GEM: Glare or Gloom, I Can Still See You -- End-to-End Multimodal Object Detection

TL;DR

This paper introduces a multi-modal object detection framework that employs sensor-aware fusion strategies to enhance robustness under varying lighting and sensor failure conditions, validated on multiple datasets including a new indoor RGB-Infra dataset.

Contribution

It proposes deterministic and stochastic sensor-aware fusion methods and a new hybrid depth modality, improving object detection robustness across diverse lighting and sensor reliability scenarios.

Findings

Outperforms state-of-the-art on FLIR-Thermal dataset

Achieves promising results on SUNRGB-D dataset

Demonstrates effectiveness on a newly recorded indoor RGB-Infra dataset

Abstract

Deep neural networks designed for vision tasks are often prone to failure when they encounter environmental conditions not covered by the training data. Single-modal strategies are insufficient when the sensor fails to acquire information due to malfunction or its design limitations. Multi-sensor configurations are known to provide redundancy, increase reliability, and are crucial in achieving robustness against asymmetric sensor failures. To address the issue of changing lighting conditions and asymmetric sensor degradation in object detection, we develop a multi-modal 2D object detector, and propose deterministic and stochastic sensor-aware feature fusion strategies. The proposed fusion mechanisms are driven by the estimated sensor measurement reliability values/weights. Reliable object detection in harsh lighting conditions is essential for applications such as self-driving vehicles and human-robot interaction. We also propose a new "r-blended" hybrid depth modality for RGB-D sensors. Through extensive experimentation, we show that the proposed strategies outperform the existing state-of-the-art methods on the FLIR-Thermal dataset, and obtain promising results on the SUNRGB-D dataset. We additionally record a new RGB-Infra indoor dataset, namely L515-Indoors, and demonstrate that the proposed object detection methodologies are highly effective for a variety of lighting conditions.