Distributed Gesture Disambiguation via Client-Server Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current gesture recognition systems are resource-intensive and can lead to delayed user experiences due to the need for local processing and potential server unavailability, limiting the complexity and speed of gesture recognition, especially in mobility situations.
Innovation Solution
The system optimizes gesture recognition by progressively refining pattern matches using server-based computational resources, allowing incremental candidate matches to be provided to the client device, reducing computational load and enabling faster identification through intelligent processing and bandwidth management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If gesture recognition is performed locally on the device, then gesture identification can proceed without server availability, but computational resources and power consumption increase significantly
Solution Approach 1:
The gesture recognition system is segmented into two parts: a lightweight local component that performs initial gesture capture and basic filtering, and a remote server component that performs complex pattern matching and identification. This segmentation allows the device to maintain reliability while reducing local computational burden and power consumption.
Solution Approach 2:
A server acts as an intermediary between the gesture-capturing device and the final identification process. The server receives gesture data, performs resource-intensive pattern matching, and returns identification results, thereby relieving the client device of heavy computational tasks while maintaining reliable gesture recognition.
2Measurement precision
If complete gesture data is transmitted to the server, then accurate gesture identification can be achieved, but transmission time and network bandwidth consumption increase
Solution Approach 1:
The system performs preliminary actions on the client side by capturing and pre-processing gesture data before transmission. Basic filtering and initial analysis are conducted locally to reduce the volume of data that needs to be transmitted, thereby maintaining identification accuracy while reducing transmission time and network bandwidth consumption.
3Adaptability or versatility
If a comprehensive gesture library is stored locally, then gesture recognition can proceed offline, but memory requirements and device complexity increase
Solution Approach 1:
The comprehensive gesture library and complex pattern matching algorithms are extracted from the client device and relocated to a remote server. This extraction allows the device to maintain offline capability for basic gesture capture while avoiding the complexity of storing extensive gesture libraries and running sophisticated recognition algorithms locally.
Data Source
Figure 1~2
Figure 3
Figure 4~5
AI summary
Optimized distributed disambiguation of gestures is disclosed. In one innovative aspect, there is a gesture controlled device. The gesture controlled device includes a sensor configured to detect an input gesture. The gesture controlled device also includes a gesture detector configured to obtain the input gesture. The gesture controlled device further includes a transmitter configured to transmit a candidate gesture request including a first portion of the input gesture, the transmission based at least in part on a resource characteristic of the gesture controlled device. The gesture controlled device also includes a receiver configured to receive a set of candidate gestures for the candidate gesture request. The gesture detector is configured to identify the input gesture based on a second portion of the input gesture and the received set of candidate gestures.