Looking through the Eye of the Mouse: A Simple Method for Measuring End-to-end ...
summary
A simple bench uses an optical mouse as sensor plus a tailored screen texture to trigger real mouse reports and timestamp them with probes at HID, pointer, toolkit and repaint stages; the setup runs in real time up to 5 measurements per second and recovers the sensor raw image via Arduino to design the pattern. Tests on 10 mice (two failed) give a mean end-to-end of about 70 ms and reveal ~20 ms differences between GLUT and Qt/Java Swing; laser mice do not work.
AI-written summary · about
chapters (13)
- 0:00Introduction to hand latency
- 1:07Limitations of camera-based methods
- 2:56Understanding mouse sensor technology
- 4:26Screen door effect and texture design
- 7:17Evaluating texture patterns
- 8:18Calibrating mouse transfer function
- 9:00Testing with different mice and monitors
- 10:04Position-dependent latency variations
- 10:45Inserting probes into the system
- 12:08Comparing toolkits and latency distributions
- 13:12Impact of system load on latency
- 14:19Conclusion and future work
- 15:27Q&A session
related talks
19mUsing High Frequency Accelerometer and Mouse to Compensate for End-to-end Latency in Indirect ...
10mDo We Need a Faster Mouse? Empirical Evaluation of Asynchronicity-Induced Jitter
16mCharacterizing Latency in Touch and Button-Equipped Interactive Systems
44mThe Input Shouldn't Matter - Building for Adaptive Input Experiences
19mInvestigating Effects of Post-Selection Feedback for Acquiring Ultra-Small Targets on Touchscreen
12mComputers are fast! But how come they sometimes feel slow?
01h 00mMeasuring Qt Performance
19mAn Eye For Design: Gaze Visualizations for Remote Collaborative Work