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

Despite much research progress in image semantic segmentation, it remainschallenging under adverse environmental conditions caused by imaginglimitations of visible spectrum. While thermal infrared cameras have severaladvantages over cameras for the visible spectrum, such as operating in totaldarkness, insensitive to illumination variations, robust to shadow effects andstrong ability to penetrate haze and smog. These advantages of thermal infraredcameras make the segmentation of semantic objects in day and night. In thispaper, we propose a novel network architecture, called edge-conditionedconvolutional neural network (EC-CNN), for thermal image semantic segmentation.Particularly, we elaborately design a gated feature-wise transform layer inEC-CNN to adaptively incorporate edge prior knowledge. The whole EC-CNN isend-to-end trained, and can generate high-quality segmentation results with theedge guidance. Meanwhile, we also introduce a new benchmark dataset named"Segment Objects in Day And night"(SODA) for comprehensive evaluations inthermal image semantic segmentation. SODA contains over 7,168 manuallyannotated and synthetically generated thermal images with 20 semantic regionlabels and from a broad range of viewpoints and scene complexities. Extensiveexperiments on SODA demonstrate the effectiveness of the proposed EC-CNNagainst the state-of-the-art methods.

Segmenting Objects in Day and Night:Edge-Conditioned CNN for Thermal Image Semantic Segmentation