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

Vision and touch are two of the important sensing modalities for humans andthey offer complementary information for sensing the environment. Robots couldalso benefit from such multi-modal sensing ability. In this paper, addressingfor the first time (to the best of our knowledge) texture recognition fromtactile images and vision, we propose a new fusion method named Deep MaximumCovariance Analysis (DMCA) to learn a joint latent space for sharing featuresthrough vision and tactile sensing. The features of camera images and tactiledata acquired from a GelSight sensor are learned by deep neural networks. Butthe learned features are of a high dimensionality and are redundant due to thedifferences between the two sensing modalities, which deteriorates theperception performance. To address this, the learned features are paired usingmaximum covariance analysis. Results of the algorithm on a newly collecteddataset of paired visual and tactile data relating to cloth textures show thata good recognition performance of greater than 90\% can be achieved by usingthe proposed DMCA framework. In addition, we find that the perceptionperformance of either vision or tactile sensing can be improved by employingthe shared representation space, compared to learning from unimodal data.

ViTac: Feature Sharing between Vision and Tactile Sensing for Cloth Texture Recognition