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

Automatically extracting roads from satellite imagery is a fundamental yetchallenging computer vision task in the field of remote sensing. Pixel-wisesemantic segmentation-based approaches and graph-based approaches are twoprevailing schemes. However, prior works show the imperfections that semanticsegmentation-based approaches yield road graphs with low connectivity, whilegraph-based methods with iterative exploring paradigms and smaller receptivefields focus more on local information and are also time-consuming. In thispaper, we propose a new scheme for multi-task satellite imagery roadextraction, Patch-wise Road Keypoints Detection (PaRK-Detect). Building on topof D-LinkNet architecture and adopting the structure of keypoint detection, ourframework predicts the position of patch-wise road keypoints and the adjacentrelationships between them to construct road graphs in a single pass.Meanwhile, the multi-task framework also performs pixel-wise semanticsegmentation and generates road segmentation masks. We evaluate our approachagainst the existing state-of-the-art methods on DeepGlobe, MassachusettsRoads, and RoadTracer datasets and achieve competitive or better results. Wealso demonstrate a considerable outperformance in terms of inference speed.

PaRK-Detect: Towards Efficient Multi-Task Satellite Imagery Road Extraction via Patch-Wise Keypoints Detection