial and temporal interference, constructing a dual-branch subnetwork that combines dynamic and static features. Simultaneously, a normalization-based attention channel submodule is introduced into the network to dynamically adjust the channel weights. Through these techniques, the model becomes more adaptable to the complexity of environmental lighting and the randomness of noise interference in real scenes. To fully leverage the respective advantages of the two subnetworks, the study also proposes a positive sample alignment strategy, leveraging the inherent nonunique characteristics of a single real value's predicted bounding box in the object detection model. Consequently, a dual alignment is achieved, addressing both the quantity and distribution of bounding boxes. A precast beam process dataset based on real scenarios is constructed and used to validate the effectiveness of the proposed method. The precision and mean average precision reach 97.2% and 97.7%, respectively, at an inference speed of 78 frame/s, which meets industrial application demands and offers an effective solution for precast beam process detection and recognition.

Key words: dynamic-static fusion, candidate box mutual learning, positive sample alignment, process detection and recognition, object detection

冯晓飞, 谢诚, 张秀振, 董仕奎, 陈军胜, 叶舒, 钟忺. 基于动静结合互学习的预制梁工序检测方法[J]. 计算机工程, 2025, 51(6): 385-394.

FENG Xiaofei, XIE Cheng, ZHANG Xiuzhen, DONG Shikui, CHEN Junsheng, YE Shu, ZHONG Xian. Detection Method of Precast Beam Process Based on Dynamic-Static Fusion Mutual Learning[J]. Computer Engineering, 2025, 51(6): 385-394.

https://www.ecice06.com/CN/Y2025/V51/I6/385

图/表 12

图1 各类图像数量分布

Fig.1 Distribution of various types of images

图2 算法框架图

Fig.2 Algorithm framework diagram

图3 YOLO-NAM结构

Fig.3 YOLO-NAM structure

图4 数据增强效果示例

Fig.4 Examples of data augmentation effects

图5 数据集示例

Fig.5 Dataset examples

图6 注意力模块验证实验

Fig.6 Validation experiment of attention module

图7 热力图和检测框的可视化效果

Fig.7 Visualization effect of thermal maps and detection boxes

参考文献 27

1	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2016: 779-788.
2	ZHANG Y, XIANG T, HOSPEDALES T M, et al. Deep mutual learning[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2018: 4320-4328.
3	王琳毅, 白静, 李文静, 等. YOLO系列目标检测算法研究进展. 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. Computer Engineering and Applications, 2023, 59 (14): 15- 29.
4	梁华刚, 赵慧霞, 刘丽华, 等. 结合跨层特征融合与级联检测器的防震锤缺陷检测. 中国图象图形学报, 2023, 28 (11): 3485- 3496.
	LIANG H G , ZHAO H X , LIU L H , et al. Combining cross-layer feature fusion with cascade detectors for anti-vibration hammer defects detection. Journal of Image and Graphics, 2023, 28 (11): 3485- 3496.
5	阎光伟, 周香君, 焦润海, 等. 融合先验信息和特征约束的杆塔螺栓缺陷检测. 中国图象图形学报, 2023, 28 (11): 3497- 3508.
	YAN G W , ZHOU X J , JIAO R H , et al. Defect detection of tower bolts by fusion of priori information and feature constraints. Journal of Image and Graphics, 2023, 28 (11): 3497- 3508.
6	闵巍庆, 刘林虎, 刘宇昕, 等. 食品图像识别方法综述. 计算机学报, 2022, 45 (3): 542- 566.
	MIN W Q , LIU L H , LIU Y X , et al. A survey on food image recognition. Chinese Journal of Computers, 2022, 45 (3): 542- 566.
7	季娟娟, 王佳, 陈亚杰, 等. 基于改进YOLO v4的热轧带钢表面缺陷检测. 计算机工程与设计, 2023, 44 (9): 2786- 2793.
	JI J J , WANG J , CHEN Y J , et al. Surface defect detection of hot rolled strip based on improved YOLO v4. Computer Engineering and Design, 2023, 44 (9): 2786- 2793.
8	CAO X H , SU Y X , GENG X , et al. YOLO-SF: YOLO for fire segmentation detection. IEEE Access, 2023, 11, 111079- 111092. doi: 10.1109/ACCESS.2023.3322143
9	黄小平, 冯涛, 郭阳阳, 等. 基于改进YOLO v5s的轻量级奶牛体况评分方法. 农业机械学报, 2023, 54 (6): 287- 296.
	HUANG X P , FENG T , GUO Y Y , et al. Lightweight dairy cow body condition scoring method based on improved YOLO v5s. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54 (6): 287- 296.
10	郑道能. 一种改进的tiny YOLO v3煤矸石快速识别模型. 工矿自动化, 2023, 49 (4): 113- 119.
	ZHENG D N . An improved tiny YOLO v3 rapid recognition model for coal-gangue. Industry and Mine Automation, 2023, 49 (4): 113- 119.
11	王金平, 刘春芽, 郑凤飞, 等. 基于目标检测与语义分割智慧工地施工人员安全状况判断研究. 公路, 2023, 68 (4): 282- 288.
	WANG J P , LIU C Y , ZHENG F F , et al. Research on safety status judgment of smart site construction workers based on target detection and semantic segmentation. Highway, 2023, 68 (4): 282- 288.
12	ZHANG Y, FANG X, LI F, et al. Mutual learning inspired prediction network for video anomaly detection[C]//Proceedings of Conference on Pattern Recognition and Computer Vision. Berlin, Germany: Springer, 2022: 578-593.
13	WU R M, FENG M Y, GUAN W L, et al. A mutual learning method for salient object detection with intertwined multi-supervision[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2019: 8142-8151.
14	MITTAL G, YAGNIK K B, GARG M, et al. SpotGarbage: smartphone app to detect garbage using deep learning[C]//Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. New York, USA: ACM Press, 2016: 940-945.
15	HUANG Y B, QIU C Y, GUO Y, et al. Surface defect saliency of magnetic tile[C]//Proceedings of the 14th IEEE International Conference on Automation Science and Engineering. Washington D. C., USA: IEEE Press, 2018: 612-617.
16	TANG S L, HE F, HUANG X L, et al. Online PCB defect detector on a new PCB defect dataset[EB/OL]. [2023-11-10]. https://arxiv.org/abs/1902.06197v1.
17	WANG C Y, BOCHKOVSKIY A, LIAO H M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2023: 7464-7475.
18	LIU Y C, SHAO Z R, TENG Y Y, et al. NAM: normalization-based attention module[EB/OL]. [2023-11-10]. https://arxiv.org/abs/2111.12419v1.
19	ZHONG Z , ZHENG L , KANG G L , et al. Random erasing data augmentation. Artificial Intelligence, 2020, 34 (7): 13001- 13008.
20	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 21-37.
21	CHEN Z H, YANG C, LI Q F, et al. Disentangle your dense object detector[C]//Proceedings of the 29th ACM International Conference on Multimedia. New York, USA: ACM Press, 2021: 4939-4948.
22	FENG C J, ZHONG Y J, GAO Y, et al. TOOD: task-aligned one-stage object detection[C]//Proceedings of IEEE/CVF International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2021: 3490-3499.
23	LYU C Q, ZHANG W W, HUANG H A, et al. RTMDet: an empirical study of designing real-time object detectors[EB/OL]. [2023-11-10]. https://arxiv.org/abs/2212.07784v2.
24	CHEN S F, SUN P Z, SONG Y B, et al. DiffusionDet: diffusion model for object detection[C]//Proceedings of IEEE/CVF International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2023: 19773-19786.
25	ZHANG S L, WANG X J, WANG J Q, et al. Dense distinct query for end-to-end object detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2023: 7329-7338.
26	LIU Y C, SHAO Z R, HOFFMANN N. Global attention mechanism: retain information to enhance channel-spatial interactions[EB/OL]. [2023-11-10]. https://arxiv.org/abs/2112.05561v1.
27	HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press 2018: 7132-7141.

