How is it possible to get tracked features from tango APIs used for motion tracking -


as shown in project tango gtc video, local features extracted , tracked motion estimation fused accelerometer data.

since developer may need track features develop his/her apps, wondering if there way features through apis. although possible extract point , retrieve flow using estimated 6dof pose returned apis, adds overhead. issue approach pure visual flow (including outliers) not achievable , influenced imu data.

so question if these features tracked using hardware-accelerated algorithms, how can them using apis without having implement , redundant task.

any answer , suggestion appreciated.

it straightforward compile opencv tango nvidia's tadp package. use 3.0r4. may need merge opencv-4-android bits it's easy, , es examples fail on device don't sweat it.


Comments

Popular posts from this blog

python - TypeError: start must be a integer -

c# - DevExpress RepositoryItemComboBox BackColor property ignored -

django - Creating multiple model instances in DRF3 -