FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude
This work addresses biometric recognition for law enforcement and surveillance, offering a novel system that improves performance in challenging conditions, though it is incremental in combining existing techniques.
The paper tackles whole-body biometric recognition from videos at large distances and altitudes, presenting FarSight, which combines physics and deep learning to address challenges like low-quality imagery and domain gaps, achieving gains of +11.82% Rank-20 identification and +11.3% TAR@1% FAR on the BRIAR dataset.
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.