A Probabilistic Approach for Fusing People Detectors

  • Natália C. Batista
  • Guilherme A. S. Pereira


Automatic detection of people is essential for automated systems that interact with persons and perform complex tasks in an environment with humans. To detect people efficiently, in this article it is proposed the use of high-level information from several people detectors, which are combined using probabilistic techniques. The detectors rely on information from one or more sensors, such as cameras and laser rangefinders. The detectors’ combination allows the prediction of the position of the persons inside the sensors’ fields of view and, in some situations, outside them. Also, the fusion of the detector’s output can make people detection more robust to failures and occlusions, yielding in more accurate and complete information than the one given by a single detector. The methodology presented in this paper is based on a recursive Bayes filter, whose prediction and update models are specified in function of the detectors used. Experiments were executed with a mobile robot that collects real data in a dynamic environment, which, in our methodology, is represented by a local semantic grid that combines three different people detectors. Results indicate the improvements brought by the approach in relation to a single detector alone.


People detection Information fusion  Bayes filter  Semantic grid 


  1. Adarve, J., Perrollaz, M., Makris, A., & Laugier, C (2012). Computing occupancy grids from multiple sensors using linear opinion pools. In: Proceedings IEEE International Conference Robotics and Automation (pp. 4074–4079).Google Scholar
  2. Antunes, M., Barreto, J., Premebida, C., & Nunes, U. (2012). Can stereo vision replace a laser rangefinder? In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 5183–5190).Google Scholar
  3. Araujo, A. R., Caminhas, D. D., & Pereira, G. A. S. (2015). An architecture for navigation of service robots in human-populated office-like environments. In: Proceedings of the IFAC Symposium on Robot Control (submitted).Google Scholar
  4. Araújo, R. L., Lacerda, V., Hernandes, A., Mendonca, A., & Becker, M. (2011). Classificação de pedestres usando câmera e sensor lidar. In: Anais do Simpósio Brasileiro de Automação Inteligente (pp. 416–420).Google Scholar
  5. Baig, Q., Perrollaz, M., & Laugier, C. (2014). A robust motion detection technique for dynamic environment monitoring: A framework for grid-based monitoring of the dynamic environment. IEEE Robotics Automation Magazine, 21(1), 40–48.CrossRefGoogle Scholar
  6. Bellotto, N., & Hu, H. (2009). Multisensor-based human detection and tracking for mobile service robots. IEEE Trans on Systems, Man, and Cybernetics, 39(1), 167–181.CrossRefGoogle Scholar
  7. Benenson, R., Omran, M., Hosang, J., & Schiele, B. (2015). Ten years of pedestrian detection, what have we learned? In: Computer Vision - ECCV 2014 Workshops, Lecture Notes in Computer Science, vol 8926 (pp. 613–627). Springer International Publishing.Google Scholar
  8. Bota, S., & Nedesvchi, S. (2008). Multi-feature walking pedestrians detection for driving assistance systems. Intelligent Transport Systems, IET, 2(2), 92–104.CrossRefGoogle Scholar
  9. Broggi, A., Cerri, P., Ghidoni, S., Grisleri, P., & Jung, H. G. (2009). A new approach to urban pedestrian detection for automatic braking. IEEE Trans on Intelligent Transportation Systems, 10(4), 594–605.CrossRefGoogle Scholar
  10. Ceccarelli, M. (2011). Problems and issues for service robots in new applications. International Journal of Social Robotics, 3(3), 299–312.MathSciNetCrossRefGoogle Scholar
  11. Cho, H., Seo, Y. W., Vijaya Kumar, B., & Rajkumar, R. (2014). A multi-sensor fusion system for moving object detection and tracking in urban driving environments. In: Proceedings of IEEE International Conference on Robotics and Automation (pp. 1836–1843).Google Scholar
  12. Cui, J., Zha, H., Zhao, H., & Shibasaki, R. (2005). Tracking multiple people using laser and vision. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 2116–2121).Google Scholar
  13. Daamen, W., & Hoogendoorn, S. (2007). Free speed distributions—based on empirical data in different traffic conditions. In: N. Waldau, P. Gattermann, H. Knoflacher, & M. Schreckenberg (Eds.), Pedestrian and Evacuation Dynamics 2005 (pp. 13–25). Berlin: Springer.Google Scholar
  14. Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol 1 (pp. 886–893).Google Scholar
  15. Dollar, P., Appel, R., Belongie, S., & Perona, P. (2014). Fast feature pyramids for object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(8), 1532–1545.CrossRefGoogle Scholar
  16. 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(4), 743–761.CrossRefGoogle Scholar
  17. Elfes, A. (1990). Occupancy grids: A stochastic spatial representation for active robot perception. In: Proceedings of Conference on Uncertainty in Artificial Intelligence (pp. 136–146). AUAI Press.Google Scholar
  18. Geronimo, D., Lopez, A., Sappa, A., & Graf, T. (2010). Survey of pedestrian detection for advanced driver assistance systems. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(7), 1239–1258.CrossRefGoogle Scholar
  19. Gidel, S., Blanc, C., Chateau, T., Checchin, P., & Trassoudaine, L. (2009). Non-parametric laser and video data fusion: Application to pedestrian detection in urban environment. In: Proceedings of International Conference on Information Fusion (pp. 626–632).Google Scholar
  20. