DOI QR코드

DOI QR Code

레이저센서 데이터융합기반의 복수 휴먼보폭 인식과 추적

Human Legs Stride Recognition and Tracking based on the Laser Scanner Sensor Data

  • Jin, Taeseok (Department of Mechatronics Engineering, Dongseo University)
  • 투고 : 2019.01.29
  • 심사 : 2019.02.27
  • 발행 : 2019.03.31

초록

본 논문에서는 레이저 센서 시스템을 이용한 이동중의 사람들을 실시간으로 추종하는 새로운 방법을 제시하였다. 제시한 방법은 $r-{\theta}$로 표현되는 센서데이터를 x-y좌표로 표현되는 2차원 공간으로 표현이 가능하다. 이러한 이동중인 사람들에 대한 정보는 보행패턴과 입력 센서데이터 값에 의해서 이동중인 사람의 특징값을 이용하여 적용하였다. 레이저 센서 기반 사람 추적 방법은 기존의 영상기반의 얼굴인식 방법보다 간단하면서도 이점을 가지고 있다. 제안방법에선 이동궤적알고리즘 기반으로 이동중인 사람의 발목부위를 계측하였도록 하였다. 게다가 제안된 추적 시스템은 중첩된 상황에서도 사람을 강건하게 추적할 수 있도록 HMM 방법을 적용하였다. 적용한 방법을 검증하기 위하여 실제 시스템을 적용한 실험결과를 제시하였다.

In this paper, we present a new method for real-time tracking of human walking around a laser sensor system. The method converts range data with $r-{\theta}$ coordinates to a 2D image with x-y coordinates. Then human tracking is performed using human's features, i.e. appearances of human walking pattern, and the input range data. The laser sensor based human tracking method has the advantage of simplicity over conventional methods which extract human face in the vision data. In our method, the problem of estimating 2D positions and orientations of two walking human's ankle level is formulated based on a moving trajectory algorithm. In addition, the proposed tracking system employs a HMM to robustly track human in case of occlusions. Experimental results using a real system demonstrate usefulness of the proposed method.

키워드

HOJBC0_2019_v23n3_247_f0001.png 이미지

Fig. 1 Kinematics of laser and image sensor

HOJBC0_2019_v23n3_247_f0002.png 이미지

Fig. 2 Geometric structure of laser sensor

HOJBC0_2019_v23n3_247_f0003.png 이미지

Fig. 3 Estimation of the leg position

HOJBC0_2019_v23n3_247_f0004.png 이미지

Fig. 4 Walking Model(o : Right leg, *: Left leg)

HOJBC0_2019_v23n3_247_f0005.png 이미지

Fig. 5 Hidden Markov Model.

HOJBC0_2019_v23n3_247_f0006.png 이미지

Fig. 6 Setups of Experiment

HOJBC0_2019_v23n3_247_f0007.png 이미지

Fig. 7 Image of walking humans for experiments

HOJBC0_2019_v23n3_247_f0008.png 이미지

Fig. 8 Evaluation of Experiment

참고문헌

  1. T.S. Jin, and H. Hashimoto, "3D walking human detection and tracking based on the IMPRESARIO Framework," International Journal of Fuzzy Logic and Intelligent Systems, vol. 8, no. 3, pp. 163-169, 2008. https://doi.org/10.5391/IJFIS.2008.8.3.163
  2. P. Perez, C. Hue, J. Vermaak, and M. Gangnet, "Color-Based Probabilistic Tracking," in Proceeding of European Conference on Computer Vision, Copenhagen, 27 May- 2 June 2002.
  3. T. Karpagavalli, and B.S. Appavu alias, "Multiple human tracking using 3D ellipsoidal model and SIR-Particle Filter technique," 2014 International Conference on Recent Trends in Information Technology, pp. 1-5, 2014.
  4. A. Ishan, K. Alok, K. Singh, and S. Rajeev, "Weighted Fast Dynamic Time Warping based multi-view human activity recognition using a RGB-D sensor," 2015 Fifth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), pp. 1-4, 2015.
  5. J. Gao, A.G. Hauptmann, A. Bharucha, and H.D. Wactlar, "Dining Activity Analysis Using a Hidden Markov Model," in Proceedings of the 17th International Conference on Pattern Recognition (ICPR), vol. 2, pp. 915-918, 2004.
  6. M. Babaee, G. Rigoll, and M. Babaee, "Joint tracking and gait recognition of multiple people in video," 2017 IEEE International Conference on Image Processing (ICIP), pp. 2592-2596, 2017.
  7. L. Xiao, T. Dacheng, S. Mingli, Z. Luming, B. Jiajun, and C. Chun, "Learning to Track Multiple Targets," IEEE Transactions on Neural Networks and Learning Systems, vol. 26, no. 5, pp.1060-1073, 2015. https://doi.org/10.1109/TNNLS.2014.2333751
  8. H. Rintaro, H. Tera, N. Takatoshi, Y. Masashi, and M. Shinya, "A Study of Tracking the Human Arm Twist Motion," 2016 Nicograph International (NicoInt), pp. 150-150, 2016.