English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Accurate segmentation of power lines in various aerial images is veryimportant for UAV flight safety. The complex background and very thinstructures of power lines, however, make it an inherently difficult task incomputer vision. This paper presents PLGAN, a simple yet effective method basedon generative adversarial networks, to segment power lines from aerial imageswith different backgrounds. Instead of directly using the adversarial networksto generate the segmentation, we take their certain decoding features and embedthem into another semantic segmentation network by considering more context,geometry, and appearance information of power lines. We further exploit theappropriate form of the generated images for high-quality feature embedding anddefine a new loss function in the Hough-transform parameter space to enhancethe segmentation of very thin power lines. Extensive experiments andcomprehensive analysis demonstrate that our proposed PLGAN outperforms theprior state-of-the-art methods for semantic segmentation and line detection.

PLGAN: Generative Adversarial Networks for Power-Line Segmentation in Aerial Images