[1]高旋,赵亚凤*,胡峻峰,等. 近似联合训练的Faster R-CNN对立木图像的检测与识别[J].西北林学院学报,2020,35(6):249-257.[doi:10.3969/j.issn.1001-7461.2020.06.35]
　GAO Xuan,ZHAO Ya-feng*,HU Jun-feng,et al. Detection and Recognition of the Tree Image by Faster R-CNN of Approximate Joint Training[J].JOURNAL OF NORTHWEST FORESTRY UNIVERSITY,2020,35(6):249-257.[doi:10.3969/j.issn.1001-7461.2020.06.35]
点击复制

 近似联合训练的Faster R-CNN对立木图像的检测与识别()
分享到：

《西北林学院学报》[ISSN:1001-7461/CN:61-1202/S]

卷:
第35卷
期数:
2020年第6期
页码:
249-257
栏目:
出版日期:
2020-11-30

文章信息/Info

Title:
 Detection and Recognition of the Tree Image by Faster R-CNN of Approximate Joint Training
文章编号:
1001-7461(2020)06-0249-09
作者:
 高旋1; 赵亚凤2*; 胡峻峰1; 陈喆2; 陈振2
 (1.东北林业大学 机电工程学院，黑龙江 哈尔滨 150040；2.东北林业大学 信息与计算机工程学院，黑龙江 哈尔滨 150040)
Author(s):
 GAO Xuan1; ZHAO Ya-feng2*; HU Jun-feng1; CHEN Zhe2; CHEN Zhen2
 (1.College of Mechanical and Electrical engineering,Northeast Forestry University,Harbin 150040,Heilongjiang,China; 2.College of Information and Computer Engineering,Northeast Forestry University,Harbin 150040,Heilongjiang,China)
关键词:
 ; 立木目标检测; 近似联合训练; Faster R-CNN; 光照平衡
Keywords:
 ; target tree detection;  approximate joint training;  Faster R-CNN;  light balance
分类号:
TP391.4
DOI:
10.3969/j.issn.1001-7461.2020.06.35
文献标志码:
A
摘要:
 为提高复杂背景下立木图像的识别准确率，提出近似联合训练的Faster R-CNN对立木图像进行目标提取并分类。首先迁移ImageNet上的模型VGG16、ResNet101和MobileNetV2提取图像特征并微调网络，然后构建新的数据集包括7科10种立木图像共2 304张，通过该数据集训练和测试3种网络模型下的Faster R-CNN。结果表明，通过近似联合训练的Faster R-CNN得到的均值平均精度分别是93.64%、92.38%、92.58%，对于不同种属的立木，VGG16网络效果最佳。由于光照会对图像识别造成影响，将光照平衡前后的结果作对比，得到光照平衡后的立木图像识别结果优于平衡前。并利用训练的模型对斜向生长的立木图片进行检测，结果显示生长方向不影响图像识别准确率。证明该方法在具有复杂背景的立木图像上具有良好的效果，对更多立木的识别有一定的参考价值。
Abstract:
 In order to improve the recognition accuracy of the tree image in the complex background,an approximate joint training Faster R-CNN was proposed to extract and classify the tree image.Firstly,VGG16,ResNet101 and MobileNetV2 on ImageNet were transferred to extract image features and fine-tuning the network.Then,a new data set was constructed,including 2 304 pictures of 7 families and 10 tree species.Through the data set,we trained and tested the Faster R-CNN under the three network models.The experimental results showed that values of the mean average precision of Faster R-CNN of approximate joint training were 93.64%,92.38%,and 92.58%,respectively.For different tree specie,VGG16 network was the best.Due to the influence of light note on image recognition,the results before and after light balance were compared.The recognition result of the tree image after light balance was better than before.And the training model was used to detect the oblique growth of the tree image.The results showed that the growth direction did not affect the accuracy of image recognition.It was proved that this method had a good recognition effect on the image of tree with complex background,and had a certain reference value for more tree recognition.

相似文献/References:

