•  
  •  
 

Corresponding Author

张健南，女，硕士研究生.E-mail：15191867017@163.com

Abstract

In view of the problems that existing monitoring methods for rock mass joints mainly rely on manual identification, with low detection efficiency and strong subjectivity, a detection and segmentation method for rock mass joints was proposed in this paper. The model improved the YOLOv8 algorithm by introducing the multi-scale feature module (MSBlock) and channel prior convolutional attention (CPCA) mechanism to enhance the image recognition accuracy of the existing YOLOv8 network model. By introducing the MSBlock algorithm, features at different scales and levels were fused, which could both capture the fine local details in the image and recognize the image features macroscopically. By introducing the CPCA mechanism, the attention distribution was adaptively adjusted according to the current image features, enabling the network to more flexibly deal with different targets. A total of 4 057 images collected from the AM Highway Project in Equatorial Guinea were trained and recognized. The results indicate that the performance evaluation indicators of the optimized algorithm, including Box (P), Box (R), Mask (P), Mask (R), rIOU, and CDICE, reach 89.4%, 87.1%, 61.6%, 58.9%, 92.8%, and 86.8%, respectively. Compared with the original model, these indicators increase by 4.6 percentage points, 9.5 percentage points, 8.5 percentage points, 12.4 percentage points, 17.5 percentage points, and 1.1 percentage points, respectively. This multi-scale feature fusion algorithm is more accurate and efficient when handling complex images and has better adaptability and robustness.

