from grid.model.perception.vo.vo_dpvo import DPVO
car = AirGenCar()

# We will be capturing an image from the AirGen simulator 
# and run model inference on it.

img =  car.getImage("front_center", "rgb").data

model = DPVO(use_local = True)
result = model.run(image=img)

The DPVO class is a wrapper for the DPVO model, which estimates camera poses from RGB images using a deep learning approach.

​
class DPVO()
​
use_local
boolean
default:true

If True, inference call is run on the local VM, else offloaded onto GRID-Cortex. Defaults to True.

​
calib
np.ndarray
default:"false"

The camera calibration matrix of shape (4,)(4,). Defaults to np.array([320, 320, 320, 240]).

​
def run()

Uses DPVO to predict the camera pose for the given RGB image relative to the previous one. If this is the first image, initializes the pose estimation routine.

​
image
np.ndarray
required

The input RGB image of shape (M,N,3)(M,N,3).

​
Returns
np.ndarray

The predicted pose as a 1x6 tensor containing X, Y, Z positions and R, P, Y orientation.

from grid.model.perception.vo.vo_dpvo import DPVO
car = AirGenCar()

# We will be capturing an image from the AirGen simulator 
# and run model inference on it.

img =  car.getImage("front_center", "rgb").data

model = DPVO(use_local = True)
result = model.run(image=img)

This code is licensed under the MIT License.

Was this page helpful?