Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks
This addresses the challenge of robust object detection across different lighting conditions for applications like surveillance or autonomous driving, representing an incremental advance in multispectral fusion techniques.
The paper tackles the problem of effectively fusing multispectral images (e.g., visible and infrared) for object detection in varying environments like day/night scenes, proposing a halfway feature fusion method with Cyclic Fuse-and-Refine blocks that improves performance on two challenging datasets compared to other state-of-the-art methods.
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.