Image Processing Apparatus Subject Determination via Posture Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing techniques struggle to accurately determine the main subject in images, especially when multiple subjects are present and a subject not targeted by the user assumes a posture of interest.
Innovation Solution
An image processing apparatus that detects specific subjects from an image, evaluates their posture, and determines the main subject based on reliability and user-defined priority targets, utilizing a neural network for probability calculations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If posture-based subject determination is used, then detection speed is improved, but determination accuracy deteriorates when multiple subjects are present
Solution Approach 1:
The patent segments the subject determination process into two independent stages: first detecting all subjects based on posture characteristics, then evaluating each subject's reliability separately using multiple criteria (posture match degree, distance to ball, team affiliation). This segmentation allows fast initial detection while enabling accurate final determination through systematic evaluation of multiple factors for each subject.
Solution Approach 2:
The patent changes from relying on a single posture parameter to evaluating multiple parameters simultaneously: posture match degree, distance to ball, distance to goal, team affiliation, and player position. By changing from one-dimensional to multi-dimensional parameter evaluation, the system maintains detection speed while significantly improving determination accuracy in complex scenes with multiple subjects.
2Device complexity
If simple posture detection is used, then device complexity is reduced, but reliability of main subject determination deteriorates
Solution Approach 1:
The patent performs preliminary actions by first detecting all subjects with matching postures, then pre-evaluating their reliability based on multiple criteria before final determination. This preliminary multi-criteria evaluation structure ensures high reliability by systematically considering posture match, spatial relationships, team affiliation, and position, while keeping the overall process organized and manageable despite the complexity of multiple factors.
Data Source
AI summary
An image processing apparatus includes one or more processors that, when executing a program stored in a memory, cause the image processing apparatus to detect specific subjects from an image, detect a posture of each of the detected subjects, acquire a degree of reliability of being a main subject for each of the detected subjects based on the posture, acquire information on a priority target, and determine the main subject based on the degree of reliability and the information on the priority target.