Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks

Abstract

Multispectral images (e.g. visible and infrared) may be particularly useful when detecting objects with the same model in different environments (e.g. day/night outdoor scenes). To effectively use the different spectra, the main technical problem resides in the information fusion process. In this paper, we propose a new halfway feature fusion method for neural networks that leverages the complementary/consistency balance existing in multispectral features by adding to the network architecture, a particular module that cyclically fuses and refines each spectral feature. We evaluate the effectiveness of our fusion method on two challenging multispectral datasets for object detection. Our results show that implementing our Cyclic Fuse-and-Refine module in any network improves the performance on both datasets compared to other state-of-the-art multispectral object detection methods.

arXiv commentAccepted by ICIP 2020

References in corpus (6)

• FSSD: Feature Fusion Single Shot Multibox Detector
• Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation
• Illuminating Pedestrians via Simultaneous Detection & Segmentation
• Gated Multimodal Units for Information Fusion
• GFD-SSD: Gated Fusion Double SSD for Multispectral Pedestrian Detection
• Is Faster R-CNN Doing Well for Pedestrian Detection?