Depth-Based Gesture Detection for Interactive Projection Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gesture detection systems face challenges in accurately distinguishing between hands making gestures and those holding objects, leading to erroneous detection and unintended actions in interactive projection systems.
Innovation Solution
The method involves acquiring depth information to determine the distance from a reference surface to a target object's representative point, using this information to differentiate between hands making gestures and those holding objects by applying a predetermined distance condition, thereby accurately detecting the gesturing hand.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If background image subtraction method is used to detect detection target, then gesture detection can be performed, but hands holding objects cannot be distinguished from gesturing hands
Solution Approach 1:
The patent transitions from 2D image processing to 3D spatial processing by acquiring depth information for each pixel. This additional dimensional data enables the system to distinguish between hands at different distances from the projection surface, allowing reliable differentiation between gesturing hands and hands holding objects.
Solution Approach 2:
The patent introduces depth information as an intermediary parameter between the captured image and the detection target identification. This intermediate depth data serves as a discriminator that resolves the ambiguity between different types of hands in the image, enabling accurate gesture detection while excluding hands holding objects.
2Adaptability or versatility
If all hands in the captured image are treated as detection targets, then no hands are excluded, but erroneous detection occurs due to hands holding objects
Solution Approach 1:
The patent applies different detection criteria to different spatial regions by using depth information. Hands within a specific distance range from the projection surface are identified as valid detection targets, while hands outside this range (likely holding objects) are excluded. This localized quality control improves gesture recognition accuracy without unnecessarily reducing detection coverage.
3Measurement precision
If depth information processing is added to distinguish hands, then detection accuracy improves, but processing complexity increases
Solution Approach 1:
The patent replaces complex mechanical or algorithmic analysis with a simpler depth-based filtering approach. Instead of using sophisticated image processing to analyze hand poses and gestures, the system simply compares depth values against a threshold, significantly reducing processing complexity while maintaining high detection accuracy.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach effectively removes hands holding objects from the detection target, ensuring accurate gesture recognition and preventing unintended actions, while maintaining a simple configuration and low processing load.
Implementation Method 1
depth information related to depth of a reference surface of a component and a target object
Data Source
AI summary
A detecting method executed by at least one processor includes acquiring depth information related to depth of a reference surface of a component and a target object. The detecting method further includes deriving a distance from the reference surface to a representative point of the target object based on the depth information. The distance is along an approximate normal to the reference surface. The detecting method further includes detecting the target object as a detection target, upon the distance satisfying a predetermined distance condition.