Study on Tree Ring Instance Segmentation and Information Detection Based on Improved YOLOv8

WANG Pinbo; WANG Yuchen; WANG Shuangyong; ZHOU Haibin

doi:10.12326/j.2096-9694.2025008

KEY SCIENTIFIC RESEARCH BASE OF HISTORICAL BUILDING WOOD | Views : 0 下载量: CSCD: 0 CNKI被引量: 0 Crossref: 0 Wos: 0 Scopus: 0 更多指标

PDF
Export
Share
Collection
Album

Study on Tree Ring Instance Segmentation and Information Detection Based on Improved YOLOv8
1.Institute of Wood Industry，Chinese Academy of Forestry，Beijing 100091，China
2.Nanjing Forestry University， Nanjing 210037，Jiangsu，China
3.Key Scientific Research Base of Wood Science and Conservation of Historical Building， State Administration of Cultural Heritage，Beijing 100091，China
Vol. 39, Issue 3, Pages: 7-18(2025)
DOI： 10.12326/j.2096-9694.2025008
稿件说明：

移动端阅览

王品博,王雨晨,王双永等.基于改进YOLOv8的树木年轮实例分割及信息检测方法[J].木材科学与技术,2025,39(03):7-18. DOI： 10.12326/j.2096-9694.2025008.

WANG Pinbo,WANG Yuchen,WANG Shuangyong,et al.Study on Tree Ring Instance Segmentation and Information Detection Based on Improved YOLOv8[J].Chinese Journal of Wood Science and Technology,2025,39(03):7-18. DOI： 10.12326/j.2096-9694.2025008.

摘要

在气候学、生态学、考古学等诸多领域，树木年轮蕴含的环境变迁与历史演替信息具有不可替代的研究价值。为解决传统年轮检测方法存在效率低、易受人为因素干扰等问题，研究提出DCW-YOLOv8年轮实例分割模型，运用可扩张残差（Dilation-wise Residual，DWR）注意力模块、轻量级通用上采样算子（Content-Aware ReAssembly of Features，CARAFE）、动态非单调聚焦机制边界框损失函数（Weighted Interpolation of Sequential Evidence for Intersection over Union，Wise-IoU）组合改进，并设计一种依据模型掩码获取年轮数量与宽度信息的检测方法。消融试验和前沿模型对比试验结果表明，DCW-YOLOv8模型掩码平均精度mAP@0.50、mAP@0.50∶0.95提升，达到86.4%、53.6%，优于同类算法；注意力可视化比较结果表明，DCW-YOLOv8对年轮特征注意力更强；年轮信息检测结果表明，年轮数量检测准确率达到86.2%，年轮宽度检测误差在±0.5 mm范围内的占70%，总体平均误差为0.295 mm。研究提出的DCW-YOLOv8模型为年轮自动化检测提供新的思路和方法。

Abstract

In climatology

ecology

and archaeology

tree rings hold irreplaceable value for studying environmental change and historical succession. To improve the efficiency and reduce human interference in traditional tree-ring detection

this study proposes DCW-YOLOv8

an instance segmentation model enhanced with dilation-wise residual (DWR) attention module

lightweight CARAFE upsampling

and dynamic Wise-IoU loss. A detection method using model-generated masks is designed to quantify ring counts and widths. The ablation and comparative experiments show DCW-YOLOv8 achieves superior mask mAP (86.4% for mAP@0.50

53.6% for mAP@0.50∶0.95) versus state-of-the-art models. Attention visualization confirms stronger focus on tree-ring features. Detection results include 86.2% count-accuracy

70% width measurements within ±0.5 mm error

and a mean width error of 0.295 mm. This model provides a novel automated approach for tree-ring analysis.

关键词

Keywords

references

朱晓龙 , 陈庆美 , 吕爱锋 , 等 . 利用树轮揭示人类活动对柴达木盆地巴音河径流量的影响 [J ] . 应用生态学报 , 2021 , 32 ( 10 ): 3653 - 3660 .

