Mean Height Aided Post-Processing for Pedestrian Detection

TL;DR

This paper introduces a simple, plug-and-play post-processing method that uses mean height information to improve pedestrian detection accuracy across various datasets and detectors.

Contribution

It proposes a novel mean height aided suppression technique that leverages pedestrian dataset characteristics for enhanced detection performance.

Findings

Significant accuracy improvements on multiple datasets.

Outperforms state-of-the-art pedestrian detectors.

Easy to implement and integrate with existing systems.

Abstract

The design of pedestrian detectors seldom considers the unique characteristics of this task and usually follows the common strategies for general object detection. To explore the potential of these characteristics, we take the perspective effect in pedestrian datasets as an example and propose the mean height aided suppression for post-processing. This method rejects predictions that fall at levels with a low possibility of containing any pedestrians or that have an abnormal height compared to the average. To achieve this, the existence score and mean height generators are proposed. Comprehensive experiments on various datasets and detectors are performed; the choice of hyper-parameters is discussed in depth. The proposed method is easy to implement and is plug-and-play. Results show that the proposed methods significantly improve detection accuracy when applied to different existing pedestrian detectors and datasets. The combination of mean height aided suppression with particular detectors outperforms state-of-the-art pedestrian detectors on Caltech and Citypersons datasets.