Pedestrian detection is a critical task in computer vision because of its role in ensuring traffic safety. However, existing methods that rely solely on RGB images suffer from performance degradation under low-light conditions due to the lack of useful information. To address this issue, recent multispectral detection approaches combine thermal images to provide complementary information. Nevertheless, these approaches have limitations such as the noisy fused feature maps and the loss of informative features. In this paper, we propose a novel target-aware fusion strategy for multispectral pedestrian detection, named TFDet. Unlike existing methods, TFDet enhances features by supervising the fusion process with a correlation-maximum loss function. Our fusion strategy highlights the pedestrian-related features while suppressing the unrelated ones. TFDet achieves state-of-the-art performances on both KAIST and LLVIP benchmarks, with a speed comparable to the previous state-of-the-art counterpart. Importantly, TFDet performs remarkably well under low-light conditions, which is a significant advancement for road safety.

翻译：行人检测是计算机视觉中的关键任务，因其在保障交通安全中的重要作用。然而，现有仅依赖RGB图像的方法在低光照条件下因缺乏有效信息导致性能下降。为解决该问题，近期多光谱检测方法引入热成像图像以提供互补信息，但此类方法存在融合特征图噪声干扰及信息特征丢失等局限。本文提出一种新颖的多光谱行人检测目标感知融合策略TFDet。与现有方法不同，TFDet通过关联最大化损失函数监督融合过程以增强特征，其融合策略能够突出行人相关特征的同时抑制无关特征。在KAIST与LLVIP基准测试中，TFDet均达到最先进性能，速度与先前最优方法持平。尤为重要的是，TFDet在低光照条件下表现卓越，为道路交通安全带来重要突破。