Abstract
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.
Highlights
With the development of remote sensing technology, there is a growing demand for the accurate detection of single trees based on high-resolution remote sensing images
To verify the validity of this method, the four methods of region-growing [30], template-matching [11], convolutional neural network (CNN) [21], and the progressive cascaded convolutional neural network were compared in these three test areas
The network parameters of the convolutional neural network and progressive cascaded network were completed by automatic model training extraction, which did not need to be set up artificially
Summary
With the development of remote sensing technology, there is a growing demand for the accurate detection of single trees based on high-resolution remote sensing images. Culvenor [6] proposed a method based on image texture information to detect a single tree They believed that the tree canopy vertex is a maximum value in the image, while the surrounding points are smaller. Pouliot et al [8] designed an adaptive multi-scale single tree detection method They selected the best Gaussian smoothing parameters according to the relationship between the number of local maximum values and the value of the Gaussian smoothing parameters, and used the extracted local maximum points as a single tree through the adaptive window size. The red dotted line diagram graph shows that the sample output, which is most classified as tree, remains a higher probability, it is labeled as the most easy-to-classify positive sample of the first branch and eliminated. The third branch can be dedicated to training the most hard-to-classify samples
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call