Feature Encoding in Band-limited Distributed Surveillance Systems

TL;DR

This paper introduces a probabilistic feature encoding algorithm that reduces data dimensionality in bandwidth-constrained distributed surveillance systems, enhancing efficiency without sacrificing recognition accuracy.

Contribution

A novel probabilistic divergence-based feature encoding method tailored for bandwidth-limited distributed wireless camera networks.

Findings

Significant bandwidth savings demonstrated in experiments

Maintains high recognition accuracy with reduced feature dimensions

Effective in two different surveillance recognition tasks

Abstract

Distributed surveillance systems have become popular in recent years due to security concerns. However, transmitting high dimensional data in bandwidth-limited distributed systems becomes a major challenge. In this paper, we address this issue by proposing a novel probabilistic algorithm based on the divergence between the probability distributions of the visual features in order to reduce their dimensionality and thus save the network bandwidth in distributed wireless smart camera networks. We demonstrate the effectiveness of the proposed approach through extensive experiments on two surveillance recognition tasks.