Display power management that detects user intent

Jae Min Kim, Minyong Kim, Joonho Kong, Hyung Beom Jang, Sung Woo Chung

Research output: Contribution to specialist publicationArticle

1 Citation (Scopus)


A scheme has been developed that refines detection by identifying states of user presence from retrieved webcam images, such as detecting if the user is attentive or inattentive. To guard against false detections, an intermediate state, weakly attentive is included, that allows the face-detection algorithm to retrieve another webcam picture a few seconds later and recheck for a frontal face image. The scheme recognizes four states that correspond to the user's physical state. The user can also go directly from an inattentive to interactive state when he turns around to look at the display and open a file. To implement the display power management (DPM) scheme, a system is used that consists of one main coordinating function and four subfunctions: message hooking control, camera control, image processing, and power management. Once the algorithm identifies the user's state, the image-processing function sends the results to the main function, which then calls the power management function to change the power mode according to the predefined policy.

Original languageEnglish
Number of pages7
Specialist publicationComputer
Publication statusPublished - 2011 Oct

Bibliographical note

Funding Information:
This research was supported by the Basic Science Research Program of the National Research Foundation of Korea, funded by the Ministry of Education, Science and Technology under contract 2011-0004917, and the Ministry of Knowledge Economy, Korea, Information Technology Research Center support program, supervised by the National IT Industry Promotion Agency under contract NIPA-2011-C1090-1121-0010.


  • Context-aware computing
  • Display power management
  • Green computing
  • Laptop energy consumption

ASJC Scopus subject areas

  • General Computer Science


Dive into the research topics of 'Display power management that detects user intent'. Together they form a unique fingerprint.

Cite this