MMDetection3D&可视化kitti数据集&bin点云

参考官方的框架：https://github.com/open-mmlab/mmdetection3d/blob/master/docs/getting_started.md

运行如下命令生成模型.pkl文件和可视化文件000000_gt.obj ,000000_points.obj

python tools/test.py ${CONFIG_FILE} ${CKPT_PATH} --out ./data/result_output/out_dir/3dssd.pkl --eval 'mAP' --eval-options 'show=True' 'out_dir=./show_result'

结果图：

 

可视化kitti数据集：

python tools/misc/browse_dataset.py configs/mvxnet/dv_mvx-fpn_second_secfpn_adamw_2x8_80e_kitti-3d-3class.py --task multi_modality-det --output-dir work_dirs1 --online

效果图：

 

 

 

Velodyne Point Cloud-激光雷达点云bin文件读取和显示-mayavi

 

import mayavi.mlab
import torch
import numpy as np

mypointcloud=np.fromfile("/home/zzn/Documents/test/lidar/000002.bin",dtype=np.float32,count=-1).reshape([-1,4])
mypointcloud=torch.from_numpy(mypointcloud)
print(mypointcloud.size())
print(mypointcloud.type())

def viz_mayavi(points,vals="distance"):
    x=points[:,0]
    y=points[:,1]
    z=points[:,2]
    r=points[:,3]
    d=torch.sqrt(x**2+y**2)

    if vals=="height":
        col=z
    else:
        col=d

    fig=mayavi.mlab.figure(bgcolor=(0,0,0),size=(1280,720))
    mayavi.mlab.points3d(x,y,z,
                         col,
                         mode="point",
                         colormap='spectral',
                         figure=fig,
                         )

    mayavi.mlab.show()

if __name__=="__main__":
    viz_mayavi(mypointcloud,vals="height")

保存：