Scene filtering using motion estimation
Scene filtering using motion estimation, including identifying, in camera data from an autonomous vehicle, based on motion relative to the autonomous vehicle, one or more pixels; filtering, from the camera data, the one or more pixels; and training, based on the filtered camera data, a neural network.
1. A method for scene filtering using motion estimation, comprising:
selecting, from a plurality of pixels in camera data from an autonomous vehicle, by a computing device other than the autonomous vehicle, one or more pixels corresponding to one or more objects appearing effectively stationary relative to the autonomous vehicle;
blacking out, in the camera data by the computing device, the one or more pixels; and
training, by the computing device and based on the camera data including the blacked out one or more pixels, a neural network.
2. The method of claim 1 , wherein identifying the one or more pixels comprises identifying, for inclusion in the one or more pixels, one or more pixels associated motion away from the autonomous vehicle.
3. The method of claim 1 , wherein identifying the one or more pixels comprises:
identifying, for each pixel of the camera data, a corresponding motion vector; and
determining, based on each pixel and the corresponding motion vector, whether to include a respective pixel in the identified one or more pixels.
4. The method of claim 3 , wherein identifying, for each pixel of the camera data, the corresponding motion vector comprises providing the video data to another neural network.
5. The method of claim 1 , further comprising providing the trained neural network to one or more autonomous vehicles.
6. The method of claim 1 , wherein the trained neural network is configured to determine, based on sensor data, one or more autonomous vehicle control operations.
7. The method of claim 1 , wherein training the machine learning model comprises providing, to the machine learning model, the camera data including the blacked out one or more pixels and one or more control operations of the autonomous vehicle corresponding to the filtered sensor data.
8. An apparatus for scene filtering using motion estimation, the apparatus configured to perform steps comprising:
selecting, from a plurality of pixels in camera data from an autonomous vehicle, by a computing device other than the autonomous vehicle, one or more pixels corresponding to one or more objects appearing effectively stationary relative to the autonomous vehicle;
blacking out, in the camera data by the computing device, the one or more pixels; and
training, by the computing device and based on the camera data including the blacked out one or more pixels, a neural network.
9. The apparatus of claim 8 , wherein identifying the one or more pixels comprises identifying, for inclusion in the one or more pixels, one or more pixels associated motion away from the autonomous vehicle.
10. The apparatus of claim 8 , wherein identifying the one or more pixels comprises:
identifying, for each pixel of the camera data, a corresponding motion vector; and
determining, based on each pixel and the corresponding motion vector, whether to include a respective pixel in the identified one or more pixels.
11. The apparatus of claim 10 , wherein identifying, for each pixel of the camera data, the corresponding motion vector comprises providing the video data to another neural network.
12. The apparatus of claim 8 , wherein the steps further comprise providing the trained neural network to one or more autonomous vehicles.
13. The apparatus of claim 8 , wherein the trained neural network is configured to determine, based on sensor data, one or more autonomous vehicle control operations.
14. The apparatus of claim 8 , wherein training the machine learning model comprises providing, to the machine learning model, the camera data including the blacked out one or more pixels and one or more control operations of the autonomous vehicle corresponding to the filtered sensor data.
15. A computer program product disposed upon a non-transitory computer readable medium, the computer program product comprising computer program instructions for scene filtering using motion estimation that, when executed, cause a computer system to carry out the steps of:
selecting, from a plurality of pixels in camera data from an autonomous vehicle, by a computing device other than the autonomous vehicle, one or more pixels corresponding to one or more objects appearing effectively stationary relative to the autonomous vehicle;
blacking out, in the camera data by the computing device, the one or more pixels; and
training, by the computing device and based on the camera data including the blacked out one or more pixels, a neural network.
16. The computer program product of claim 15 , wherein identifying the one or more pixels comprises identifying, for inclusion in the one or more pixels, one or more pixels associated motion away from the autonomous vehicle.
17. The computer program product of claim 15 , wherein identifying the one or more pixels comprises:
identifying, for each pixel of the camera data, a corresponding motion vector; and
determining, based on each pixel and the corresponding motion vector, whether to include a respective pixel in the identified one or more pixels.
18. The computer program product of claim 17 , wherein identifying, for each pixel of the camera data, the corresponding motion vector comprises providing the video data to another neural network.
19. The computer program product of claim 15 , wherein the steps further comprise providing the trained neural network to one or more autonomous vehicles.
20. The computer program product of claim 15 , wherein training the machine learning model comprises providing, to the machine learning model, the camera data including the blacked out one or more pixels and one or more control operations of the autonomous vehicle corresponding to the filtered sensor data.