[1]李亚藏,梁彦兰,王庆成. 铅对山梨和山荆子光合作用和叶绿素荧光特性的影响[J].西北林学院学报,2012,27(05):21.
　LI Ya-cang,LIANG Yan-lan,WANG Qing-cheng. Influence of Pb on Photosynthesis and Chlorophyll Fluorescence Characteristics in Pyrus ussuriensis and Malus baccata [J].JOURNAL OF NORTHWEST FORESTRY UNIVERSITY,2012,27(6):21.
[2]张小咏,李佳,杨艳昭,等. 基于SWAT模型的长江源区径流模拟[J].西北林学院学报,2012,27(05):38.
　ZHANG Xiao-yong,LI Jia,YANG Yan-zhao,et al. Runoff Simulation of the Catchment of the Headwaters of the Yangtze River Based on SWAT Model[J].JOURNAL OF NORTHWEST FORESTRY UNIVERSITY,2012,27(6):38.
[3]杨红旗,陈广辉,王金林. PVAc改性酚醛树脂制备铝木复合材料研究[J].西北林学院学报,2013,28(01):170.[doi:10.3969/j.issn.1001-7461.2013.01.34]
　YANG Hong-qi,CHEN Guang-hui,WANG Jin-lin. PF Adhesive Modified by PVAc for Manufacturing Technology of Decorative Fiberboard with Aluminum Foils[J].JOURNAL OF NORTHWEST FORESTRY UNIVERSITY,2013,28(6):170.[doi:10.3969/j.issn.1001-7461.2013.01.34]
[4]江涛,李秀荣,谢延军,等. 微波预处理对巨尾桉木材渗透性的影响[J].西北林学院学报,2013,28(01):174.[doi:10.3969/j.issn.1001-7461.2013.01.35]
　JIANG Tao,LI Xiu-rong,XIE Yan-jun,et al. Effects of Microwave Pretreatment on the Permeability of Eucalyptus grandis×Eucalyptus urophylla[J].JOURNAL OF NORTHWEST FORESTRY UNIVERSITY,2013,28(6):174.[doi:10.3969/j.issn.1001-7461.2013.01.35]
[5]牛晓霆,王逢瑚,曹新民. 明清家具匠师原木下料的工艺原则及措施[J].西北林学院学报,2013,28(01):178.[doi:10.3969/j.issn.1001-7461.2013.01.36]
　NIU Xiao-ting,WANG Feng-hu,CAO Xin-min. Techniques and Principles of Log Cuttings of Furniture Makers in Ming and Qing Dynasties[J].JOURNAL OF NORTHWEST FORESTRY UNIVERSITY,2013,28(6):178.[doi:10.3969/j.issn.1001-7461.2013.01.36]
[6]吕金阳,覃卓凯,舒辉,等. 银杉木材构造美学价值[J].西北林学院学报,2013,28(01):183.[doi:10.3969/j.issn.1001-7461.2013.01.37]
　LV Jin-yang,QIN Zhuo-kai,SHU Hui,et al. Esthetical Values in Wood Structure of Cathaya argyrophylla[J].JOURNAL OF NORTHWEST FORESTRY UNIVERSITY,2013,28(6):183.[doi:10.3969/j.issn.1001-7461.2013.01.37]
[7]杨艳红,张海敏,孙景荣. 基于传统文化视角的现代家具设计探析[J].西北林学院学报,2013,28(01):188.[doi:10.3969/j.issn.1001-7461.2013.01.38]
　YANG Yan-hong,ZHANG Hai-min,SUN Jing-rong. Study of Modern Furniture Design Based on Traditional Culture[J].JOURNAL OF NORTHWEST FORESTRY UNIVERSITY,2013,28(6):188.[doi:10.3969/j.issn.1001-7461.2013.01.38]
[8]黄圣游,叶喜. 新中式家具“中式”传统的界定[J].西北林学院学报,2013,28(01):192.[doi:10.3969/j.issn.1001-7461.2013.01.39]
　HUANG Sheng-You,YE Xi. Definition of Traditional Element in New Chinese Style Furniture[J].JOURNAL OF NORTHWEST FORESTRY UNIVERSITY,2013,28(6):192.[doi:10.3969/j.issn.1001-7461.2013.01.39]
[9]韩维生,赵明磊,王宏斌. 基于阈限理论的设计尺度体系[J].西北林学院学报,2013,28(01):197.[doi:10.3969/j.issn.1001-7461.2013.01.40]
　HAN Wei-sheng,ZHAO Ming-lei,WANG Hong-bin. Design Scale System Based on Threshold Theory[J].JOURNAL OF NORTHWEST FORESTRY UNIVERSITY,2013,28(6):197.[doi:10.3969/j.issn.1001-7461.2013.01.40]
[10]宋杰,侯建军,申黎明. 按摩椅按摩头包覆层对按摩舒适性的影响[J].西北林学院学报,2013,28(01):202.[doi:10.3969/j.issn.1001-7461.2013.01.41]
　SONG Jie,HOU Jian-jun,SHEN Li-ming. Influence of Massager Coat Layer of Massage Chairs on the Degree of Comfort[J].JOURNAL OF NORTHWEST FORESTRY UNIVERSITY,2013,28(6):202.[doi:10.3969/j.issn.1001-7461.2013.01.41]

备注/Memo

备注/Memo:
 收稿日期：2019-12-25修回日期：2020-01-07
基金项目：中央高校基本科研业务费专项资金(2572017CB10，2572019BF09)；黑龙江省博士后经费(LBH-Z16011)；黑龙江省自然科学基金项目(QC2015080)。
作者简介：高旋，硕士在读。研究方向：机器视觉。E-mail：gao6754996@163.com
*通信作者：赵亚凤，博士，副教授。研究方向：深度学习和机器视觉。E-mail：nefuzyf@126.com
更新日期/Last Update: