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

Knowing how many and where are people in various indoor spaces is criticalfor reducing HVAC energy waste, space management, spatial analytics and inemergency scenarios. While a range of technologies have been proposed to detectand track people in large indoor spaces, ceiling-mounted fisheye cameras haverecently emerged as strong contenders. Currently, RAPiD is the SOTA algorithmfor people detection in images captured by fisheye cameras. However, in largespaces several overhead fisheye cameras are needed to assure high accuracy ofcounting and thus multiple instances of RAPiD must be executed simultaneously.This report evaluates inference time when multiple instances of RAPiD run inparallel on an Ubuntu NUC PC with Intel I7 8559U CPU. We consider threemechanisms of CPU-resource allocation to handle multiple instances of RAPiD: 1)managed by Ubuntu, 2) managed by user via operating-system calls to assignlogical cores, and 3) managed by user via PyTorch-library calls to limit thenumber of threads used by PyTorch. Each scenario was evaluated on 300 images.The experimental results show, that when one or two instances of RAPiD areexecuted in parallel all three approaches result in similar inference times of1.8sec and 3.2sec, respectively. However, when three or more instances of RAPiDrun in parallel, limiting the number of threads used by PyTorch results in theshortest inference times. On average, RAPiD completes inference of 2 imagessimultaneously in about 3sec, 4 images in 6sec and 8 images in less than 14sec.This is important for real-time system design. In HVAC-application scenarios,with a typical reaction time of 10-15min, a latency of 14sec is negligible so asingle 8559U CPU can support 8 camera streams thus reducing the system cost.However, in emergency scenarios, when time is of essence, a single CPU may beneeded for each camera to reduce the latency to 1.8sec.

Complexity Evaluation of Parallel Execution of the RAPiD Deep-Learning Algorithm on Intel CPU