search

lyft / nuscenes-devkit

Devkit for the public 2019 Lyft Level 5 AV Dataset (fork of https://github.com/nutonomy/nuscenes-devkit)
Other
365 stars 103 forks source link

Transformation of vehicle data from global to sensor coordinate is not matching as given in the data set #97

Open mishrap9 opened 2 years ago

mishrap9 commented 2 years ago

veh_trans = np.array([1048.155950230245, 1691.8102354006162, -23.304943447792454]) ego_trans = np.array([1007.2332778546752, 1725.4217301399465, -24.58000073380586]) ego_rot = np.array([[ 9.99991535e-01, -1.94042865e-03, -3.62842040e-03], [ 4.02573511e-03, 2.79013810e-01, 9.60278651e-01], [-8.50972801e-04, -9.60285129e-01, 2.79019260e-01]]) sens_trans = np.array([1.1970962545449502, 3.680498291456359e-05, 1.8279670539933053]) sens_rot = np.array([[ 9.99742609e-01, -2.87538929e-04, -2.26855114e-02], [-8.12880579e-17, 9.99919682e-01, -1.26739852e-02], [ 2.26873336e-02, 1.26707230e-02, 9.99662312e-01]])

veh_with_ego = np.dot(np.linalg.inv(ego_rot),(veh_trans - ego_trans)) veh_with_sens = np.dot(np.linalg.inv(sens_rot),(veh_with_ego -sens_trans))

veh_with_sens = array([ 38.80960936, -11.12196007, -34.6483506])

result as given in the dataset = [-19.02, -48.93, -1.20]

Can someone help with what is wrong in the above method??