The Study of Applying Deep Learning to Vegetation Classification Using UAV Images

被引：0
作者：
Lin D.-Y. [1 ]
Hsieh C.-S. [1 ]
Weng C.-C. [1 ]
机构：
[1] Department of Civil Engineering, National Kaohsiung University of Science and Technology, Kaohsiung
来源：
Journal of the Chinese Institute of Civil and Hydraulic Engineering | 2019年 / 31卷 / 06期
关键词：
Deep learning; UAV images; Vegetation area;
D O I：
10.6652/JoCICHE.201910_31(6).0006
中图分类号：
学科分类号：
摘要：
The advantages of capturing images by UAV are high maneuverability and high resolution. Therefore, this technique is widely used in many fields. However, the process of taking pictures is susceptible to environmental influences, so that it is necessary to consider the characteristics of small view frames, large number of images, and oblique shooting when performing image processing. In addition, UAV imagery often captures a lot of vegetation. However, vegetation has non-uniform distribution and high variability that is susceptible to space-time environment, which may cause problems such as image matching errors and shielding of ground objects. It causes a large error in the vegetation area. Therefore, using the classification method to remove the vegetation area, it can obtain the high-precision numerical surface model to do more application. In recent years, the deep learning technology have the superior classification effect, this study attempts to explore the image classification by the Mask-RCNN algorithm in the deep learning method. However, this algorithm is easy to classify wrongly near image border due to incomplete information. Therefore, this study proposes an overlapped orthophotos method to avoid the problem. And, the vegetation types in the study area are different from the public sample training sets in the network. Here the transfer learning method is used to solve the problem of a small sample set in this study area. Using the process proposed by this research, the experimental results show that the overall classification accuracy is improved to 96%, and the vegetation area can be effectively selected. © 2019, Chinese Institute of Civil and Hydraulic Engineering. All right reserved.
引用
收藏
页码：579 / 588
页数：9
相关论文
共 20 条
  • [1] Vasuki Y., Holden E.J., Kovesi P., Micklethwaite S., Semi-automatic mapping of geological Structures using UAV-based photogrammetric data: An image analysis approach, Computers & Geosciences, 69, pp. 22-32, (2014)
  • [2] Turner D., Lucieer A., De Jong S.M., Time series analysis of landslide dynamics using an unmanned aerial vehicle (UAV), Remote Sensing, 7, 2, pp. 1736-1757, (2015)
  • [3] Cook K.L., An evaluation of the effectiveness of low-cost UAVs and structure from motion for geomorphic change detection, Geomorphology, 278, pp. 195-208, (2017)
  • [4] Gruszczynski W., Matwij W., Cwiakala P., Comparison of low-altitude UAV photogrammetry with terrestrial laser scanning as data-source methods for terrain covered in low vegetation, ISPRS Journal of Photogrammetry and Remote Sensing, 126, pp. 168-179, (2017)
  • [5] LeCun Y., Bengio Y., Hinton G., Deep learning, Nature, 521, pp. 436-444, (2015)
  • [6] Zhao W., Du S., Learning multiscale and deep representations for classifying remotely sensed imagery, ISPRS Journal of Photogrammetry and Remote Sensing, 113, pp. 155-165, (2016)
  • [7] Ma X., Wang H., Wang J., Semisupervised classification for hyperspectral image based on multi-decision labeling and deep feature learning, ISPRS Journal of Photogrammetry and Remote Sensing, 120, pp. 99-107, (2016)
  • [8] Makantasis K., Karantzalos K., Doulamis A., Doulamis N., Deep supervised learning for hyperspectral data classification through convolutional neural networks, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 4959-4962, (2015)
  • [9] Zhang P., Gong M., Su L., Liu J., Li Z., Change detection based on deep feature representation and mapping transformation for multi-spatial-resolution remote sensing images, ISPRS Journal of Photogrammetry and Remote Sensing, 116, pp. 24-41, (2016)
  • [10] Cheng G., Han J., Lu X., Remote sensing image scene classification: benchmark and state of the art, Proceedings of the IEEE, 105, pp. 1865-1883, (2017)
12