English

Low-Power Multi-Camera Object Re-Identification using Hierarchical Neural Networks

Computer Vision and Pattern Recognition 2021-06-22 v1 Image and Video Processing

Abstract

Low-power computer vision on embedded devices has many applications. This paper describes a low-power technique for the object re-identification (reID) problem: matching a query image against a gallery of previously seen images. State-of-the-art techniques rely on large, computationally-intensive Deep Neural Networks (DNNs). We propose a novel hierarchical DNN architecture that uses attribute labels in the training dataset to perform efficient object reID. At each node in the hierarchy, a small DNN identifies a different attribute of the query image. The small DNN at each leaf node is specialized to re-identify a subset of the gallery: only the images with the attributes identified along the path from the root to a leaf. Thus, a query image is re-identified accurately after processing with a few small DNNs. We compare our method with state-of-the-art object reID techniques. With a 4% loss in accuracy, our approach realizes significant resource savings: 74% less memory, 72% fewer operations, and 67% lower query latency, yielding 65% less energy consumption.

Keywords

Cite

@article{arxiv.2106.10588,
  title  = {Low-Power Multi-Camera Object Re-Identification using Hierarchical Neural Networks},
  author = {Abhinav Goel and Caleb Tung and Xiao Hu and Haobo Wang and James C. Davis and George K. Thiruvathukal and Yung-Hsiang Lu},
  journal= {arXiv preprint arXiv:2106.10588},
  year   = {2021}
}

Comments

Accepted to ISLPED 2021

R2 v1 2026-06-24T03:23:35.508Z