chen-judge / RGBTCrowdCounting

Official Implement of CVPR 2021 paper “Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting”
65 stars 11 forks source link

我检查了已有的数据集,发现标注的点与图片上的人物都对应不上,想请教您是通过怎样的工具或方式确定标注点? #5

Open wileychan opened 2 years ago

wileychan commented 2 years ago

ff6c39e9130cff584ed93ecd0dd8b399_ 9648ef5d7f3054ea7d4b47f18022bd31_ 48bcdcee8b256b393bf6204e103f1e22_

chen-judge commented 2 years ago

我们是使用VGG标注工具,基于热感模态进行标注的。RGB和thermal是同一个摄像机上的两个传感器,存在一定的未对齐现象。4.2节有提及:Thanks to the translation invariance of max-pooling layers, we can eliminate the misalignment of RGB-thermal images to some extent.