.png){kind=icon}
.png){kind=icon}
Return
Four-point trapezoidal calibration algorithm for human-computer interaction system based on 3D sensor
.png){kind=icon}
PRE
AI
DOI：10.1016/j.measurement.2018.11.016.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In the depth image interaction system, there is a deviation between the detection range of the Kinect sensor and the projection interaction surface. Aiming at this problem, this paper proposes a trapezoidal correction algorithm based on the three-dimensional sensor Kinect, and performs the calibration on the interaction space to achieve precise interactive control. The performance of the algorithm is verified by the human-computer interaction control platform, which is developed independently. The algorithm proposed in this paper was applied to the 3D interactive software system, which can achieve accurate single-touch and multi-touch performance. Compared with the traditional optical trapezoidal calibration algorithm, the algorithm tracking accuracy rate and the tracking time have been greatly improved, and a good interactive effect can be well obtained. The presented method can be widely applied to various interactive systems such as image interaction systems, human-computer interaction systems, and multi-touch systems, etc. (C) 2018 Elsevier Ltd. All rights reserved.
Keywords:
Interactive system
3D sensors
Kinect
Trapezoidal calibration algorithm
Human-computer interactive
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.6
Papers:
2.0W
Citations:
5.4W