BriefGPT.xyz
May, 2022
Time3D: 自动驾驶端到端联合单目三维目标检测与跟踪
Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving
HTML
PDF
Peixuan Li, Jieyu Jin
TL;DR
该篇论文提出了一种通过空间时间信息流模块和transformer结合监督,联合训练3D目标检测和跟踪模型的方法,同时还加入了时间相容性损失,最终在nuScenes数据集上取得了领先成绩。
Abstract
While separately leveraging
monocular 3d object detection
and
2d multi-object tracking
can be straightforwardly applied to sequence images in a frame-by-frame fashion, stand-alone tracker cuts off the transmissio
→