Map and high-resolution snippet for object detection

A method for navigating a host vehicle relative to a road segment, the method comprising:

• receiving a captured image acquired by a camera onboard the host vehicle, wherein the captured image is representative of an environment of the host vehicle, and wherein the captured image is captured at a first resolution;
• generating a resampled image based on at least a portion of the captured image, wherein the resampled image has a second resolution lower than the first resolution;
• determining a first navigational action for the host vehicle based on the resampled image and a map, wherein the map includes a representation of one or more target trajectories available to the host vehicle and 3D location information for a plurality of road topography features in the environment of the host vehicle;
• identifying a region of interest in the captured image or the resampled image based on a future path of a mapped target trajectory selected by the navigation system;
• extracting an image snippet corresponding to the region of interest, the image snippet having a third resolution of the captured image;
• analyzing the image snippet to determine a second navigational action for the host vehicle;
• and
• causing the host vehicle to implement the second navigational action.

A non-transitory computer-readable medium storing instructions for navigating a host vehicle relative to a road segment according to a method, the method comprising:

• receiving a captured image acquired by a camera onboard the host vehicle, wherein the captured image is representative of an environment of the host vehicle, and wherein the captured image is captured at a first resolution;
• generating a resampled image based on at least a portion of the captured image, wherein the resampled image has a second resolution lower than the first resolution;
• determining a first navigational action for the host vehicle based on the resampled image and a map, wherein the map includes a representation of one or more target trajectories available to the host vehicle and 3D location information for a plurality of road topography features in the environment of the host vehicle;
• identifying a region of interest in the captured image or the resampled image based on a future path of a mapped target trajectory selected by the navigation system;
• extracting an image snippet corresponding to the region of interest, the image snippet having a third resolution of the captured image;
• analyzing the image snippet to determine a second navigational action for the host vehicle;
• and
• causing the host vehicle to implement the second navigational action.