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/

Zendy Plus

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

Zendy Tools

Zendy Open

Measuring and analyzing the flow of customers in retail stores is essentialfor a retailer to better comprehend customers' behavior and supportdecision-making. Nevertheless, not much attention has been given to thedevelopment of novel technologies for automatic people counting. We introduceLRCN-RetailNet: a recurrent neural network architecture capable of learning anon-linear regression model and accurately predicting the people count fromvideos captured by low-cost surveillance cameras. The input video formatfollows the recently proposed RGBP image format, which is comprised of colorand people (foreground) information. Our architecture is capable of consideringtwo relevant aspects: spatial features extracted through convolutional layersfrom the RGBP images; and the temporal coherence of the problem, which isexploited by recurrent layers. We show that, through a supervised learningapproach, the trained models are capable of predicting the people count withhigh accuracy. Additionally, we present and demonstrate that a straightforwardmodification of the methodology is effective to exclude salespeople from thepeople count. Comprehensive experiments were conducted to validate, evaluateand compare the proposed architecture. Results corroborated that LRCN-RetailNetremarkably outperforms both the previous RetailNet architecture, which waslimited to evaluating a single image per iteration; and a state-of-the-artneural network for object detection. Finally, computational performanceexperiments confirmed that the entire methodology is effective to estimatepeople count in real-time.

LRCN-RetailNet: A recurrent neural network architecture for accurate people counting