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

Innovative enhancement in embedded system platforms, specifically hardwareaccelerations, significantly influence the application of deep learning inreal-world scenarios. These innovations translate human labor efforts intoautomated intelligent systems employed in various areas such as autonomousdriving, robotics, Internet-of-Things (IoT), and numerous other impactfulapplications. NVIDIA's Jetson platform is one of the pioneers in offeringoptimal performance regarding energy efficiency and throughput in the executionof deep learning algorithms. Previously, most benchmarking analysis was basedon 2D images with a single deep learning model for each comparison result. Inthis paper, we implement an end-to-end video-based crime-scene anomalydetection system inputting from surveillance videos and the system is deployedand completely operates on multiple Jetson edge devices (Nano, AGX Xavier, OrinNano). The comparison analysis includes the integration of Torch-TensorRT as asoftware developer kit from NVIDIA for the model performance optimisation. Thesystem is built based on the PySlowfast open-source project from Facebook asthe coding template. The end-to-end system process comprises the videos fromcamera, data preprocessing pipeline, feature extractor and the anomalydetection. We provide the experience of an AI-based system deployment onvarious Jetson Edge devices with Docker technology. Regarding anomalydetectors, a weakly supervised video-based deep learning model called RobustTemporal Feature Magnitude Learning (RTFM) is applied in the system. Theapproach system reaches 47.56 frames per second (FPS) inference speed on aJetson edge device with only 3.11 GB RAM usage total. We also discover thepromising Jetson device that the AI system achieves 15% better performance thanthe previous version of Jetson devices while consuming 50% less energy power.

Benchmarking Jetson Edge Devices with an End-to-end Video-based Anomaly Detection System