Gesture Pre-Processing Hold-Off Period for Power Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current gesture recognition systems consume excessive power due to continuous image processing, even when no relevant gestures are being performed, leading to CPU utilization maxing out and increased power consumption, especially in mobile devices.
Innovation Solution
A stepped and distributed pipeline process for gesture pre-processing that selectively halts image processing during gesture-free periods and introduces a hold-off period when the user is engaged in other activities, reducing power consumption by processing key stages near the camera and CPU.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If continuous image processing is performed for gesture recognition, then gesture detection capability is maintained, but platform power consumption increases excessively
Solution Approach 1:
The patent implements periodic action by introducing a hold-off period mechanism that temporarily suspends gesture processing during specific time windows (e.g., during mouse or keyboard activity). The system alternates between active processing states and suspended states, reducing power consumption while maintaining gesture detection capability when needed. This periodic suspension of processing directly addresses the contradiction by allowing the system to conserve energy during periods when gesture input is unlikely to occur.
Solution Approach 2:
The patent applies dynamics by making the processing state adjustable rather than fixed. The system dynamically transitions between full processing mode and suspended mode based on detected user activity. When mouse or keyboard activity is detected, the system dynamically suspends gesture processing to save power. This dynamic state change allows the system to adapt its power consumption level to current usage conditions, resolving the contradiction between continuous detection capability and power savings.
2Productivity
If image processing continues during user interaction with mouse/keyboard, then gesture recognition remains ready, but CPU utilization maxes out and power consumption increases
Solution Approach 1:
The patent extracts the gesture processing function from continuous operation and separates it into conditional activation. By detecting mouse or keyboard activity as a trigger condition, the system extracts and suspends the processing function during these periods. This extraction allows the system to maintain readiness to process gestures when needed while eliminating unnecessary processing during periods when other input methods are active, thereby reducing CPU utilization and energy loss.
Solution Approach 2:
The system performs preliminary detection of user activity state (mouse/keyboard usage) before initiating full gesture processing. This preliminary check prevents unnecessary processing cycles from being executed, saving CPU resources and energy. The hold-off period mechanism acts as a preliminary barrier that stops processing before it can consume unnecessary cycles during periods when gesture input is unlikely.
3Use of energy by moving object
If gesture processing is suspended during other activities, then power consumption is reduced, but response time may be affected
Solution Approach 1:
The periodic hold-off period mechanism suspends processing only during specific time windows corresponding to other user activities. After the hold-off period expires, the system resumes normal gesture processing without significant delay. This periodic suspension approach minimizes the impact on response time by limiting suspension duration to periods when gesture input is unlikely, while still achieving substantial power savings during the suspended intervals.
Data Source
AI summary
Techniques are disclosed for processing a video stream to reduce platform power by employing a stepped and distributed pipeline process, wherein CPU-intensive processing is selectively performed. In one example case, the techniques are implemented in a user's computer system wherein initial threshold detection (image disturbance) and optionally user presence (e.g., hand image) processing components are proximate to or within the system's camera, and the camera is located in or proximate to the system's primary display. The threshold detection and/or target presence stages can be selectively disabled for a hold-off period. The hold-off period may be, for example, in the range of 50 to 1000 mSec and triggered in response to an indication that a user of the system is unlikely to be making navigational gestures or that the system is not ready to process video, thereby conserving power by avoiding processing of video frames free of navigation gestures.


