곡률과 HOG에 의한 연속 방법에 기반한 아다부스트 알고리즘을 이용한 보행자 인식

Pedestrian Recognition using Adaboost Algorithm based on Cascade Method by Curvature and HOG

  • 투고 : 2010.01.18
  • 심사 : 2010.04.06
  • 발행 : 2010.06.15

초록

본 논문은 2단계 연속(cascade) 방법을 이용한 향상된 보행자/비보행자 인식 알고리즘을 제안한다. 인식을 위한 분류기로는 약한 분류기를 강한 분류기로 만드는 아다부스트 알고리즘을 적용하였다. 먼저 두 가지 특징벡터를 추출 한다: (i) 기존의 기울기 히스토그램(HOG) 특성과 (ii) 한 점이 가지는 곡률특성 네 가지를 이용한 곡률-HOG를 제안하고 이용하였다. 그 다음 훈련 영상을 통하여 두 가지의 특징 벡터에 대해 약한 분류기로부터 강한 분류기를 얻었으며, 인식은 입력 영상으로부터 하나의 특징을 선택하여 이미 만들어진 강한 분류기를 통하여 1차적인 인식과 오인식을 실시하며, 오인식된 영상에 대해 2차적인 특징을 투입하여 이에 해당하는 강한 분류기를 통하여 2단계 아다부스트 알고리즘을 적용하여 최종적인 인식결과를 얻는다. 두 가지의 서로 다른 특성 벡터를 이용하여 연속 방법에 의한 2단계 아다부스트 알고리즘을 적용한 결과 기존의 실험 방법보다 더 정확한 인식 결과를 얻을 수 있었다.

In this paper, we suggest an advanced algorithm, to recognize pedestrian/non-pedestrian using second-stage cascade method, which applies Adaboost algorithm to make a strong classification from weak classifications. First, we extract two feature vectors: (i) Histogram of Oriented Gradient (HOG) which includes gradient information and differential magnitude; (ii) Curvature-HOG which is based on four different curvature features per pixel. And then, a strong classification needs to be obtained from weak classifications for composite recognition method using both HOG and curvature-HOG. In the proposed method, we use one feature vector and one strong classification for the first stage of recognition. For the recognition-failed image, the other feature and strong classification will be used for the second stage of recognition. Based on our experiment, the proposed algorithm shows higher recognition rate compared to the traditional method.

키워드

참고문헌

  1. Paisitkriangkrai, S., Shen, C. and Zhang J., "Fast Fedestrian Detection Using a Cascade of Boosted Covariance Features," IEEE Trans. Circuit and System for Video Technology, vol.18, no.8, pp.1140-1151, 2008.
  2. Enzweiler, M. and Gavrila, D., "Monocular Pedestrian Detection: Survey and Experiments," IEEE Transactions on Pattern Analysis and Machine Intelligence (available online: IEEE Computer Society Digital Library, http://doi.ieeecomputersociety.org/10.1109/TPAMI.2008.260), 2009.
  3. Lim, J. S., and Kim, W. H., "Multiple Pedestrians Detection and Tracking using Color Information from a Moving Camera," Journal of KIPS : Korea Information and Applications B, vol.11-B, no.3, pp.317-326, 2004. (in Korean)
  4. Broggi, A., Bertozzi, M. and Fascioli, A., "Shapebased Pedestrian Detection," Proc. of the IEEE Intelligent Vehicles Symposium 2000, pp.215-220, 2000.
  5. Mahlisch, M., Oberlander, M., Lohlein, O., Gavrila, D. and Ritter W., "A multiple detector approach to low-resolution for pedestrian recognition," In Procs. IEEE Intelligent Vehicles Symposium 2005, pp.23-28, 2005.
  6. Gavrila, D. M., "Pedestrian Detection from a Moving Vehicle," In Procs. of European Conference on Computer Vision, vol.2, pp.37-49, 2000.
  7. Curio, C., Edelbrunner, J., Kalinke, T., Tzomakas, C. and von Seelen, W., "Walking Pedestrian Recognition," IEEE Trans. on Intelligent Transportation Systems, vol.1, no.3, pp.155-163, 2000. https://doi.org/10.1109/6979.892152
  8. Papageorgiou, C. and Poggio, T., "A trainable system for object detection," International Journal of Computer Vision, vol.38, no.1, pp.15-33, 2000. https://doi.org/10.1023/A:1008162616689
  9. Fransens, R., Depoortere, V. and Prins, J. D., "Boundary based feature selection," Technical report, KU. Leuven, 2002.
  10. Gavrila, D. and Philomin, V., "Real-time object detection for "smart" vehicles," In IEEE International Conference on Computer Vision, pp.87-93, 1999.
  11. Viola, P., Jones, M. and Snow, D., "Detecting pedestrians using patterns of motion and appearance," International Journal of Computer Vision, vol.63, no.2, pp.153-161, 2005. https://doi.org/10.1007/s11263-005-6644-8
  12. Ronfard, R., Schmid, C. and Triggs, B., "Learning to parse pictures of people," The 7th ECCV, vol.IV, pp.700-714, 2002.
  13. 松島千佳, 山内悠嗣, 山下隆義, 藤吉弘亘, "人檢出のためのReal daBoostに基づくHOG特徴量の効率的な削減法," 情報處理學會研究報告, pp.1-8, 2009.
  14. Peet, F. G. and Sahota, T. S., "Surface Curvature as a Measure of Image Texture," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 7, no. 6, pp.734-738, 1985.
  15. Pedersoli, M., Gonzalez, J., Chakraborty, B. and Villanueva, J. J., "Enhancing Real-Time Human Detection Based on Histograms of Oriented Gradients," Advances in Soft Computing, vol.45/2008, pp.739-746, 2008.
  16. Sabzmeydani, P. and Mori, G., "Detecting Pedestrians by Learning Shapelet Features," IEEE Computer Vision and Pattern Recognition, pp.1-8, 2007.