Welcome to Smart Agriculture

Smart Agriculture ›› 2019, Vol. 1 ›› Issue (4): 50-61.doi: 10.12133/j.smartag.2019.1.4.201908-SA005

• Information Perception and Acquisition • Previous Articles     Next Articles

Edge extraction method of remote sensing UAV terrace image based on topographic feature

Yang Yanan1, Kang Yang1, Fan Xiao1, Chang Yadong1, Zhang Hanwen2, Zhang Hongming1()   

  1. 1. College of Information Engineering, Northwest A & F University, Yangling 712100, China
    2. College of Mechanical and Electronic Engineering, Northwest A & F University, Yangling 712100, China
  • Received:2019-08-19 Revised:2019-11-15 Online:2019-10-30

Abstract:

Terraces achieve water storage and sediment function by slowing down the slope and soil erosion. This kind of terraced or wave-section farmland built along the contour line on is a high-yield and stable farmland facility with key construction in the dry farming area. It provides a strong guarantee for increasing grain production and farmers' income. In recent years, Gansu province has carried out a large amount of construction on terraces, however, due to the poor quality of the previous construction and management, the terraced facilities are in danger of being destroyed. In order to prevent and repair the terraces, it is necessary to timely and accurately extract the terrace information. The segmentation of terraces can be obtained by edge extraction, but the effect of satellite data is not ideal. With the continuous development of remote sensing technology of drones, the acquisition of high-precision terrace topographic information has become possible. In this research, the slope is extracted from the digital elevation model data in the data preprocessing stage, then the orthophoto data of the three experimental areas are merged with the corresponding slope data, respectively. Then the rough edge extraction method based on Canny operator and the fine edge extraction method based on multi-scale segmentation are used to perform edge detection on two data sources. Finally, the influence of slope on the extraction of terraced edges of remote sensing images of UAVs was analyzed based on the overall accuracy of edge detection and user accuracy. The experimental results showed that, in the rough edge extraction method, the data source accuracy of the fusion slope and image was improved by 23.97% in the OA precision evaluation, and the average improvement in the UV accuracy was 20.68%. In the fine edge extraction method, the accuracy based on the data source 2 was also increased by 17.84% on average in the OA accuracy evaluation of the data source 1, and by an average of 19.0% in the UV accuracy evaluation. The research shows that in the extraction of terraced edges of UAV remote sensing images, adding certain terrain features can achieve better edge extraction results.

Key words: UAV image, terrace, edge extraction, slope, region segmentation

CLC Number: