Instance segmentation imaging system
AssigneeISEE, Inc.
InventorsJonah Philion, Yibiao Zhao
Life of this patent
Estimating the term…
Abstract
A method of instance segmentation in an image and a system for instance segmentation of images. The method includes identifying, with a processor, a starting pixel associated with an object in an image, the image having a plurality of rows of pixels, the starting pixel located in a row of the plurality of rows; identifying, with the processor, at least one pixel located in an adjacent row to the row in which the starting pixel is located, the at least one pixel being part of the same object as the starting pixel; iterating the previous two identification steps using the at least one identified adjacent row pixel as a start pixel for the next iteration; and connecting, with the processor, the at least one identified adjacent row pixels to form polylines representing the object.
Claims20
A method for identifying an object in an image associated with operation of an autonomous vehicle comprising:
- (a) identifying, with a processor, at least one starting pixel associated with the object in the image, the image having a plurality of rows of pixels, the at least one starting pixel located in a first identified row of the plurality of rows;
- (b) identifying, with the processor, at least one adjacent pixel located in an adjacent row to the first identified row, the at least one adjacent pixel being part of the object;
- (c) iterating steps (a)-(b) using the identified at least one adjacent pixel as a starting pixel or starting pixels for a next iteration of steps (a)-(b);
- and
- (d) forming, with the processor, a line through the identified at least one adjacent pixel located in the adjacent row to the first identified row, to represent the object.
An autonomous driving system for a vehicle comprising a motion planning subsystem and a lane object detection system,
- wherein the lane object detection system comprises a processor configured to:
- (a) identify at least one starting pixel in an image, the at least one starting pixel associated with a lane object in the image;
- the image having a plurality of rows of pixels, the at least one starting pixel located in a first row of the plurality of rows;
- (b) identify at least one adjacent pixel in a row adjacent to the first row, wherein the at least one adjacent pixel is part of the lane object;
- (c) iterate steps (a)-(b) using the at least one identified adjacent pixel as a starting pixel or starting pixels for a next iteration of steps (a)-(b);
- and
- (d) form a line through the at least one adjacent pixel located in the adjacent row to the first identified row, to represent the lane object.
Dependencies are inferred from the claim text.