Interest area selection for navigation based on structured edge detection

Xiao Sun; Ke Shang; ShaoJun Li; Hao Dou; JinWen Tian; Delie Ming

doi:10.1117/12.2205657

Translator Disclaimer

14 December 2015 Interest area selection for navigation based on structured edge detection

Xiao Sun, Ke Shang, ShaoJun Li, Hao Dou, JinWen Tian, Delie Ming

Author Affiliations +

Proceedings Volume 9812, MIPPR 2015: Automatic Target Recognition and Navigation; 98120M (2015) https://doi.org/10.1117/12.2205657
Event: Ninth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2015), 2015, Enshi, China

Abstract

The scene matching based navigation is an important precision navigation technology for unmanned aerial vehicles (UAV). Selection of interest area where reference image is made has an important influence on the precision of matching result besides the performance of match algorithm. In this paper, a method to select interest area based on structured edge detection is proposed. We use a data driven approach that classifies each pixel with a typical structured edge label. We propose a method that combines these labels into a feature measuring suitable to match of a region. Then a SVM classifier is trained to classify the features and get the final result of the selection of interest area. The experimental result shows that the proposed method is valid and effective.

Citation Download Citation

Xiao Sun, Ke Shang, ShaoJun Li, Hao Dou, JinWen Tian, and Delie Ming "Interest area selection for navigation based on structured edge detection", Proc. SPIE 9812, MIPPR 2015: Automatic Target Recognition and Navigation, 98120M (14 December 2015); https://doi.org/10.1117/12.2205657

ACCESS THE FULL ARTICLE