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

The Segment Anything Model (SAM) has shown impressive performance whenapplied to natural image segmentation. However, it struggles with geographicalimages like aerial and satellite imagery, especially when segmenting mobilityinfrastructure including roads, sidewalks, and crosswalks. This inferiorperformance stems from the narrow features of these objects, their texturesblending into the surroundings, and interference from objects like trees,buildings, vehicles, and pedestrians - all of which can disorient the model toproduce inaccurate segmentation maps. To address these challenges, we proposeGeographical SAM (GeoSAM), a novel SAM-based framework that implements afine-tuning strategy using the dense visual prompt from zero-shot learning, andthe sparse visual prompt from a pre-trained CNN segmentation model. Theproposed GeoSAM outperforms existing approaches for geographical imagesegmentation, specifically by 20%, 14.29%, and 17.65% for road infrastructure,pedestrian infrastructure, and on average, respectively, representing amomentous leap in leveraging foundation models to segment mobilityinfrastructure including both road and pedestrian infrastructure ingeographical images.

GeoSAM: Fine-tuning SAM with Sparse and Dense Visual Prompting for Automated Segmentation of Mobility Infrastructure