Main Subject Determination Using Posture and Reliability Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image capturing technologies struggle to determine a main subject in images with multiple subjects, failing to accurately match user intentions.
Innovation Solution
A main subject determining apparatus that detects multiple subjects from an image, obtains posture information for each subject, calculates a reliability score based on this information, and determines the main subject based on these scores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional subject detection techniques are used to detect subjects in an image, then multiple subjects can be detected, but the main subject cannot be accurately determined among them
Solution Approach 1:
The patent changes the parameter of subject evaluation from simple detection to multi-dimensional assessment including posture information and interaction relationships. By introducing posture parameters (standing, sitting, kneeling, lying down) and interaction parameters (gaze direction, body orientation relative to other subjects), the system transforms the determination criterion from binary detection to graded evaluation, thereby improving main subject identification accuracy among multiple detected subjects.
Solution Approach 2:
The patent introduces posture information and interaction relationship information as intermediary elements between subject detection and main subject determination. These intermediaries serve as additional criteria that mediate the selection process: posture information indicates subject stability and prominence, while interaction relationships (gaze direction, body orientation) reveal social dynamics and focal points, collectively enabling more reliable main subject identification.
2Measurement precision
If simple subject detection is performed without posture information, then detection speed is maintained, but the ability to determine the main subject is insufficient
Solution Approach 1:
The patent segments the main subject determination process into distinct modular components: (1) subject detection module that identifies multiple subjects, (2) posture information extraction module that determines posture states, (3) interaction relationship analysis module that evaluates gaze and body orientation, and (4) main subject determination module that synthesizes these inputs. This segmentation allows each module to perform its specific function independently, managing complexity through functional decomposition while achieving comprehensive analysis.
Solution Approach 2:
The patent applies partial action by selectively extracting only the most relevant features (posture state and interaction relationships) rather than analyzing all possible image attributes. This partial analysis approach focuses computational resources on key discriminative features that most strongly indicate main subject status, achieving high accuracy without requiring exhaustive processing of all image data.
3Measurement precision
If posture information and interaction relationships are analyzed for all subjects, then main subject determination accuracy improves, but processing time increases
Solution Approach 1:
The patent performs preliminary subject detection and grouping before detailed posture and interaction analysis. By first identifying all subjects and their spatial relationships, the system prepares structured input data that facilitates faster subsequent analysis of posture and interaction features. This preliminary organization prevents redundant processing and enables efficient computation during the main subject determination phase.
Solution Approach 2:
The patent applies local quality by focusing detailed posture and interaction analysis primarily on subjects that are likely to be the main subject based on initial detection results. Rather than uniformly analyzing all detected subjects with equal computational resources, the system concentrates processing effort on regions and subjects with higher probability of being the main subject (e.g., centrally located subjects, those with prominent postures), thereby reducing overall processing time while maintaining accuracy.
Data Source
AI summary
There is provided a main subject determining apparatus. A subject detecting unit detects a plurality of subjects from a first image. An obtaining unit obtains posture information of each of the plurality of subjects. For each of the plurality of subjects, a calculating unit calculates, on the basis of the posture information of the subject, a reliability corresponding to a likelihood that the subject is a main subject in the first image. A determining unit determines the main subject of the first image from among the plurality of subjects on the basis of the plurality of reliabilities calculated for the plurality of subjects.