DOI QR코드

DOI QR Code

Design of Upper Body Detection System Using RBFNN Based on HOG Algorithm

HOG기반 RBFNN을 이용한 상반신 검출 시스템의 설계

  • Kim, Sun-Hwan (Department of Electrical Engineering, The University of Suwon) ;
  • Oh, Sung-Kwun (Department of Electrical Engineering, The University of Suwon) ;
  • Kim, Jin-Yul (Department of Electronic Engineering, The University of Suwon)
  • Received : 2016.05.23
  • Accepted : 2016.08.11
  • Published : 2016.08.25

Abstract

Recently, CCTV cameras are emplaced actively to reinforce security and intelligent surveillance systems have been under development for detecting and monitoring of the objects in the video. In this study, we propose a method for detection of upper body in intelligent surveillance system using FCM-based RBFNN classifier realized with the aid of HOG features. Firstly, HOG features that have been originally proposed to detect the pedestrian are adopted to train the unique gradient features about upper body. However, HOG features typically exhibit a very high dimension of which is proportional to the size of the input image, it is necessary to reduce the dimension of inputs of the RBFNN classifier. Thus the well-known PCA algorithm is applied prior to the RBFNN classification step. In the computer simulation experiments, the RBFNN classifier was trained using pre-classified upper body images and non-person images and then the performance of the proposed classifier for upper body detection is evaluated by using test images and video sequences.

최근 감시와 보안을 목적으로 활발하게 CCTV가 설치되고 있고, 지능형 감시시스템은 영상에서 객체의 검출 및 감시 등으로 광범위하게 응용되고 있다. 본 연구에서는 지능형 영상 감시 시스템에서 HOG 특징과 FCM 기반의 RBFNN 분류기를 이용한 상반신 검출 방법을 제안한다. HOG는 보행자를 검출하기 위해 기존에 제안되었던 특징으로 본 논문에서는 이를 사용해 상반신의 고유한 기울기를 학습하였다. HOG 특징은 입력 이미지의 크기에 비례하는 고차원의 특징 벡터로 기울기를 표현하기 때문에 RBFNN분류기의 입력데이터로 쓰려면 차원 축소가 필요하다. 이를 위해 PCA 알고리즘을 RBFNN 분류기 앞에 적용하여 HOG 특징의 차원을 저차원으로 축소하였다. 컴퓨터 실험에서는 미리 분류된 상반신 영상과 사람이 아닌 영상을 통해 분류기를 훈련시킨 후 테스트 영상과 동영상을 이용하여 제안된 상반신 검출 방법의 성능을 평가하였다.

Keywords

References

  1. Ran Choi, "A Study on Applying MCT Algorithm to Detection of Pedestrian", Ph. D. Dissertation, Hanshin University, Hanshin, 2013.
  2. Dalal and B. Triggs, "Histograms of oriented gradients for human detection" IEEE Computer Society Conference on Computer Vision and Pattem Recognition, pp. 886-893, 2005
  3. S. B. Roh, S. K. Oh, and W. Pedrycz. "Design of fuzzy radial basis function-based polynomial neural networks." Fuzzy sets and systems Vol. 185, pp. 15-37, December 2011 https://doi.org/10.1016/j.fss.2011.06.014
  4. S-K. Oh, W-D. Kim, and W. Pedrycz, "Polynomial based radial basis function neural networks (P-RBFNNs) realized with the aid of particle swarm optimization," Fuzzy Sets and Systems, Vol. 163, No. 1, pp. 54-77, 2011 https://doi.org/10.1016/j.fss.2010.08.007
  5. J-Y. Kim, C-J. Park and S-K. Oh, "Design & Implementation of Pedestrian Detection System Using HOG-PCA Based pRBFNNs Pattern Classifier," The Transactions of the Korean Institute of Electrical Engineers Vol. 64, No. 7, pp. 1064-1073, 2015 https://doi.org/10.5370/KIEE.2015.64.7.1064
  6. W. K. Kim, S. K. Oh, H. K. Kim, "A Study on Feature Selection In Face Image Using Principal Component Analysis and Particle Swarm Optimization Algorithm", KIEE, Vol. 58, No. 12, pp. 2511-2519, 2009
  7. J. H. Baek, J. S. Kim, C. Y. Yoon, E. T. Kim, "Part-based Hand Detection Using HOG", Korean Institute of Intelligent Systems, Vol. 23, No. 6, pp. 551-557, 2013 https://doi.org/10.5391/JKIIS.2013.23.6.551
  8. S. K. Oh, S. H. Yoo and W. Pedrycz, "Design of face recognition algorithm using PCA -LDA combined for hybrid data preprocessing and polynomial-based RBF neural networks : Design and its application", Expert Systems with Applications, Vol. 40, pp. 1451-1466, 2013 https://doi.org/10.1016/j.eswa.2012.08.046
  9. Mathworks, "Train support vector machine classifier", http://kr.mathworks.com/help/stats/svmtrain.html