Multi-feature Real Time Pedestrian Detection from Dense Stereo SORT-SGM Reconstructed Urban Traffic Scenarios

Ion Giosan, Sergiu Nedevschi

2014

Abstract

In this paper, a real-time system for pedestrian detection in traffic scenes is proposed. It takes the advantage of having a pair of stereo video-cameras for acquiring the image frames and uses a sub-pixel level optimized semi-global matching (SORT-SGM) based stereo reconstruction for computing the dense 3D points map with high accuracy. A multiple paradigm detection module considering 2D, 3D and optical flow information is used for segmenting the candidate obstacles from the scene background. Novel features like texture dissimilarity, humans’ body specific features, distance related measures and speed are introduced and combined in a feature vector with traditional features like HoG score, template matching contour score and dimensions. A random forest (RF) classifier is trained and then applied in each frame for distinguishing the pedestrians from other obstacles based on the feature vector. A k-NN algorithm on the classification results over the last frames is applied for improving the accuracy and stability of the tracked obstacles. Finally, two comparisons are made: first between the classification results obtained by using the new SORT-SGM and the older local matching approach for stereo reconstruction and the second by comparing the different features RF classification results with other classifiers’ results.

References

  1. Benenson, R., Mathias, M., Timofte, R. & Van Gool, L. 2012. Pedestrian detection at 100 frames per second. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 2903-2910.
  2. Bota, S. & Nedevschi, S. 2011a. Tracking multiple objects in urban traffic environments using dense stereo and optical flow. 14th International IEEE Conference on Intelligent Transportation Systems. pp. 791-796.
  3. Bota, S. & Nedevschi, S. 2011b. Vision based obstacle tracking in urban traffic environments. IEEE International Conference on Intelligent Computer Communication and Processing (ICCP). pp. 231-238.
  4. Bota, S., Nedevschi, S. & Konig, M. 2009. A framework for object detection, tracking and classification in urban traffic scenarios using stereovision. IEEE 5th International Conference on Intelligent Computer Communication and Processing. pp. 153-156.
  5. Bregler, C. 1997. Learning and recognizing human dynamics in video sequences. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. pp. 568-574.
  6. Broggi, A., Bertozzi, M., Fascioli, A. & Sechi, M. 2000. Shape-based pedestrian detection. IEEE Intelligent Vehicles Symposium. pp. 215-220.
  7. Dalal, N. & Triggs, B. 2005. Histograms of oriented gradients for human detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. pp. 886-893 vol. 1.
  8. Danescu, R., Nedevschi, S., Meinecke, M. M. & Graf, T. 2007. Stereovision Based Vehicle Tracking in Urban Traffic Environments. Intelligent Transportation Systems Conference. pp. 400-404.
  9. Dollar, P., Wojek, C., Schiele, B. & Perona, P. 2012. Pedestrian Detection: An Evaluation of the State of the Art. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34, pp. 743-761.
  10. Elgammal, A., Duraiswami, R., Harwood, D. & Davis, L. S. 2002. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proceedings of the IEEE, 90, pp. 1151- 1163.
  11. Fardi, B., Schuenert, U. & Wanielik, G. 2005. Shape and motion-based pedestrian detection in infrared images: a multi sensor approach. IEEE Intelligent Vehicles Symposium. pp. 18-23.
  12. Gandhi, T. & Trivedi, M. M. 2006. Pedestrian collision avoidance systems: a survey of computer vision based recent studies. Intelligent Transportation Systems Conference. pp. 976-981.
  13. Gavrila, D. 2000. Pedestrian Detection from a Moving Vehicle. Proceedings of the 6th European Conference on Computer Vision-Part II, pp. 37-49.
  14. Gavrila, D. M., Giebel, J. & Munder, S. 2004. Visionbased pedestrian detection: the PROTECTOR system. IEEE Intelligent Vehicles Symposium. pp. 13-18.
  15. Gavrila, D. M. & Munder, S. 2007. Multi-cue Pedestrian Detection and Tracking from a Moving Vehicle. International Journal of Computer Vision, 73, pp. 41- 59.
  16. Gavrila, D. M. & Philomin, V. 1999. Real-time object detection for “smart” vehicles. Proceedings of the Seventh IEEE International Conference on Computer Vision. pp. 87-93 vol.1.
  17. Giosan, I. & Nedevschi, S. 2009. Building Pedestrian Contour Hierarchies for Improving Detection in Traffic Scenes. Proceedings of the International Conference on Computer Vision and Graphics: Revised Papers, pp. 154-163.
  18. Giosan, I., Nedevschi, S. & Bota, S. 2009. Real time stereo vision based pedestrian detection using full body contours. IEEE 5th International Conference on Intelligent Computer Communication and Processing. pp. 79-86.
  19. Haller, I. & Nedevschi, S. 2010. GPU optimization of the SGM stereo algorithm. IEEE International Conference on Intelligent Computer Communication and Processing (ICCP). pp. 197-202.
  20. Haritaoglu, I., Harwood, D. & Davis, L. S. 2000. W4: real-time surveillance of people and their activities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22, pp. 809-830.
  21. Havasi, L., Szlavik, Z. & Sziranyi, T. 2004. Pedestrian Detection Using Derived Third-Order Symmetry of Legs. Proceedings of the IEEE International Conference on Computer Vision and Graphics, pp. 11- 17.