ZHU X L , CHEN Q M , LYU A F , et al . Impacts of human activity on Bayin River runoff as revealed by tree rings in Qaidam Basin, China [J ] . Chinese Journal of Applied Ecology , 2021 , 32 ( 10 ): 3653 - 3660 .

韦晓旭 , 彭剑峰 , 彭猛 , 等 . 中国南北过渡带油松径向生长对气候因子的响应研究：以鸡公山国家级自然保护区为例 [J ] . 地理科学 , 2024 , 44 ( 9 ): 1643 - 1652 .

WEI X X , PENG J F , PENG M , et al . Response of Pinus tabuliformis radial growth to climate factors in the north-south transition zone of China: case study in the Jigong Mountain [J ] . Scientia Geographica Sinica , 2024 , 44 ( 9 ): 1643 - 1652 .

MARCELO-PEÑA J L , ROIG F A , GOODWIN Z A , et al . Characterizing growth rings in the trees of perú: a wood anatomical overview for potential applications in dendroecological-related fields [J ] . Dendrochronologia , 2020 , 62 : 125728 .

RYBNÍČEK M , KOČÁR P , MUIGG B , et al . World’s oldest dendrochronologically dated archaeological wood construction [J ] . Journal of Archaeological Science , 2020 , 115 : 105082 .

ESPER J , COOK E R , SCHWEINGRUBER F H . Low-frequency signals in long tree-ring chronologies for reconstructing past temperature variability [J ] . Science , 2002 , 295 ( 5563 ): 2250 - 2253 .

李天昊 . 古建筑木结构Benchmark平台构建及监测方法研究 [D ] . 北京 : 北京交通大学 , 2022 .

徐文君 , 马超 , 吕立群 , 等 . 西藏热玛沟流域冰川型泥石流历史的树木年代学重建 [J ] . 山地学报 , 2025 , 43 ( 1 ): 122 - 131 .

XU W J , MA C , LYU L Q , et al . Dendrochronological interpretation of glacial debris flow history in the Rema Gully, Xizang, China [J ] . Mountain Research , 2025 , 43 ( 1 ): 122 - 131 .

MANNING S W , LORENTZEN B , BAKIRTZIS N , et al . Progress towards a Byzantine-medieval historic buildings tree-ring chronology from Cyprus using dendrochronology and radiocarbon [J ] . Radiocarbon , 2024 , 66 ( 6 ): 1643 - 1661 .

黄磊 , 王雨晨 , 韩旭 , 等 . 应县木塔普拍枋用材方法与残损状况分析 [J ] . 木材科学与技术 , 2024 , 38 ( 4 ): 8 - 19 .

HUANG L , WANG Y C , HAN X , et al . Material application method and component damage analysis of the Pu-Pai Fang in Yingxian wooden pagoda [J ] . Chinese Journal of Wood Science and Technology , 2024 , 38 ( 4 ): 8 - 19 .

彭钟通 , 郭明明 , 张远东 , 等 . 升温突变对川西道孚林线川西云杉和鳞皮冷杉生长的影响 [J ] . 生态学报 , 2021 , 41 ( 20 ): 8202 - 8211 .

PENG Z T , GUO M M , ZHANG Y D , et al . Effects of abrupt warming on Picea likiangensis var. balfouriana and Abies squamata growth at tree line in Dafu, Sichuan, China [J ] . Acta Ecologica Sinica , 2021 , 41 ( 20 ): 8202 - 8211 .

HU X Y , ZHENG Y L , XING D , et al . Research on tree ring micro-destructive detection technology based on digital micro-drilling resistance method [J ] . Forests , 2022 , 13 ( 7 ): 1139 .

潘虹 , 卢军 , 雷相东 , 等 . 基于针刺仪平稳卡尔曼滤波器的树木年龄估计 [J ] . 林业科学 , 2021 , 57 ( 6 ): 14 - 23 .

PAN H , LU J , LEI X D , et al . Tree age estimation based on resistograph stationary Kalman filter [J ] . Scientia Silvae Sinicae , 2021 , 57 ( 6 ): 14 - 23 .

