DOI QR코드

DOI QR Code

Noise Reduction Method Using Randomized Unscented Kalman Filter for RGB+D Camera Sensors

랜덤 무향 칼만 필터를 이용한 RGB+D 카메라 센서의 잡음 보정 기법

  • Kwon, Oh-Seol (School of Electronical Electronics and Control Engineering, Changwon National University)
  • 권오설 (창원대학교 전기전자제어공학부)
  • Received : 2020.08.31
  • Accepted : 2020.09.17
  • Published : 2020.09.30

Abstract

This paper proposes a method to minimize the error of the Kinect camera sensor by using a random undirected Kalman filter. Kinect cameras, which provide RGB values and depth information, cause nonlinear errors in the sensor, causing problems in various applications such as skeleton detection. Conventional methods have tried to remove errors by using various filtering techniques. However, there is a limit to removing nonlinear noise effectively. Therefore, in this paper, a randomized unscented Kalman filter was applied to predict and update the nonlinear noise characteristics, we next tried to enhance a performance of skeleton detection. The experimental results confirmed that the proposed method is superior to the conventional method in quantitative results and reconstructed images on 3D space.

본 논문은 랜덤 무향 칼만 필터를 이용하여 키넥트 카메라 센서의 오차를 최소화하는 방법을 제안한다. RGB 값과 깊이(Depth) 정보를 제공하는 RGB+D 카메라는 센서의 오차로 인해 뻐대 검출 과정에서 성능 저하의 원인을 제공한다. 기존에는 다양한 필터링 기법을 이용하여 오차를 제거하였으나 비선형 잡음을 효과적으로 제거하는데 한계가 있었다. 이에 본 논문에서는 비선형 잡음 특성을 예측하고 업데이트하기 위해 랜덤 무향 칼만 필터를 적용하였으며 이를 바탕으로 뻐대 검출 성능을 높이고자 하였다. 실험 결과 제안한 방법은 기존의 방법에 비해 정량적 오차를 줄였으며 뼈대의 3D 검출 시 우수한 결과를 확인할 수 있었다.

Keywords

References

  1. Microsoft Robotics. Kinect Sensor. from http://msdn.microsoft.com/en-us/library/hh438998.aspx. (accessed Oct. 06, 2017)
  2. G. Han, I. Lee, H. and Choi, "MPEG-U based advanced user interaction interface system using hand posture recognition," The Korean Institute of Broadcast and Media Engineers, Vol. 19, No. 1, pp. 83-95, 2014.
  3. M. Goulao, "Kinematic data filtering with unscented kalman filter," Thesis of Tecnico Lisboa, 2017.
  4. A. Baghdadi, L. Cavuoto, and J. Crassidis, "Hip and trunk kinematics estimation in gait through kalman filter using IMU data at the ankle," IEEE Sensors Journal, Vol. 18, No. 10, pp. 4253-4259, 2018. https://doi.org/10.1109/jsen.2018.2817228
  5. O. Straka, J. Dunik, and M. Simandl, "Randomized unscented kalman filter in target tracking," IEEE International Conference on Information Fusion, Singapore, pp. 503-510, July 2012.