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

TL;DR

This paper introduces a hierarchical neural network architecture for low-power object re-identification on embedded devices, significantly reducing resource consumption while maintaining high accuracy.

Contribution

The paper presents a novel hierarchical DNN design that uses attribute labels to enable efficient object reID with reduced computational resources.

Findings

Achieves 74% less memory usage

Reduces 72% of operations and 67% query latency

Maintains comparable accuracy with only 4% loss

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.