Progressive Cascaded Convolutional Neural Networks for Single Tree Detection with Google Earth Imagery
Progressive Cascaded Convolutional Neural Networks for Single Tree Detection with Google Earth Imagery
复制标题
使用 Google 地球图像进行单树检测的渐进级联卷积神经网络
DOI：
10.3390/rs11151786
复制
发表时间：
2019-07
期刊：
影响因子：
5
通讯作者：
Fan Jing
中科院分区：
文献类型：
--
作者：
Dong Tianyang;Shen Yuqi;Zhang Jian;Ye Yang;Fan Jing
高分辨率遥感图像不仅可以帮助林业行政主管部门实现高精度的森林资源调查、木材产量估算和森林制图，还可以为城市绿化工程提供决策支持。许多学者对如何从遥感图像中检测单株树木进行了研究，提出了多种检测方法。然而，现有的单树检测方法在复杂场景下存在着大量的误用和遗漏、背景和树木在图像数字数据上的数值接近、树冠轮廓不清晰以及光照阴影导致的形状异常等问题。针对这些问题，本文提出了渐进式级联卷积神经网络用于谷歌地球图像的单树检测，并采用三个渐进式分类分支对不同分类难度的树样本进行训练和检测。该方法将三个CNN网络的特征提取模块逐级级联，由分支中的网络层决定是否对样本进行滤波并反馈给特征提取模块，以提高单树检测的精度。此外，利用两阶段训练的机制，提高了模型训练的效率。为了验证该方法的有效性和实用性，分别以中国杭州、泰国盘牙省和美国佛罗里达州的3个森林样地为试验区，给出了区域生长、模板匹配、卷积神经网络和我们的渐进级联卷积神经网络等不同方法的树木检测结果。结果表明，该方法具有较好的检测性能。该方法不仅具有较高的查全率和查全率，而且对不同复杂程度的森林场景具有较好的鲁棒性。3个样地的F1测度分析为81.0%，分别比现有方法提高14.5%、18.9%和5.0%。
High-resolution remote sensing images can not only help forestry administrative departments achieve high-precision forest resource surveys, wood yield estimations and forest mapping but also provide decision-making support for urban greening projects. Many scholars have studied ways to detect single trees from remote sensing images and proposed many detection methods. However, the existing single tree detection methods have many errors of commission and omission in complex scenes, close values on the digital data of the image for background and trees, unclear canopy contour and abnormal shape caused by illumination shadows. To solve these problems, this paper presents progressive cascaded convolutional neural networks for single tree detection with Google Earth imagery and adopts three progressive classification branches to train and detect tree samples with different classification difficulties. In this method, the feature extraction modules of three CNN networks are progressively cascaded, and the network layer in the branches determined whether to filter the samples and feed back to the feature extraction module to improve the precision of single tree detection. In addition, the mechanism of two-phase training is used to improve the efficiency of model training. To verify the validity and practicability of our method, three forest plots located in Hangzhou City, China, Phang Nga Province, Thailand and Florida, USA were selected as test areas, and the tree detection results of different methods, including the region-growing, template-matching, convolutional neural network and our progressive cascaded convolutional neural network, are presented. The results indicate that our method has the best detection performance. Our method not only has higher precision and recall but also has good robustness to forest scenes with different complexity levels. The F1 measure analysis in the three plots was 81.0%, which is improved by 14.5%, 18.9% and 5.0%, respectively, compared with other existing methods.
登录
查看更多内容
影响因子：
1.8
作者：
M. J. Tarp-Johansen
通讯作者：
M. J. Tarp-Johansen
影响因子：
4.4
作者：
Culvenor, DS
通讯作者：
Culvenor, DS
DOI：
--
发表时间：
2011
期刊：
--
影响因子：
--
作者：
J. Novotný
通讯作者：
J. Novotný
DOI：
--
发表时间：
2017-06
期刊：
ArXiv
影响因子：
--
作者：
E. Guirado;S. Tabik;D. Alcaraz‐Segura;J. Cabello;Francisco Herrera
通讯作者：
E. Guirado;S. Tabik;D. Alcaraz‐Segura;J. Cabello;Francisco Herrera
影响因子：
7
作者：
Daniel Peralta;I. Triguero;S. García;Y. Saeys;J. M. Benítez;F. Herrera
通讯作者：
Daniel Peralta;I. Triguero;S. García;Y. Saeys;J. M. Benítez;F. Herrera