DOI QR코드

DOI QR Code

Implementation of Pedestrian Recognition Based on HOG using ROI for Real Time Processing

실시간 처리를 위한 ROI가 적용된 HOG 기반 보행자 인식 구현

  • Lee, Joo-Young (Dept. of Electronics Engineering, Seokyeong University)
  • Received : 2014.12.08
  • Accepted : 2014.12.12
  • Published : 2014.12.31

Abstract

In this paper, we propose a pedestrian detection by applying the HOG feature using ROI. Conventional HOG method has high accuracy, but shows the disadvantage of slow processing speed. By applying the ROI to the conventional method reduce computations for unnecessary area. Therefore proposed method improves the processing speed. In order to set the ROI area, we propose a structure that combined odd frames and even frames. Odd frame is in charge of operation for the entire area. And even frame does the operation for the ROI area. Implementation results of proposed method maintaining the same accuracy as the conventional method show a 20% improved performance of 8.3 frames per second.

본 논문은 ROI가 적용된 HOG 특징을 적용한 보행자 인식에 대해서 제안한다. 기존의 HOG 방법은 높은 인식률을 갖지만 처리 속도가 느린 단점이 존재한다. 처리 속도가 느린 기존의 HOG 방법에 ROI를 적용하여 불필요한 영역에 대한 연산을 줄여 처리 속도를 향상시켰다. ROI 영역을 설정하기 위해 영상 전체를 연산하는 홀수 프레임과 설정된 ROI 영역만을 연산하는 짝수 프레임을 조합한 구조를 사용하였다. 구현 결과 본 논문에서 제안하는 방법은 기존의 방법과 동일한 정확도를 유지하면서 처리 속도측면에서 약 20% 향상된 초당 8.3 프레임의 성능을 보였다.

Keywords

References

  1. Navneet Dalal, Bill Triggs. "Histograms of Oriented Gradients for Human Detection," IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 886-893, 2005
  2. T. Thummanuntawat, W. Kumwilaisak, J. Chinrungrueng, "Automatic region of interest detection in multi-view video," Electrical Engineering/Electronics Computer Telecommunications and Information Technology (ECTI-CON), International Conference on, ]]. 889-893, 2010
  3. Qiang Zhu, Shai Avidan, Mei-Chen Yeh, Kwang-Ting Cheng. "Fast Human Detection Using a Cascade of Histograms of Oriented Gradients," IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1491-1498, 2006
  4. Felzenszwalb. P, McAllester. D, Ramanan. D, "A discriminatively trained, multiscale, deformable part model," Computer Vision and Pattern Recognition, pp. 1-8, 2008
  5. Paul Viola, Michael Jones. "Rapid Object Detection using a Boosted Cascade of Simple Features," Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 511-518, 2001
  6. Miyamoto. R, Jaehoon Yu, Onoye. T, "Normalized channel features for accurate pedestrian detection," Communications, Control and Signal Processing (ISCCSP), pp. 582-585, 2014
  7. Dollar. P, Wojek. C, Schiele. B, Perona. P, "Pedestrian detection: A benchmark," Computer Vision and Pattern Recognition, pp 304-311, 2009

Cited by

  1. 객체 추적을 위한 특징점 검출기의 설계 및 구현 vol.23, pp.1, 2014, https://doi.org/10.7471/ikeee.2019.23.1.207