Achieving Real-time Visual Tracking with Low-Cost Edge AI

Visual multiple object tracking (MOT) algorithms based on deep learning are computationally intensive, and often cannot achieve real-time performance on low-cost edge computing platforms. We propose an algorithmic-hardware co-design methodology that combines novel algorithm augmentations and archite...

Full description

Saved in:
Bibliographic Details
Published in2024 ACM/IEEE 15th International Conference on Cyber-Physical Systems (ICCPS) pp. 279 - 280
Main Authors Do, Van Minh, Wu, Meiqing, Lam, Siew-Kei, Srikanthan, Thambipillai
Format Conference Proceeding
LanguageEnglish
Published IEEE 13.05.2024
Subjects
Deep learning
embedded devices
heterogeneous multi-core
Heuristic algorithms
Multicore processing
object tracking
Performance evaluation
Pipelines
real-time
Surveillance
Visualization
Online AccessGet full text

Cover

More Information
Summary:Visual multiple object tracking (MOT) algorithms based on deep learning are computationally intensive, and often cannot achieve real-time performance on low-cost edge computing platforms. We propose an algorithmic-hardware co-design methodology that combines novel algorithm augmentations and architecture mapping of state-of-the-art visual MOT on heterogeneous multi-core processor. We applied the proposed algorithm augmentations to two deep visual MOT pipelines. Experiments based on widely-used datasets demonstrate that the proposed methods outperform the baselines. We also show that the proposed methodology is able to achieve high performance on a low-cost embedded device (Odroid N2+), making it viable for real-time automated traffic surveillance with edge AI.
DOI:10.1109/ICCPS61052.2024.00035