Publication Date

8-16-2026

DOI

10.14048/j.issn.1671-2579.2026.04.028

First Page

259

Last Page

270

Submission Date

August 2026

Reference

[1]Mao J Y,Song Z P,Fan S Y,et al.Exploration and verification of tunnel stability evolution law under jointed rock mass with various attitudes [J].International Journal of Civil Engineering,2024,22(5):689-703.
[2]Song Z P,Li X,Huo R K,et al.Intelligent early-warming platform for open-pit mining:Current status and prospects[J].Rock Mechanics Bulletin,2023:100098
[3]孙泽,宋战平,岳波,等.基于 SGD算法优化的 BP神经网络围岩参数反演模型研究 [J].隧道建设 (中英文 ),2023,43(12):2066 -2076.Sun Ze,Song Zhanping,Yue Bo,et al.Inversion model for surrounding rock parameters based on back propagation neural networks improved by stochastic gradient descent algorithm [J].Tunnel Construction,2023,43(12):2066 -2076.
[4]宋战平,刘洪珂,郑方,等.考虑层理倾角的硬质砂岩力学行为及破裂响应特征 [J].煤田地质与勘探,2023,51(12):167-175.Song Zhanping,Liu Hongke,Zheng Fang,et al.Mechanical behavior and failure response characteristics of hard sandstones considering bedding dip angles [J].Coal Geology & Exploration,2023,51(12):167-175.
[5]Liu L,Song Z P,Li X.Artificial intelligence in tunnel construction:A comprehensive review of hotspots and frontier topics [J].Geohazard Mechanics,2024,2(1):1-12.
[6]黄鹏,范文哲,胡玲玲,等.基于图像连通域的桥梁裂缝识别算法应用研究 [J].中外公路,2025,45(2):126-132.Huang Peng,Fan Wenzhe,Hu Lingling,et al.Application of bridge crack recognition algorithm based on image connected domain [J].Journal of China & Foreign Highway,2025,45(2):126-132.
[7]陈伟,江志成,田子建,等.基于 YOLOv 8的煤矿井下人员不安全动作检测算法 [J].煤炭科学技术,2024,52(增刊2):267-283.Chen Wei,Jiang Zhicheng,Tian Zijian,et al.Unsafe action detection algorithm of underground personnel in coal mine based on YOLOv 8[J].Coal Science and Technology,2024,52(S2):267-283.
[8]Girshick R,Donahue J,Darrell T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation [C]//2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus:IEEE,2014:580-587.
[9]高洪飞,杨仁松,张运波,等.基于增强 Mask RCNN 算法的隧道掌子面节理智能识别方法与应用 [J].工业建筑,2023,53(增刊 2):583-587.Gao Hongfei,Yang Rensong,Zhang Yunbo,et al.The intelligent identification method and application of tunnel face joints based on the enhanced Mask RCNN algorithm[J].Industrial Construction,2023,53(S2):583-587.
[10]彭磊,周春,胡锋,等.基于深度学习的隧道掌子面节理智能检测与分割 [J].人民长江,2023,54(10):243-250.Peng Lei,Zhou Chun,Hu Feng,et al.Intelligent detection and segmentation of tunnel face joints based on deep learning [J].Yangtze River,2023,54(10):243-250.
[11]张农,袁钰鑫,韩昌良,等.基于 Mask R-CNN 的煤矿巷道掘进迎头裂隙检测与定位算法 [J].采矿与安全工程学报,2023,40(5):925-932.Zhang Nong,Yuan Yuxin,Han Changliang,et al.Research on crack detection and localization algorithm for advancing face in coalmine roadways based on Mask R-CNN [J].Journal of Mining & Safety Engineering,2023,40(5):925-932.
[12]景莹,阮顺领,卢才武,等.基于改进 Mask R-CNN 的露天矿边坡裂隙智能检测算法 [J].重庆大学学报,2023,46(2):67-80.Jing Ying,Ruan Shunling,Lu Caiwu,et al.An intelligent detection method for open-pit slope fracture based on the improved Mask R-CNN [J].Journal of Chongqing University,2023,46(2):67-80.
[13]Liu W,Anguelov D,Erhan D,et al.SSD:Single shot multibox detector [C]//Proceedings of the European Conference on Computer Vision.Chan:Springer,2016:21-37.
[14]邵延华,张铎,楚红雨,等.基于深度学习的 YOLO目标检测综述 [J].电子与信息学报,2022,44(10):3697 -3708.Shao Yanhua,Zhang Duo,Chu Hongyu,et al.A review of YOLO object detection based on deep learning [J].Journal of Electronics & Information Technology,2022,44(10):3697 -3708.
[15]赵南南,高翡晨.基于改进 YOLOv 8的交通场景实例分割算法 [J].计算机工程,2025,51(1):198-207.Zhao Nannan,Gao Feichen.Improved YOLOv 8-based algorithm for instance segmentation in traffic scenes [J].Computer Engineering,2025,51(1):198-207.
[16]赵志宏,郝子晔.改进 YOLOv 8的航拍小目标检测方法:CRP-YOLO [J].计 算 机 工 程 与 应 用,2024,60(13):209-218.Zhao Zhihong,Hao Ziye.Improved YOLOv 8 aerial small target detection method:CRP-YOLO [J].Computer Engineering and Applications,2024,60(13):209-218.
[17]曾志超,徐玥,王景玉,等.基于 SOE-YOLO 轻量化的水面目标检测算法 [J].图学学报,2024,45(4):736-744.Zeng Zhichao,Xu Yue,Wang Jingyu,et al.A water surface target detection algorithm based on SOE-YOLO lightweight network [J].Journal of Graphics,2024,45(4):736-744.
