Which to Match? Selecting Consistent GT-Proposal Assignment for Pedestrian Detection

TL;DR

This paper introduces a geometric sensitive search algorithm for pedestrian detection that improves proposal-ground truth matching, addressing limitations of IoU-based assignment and enhancing detection performance.

Contribution

It proposes a novel assignment and regression metric based on geometric sensitivity, replacing IoU-based methods to improve pedestrian detection accuracy.

Findings

Boosts MR-FPPI under R75 by 8.8% on Citypersons dataset

Achieves consistent improvements when integrated into state-of-the-art detectors

Addresses the inconsistency problem in proposal-ground truth assignment

Abstract

Accurate pedestrian classification and localization have received considerable attention due to their wide applications such as security monitoring, autonomous driving, etc. Although pedestrian detectors have made great progress in recent years, the fixed Intersection over Union (IoU) based assignment-regression manner still limits their performance. Two main factors are responsible for this: 1) the IoU threshold faces a dilemma that a lower one will result in more false positives, while a higher one will filter out the matched positives; 2) the IoU-based GT-Proposal assignment suffers from the inconsistent supervision problem that spatially adjacent proposals with similar features are assigned to different ground-truth boxes, which means some very similar proposals may be forced to regress towards different targets, and thus confuses the bounding-box regression when predicting the location results. In this paper, we first put forward the question that \textbf{Regression Direction} would affect the performance for pedestrian detection. Consequently, we address the weakness of IoU by introducing one geometric sensitive search algorithm as a new assignment and regression metric. Different from the previous IoU-based \textbf{one-to-one} assignment manner of one proposal to one ground-truth box, the proposed method attempts to seek a reasonable matching between the sets of proposals and ground-truth boxes. Specifically, we boost the MR-FPPI under R$_{75}$ by 8.8\% on Citypersons dataset. Furthermore, by incorporating this method as a metric into the state-of-the-art pedestrian detectors, we show a consistent improvement.