search

PaddlePaddle / Paddle3D

A 3D computer vision development toolkit based on PaddlePaddle. It supports point-cloud object detection, segmentation, and monocular 3D object detection models.
Apache License 2.0
573 stars 141 forks source link

请问pointpillars的infer.py推理完成后的结果是什么意思呢，可以说明下吗 #435

Closed jasper-cell closed 9 months ago

jasper-cell commented 10 months ago

image

will-jl944 commented 10 months ago

Score: 检测结果置信度 Label: 检测结果类别标签 Box(x_c, y_c, z_c, w, l, h, -rot): 检测结果bounding box信息，包含7个数值吗，按照顺序依次为中心点x轴坐标、中心点y轴坐标、中心点z轴坐标、宽度、长度、高度、偏航角（弧度制）。