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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Tracking of inventory and rearrangement of misplaced items are some of themost labor-intensive tasks in a retail environment. While there have beenattempts at using vision-based techniques for these tasks, they mostly useplanogram compliance for detection of any anomalies, a technique that has beenfound lacking in robustness and scalability. Moreover, existing systems rely onhuman intervention to perform corrective actions after detection. In thispaper, we present Co-AD, a Concept-based Anomaly Detection approach using aVision Transformer (ViT) that is able to flag misplaced objects without using aprior knowledge base such as a planogram. It uses an auto-encoder architecturefollowed by outlier detection in the latent space. Co-AD has a peak successrate of 89.90% on anomaly detection image sets of retail objects drawn from theRP2K dataset, compared to 80.81% on the best-performing baseline of a standardViT auto-encoder. To demonstrate its utility, we describe a robotic mobilemanipulation pipeline to autonomously correct the anomalies flagged by Co-AD.This work is ultimately aimed towards developing autonomous mobile robotsolutions that reduce the need for human intervention in retail storemanagement.

Concept-based Anomaly Detection in Retail Stores for Automatic Correction using Mobile Robots