[18]马超伟,张浩,马新明,等.基于改进 YOLOv 8的轻量化小 麦 病 害 检 测 方 法 [J].农 业 工 程 学 报,2024,40(5):187-195.Ma Chaowei,Zhang Hao,Ma Xinming,et al.Method for the lightweight detection of wheat disease using improved YOLOv 8[J].Transactions of the Chinese Society of Agricultural Engineering,2024,40(5):187-195.
[19]高 明 星,关 雪 峰,范 井 丽,等.基 于 改 进 YOLOv 5-DeepSORT 算法的公路路面病害智能识别 [J].森林工程,2023,39(5):161-174.Gao Mingxing,Guan Xuefeng,Fan Jingli,et al.Intelligent recognition of road surface disease based on improved YOLOv 5-DeepSORT algorithm [J].Forest Engineering,2023,39(5):161-174.
[20]Wang G,Chen Y F,An P,et al.UAV-YOLOv 8:A small-object-detection model based on improved YOLOv 8 for UAV aerial photography scenarios [J].Sensors,2023,23(16):7190.
[21]赵小虎,谢礼逊,慕灯聪,等.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.Zhao Xiaohu,Xie Lixun,Mu Dengcong,et al.Metal surface defect detection method based on TCM-YOLO network [J].Computer Engineering,2025,51(6):338-348.
[22]刘洺睿,车奔,董洪波,等.露天煤矿采场无人机遥感图像 小 目 标 检 测 [J].煤 田 地 质 与 勘 探,2023,51(11):132-140.Liu Mingrui,Che Ben,Dong Hongbo,et al.Detection of small objects in open-pit coal mine stopes using UAV remote sensing images [J].Coal Geology & Exploration,2023,51(11):132-140.
[23]Terven J R,Esparza D M C.A comprehensive review of YOLO:From YOLOv 1 to YOLOv 8 and Beyond [J].ArXiv,2023,abs/2304.00501.
[24]周丰峻,康怀强,高伸,等.基于改进的 YOLOv 8模型对地下工程混凝土裂纹的检测识别 [J].计算机工程与科学,2025,47(6):1079 -1089.Zhou Fengjun,Kang Huaiqiang,Gao Shen,et al.Detection and recognition of concrete cracks in underground engineering based on improved YOLOv 8 model [J].Computer Engineering and Science,2025,47(6):1079 -1089.
[25]Bodla N,Singh B,Chellappa R,et al.Soft-NMS:improving object detection with one line of code [C]//Proceedings of the IEEE International Conference on Computer Vision.Venice:IEEE,2017:5562 -5570.
[26]Lou H,Duan X,Guo J,et al.DC-YOLOv 8:Small-size object detection algorithm based on camera sensor [J].Electronics,2023,12(10):2323.
[27]Tang Y Z,Qian Y.High-speed railway track components inspection framework based on YOLOv 8 with high-performance model deployment [J].High-Speed Railway,2024,2(1):42-50.
[28]卢宏涛,张秦川.深度卷积神经网络在计算机视觉中的应用研究综述 [J].数据采集与处理,2016,31(1):1-17.Lu Hongtao,Zhang Qinchuan.Applications of deep convolutional neural network in computer vision [J].Journal of Data Acquisition and Processing,2016,31(1):1-17.
[29]Huang H J,Chen Z G,Zou Y,et al.Channel prior convolutional attention for medical image segmentation[J].Computers in Biology and Medicine,2024,178:108784.
[30]吴胜垚,陈星.图像任务中空间和通道注意力机制研究综述 [J].微电子学与计算机,2025,42(3):1-13.Wu Shengyao,Chen Xing.A review of the spatial and channel attention mechanisms in image tasks [J].Microelectronics & Computer,2025,42(3):1-13.
[31]朱成杰,蔡子正,朱洪波.基于改进 YOLOv 8的路面坑洼检测[J].重庆工商大学学报 (自然科学版 ),2026,43(2):93-100.Zhu Chengjie,Cai Zizheng,Zhu Hongbo.Road surface pothole detection based on improved YOLOv 8[J].Journal of Chongqing Technology and Business University (Natural Science Edition ),2026,43(2):93-100.
[32]Chen Y,Yuan X,Wang J,et al.YOLO-MS:Rethinking multi-scale representation learning for real-time object detection [J].IEEE Trans Pattern Anal Mach Intell,2025,47(6):4240 -4252.
[33]文燕,郭晓倩,唐由之,等.基于 Sobel+匹配滤波联合算法的裂缝识别技术 [J].中外公路,2025,45(4):33-41.Wen Yan,Guo Xiaoqian,Tang Youzhi,et al.Research on crack identification technology based on Sobel+Matched filter joint algorithm [J].Journal of China & Foreign Highway,2025,45(4):33-41.
[34]高亮,饶法强,杨忠民,等.基于语义分割的公路路面裂缝智能识别技术研究 [J].中外公路,2024,44(5):241-247.Gao Liang,Rao Faqiang,Yang Zhongmin,et al.Intelligent recognition technology of highway cracks based on semantic segmentation [J].Journal of China & Foreign Highway,2024,44(5):241-247.
[35]Russell B C,Torralba A,Murphy K P,et al.LabelMe:A database and web-based tool for image annotation [J].International Journal of Computer Vision,2008,77(1):157-173.

Download

Share

COinS