Human Body Orientation Detection via Head Contour Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Smart full-length mirrors struggle to accurately determine human body orientation, leading to unreasonable visual effects when users are positioned sideways, as existing systems often rely on face detection, which can be misleading.

Innovation Solution

A detection device and method using a camera and processing device to capture human-body images, isolate the head contour, and input the image to a classifier to determine human-body orientation probabilities, ensuring accurate determination of body orientation (front, side, or back) by setting an accuracy threshold.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If face detection is used to determine human body orientation, then the detection process is simple, but the orientation determination accuracy deteriorates when users are positioned sideways

Engineering Contradiction:

Improvedetection process complexityVSAvoidorientation determination accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent segments the human body detection task into multiple parts: first detecting the head contour, then detecting the body contour separately, and finally combining both to determine orientation. This segmentation allows the system to capture both head orientation and body orientation, resolving the contradiction by using multiple detection targets rather than relying solely on face detection.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary processing step that combines head contour detection results with body contour detection results. The head contour serves as an intermediary element that helps determine overall body orientation, especially when the body and head are in different orientations (e.g., user looking at mirror while body is sideways).

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If head contour detection is added to body contour detection, then orientation determination accuracy improves, but device complexity increases

Engineering Contradiction:

Improveorientation determination accuracyVSAvoiddetection system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent merges the head contour detection function with the body contour detection function into a unified detection system. Both contours are detected simultaneously using the same camera and processing device, and their results are combined to determine orientation. This merging approach improves accuracy without proportionally increasing device complexity.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS11816860B2Detection device for detecting human-body orientation and detection method for detecting human-body orientation

Publication Date: 2023.11.14 WISTRON CORP

AI summary

A detection device for detecting human-body orientation includes a camera and a processing device. The camera is configured to capture a human-body image. The processing device is configured to cut a human head contour image in the human-body image to obtain an input image, and input the input image to a classifier. The classifier outputs a plurality of human-body orientation probabilities for the input image. The processing device finds the highest human-body orientation probability, and determines whether the highest human-body orientation probability is above the accuracy threshold. In response to the highest human-body orientation probability being above the accuracy threshold, the processing device regards the human-body orientation corresponding to the highest human-body orientation probability as the determined human-body orientation.