Object detection in visible (RGB) and infrared (IR) images has been widely applied in recent years. Leveraging the complementary characteristics of RGB and IR images, the object detector provides reliable and robust object localization from day to night. Most existing fusion strategies directly input RGB and IR images into deep neural networks, leading to inferior detection performance. However, the RGB and IR features have modality-specific noise, these strategies will exacerbate the fused features along with the propagation. Inspired by the mechanism of the human brain processing multimodal information, in this paper, we introduce a new coarse-to-fine perspective to purify and fuse two modality features. Specifically, following this perspective, we design a Redundant Spectrum Removal module to coarsely remove interfering information within each modality and a Dynamic Feature Selection module to finely select the desired features for feature fusion. To verify the effectiveness of the coarse-to-fine fusion strategy, we construct a new object detector called the Removal and Selection Detector (RSDet). Extensive experiments on three RGB-IR object detection datasets verify the superior performance of our method.

翻译：近年来，可见光（RGB）与红外（IR）图像中的目标检测技术得到广泛应用。通过利用 RGB 与 IR 图像的互补特性，目标检测器能够在昼夜条件下实现可靠稳健的目标定位。现有融合策略大多直接将 RGB 与 IR 图像输入深度神经网络，导致检测性能欠佳。然而，RGB 与 IR 特征包含模态特异性噪声，此类策略会随着特征传播加剧融合特征中的噪声。受人类大脑处理多模态信息机制的启发，本文提出一种全新的由粗到细视角，用于净化并融合两种模态特征。具体而言，基于该视角，我们设计了冗余频谱移除模块（Redundant Spectrum Removal）以粗略移除各模态内的干扰信息，以及动态特征筛选模块（Dynamic Feature Selection）以精细选取所需特征进行特征融合。为验证由粗到细融合策略的有效性，我们构建了名为移除与筛选检测器（RSDet）的新型目标检测器。在三个 RGB-IR 目标检测数据集上的大量实验证实了本方法的优越性能。