Subject Extraction Device Dynamic Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing subject extraction technologies face challenges in efficiently processing high-definition images in real-time, particularly when dealing with multiple subjects or complex shapes, leading to increased processing time and resource demands.
Innovation Solution
A subject extraction device that reduces image resolution, extracts subject possibilities, increases resolution of boundary areas, and dynamically assigns calculation resources based on the number of subjects, optimizing processing efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If resolution is reduced to low resolution for subject extraction, then processing speed is improved, but manufacturing precision (extraction accuracy) deteriorates
Solution Approach 1:
The image processing is divided into two stages: low-resolution processing for initial subject candidate extraction, and high-resolution processing only for boundary portions. This segmentation allows most of the image to be processed quickly at low resolution while only critical areas consume high computational resources.
Solution Approach 2:
Different resolution qualities are applied to different regions of the image. The boundary portions between subject and non-subject areas are processed at high resolution to ensure accurate extraction, while the rest of the image is processed at low resolution to maintain overall processing speed.
2Manufacturing precision
If calculation resources are increased for processing unclassified regions, then subject extraction accuracy is improved, but productivity (processing efficiency) deteriorates
Solution Approach 1:
The boundary portions requiring high-precision processing are extracted from the entire image and processed separately at high resolution. This allows concentrated calculation resources to be applied only where needed, rather than uniformly across the entire image.
Solution Approach 2:
Instead of processing the entire image at high resolution, only the necessary boundary portions are processed at high resolution. This partial action approach provides sufficient processing power for accurate extraction without the excessive computational cost of full high-resolution processing.
3Manufacturing precision
If the number of subjects increases or subject shapes become complicated, then the area of unclassified regions increases, but processing time exceeds the limited time available
Solution Approach 1:
The low-resolution processing is performed first to preliminarily identify subject candidates and their boundary portions. This preliminary action creates a roadmap for subsequent high-resolution processing, ensuring that time-critical processing is focused only on relevant areas.
Solution Approach 2:
The calculation resource allocation is made dynamic based on the number of subjects and the area of unclassified regions. When multiple subjects or complicated shapes are detected, the system automatically adjusts the proportion of high-resolution processing to handle the increased complexity while maintaining real-time performance.
Data Source
AI summary
A subject extraction device (10) according to the present disclosure includes: a resolution reducing unit (111) that reduces resolution of an image to generate a low resolution image; a subject possibility extraction unit (112) that extracts possibilities of a subject portion from the low resolution image; a resolution increasing unit (113) that increases resolution of a boundary portion between the subject portion and a non-subject portion, judges whether the boundary portion is the non-subject portion pixel by pixel, and decides the subject portion and the non-subject portion on the basis of a judgement result; and a calculation resource assignment unit (114) that determines a value of the calculation resource to be assigned to the subject possibility extraction unit (112) as a first value and determines a value of the calculation resource to be assigned to the resolution increasing unit (113) as a second value according to the number of subject portions, and assigns the calculation resource to the subject possibility extraction unit (112) and the resolution increasing unit (113) on the basis of the first value and the second value that have been determined.