Back to results
US 10,650,523 B2Granted
Image segmentation method, image segmentation system and storage medium and apparatus including the same
AssigneeBoe Technology Group Co., Ltd.
InventorsJibo Zhao, Xiaojun Tang
Life of this patent
Estimating the term…
Abstract
An image segmentation method, an image segmentation system, a storage medium and an apparatus including the image segmentation system or the storage medium are provided. The image segmentation method includes: obtaining a connected region where a target object is located from a depth image; determining a principal direction or a secondary direction of the connected region by a principal component analysis method; and acquiring an image of the target object from the connected region according to relationship between morphology of the target object and the principal direction or the secondary direction.
Claims18
An image segmentation method, comprising:
- obtaining a connected region where a target object is located from a depth image;
- determining a principal direction or a secondary direction of the connected region by a principal component analysis method;
- and
- acquiring an image of the target object from the connected region according to a relationship between a morphology of the target object and the principal direction or the secondary direction, wherein the acquiring the image of the target object comprises:
- determining a variation trend of pixel-point numbers respectively at a plurality of positions in the connected region along the principal direction, wherein pixel points at each of the plurality of positions are sequentially arranged along the secondary direction of the connected region, and the secondary direction is perpendicular to the principal direction;
- comparing the variation trend with a variation trend of the morphology of the target object along the principal direction;
- and
- determining a segmentation position for acquiring the image of the target object in the connected region according to a comparison result.
5 more elements
An image segmentation system, comprising:
- a first image segmentation device configured to process a depth image to obtain a connected region where a target object is located from the depth image;
- an analysis device connected to the first image segmentation device and configured to determine a principal direction or a secondary direction of the connected region acquired by the first image segmentation device by a principal component analysis method;
- and
- a second image segmentation device connected to the analysis device and configured to acquire an image of the target object from the connected region according to relationship between morphology of the target object and the principal direction or the secondary direction, wherein the second image segmentation device comprises:
- a calculator device connected to the analysis device and configured to calculate pixel-point numbers respectively at a plurality of positions in the connected region and to determine a variation trend of the pixel-point numbers along the principal direction, in which pixel points at each of the plurality of positions are sequentially arranged along the secondary direction of the connected region, and the secondary direction is perpendicular to the principal direction;
- and
- a comparison device connected to the calculator device and configured to compare the variation trend with a variation trend of the morphology of the target object along the principal direction, to determine a segmentation position for acquiring the image of the target object in the connected region.
4 more elements
An image segmentation method, comprising:
- obtaining a connected region where a target object is located from a depth image;
- determining a principal direction or a secondary direction of the connected region by a principal component analysis method;
- and
- acquiring an image of the target object from the connected region according to a relationship between a morphology of the target object and the principal direction or the secondary direction, wherein the acquiring the image of the target object comprises:
- determining a real width of the connected region along the secondary direction at each of a plurality of positions, wherein the secondary direction is perpendicular to the principal direction, the plurality of positions are sequentially arranged along the principal direction, and pixel points at each of the plurality of positions are sequentially arranged along the secondary direction;
- and
- comparing the real width with a reference width to determine a segmentation position for acquiring the image of the target object in the connected region.
4 more elements
Dependencies are inferred from the claim text.