Behavior Recognition via Distance-Based Field of Vision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current face recognition and behavior recognition technologies in smart interaction systems face challenges in accuracy, particularly when determining if a face is with closed eyes, which affects the precision of user behavior detection and subsequent operating instructions.
Innovation Solution
A method that involves collecting images, detecting faces, determining if eyes are closed, computing the distance between the face and the image collecting unit, and calculating the maximum field of vision to accurately assess user behavior and generate operating instructions, using techniques like CenterFace and RT-BENE for face detection and closed-eye detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional face recognition technology is used, then the system can detect faces, but the accuracy of expression or behavior recognition fails to meet requirements
Solution Approach 1:
The patent segments the face detection and behavior recognition into distinct modules: face detection module, closed-eye detection module, distance calculation module, and behavior recognition module. Each module handles a specific aspect independently, improving overall accuracy by allowing specialized processing for each function without compromising the other.
Solution Approach 2:
The patent introduces a new dimension of analysis by calculating the distance between the face and image collecting unit, and using this to determine the maximum field of vision. This spatial dimension addition enables more accurate behavior recognition by considering both the facial features and the spatial relationship with the imaging device.
2Measurement precision
If the system calculates distance and maximum field of vision, then behavior recognition accuracy improves, but the processing complexity increases
Solution Approach 1:
The patent performs preliminary actions by pre-establishing the relationship between image collecting unit parameters and field of vision calculations. The maximum field of vision is calculated based on pre-determined geometric relationships and camera parameters, allowing the system to avoid complex real-time calculations while maintaining high accuracy in behavior recognition.
Data Source
AI summary
A method and device for behavior recognition are provided. According the present disclosure, an image is collected. It is detected whether the image includes a face. When the image includes a face, it is determined whether the face in the image is a face with closed eyes. When the face in the image is not with closed eyes, a distance between the face and an image collecting unit is computed. A maximum field of vision of a target to which the face belongs is determined according to the distance and a parameter of the image collecting unit. It is determined, according to the maximum field of vision, whether the target has a set behavior.