Image Processing for Main Subject Selection Using Posture and Depth
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image capturing systems struggle to accurately determine the main subject when multiple subjects are present, particularly when the intended subject is facing away, leading to unintended subjects being focused on.
Innovation Solution
An electronic apparatus and method that utilizes multiple detection units to analyze subject posture, depth information, and machine learning to determine the main subject by adjusting reliability based on subject distance and object distance, ensuring the intended subject is prioritized.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If face detection is used to determine the main subject, then the main subject can be accurately identified when the subject is facing forward, but the system fails to identify the intended subject when the subject is facing backward
Solution Approach 1:
The system changes the detection parameters from face-only detection to body posture detection, allowing identification of subjects regardless of their facing direction. By detecting body orientation and posture parameters instead of relying solely on face detection, the system can accurately identify the intended subject even when facing backward.
Solution Approach 2:
The system adds depth dimension information to the detection process by acquiring depth images and calculating distance information. This third dimension (depth) allows the system to distinguish between subjects based on their spatial position relative to the camera, complementing the 2D posture detection and improving main subject identification accuracy.
2Productivity
If only face detection is used to determine main subject, then the detection process is simple and fast, but subjects without detected faces cannot be set as main subject
Solution Approach 1:
The detection system is enhanced to perform multiple functions: it can detect both faces and body postures, and can process both 2D image data and 3D depth data. This multi-functional approach allows the system to handle various subject types and postures reliably while maintaining efficient processing through integrated detection algorithms.
Solution Approach 2:
The system introduces an intermediary reliability calculation mechanism that combines multiple detection results (face detection, body posture detection, depth distance measurement) to determine the final main subject. This intermediary reliability score allows the system to weigh different detection outcomes and make more reliable decisions about which subject is the intended main subject.
Data Source
AI summary
An electronic apparatus comprises: a first detection unit that detects one or more subjects from any of images obtained by repeatedly performing shooting; a second detection unit that detects a predetermined object from the image from which the subject/subjects are detected; a determination unit that determines a reliability indicating a degree of possibility of a subject being a main subject based on a posture of each subject detected by the first detection means; an adjustment unit that adjusts the reliability based on a difference between information about a distance to each of the subjects in a depth direction and information about a distance to the object in a depth direction; and a decision unit that decides, based on the reliability adjusted by the adjustment unit, one of the subject/subjects detected by the first detecting unit as a main subject.