| CPC G06V 10/44 (2022.01) [G06T 7/70 (2017.01); G06T 7/80 (2017.01); G06V 20/56 (2022.01); G06T 2200/04 (2013.01); G06T 2207/30244 (2013.01); G06T 2207/30252 (2013.01)] | 20 Claims |
|
1. An information processing device for vehicle mounted systems for acquiring information about a surrounding environment, the information processing device comprising:
an image acquisition unit connected to a camera on a vehicle;
a pixel extraction unit configured to select certain pixels in an array pattern for extraction from a first image from the image acquisition unit, then extracting the selected certain pixels for a plurality of extracted pixels to acquire information from the plurality of extracted pixels in the first image, the first image comprising pixels rows along a first direction and pixel columns along a second direction crossing the first direction, the plurality of extracted pixels being less than all pixels in the first image and including pixels in a first pixel row that are spaced from each other at a shift in the first direction equal to a first number of pixels and pixels in a second pixel row along the first direction that are spaced from each other at a shift in the first direction equal to the first number of pixels but offset from the pixels in the first pixel row by at least one pixel in the first direction, the second pixel row having a shift of a second number of pixels from the first pixel row in the second direction;
a self-location estimation unit configured to estimate a location and orientation of the camera on the vehicle, the camera having a lens aberration and providing the first image as distorted by the lens aberration;
a determination unit configured to detect whether a the target object is present in the first image based on the plurality of extracted pixels;
a three-dimensional location estimation unit configured to reconstruct three-dimensional information related to a surrounding environment of the vehicle based on the information from the plurality of extracted pixels and the location and orientation of the camera as estimated by the self-location estimation unit to estimate a three-dimensional location of the target object in the surrounding environment of the vehicle from the first image; and
an image processing unit configured to execute image processing to correct the first image with respect to one or more characteristics of the camera, wherein
the pixel extraction unit acquires the information from the plurality of extracted pixels in the first image based on a corrected image from the image processing unit, and
the image processing unit corrects the original first image to remove a distortion resulting from the lens aberration affecting the original first image and to place a vertically standing object depicted in the original image to be parallel to the second direction in the corrected first image.
|