18365253. IMAGE PROCESSING APPARATUS AND CONTROL METHOD FOR SAME simplified abstract (CANON KABUSHIKI KAISHA)
IMAGE PROCESSING APPARATUS AND CONTROL METHOD FOR SAME
Organization Name
Inventor(s)
IMAGE PROCESSING APPARATUS AND CONTROL METHOD FOR SAME - A simplified explanation of the abstract
This abstract first appeared for US patent application 18365253 titled 'IMAGE PROCESSING APPARATUS AND CONTROL METHOD FOR SAME
Simplified Explanation
The patent application describes an image processing apparatus that can determine the region of an object in a captured image based on likelihood maps and region tensors.
- Obtaining unit captures an image.
- Likelihood obtaining unit obtains a likelihood map indicating the likelihood of an object's existence at each position in the image.
- Region obtaining unit obtains region tensors indicating the position and size of an object at each position in the image.
- Accepting unit accepts first position coordinates in the captured image.
- Region determining unit determines the object region corresponding to the first position coordinates based on the region tensors and likelihoods of multiple region candidates.
- Potential Applications
- Object detection in images
- Image segmentation for medical imaging
- Autonomous driving for identifying objects on the road
- Problems Solved
- Accurate object detection in images
- Efficient image processing for identifying objects
- Improved accuracy in determining object regions
- Benefits
- Enhanced image processing capabilities
- Increased accuracy in object detection
- Improved efficiency in analyzing images
Original Abstract Submitted
An image processing apparatus comprises: an obtaining unit configured to obtain a captured image; a likelihood obtaining unit configured to obtain a likelihood map indicating a likelihood of existence of an object at each position of the captured image; a region obtaining unit configured to obtain, at each position of the captured image, a region tensor indicating a position and a size of an object with respect to each position; an accepting unit configured to accept first position coordinates with respect to the captured image; and a region determining unit configured to determine an object region corresponding to the first position coordinates, based on the region tensor and likelihoods of the likelihood map corresponding to two or more region candidates each indicated by the region tensor based on the first position coordinate.
(Ad) Transform your business with AI in minutes, not months
Trusted by 1,000+ companies worldwide