姚建峰 , 赵燕东 , 符利勇 , 等 . 基于微钻阻力的树木年轮测量方法研究 [J ] . 农业机械学报 , 2022 , 53 ( 4 ): 52 - 59 .

YAO J F , ZHAO Y D , FU L Y , et al . Tree-rings measurement method based on micro drill resistance [J ] . Transactions of the Chinese Society for Agricultural Machinery , 2022 , 53 ( 4 ): 52 - 59 .

VAN DEN BULCKE J , BOONE M A , DHAENE J , et al . Advanced X-ray CT scanning can boost tree ring research for earth system sciences [J ] . Annals of Botany , 2019 , 124 ( 5 ): 837 - 847 .

刘志洋 , 韩忠玲 , 程勇翔 , 等 . 基于CT扫描的多枝柽柳年轮生长参数测量及验证 [J ] . 生态学报 , 2024 , 44 ( 20 ): 9401 - 9411 .

LIU Z Y , HAN Z L , CHENG Y X , et al . Measurement and verification of tree-ring growth parameters of Tamarix ramosissima based on computed tomography scanning [J ] . Acta Ecologica Sinica , 2024 , 44 ( 20 ): 9401 - 9411 .

LIN Q Z , HE T , SUN Y K , et al . A computer-aided method for identifying the presence of softwood growth ring boundaries [J ] . PLoS One , 2020 , 15 ( 9 ): e0235727 .

姚建峰 , 郭旭展 , 宋新宇 , 等 . 基于灰度图像的峰谷年轮识别方法研究 [J ] . 信阳师范学院学报(自然科学版) , 2022 , 35 ( 3 ): 475 - 480 .

YAO J F , GUO X Z , SONG X Y , et al . Research on peak-valley tree-ring recognition method based on gray image [J ] . Journal of Xinyang Normal University (Natural Science Edition) , 2022 , 35 ( 3 ): 475 - 480 .

YU X Z , ZHONG L H , ZHOU H , et al . Tree-ring based forest model calibrations with a deep learning algorithm [J ] . Forest Ecology and Management , 2024 , 569 : 122154 .

ABDELJABER O , HABITE T , OLSSON A . Automatic estimation of annual ring profiles in Norway spruce timber boards using optical scanning and deep learning [J ] . Computers & Structures , 2023 , 275 : 106912 .

KIM D , KO C , KIM D . Method for detecting tree ring boundary in conifers and broadleaf trees using Mask R-CNN and linear interpolation [J ] . Dendrochronologia , 2023 , 79 : 126088 .

LI W , SOLIHIN M I , NUGROHO H A . RCA: YOLOv8-based surface defects detection on the inner wall of cylindrical high-precision parts [J ] . Arabian Journal for Science and Engineering , 2024 , 49 ( 9 ): 12771 - 12789 .

李琳琳 , 孙海龙 . 基于YOLOv8的林区行人目标检测研究 [J ] . 森林工程 , 2025 , 41 ( 1 ): 138 - 150 .

LI L L , SUN H L . Forest pedestrian detection based on improved YOLOv8 [J ] . Forest Engineering , 2025 , 41 ( 1 ): 138 - 150 .

刘进军 , 李磊磊 , 张昊宇 , 等 . 基于改进YOLOv7算法的建筑垃圾分类检测 [J ] . 环境工程学报 , 2024 , 18 ( 1 ): 270 - 279 .

LIU J J , LI L L , ZHANG H Y , et al . Construction waste classification and detection algorithm based on improved YOLOv7 [J ] . Chinese Journal of Environmental Engineering , 2024 , 18 ( 1 ): 270 - 279 .

DUAN Z Q , XIE T , WANG L C , et al . Microalgae detection based on improved YOLOv5 [J ] . IET Image Processing , 2024 , 18 ( 10 ): 2602 - 2613 .

Alert me when the article has been cited

提交

Detecting Method for Particleboard Surface Defects Based on the Lite-YOLOv5s Model

Application of Machine Vision in Manufacturing of Wood Products

Detecting Method of the Wood Surface Defects Based on Modified LeNet-5 Model

Research Progress of Convolutional Neural Network in Wood Defect Detection