Hand Posture Inference for CG Alignment Under Occlusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to accurately calculate the orientation of a CG object relative to a user's hand during hand gesture recognition due to partial occlusion of hand parts, such as fingertips, making it difficult to align the CG object with the actual hand orientation.
Innovation Solution
An information processing apparatus that stores information on a first hand posture and infers the posture of a second hand based on specific parts, using a processor to execute storage and inference processing, even when the second hand is partially occluded.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If hand gesture recognition is performed using captured images, then interaction with CG objects is enabled, but accurate alignment of CG object orientation with hand orientation cannot be achieved when hand parts are occluded
Solution Approach 1:
The system performs preliminary action by storing reference information about hand postures in advance. When the hand is in a specific gesture, the system stores image data and gesture posture information in a storage unit. This pre-stored information is then used to infer the gesture posture even when the hand is occluded in later frames, enabling continuous accurate alignment without requiring real-time detection of all hand parts.
Solution Approach 2:
The system uses copying by creating a virtual model of the hand gesture posture based on stored reference information. When the actual hand is occluded, the system copies the previously stored gesture posture data and applies it to maintain the CG object alignment, rather than attempting to detect the occluded hand directly.
2Productivity
If only currently visible hand parts are used for gesture recognition, then real-time processing is simplified, but gesture posture cannot be accurately determined when fingertips are occluded
Solution Approach 1:
The system performs preliminary action by storing reference information about hand postures in advance. When the hand is in a specific gesture, the system stores image data and gesture posture information in a storage unit. This pre-stored information is then used to infer the gesture posture even when the hand is occluded in later frames, enabling continuous accurate alignment without requiring real-time detection of all hand parts.
Solution Approach 2:
The system introduces an intermediary mechanism - the storage unit containing reference gesture information - that mediates between the occluded hand in the current frame and the required gesture posture determination. Instead of directly detecting the occluded hand, the system uses the stored reference information as an intermediary to infer the current gesture posture.
Data Source
AI summary
An information processing apparatus includes a processor and a memory storing a program which, when executed by the processor, causes the information processing apparatus to execute storage processing for storing information that is based on a first posture in the memory when a first hand included in a first captured image is in the first posture representing a specific gesture in the first captured image, and execute inference processing, when a specific part of a second hand is included in a second captured image that is captured after the first captured image, for inferring a posture of the second hand corresponding to the specific gesture, wherein the inference processing is performed based on the information and a posture of the specific part, even if the second hand included in the second captured image does not exhibit the specific gesture.