Identifying the vegetation type in Google Earth images using a convolutional neural network: a case study for Japanese b
- PDF / 1,698,794 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 105 Downloads / 265 Views
RESEARCH ARTICLE
BMC Ecology Open Access
Identifying the vegetation type in Google Earth images using a convolutional neural network: a case study for Japanese bamboo forests Shuntaro Watanabe1,3* , Kazuaki Sumi2 and Takeshi Ise1
Abstract Background: Classifying and mapping vegetation are crucial tasks in environmental science and natural resource management. However, these tasks are difficult because conventional methods such as field surveys are highly laborintensive. Identification of target objects from visual data using computer techniques is one of the most promising techniques to reduce the costs and labor for vegetation mapping. Although deep learning and convolutional neural networks (CNNs) have become a new solution for image recognition and classification recently, in general, detection of ambiguous objects such as vegetation is still difficult. In this study, we investigated the effectiveness of adopting the chopped picture method, a recently described protocol for CNNs, and evaluated the efficiency of CNN for plant community detection from Google Earth images. Results: We selected bamboo forests as the target and obtained Google Earth images from three regions in Japan. By applying CNN, the best trained model correctly detected over 90% of the targets. Our results showed that the identification accuracy of CNN is higher than that of conventional machine learning methods. Conclusions: Our results demonstrated that CNN and the chopped picture method are potentially powerful tools for high-accuracy automated detection and mapping of vegetation. Keywords: Convolutional neural network, Vegetation mapping, Google earth imagery Background Classifying and mapping vegetation are essential tasks in environmental science research and natural resource management [1]. Conventional methods (e.g., field surveys, manual interpretation of aerial photographs), however, are not effective for acquiring vegetation data because they are labor-intensive and often economically expensive. Remote sensing technology offers a practical and economical means to acquire information on *Correspondence: [email protected]‑u.ac.jp 1 Field Science Education and Research Center (FSERC), Kyoto University, Kitashirakawaoiwake‑cho, Sakyo‑ku, Kyoto 606‑8502, Japan Full list of author information is available at the end of the article
vegetation cover, especially over large areas [2]. Because of its ability to perform systematic observations at various scales, remote sensing can potentially enable classification and mapping of vegetation at high temporal resolutions. Detection of discriminating visual features is one of the most important steps in almost all computer vision problems, including in the field of remote sensing. Because conventional methods such as support vector machines [3] require hand-designed, time-consuming feature extraction, substantial efforts have been dedicated toward the development of methods for the automatic extraction of features. Recently, deep learning has become a new solution for image recognition
Data Loading...
