Event-Based Vision Sensor for Gesture Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing user interface technologies, such as touch panels, face issues with screen damage and unhygienic interactions due to direct contact, and struggle to accurately distinguish between small and large movements for effective gesture recognition.
Innovation Solution
An apparatus and method using a vision sensor to recognize motion by determining movement types based on event frequency, tracking trajectories, and controlling devices with a motion controller, capable of rapid recognition (1 ms) and low power consumption, while being insensitive to environmental brightness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If touch panel technology is used for user interaction, then direct contact control is achieved, but screen damage occurs and hygiene issues arise due to repeated contact
Solution Approach 1:
The patent introduces an event-based vision sensor as an intermediary device that detects hand gestures and movements in the air space above the screen without requiring direct contact. The sensor captures motion events and translates them into control signals, serving as a mediator between the user and the device while eliminating physical contact with the screen surface.
Solution Approach 2:
The patent replaces the mechanical touch contact system with an optical detection system. Instead of relying on physical touch events that damage the screen, the system uses an event-based vision sensor to detect hand gestures, finger movements, and object interactions through optical fields, thereby substituting mechanical interaction with optical sensing.
2Measurement precision
If conventional vision sensors are used for gesture recognition, then motion detection is achieved, but power consumption is high and recognition speed is slow
Solution Approach 1:
The patent employs event-based sampling where the vision sensor only activates and captures data when motion events occur, rather than continuously sampling at high frequencies. This event-triggered periodic action allows the system to maintain high recognition accuracy for gestures while dramatically reducing average power consumption by keeping the sensor in a low-power state between events.
3Measurement precision
If conventional vision sensors are used for motion recognition, then motion detection is achieved, but performance is affected by environmental brightness
Solution Approach 1:
The patent implements preliminary differentiation of event types based on motion direction (toward or away from the sensor) before full processing occurs. This preliminary action allows the system to quickly categorize events and apply appropriate processing algorithms that are robust to varying lighting conditions, maintaining detection accuracy across different environmental brightness levels.
4Measurement precision
If distinction between small and large movements is made, then accurate gesture recognition is achieved, but device complexity increases
Solution Approach 1:
The patent applies partial action by implementing a hierarchical analysis approach where only the necessary level of motion analysis is performed. For small movements, the system focuses on fine-grained trajectory analysis, while for large movements, it uses coarser direction-based classification. This selective application of analysis depth maintains measurement precision while avoiding the complexity of implementing all possible analysis methods simultaneously.
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
Enables intuitive and hygienic interaction by accurately distinguishing between small and large movements, reducing screen damage and power consumption, and maintaining performance across varying environmental conditions.
Implementation Method 1
a vision sensor for sensing a movement-occurring part
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
An apparatus and method for recognizing motion by using an event-based vision sensor is provided. An apparatus for recognizing motion using an event-based vision sensor includes: a vision sensor to sense a movement-occurring part and output events; a movement type determiner configured to determine a type of movement using a frequency of occurrence of the events outputted through the vision sensor; a first motion determiner configured to track a movement trajectory of the movement-occurring part and determine a motion pattern based on the movement trajectory in response to a result of the movement type determination unit indicating a small movement; a second motion determiner configured to determine a direction of movement direction in which an object moves based on the events in response to a result of the movement type determination indicating a large movement; and a motion controller configured to output a control instruction to control a device.