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

This work addresses the task of open world semantic segmentation using RGBDsensing to discover new semantic classes over time. Although there are manytypes of objects in the real-word, current semantic segmentation methods make aclosed world assumption and are trained only to segment a limited number ofobject classes. Towards a more open world approach, we propose a novel methodthat incrementally learns new classes for image segmentation. The proposedsystem first segments each RGBD frame using both color and geometricinformation, and then aggregates that information to build a single segmenteddense 3D map of the environment. The segmented 3D map representation is a keycomponent of our approach as it is used to discover new object classes byidentifying coherent regions in the 3D map that have no semantic label. The useof coherent region in the 3D map as a primitive element, rather thantraditional elements such as surfels or voxels, also significantly reduces thecomputational complexity and memory use of our method. It thus leads tosemi-real-time performance at {10.7}Hz when incrementally updating the dense 3Dmap at every frame. Through experiments on the NYUDv2 dataset, we demonstratethat the proposed method is able to correctly cluster objects of both known andunseen classes. We also show the quantitative comparison with thestate-of-the-art supervised methods, the processing time of each step, and theinfluences of each component.

Incremental Class Discovery for Semantic Segmentation with RGBD Sensing