Image Processing Apparatus Subject Orientation Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image processing systems fail to accurately determine the orientation of a subject in a captured image, leading to inappropriate framing in lecture capture systems and other applications where precise subject tracking is necessary.

Innovation Solution

An image processing apparatus that detects a face and predetermined parts of a subject, determines the direction each part faces, and decides the subject's orientation by combining the face and part direction determinations, using a counter value system to smooth out orientation changes over time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If face direction and part direction are determined separately and combined, then measurement precision of subject orientation is improved, but device complexity increases due to multiple detectors and determiners

Engineering Contradiction:
Improvesubject orientation detection accuracyVSAvoidsystem structure complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the subject orientation detection into multiple independent components: face direction determination and part direction determination. Each component processes specific features separately, allowing for specialized algorithms optimized for each body part type. This segmentation improves measurement precision by treating different body parts with appropriate methods while maintaining manageable system complexity through modular architecture.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent merges the results from face direction determination and part direction determination through a weighted combination process. The counter value accumulation mechanism integrates multiple direction measurements, combining them to produce a final subject orientation decision. This merging approach leverages the strengths of both face-based and part-based detection to achieve higher overall accuracy.

Inventive Principle:
Principle #5Merging (Combining)

2Measurement precision

If multiple body parts are detected and analyzed, then measurement precision of subject orientation is improved, but loss of time increases due to multiple detection steps

Engineering Contradiction:
Improvesubject orientation detection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent implements preliminary action by detecting and analyzing body parts in parallel rather than sequentially. Multiple detectors operate simultaneously on different body parts, and direction determiners process their respective inputs concurrently. This parallel processing approach maintains high measurement precision while significantly reducing the total processing time compared to sequential analysis.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent maintains continuity of useful action through the counter value accumulation mechanism, which continuously integrates direction information from multiple body parts as they are detected. Rather than waiting for all detections to complete before processing, the system continuously updates orientation estimates as new detection data becomes available, ensuring uninterrupted and efficient processing.

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentUS20230215038A1Image processing apparatus, image processing method, and recording medium
Publication Date: 2023.07.06 SONY GROUP CORP
  • US20230215038A1 patent drawing
  • US20230215038A1 patent drawing
  • US20230215038A1 patent drawing

AI summary

The present technology relates to an image processing apparatus, an image processing method, and a recording medium capable of appropriately determining a direction in which a subject being imaged faces.The present technology includes a detector that detects a face and a predetermined part of a subject in a captured image, a face direction determiner that determines a direction in which the face detected by the detector faces, a part direction determiner that determines a direction in which the predetermined part detected by the detector faces, and a first direction decider that decides a direction in which the subject faces by using a determination result by the face direction determiner and a determination result by the part direction determiner. The present technology can be applied to an image processing apparatus that controls framing.