Method for Automatic Recognition of at Least the Type and/or Position of a Gesture Formed with a Limb, in Particular a Hand Gesture

Simple SummaryContent extracted from patent full text and abstract with AI.

This patent describes a method for automatically recognizing the type and/or position of a gesture made with a body part, especially a hand, by using multiple two-dimensional images captured simultaneously from different directions. The images are combined into a three-dimensional representation, which is then analyzed to determine gesture characteristics such as type (e.g., pointing, grasping) and spatial orientation. The method operates without needing markers attached to the limb and can run in real time, enabling intuitive and efficient gesture-based control systems.

Use CasesContent extracted from patent full text and abstract with AI.

• Controlling vehicles, robots, or machines using hand gestures
• Human-computer interaction in virtual or augmented reality environments
• Touchless operation of devices (e.g., smart TVs, kiosks, medical equipment)
• Interactive gaming systems based on gesture recognition
• Accessibility tools for users with limited mobility
• Industrial automation where workers can control machinery hands-free
• Smart home control through intuitive hand gestures

BenefitsContent extracted from patent full text and abstract with AI.

• Real-time gesture recognition enabling immediate response
• Works without physical markers on the hand or limb, improving user comfort
• Automatically initializes—no specific gesture required to start detection
• Provides both gesture type and spatial orientation for complex controls
• Can adapt to different users without manual calibration
• Enables natural and intuitive human-machine interaction
• Reduces need for physical contact with devices, increasing hygiene and convenience (especially important in medical or public settings)

Technical Classifications (CPCs)

Inventors & Applicants

Patent Abstract

The invention relates to a method for automatically detecting at least the type and/or the location (position and orientation) of a gesture made using an appendage, particularly a hand gesture, a plurality of two-dimensional images of the appendage being captured simultaneously from different directions. According to the invention, the two-dimensional images are combined into a three-dimensional image, and the three-dimensional image is analyzed with regard to at least one gesture characteristic. In this manner, a method for automatically recognizing gestures is disclosed, which can be performed in a simple and reliable manner in real time, and thus allows complex process controls, such as the control of a vehicle.