Enhanced object detection for autonomous vehicles based on field view
Systems and methods for enhanced object detection for autonomous vehicles based on field of view. An example method includes obtaining an image from an image sensor of one or more image sensors positioned about a vehicle. A field of view for the image is determined, with the field of view being associated with a vanishing line. A crop portion corresponding to the field of view is generated from the image, with a remaining portion of the image being downsampled. Information associated with detected objects depicted in the image is outputted based on a convolutional neural network, with detecting objects being based on performing a forward pass through the convolutional neural network of the crop portion and the remaining portion.
1. A method comprising:
determining, by a processor, a field of view of an image associated with a driving session, wherein the field of view is associated with a vanishing line indicative of a horizon line;
generating, by the processor, a crop portion of the image corresponding to the field of view and a remaining portion of the image, wherein the remaining portion of the image is downsampled; and
transmitting, by the processor, the crop portion of the image and the downsampled remaining portion of the image to a neural network causing the neural network to detect at least one object depicted within the image, wherein an output of the neural network is configured for use in autonomous driving.
2. The method of claim 1 , wherein the image is captured by a camera associated with a vehicle.
3. The method of claim 1 , wherein the image is associated with a forward direction of a vehicle.
4. The method of claim 1 , wherein the neural network receives additional data to detect the at least one object, the additional data comprising at least data from an inertial measurement unit.
5. The method of claim 1 , wherein the neural network receives additional data to detect the at least one object, the additional data comprising at least map data.
6. The method of claim 1 , wherein the crop portion is aligned with the remaining portion.
7. The method of claim 1 , wherein the neural network detects a first object depicted in the crop portion and a second object depicted in the remaining portion corresponding to a same real-world object, and wherein the method further comprises:
removing, by the processor, one of the first object or the second object.
8. A system comprising one or more processors and non-transitory computer storage media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
determining a field of view of an image associated with a driving session, wherein the field of view is associated with a vanishing line indicative of a horizon line;
generating a crop portion of the image corresponding to the field of view and a remaining portion of the image, wherein the remaining portion of the image is downsampled; and
transmitting the crop portion of the image and the downsampled remaining portion of the image to a neural network causing the neural network to detect at least one object depicted within the image, wherein an output of the neural network is configured for use in autonomous driving.
9. The system of claim 8 , wherein the image is captured by a camera associated with a vehicle.
10. The system of claim 8 , wherein the image is associated with a forward direction of a vehicle.
11. The system of claim 8 , wherein the neural network receives additional data to detect the at least one object, the additional data comprising at least data from an inertial measurement unit.
12. The system of claim 8 , wherein the neural network receives additional data to detect the at least one object, the additional data comprising at least map data.
13. The system of claim 8 , wherein the crop portion is aligned with the remaining portion.
14. The system of claim 8 , wherein the neural network detects a first object depicted in the crop portion and a second object depicted in the remaining portion corresponding to a same real-world object, and wherein the instruction cause the one or more processors to further remove one of the first object or the second object.
15. A non-transitory computer storage media storing instructions that when executed by a system of one or more processors, cause the one or more processors to perform operations comprising:
determining a field of view of an image associated with a driving session, wherein the field of view is associated with a vanishing line indicative of a horizon line;
generating a crop portion of the image corresponding to the field of view and a remaining portion of the image, wherein the remaining portion of the image is downsampled; and
transmitting the crop portion of the image and the downsampled remaining portion of the image to a neural network causing the neural network to detect at least one object depicted within the image, wherein an output of the neural network is configured for use in autonomous driving.
16. The non-transitory computer storage media of claim 15 , wherein the image is captured by a camera associated with a vehicle.