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

Intelligent edge vision tasks encounter the critical challenge of ensuringpower and latency efficiency due to the typically heavy computational load theyimpose on edge platforms.This work leverages one of the first "AI in sensor"vision platforms, IMX500 by Sony, to achieve ultra-fast and ultra-low-powerend-to-end edge vision applications. We evaluate the IMX500 and compare it toother edge platforms, such as the Google Coral Dev Micro and Sony Spresense, byexploring gaze estimation as a case study. We propose TinyTracker, a highlyefficient, fully quantized model for 2D gaze estimation designed to maximizethe performance of the edge vision systems considered in this study.TinyTracker achieves a 41x size reduction (600Kb) compared to iTracker [1]without significant loss in gaze estimation accuracy (maximum of 0.16 cm whenfully quantized). TinyTracker's deployment on the Sony IMX500 vision sensorresults in end-to-end latency of around 19ms. The camera takes around 17.9ms toread, process and transmit the pixels to the accelerator. The inference time ofthe network is 0.86ms with an additional 0.24 ms for retrieving the resultsfrom the sensor. The overall energy consumption of the end-to-end system is 4.9mJ, including 0.06 mJ for inference. The end-to-end study shows that IMX500 is1.7x faster than CoralMicro (19ms vs 34.4ms) and 7x more power efficient (4.9mJVS 34.2mJ)

TinyTracker: Ultra-Fast and Ultra-Low-Power Edge Vision In-Sensor for Gaze Estimation