Benchmarking Jetson Edge Devices with an End-to-end Video-based Anomaly Detection System
Hoang Viet Pham, Thinh Gia Tran, Chuong Dinh Le, An Dinh Le, Hien Bich, Vo

TL;DR
This paper benchmarks Jetson edge devices by deploying an end-to-end video anomaly detection system, demonstrating performance improvements and energy efficiency gains across different Jetson models using deep learning models and NVIDIA software tools.
Contribution
It presents a comprehensive deployment and benchmarking of a video-based anomaly detection system on multiple Jetson edge devices, highlighting performance and energy efficiency improvements.
Findings
Achieves 47.56 FPS inference speed on Jetson devices.
System uses only 3.11 GB RAM during operation.
15% better performance with 50% less energy consumption compared to previous Jetson models.
Abstract
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,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAnomaly Detection Techniques and Applications · Advanced Malware Detection Techniques · Network Security and Intrusion Detection
MethodsSPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings
