20240037926. SEGMENTING OBJECTS BY REFINING SHAPE PRIORS simplified abstract (GOOGLE LLC)
Contents
SEGMENTING OBJECTS BY REFINING SHAPE PRIORS
Organization Name
Inventor(s)
Weicheng Kuo of Berkeley CA (US)
Anelia Angelova of Sunnyvale CA (US)
Tsung-Yi Lin of Sunnyvale CA (US)
SEGMENTING OBJECTS BY REFINING SHAPE PRIORS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240037926 titled 'SEGMENTING OBJECTS BY REFINING SHAPE PRIORS
Simplified Explanation
The patent application describes methods, systems, and apparatus for performing instance segmentation by detecting and segmenting individual objects in an image. Here is a simplified explanation of the abstract:
- The method involves processing an image to identify a region depicting a specific object.
- Example object segmentations are obtained and weight values are generated for each of them.
- For each pixel in the region, a score is determined to indicate the likelihood of it being part of the object, using the example object segmentations and their weight values.
- A segmentation of the object in the region is generated based on the scores of the pixels.
Potential applications of this technology:
- Object recognition and tracking in computer vision systems.
- Autonomous vehicles for identifying and segmenting objects in real-time.
- Medical imaging for identifying and segmenting specific structures or organs.
Problems solved by this technology:
- Accurate and efficient detection and segmentation of individual objects in images.
- Overcoming challenges in object recognition and tracking in complex scenes.
- Improving the accuracy and reliability of medical imaging analysis.
Benefits of this technology:
- Enhanced object detection and segmentation capabilities.
- Improved accuracy and efficiency in computer vision systems.
- Facilitates advanced analysis and understanding of complex images.
- Enables automation and efficiency in various industries such as autonomous vehicles and healthcare.
Original Abstract Submitted
methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing instance segmentation by detecting and segmenting individual objects in an image. in one aspect, a method comprises: processing an image to generate data identifying a region of the image that depicts a particular object; obtaining data defining a plurality of example object segmentations; generating a respective weight value for each of the example object segmentations; for each of a plurality of pixels in the region of the image, determining a score characterizing a likelihood that the pixel is included in the particular object depicted in the region of the image using: (i) the example object segmentations, and (ii) the weight values for the example object segmentations; and generating a segmentation of the particular object depicted in the region of the image using the scores for the pixels in the region of the image.
