UIFD: A Unified Interactive Network for Image Fusion and Traffic Object Detection Under Low-Light Conditions

Under low-light conditions, perceptual fusion techniques, such as image fusion, can mitigate the inherent limitations of source images, thereby enhancing the safety performance of automated driving. However, these methods typically perform fusion and detection tasks separately, making it difficult to improve detection precision, as the fused images often lack the rich target information necessary for effective low-light traffic detection. In this paper, an end-to-end unified interactive network is proposed, which eliminates the problem of structural inconsistency between fusion and detection tasks by constructing interaction relationships. In this work, a dual-branch coupled feature extraction module is proposed. Different from other dual-branch methods, this module couples weak features from different modalities to enhance features. In addition, an interactive fusion module is proposed to achieve mutual enhancement between fusion and detection tasks while adaptively weighting the fusion of infrared and visible features. Extensive experimental results on traffic scene datasets, such as LLVIP and FMB, demonstrate that the proposed unified network not only achieves excellent fusion results but also significantly improves traffic object detection precision in low-light environments.