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

arXiv: https://arxiv.org/abs/2307.16834 · HTML: https://mlsanity.com/paper/2307.16834/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 21 references that are in the map.
- First posted on arXiv 28 Jul 2023.

## Builds on (most cited first, 5 of 5)

- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [Multiple Instance Learning: A Survey of Problem Characteristics and Applications](https://mlsanity.com/paper/1612.03365/) (2016)
- [DeepEdgeBench: Benchmarking Deep Neural Networks on Edge Devices](https://mlsanity.com/paper/2108.09457/) (2021)
- [Anomaly Detection in Residential Video Surveillance on Edge Devices in IoT Framework](https://mlsanity.com/paper/2107.04767/) (2021)

## Built on by (most cited first, 1 of 1)

- [Energy-Efficient Fast Object Detection on Edge Devices for IoT Systems](https://mlsanity.com/paper/2602.09515/) (2026)

## Abstract (arXiv)

Innovative enhancement in embedded system platforms, specifically hardware accelerations, significantly influence the application of deep learning in real-world scenarios. These innovations translate human labor efforts into automated intelligent systems employed in various areas such as autonomous driving, robotics, Internet-of-Things (IoT), and numerous other impactful applications. NVIDIA's Jetson platform is one of the pioneers in offering optimal performance regarding energy efficiency and throughput in the execution of deep learning algorithms. Previously, most benchmarking analysis was based on 2D images with a single deep learning model for each comparison result. In this paper, we implement an end-to-end video-based crime-scene anomaly detection system inputting from surveillance videos and the system is deployed and completely operates on multiple Jetson edge devices (Nano, AGX Xavier, Orin Nano). The comparison analysis includes the integration of Torch-TensorRT as a software developer kit from NVIDIA for the model performance optimisation. The system is built based on the PySlowfast open-source project from Facebook as the coding template. The end-to-end system process comprises the videos from camera, data preprocessing pipeline, feature extractor and the anomaly detection. We provide the experience of an AI-based system deployment on various Jetson Edge devices with Docker technology. Regarding anomaly detectors, a weakly supervised video-based deep learning model called Robust Temporal Feature Magnitude Learning (RTFM) is applied in the system. The approach system reaches 47.56 frames per second (FPS) inference speed on a Jetson edge device with only 3.11 GB RAM usage total. We also discover the promising Jetson device that the AI system achieves 15% better performance than the previous version of Jetson devices while consuming 50% less energy power.