FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude

TL;DR

FarSight is a novel system that combines physics-based imaging and deep learning to improve whole-body biometric recognition from videos captured at large distances and altitudes, addressing challenges like low quality and pose variations.

Contribution

It introduces an end-to-end system integrating physics-driven image restoration with deep biometric feature encoding for enhanced recognition accuracy.

Findings

Achieved +11.82% Rank-20 identification improvement

Attained +11.3% TAR@1% FAR performance gain

Validated effectiveness on the new BRIAR dataset

Abstract

Whole-body biometric recognition is an important area of research due to its vast applications in law enforcement, border security, and surveillance. This paper presents the end-to-end design, development and evaluation of FarSight, an innovative software system designed for whole-body (fusion of face, gait and body shape) biometric recognition. FarSight accepts videos from elevated platforms and drones as input and outputs a candidate list of identities from a gallery. The system is designed to address several challenges, including (i) low-quality imagery, (ii) large yaw and pitch angles, (iii) robust feature extraction to accommodate large intra-person variabilities and large inter-person similarities, and (iv) the large domain gap between training and test sets. FarSight combines the physics of imaging and deep learning models to enhance image restoration and biometric feature encoding. We test FarSight's effectiveness using the newly acquired IARPA Biometric Recognition and Identification at Altitude and Range (BRIAR) dataset. Notably, FarSight demonstrated a substantial performance increase on the BRIAR dataset, with gains of +11.82% Rank-20 identification and +11.3% TAR@1% FAR.