Silhouette-Based Motion Capture Using Depth Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current motion capturing technologies require expensive equipment and are spatially limited, making them difficult to commercialize, as they often rely on markers, sensors, and multiple cameras to achieve accurate 3D motion capture of human bodies for applications like video games and virtual reality.
Innovation Solution
An image processing apparatus and method that extracts silhouette images from depth images using a rectangle fitting algorithm to determine limb and joint locations, applying inverse-kinematics to generate a skeleton model and calculate motion capture information without the need for external markers or sensors, thereby reducing equipment costs and spatial restrictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If motion capturing is performed using markers, sensors, or multiple cameras, then motion capture accuracy is improved, but equipment cost and device complexity increase
Solution Approach 1:
The patent extracts and removes the requirement for external markers and sensors from the motion capture system. By using only a single depth camera to capture and process silhouette images, the system eliminates the need for additional marking devices and sensor equipment, thereby reducing device complexity while maintaining motion capture functionality
Solution Approach 2:
The depth camera performs multiple functions: it captures depth information, generates silhouette images, and enables motion capture without requiring separate specialized equipment for each function. This multi-functionality reduces the overall number of devices needed while maintaining measurement accuracy
2Measurement precision
If motion capturing is performed using markers, sensors, or multiple cameras, then motion capture accuracy is improved, but spatial limitations increase
Solution Approach 1:
The patent removes the requirement for multiple cameras and specialized marking equipment, extracting only the essential depth imaging function. This reduction in equipment requirements eliminates spatial constraints associated with positioning multiple cameras and markers, thereby improving spatial flexibility and adaptability
Solution Approach 2:
The system changes the operational parameters from requiring multiple devices with specific spatial arrangements to using a single depth camera with depth-based silhouette extraction. This parameter change enables the system to operate in more varied spatial environments without strict positioning requirements
3Measurement precision
If traditional motion capturing schemes are used, then motion capture accuracy is improved, but commercialization difficulty increases due to expensive equipment
Solution Approach 1:
The patent replaces expensive, specialized motion capture equipment with a single, relatively inexpensive depth camera. This substitution dramatically reduces equipment costs, making the system more accessible and easier to commercialize while maintaining adequate motion capture accuracy for practical applications
Solution Approach 2:
The system replaces complex mechanical and optical systems (multiple cameras, markers, sensors) with a simplified electronic depth imaging and image processing system. This substitution reduces hardware complexity and cost while maintaining the core functionality of motion capture
Data Source
AI summary
An image processing apparatus is provided. A silhouette extractor may extract a silhouette image of a target object from an input depth image. A first calculator may determine a location of at least one limb of the target object and a location of at least one joint connecting the at least one limb by applying a rectangle fitting algorithm with respect to the silhouette image.