[1]	黄琦强, 安国成, 熊刚. 基于视觉-语言预训练模型的开集交通目标检测算法[J]. 计算机工程, 2025, 51(6): 375-384.
[2]	李毅, 徐慧英, 朱信忠, 黄晓, 王舒梦, 李悉钰. 基于YOLOv5n模型改进的口罩检测算法: Mask-YOLO[J]. 计算机工程, 2025, 51(6): 297-310.
[3]	奚琦, 王明杰, 魏敬和, 赵伟. 基于改进YOLOv3的航拍小目标检测算法[J]. 计算机工程, 2025, 51(6): 184-192.
[4]	赵小虎, 谢礼逊, 慕灯聪, 张悦. 基于TCM-YOLO网络的金属表面缺陷检测方法[J]. 计算机工程, 2025, 51(6): 338-348.
[5]	周思瑜, 徐慧英, 朱信忠, 黄晓, 盛轲, 曹雨淇, 陈晨. 基于改进YOLOv8n的手机屏幕瑕疵检测算法: PGS-YOLO[J]. 计算机工程, 2025, 51(5): 326-339.
[6]	许华杰, 郑力文, 张品, 秦远卓. 基于多维注意力模块的轻量化混凝土裂缝检测方法[J]. 计算机工程, 2025, 51(5): 351-360.
[7]	黄昆, 齐肇建, 王娟敏, 胡倩, 胡伟超, 皮建勇. 基于改进YOLOv8的密集行人检测模型[J]. 计算机工程, 2025, 51(5): 133-142.
[8]	王晓龙, 江波, 罗润书, 安国成. 基于多信息融合的高速收费站拥堵检测算法[J]. 计算机工程, 2025, 51(5): 377-386.
[9]	李书玮, 黄正翔, 胡云, 刘兴, 卢笑, 郭畅, 吴成中, 王耀南. 基于无源领域自适应的低光照显著性目标检测[J]. 计算机工程, 2025, 51(4): 75-84.
[10]	王泽宇, 徐慧英, 朱信忠, 黄晓, 梁佳杰, 李琛. 基于改进YOLOv8的轻量化鱼苗检测算法: FD-YOLO[J]. 计算机工程, 2025, 51(4): 327-338.
[11]	袁亚剑, 毛力. 一种增强前景的轻量级交通标志检测模型[J]. 计算机工程, 2025, 51(3): 54-63.
[12]	张肇鑫, 黄世泽, 张兵杰, 沈拓. 面向交通场景的运动模糊伪装对抗样本生成方法[J]. 计算机工程, 2025, 51(3): 45-53.
[13]	崔金荣, 叶伟浩, 郑鸿, 刘同来, 齐龙, 徐勇. 基于域自适应NWD-YOLOv5的复杂环境下水稻幼苗计数[J]. 计算机工程, 2025, 51(3): 320-333.
[14]	张元, 吕德芳, 孟建军, 祁文哲. 基于双注意力和GSSN轻量化的钢轨扣件缺陷检测[J]. 计算机工程, 2025, 51(2): 289-299.
[15]	孙浩淼, 李宗民, 肖倩, 孙文洁, 张雯欣. AI-Curling: 一种冰壶现场分析与决策方法[J]. 计算机工程, 2025, 51(2): 102-110.

选择文件类型/文献管理软件名称

选择包含的内容