NIRPed

A narrowband near-infrared (NIR) imaging system is developed, combined with LiDAR to obtain nighttime driving scene images and distance information of pedestrian targets in the images, and constructed a large-scale nighttime pedestrian dataset (NIRPed) containing distance attributes. Unlike VIS, NIR is difficult to detect by human eyes, so it does not affect other road users and is not restricted by traffic laws; narrowband NIR is outside the VIS spectral band and its imaging can greatly weaken the interference of uneven VIS in nighttime driving scenes. With the help of supplementary light, narrowband NIR imaging quality will be significantly improved.本研究开发了一套窄带近红外（NIR）成像系统，结合激光雷达（LiDAR）采集夜间驾驶场景图像与图像内行人目标的距离信息，并构建了包含距离属性的大规模夜间行人数据集（NIRPed）。与可见光（VIS）不同，近红外难以被人眼察觉，因此不会对其他道路使用者造成干扰，亦不受交通法规约束；窄带近红外处于可见光光谱波段之外，其成像可大幅削弱夜间驾驶场景中可见光不均匀分布带来的干扰。辅以补光手段后，窄带近红外的成像质量将得到显著提升。

搜集汇总

背景与挑战

背景概述

NIRPed是一个夜间驾驶场景下的行人检测与距离估计联合数据集，采用窄带近红外摄像头和LiDAR采集，包含146k行人标注，是现有最大夜间行人数据集NightOwls的三倍。该数据集提供了MS-COCO格式的标注，并基于Faster-RCNN实现了行人与距离的联合检测，漏检率为6.5%，距离估计平均绝对误差率为5.5%。