Multimodal Object Detection via Probabilistic Ensembling

TL;DR

This paper introduces ProbEn, a probabilistic ensembling method for multimodal object detection that fuses RGB and thermal camera data, improving detection accuracy especially under poor illumination conditions.

Contribution

The paper presents ProbEn, a non-learned probabilistic fusion technique derived from Bayes' rule that effectively combines multimodal detections and handles missing data.

Findings

ProbEn outperforms previous methods by over 13% on benchmark datasets.

ProbEn improves detection accuracy even when the independence assumption is violated.

ProbEn effectively handles missing modalities during fusion.

Abstract

Object detection with multimodal inputs can improve many safety-critical systems such as autonomous vehicles (AVs). Motivated by AVs that operate in both day and night, we study multimodal object detection with RGB and thermal cameras, since the latter provides much stronger object signatures under poor illumination. We explore strategies for fusing information from different modalities. Our key contribution is a probabilistic ensembling technique, ProbEn, a simple non-learned method that fuses together detections from multi-modalities. We derive ProbEn from Bayes' rule and first principles that assume conditional independence across modalities. Through probabilistic marginalization, ProbEn elegantly handles missing modalities when detectors do not fire on the same object. Importantly, ProbEn also notably improves multimodal detection even when the conditional independence assumption does not hold, e.g., fusing outputs from other fusion methods (both off-the-shelf and trained in-house). We validate ProbEn on two benchmarks containing both aligned (KAIST) and unaligned (FLIR) multimodal images, showing that ProbEn outperforms prior work by more than 13% in relative performance!