FRIDA: Fisheye Re-Identification Dataset with Annotations

TL;DR

This paper introduces FRIDA, a large-scale fisheye camera person re-identification dataset with extensive annotations, and demonstrates that training on FRIDA improves the performance of existing algorithms significantly.

Contribution

The paper presents FRIDA, the first large-scale fisheye re-identification dataset, and shows its effectiveness in enhancing algorithm performance.

Findings

Training on FRIDA improves CNN-based PRID algorithms by up to 11.64% in mAP.

FRIDA captures 240k+ annotations from ceiling-mounted fisheye cameras.

Fisheye PRID differs from traditional PRID due to field-of-view overlap.

Abstract

Person re-identification (PRID) from side-mounted rectilinear-lens cameras is a well-studied problem. On the other hand, PRID from overhead fisheye cameras is new and largely unstudied, primarily due to the lack of suitable image datasets. To fill this void, we introduce the "Fisheye Re-IDentification Dataset with Annotations" (FRIDA), with 240k+ bounding-box annotations of people, captured by 3 time-synchronized, ceiling-mounted fisheye cameras in a large indoor space. Due to a field-of-view overlap, PRID in this case differs from a typical PRID problem, which we discuss in depth. We also evaluate the performance of 10 state-of-the-art PRID algorithms on FRIDA. We show that for 6 CNN-based algorithms, training on FRIDA boosts the performance by up to 11.64% points in mAP compared to training on a common rectilinear-camera PRID dataset.