A Content-Based Late Fusion Approach Applied to Pedestrian Detection

TL;DR

This paper introduces a novel content-based spatial consensus method for fusing pedestrian detectors, improving accuracy by reducing false alarms and outperforming existing fusion techniques on standard datasets.

Contribution

The proposed CSBC method uniquely combines spatial consensus with content analysis for detector fusion, requiring fewer detectors for effective pedestrian detection.

Findings

CSBC outperforms state-of-the-art fusion methods on ETH and Caltech datasets.

The method is efficient, using simple features with minimal impact on performance.

Fewer detectors are needed to achieve high detection accuracy.

Abstract

The variety of pedestrians detectors proposed in recent years has encouraged some works to fuse pedestrian detectors to achieve a more accurate detection. The intuition behind is to combine the detectors based on its spatial consensus. We propose a novel method called Content-Based Spatial Consensus (CSBC), which, in addition to relying on spatial consensus, considers the content of the detection windows to learn a weighted-fusion of pedestrian detectors. The result is a reduction in false alarms and an enhancement in the detection. In this work, we also demonstrate that there is small influence of the feature used to learn the contents of the windows of each detector, which enables our method to be efficient even employing simple features. The CSBC overcomes state-of-the-art fusion methods in the ETH dataset and in the Caltech dataset. Particularly, our method is more efficient since fewer detectors are necessary to achieve expressive results.