  22. Hilario, C., Collado, J. M., Armingol, J. M. & Escalera, A. D. L. 2005. Pedestrian detection for intelligent vehicles based on active contour models and stereo vision. Proceedings of the 10th international conference on Computer Aided Systems Theory, pp. 537-542.
  23. Javed, O. & Shah, M. 2002. Tracking and Object Classification for Automated Surveillance. Proceedings of the 7th European Conference on Computer Vision-Part IV, pp. 343-357.
  24. Keller, C. G., Enzweiler, M. & Gavrila, D. M. 2011a. A new benchmark for stereo-based pedestrian detection. IEEE Intelligent Vehicles Symposium (IV). pp. 691- 696.
  25. Keller, C. G., Enzweiler, M., Rohrbach, M., Fernandez Llorca, D., Schnorr, C. & Gavrila, D. M. 2011b. The Benefits of Dense Stereo for Pedestrian Detection. IEEE Transactions on Intelligent Transportation Systems, 12, pp. 1096-1106.
  26. Khammari, A., Nashashibi, F., Abramson, Y. & Laurgeau, C. 2005. Vehicle detection combining gradient analysis and AdaBoost classification. Proceedings of Intelligent Transportation Systems. pp. 66-71.
  27. Koller, D., Danilidis, K. & Nagel, H.-H. 1993. Modelbased object tracking in monocular image sequences of road traffic scenes. International Journal of Computer Vision, 10, pp. 257-281.
  28. Lipton, A. J., Fujiyoshi, H. & Patil, R. S. 1998. Moving target classification and tracking from real-time video. Fourth IEEE Workshop on Applications of Computer Vision. pp. 8-14.
  29. Llorca, D. F., Sotelo, M. A., Hellín, A. M., Orellana, A., Gavilan, M., Daza, I. G. & Lorente, A. G. 2012. Stereo regions-of-interest selection for pedestrian protection: A survey. Transportation research part C: emerging technologies, 25, pp. 226-237.
  30. Lun, Z., Li, S. Z., Xiaotong, Y. & Shiming, X. 2007. Realtime Object Classification in Video Surveillance Based on Appearance Learning. IEEE Conference on Computer Vision and Pattern Recognition. pp. 1-8.
  31. Marita, T., Oniga, F., Nedevschi, S., Graf, T. & Schmidt, R. 2006. Camera Calibration Method for Far Range Stereovision Sensors Used in Vehicles. IEEE Intelligent Vehicles Symposium. pp. 356-363.
  32. Masoud, O. & Papanikolopoulos, N. P. 2001. A novel method for tracking and counting pedestrians in realtime using a single camera. IEEE Transactions on Vehicular Technology, 50, pp. 1267-1278.
  33. Nedevschi, S., Bota, S. & Tomiuc, C. 2009. Stereo-Based Pedestrian Detection for Collision-Avoidance Applications. IEEE Transactions on Intelligent Transportation Systems, 10, pp. 380-391.
  34. Nedevschi, S., Danescu, R., Marita, T., Oniga, F., Pocol, C., Sobol, S., Tomiuc, C., Vancea, C., Meinecke, M. M., Graf, T., Thanh Binh, T. & Obojski, M. A. 2007. A Sensor for Urban Driving Assistance Systems Based on Dense Stereovision. IEEE Intelligent Vehicles Symposium. pp. 276-283.
  35. Pantilie, C. D. & Nedevschi, S. 2012. SORT-SGM: Subpixel Optimized Real-Time Semiglobal Matching for Intelligent Vehicles. IEEE Transactions on Vehicular Technology, 61, pp. 1032-1042.
  36. Papageorgiou, C. & Poggio, T. 2000. A Trainable System for Object Detection. International Journal of Computer Vision, 38, pp. 15-33.
  37. Pocol, C., Nedevschi, S. & Obojski, M. A. 2007. Obstacle Detection for Mobile Robots, Using Dense Stereo Reconstruction. IEEE International Conference on Intelligent Computer Communication and Processing. pp. 127-132.
  38. Rivlin, E., Rudzsky, M., Goldenberg, R., Bogomolov, U. & Lepchev, S. 2002. A real-time system for classification of moving objects. 16th International Conference on Pattern Recognition. pp. 688-691 vol.3.
  39. Rujikietgumjorn, S. & Collins, R. T. 2013. Optimized Pedestrian Detection for Multiple and Occluded People. IEEE Conference on Computer Vision and Pattern Recognition. pp. 3690-3697.
  40. Stauffer, C. & Grimson, W. E. L. 2000. Learning patterns of activity using real-time tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22, pp. 747-757.
  41. Toth, D. & Aach, T. 2003. Detection and recognition of moving objects using statistical motion detection and Fourier descriptors. 12th International Conference on Image Analysis and Processing. pp. 430-435.
  42. Woodlill, J. I., Gordon, G. & Buck, R. 2004. Tyzx DeepSea High Speed Stereo Vision System. IEEE Conference on Computer Vision and Pattern Recognition Workshop. pp. 41-41.
Download


Paper Citation


in Harvard Style

Giosan I. and Nedevschi S. (2014). Multi-feature Real Time Pedestrian Detection from Dense Stereo SORT-SGM Reconstructed Urban Traffic Scenarios . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 131-142. DOI: 10.5220/0004722901310142


in Bibtex Style

@conference{visapp14,
author={Ion Giosan and Sergiu Nedevschi},
title={Multi-feature Real Time Pedestrian Detection from Dense Stereo SORT-SGM Reconstructed Urban Traffic Scenarios},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={131-142},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004722901310142},
isbn={978-989-758-004-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - Multi-feature Real Time Pedestrian Detection from Dense Stereo SORT-SGM Reconstructed Urban Traffic Scenarios
SN - 978-989-758-004-8
AU - Giosan I.
AU - Nedevschi S.
PY - 2014
SP - 131
EP - 142
DO - 10.5220/0004722901310142