A Brief Survey on Person Recognition at a Distance

TL;DR

This survey reviews recent advances and challenges in remote person recognition using long-range imaging systems, focusing on multi-spectral face verification, re-identification, and gait analysis.

Contribution

It provides a comprehensive overview of current methods, discusses their strengths and limitations, and highlights underexplored challenges for in-the-wild deployment.

Findings

Multi-spectral face verification shows promise but faces illumination challenges.

Person re-identification techniques are effective in controlled settings but less so in the wild.

Gait-based analysis offers a non-invasive recognition method with ongoing research challenges.

Abstract

Person recognition at a distance entails recognizing the identity of an individual appearing in images or videos collected by long-range imaging systems such as drones or surveillance cameras. Despite recent advances in deep convolutional neural networks (DCNNs), this remains challenging. Images or videos collected by long-range cameras often suffer from atmospheric turbulence, blur, low-resolution, unconstrained poses, and poor illumination. In this paper, we provide a brief survey of recent advances in person recognition at a distance. In particular, we review recent work in multi-spectral face verification, person re-identification, and gait-based analysis techniques. Furthermore, we discuss the merits and drawbacks of existing approaches and identify important, yet under explored challenges for deploying remote person recognition systems in-the-wild.