Evaluation of Hand Pointing System Based on 3-D Computer Vision
Evaluation of hand pointing system is presented. The system is based on 3D computer vision and implemented using open source computer vision library (OpenCV). The system is able to detect and track user’s head and hand and return 3D coordinates in real time. The detection of head and hand is based on Viola-Jones detector applying human skin color model information. The detection rate is about 90%. The tracking is based on Kanade-Lucas-Tomasi iterative algorithm, customized for 3D computer vision case. High tracking robustness (90%) is achieved due to skin color model and variable size search window according to depth information. The speed of the system is 15–23 frames per second on 3 GHz desktop PC. Ill. 3, bibl. 11 (in English; summaries in English, Russian and Lithuanian).
Authors retain copyright and grant the journal the right of the first publication with the paper simultaneously licensed under the Creative Commons Attribution 4.0 (CC BY 4.0) licence.
Authors are allowed to enter into separate, additional contractual arrangements for the non-exclusive distribution of the paper published in the journal with an acknowledgement of the initial publication in the journal.
Copyright terms are indicated in the Republic of Lithuania Law on Copyright and Related Rights, Articles 4-37.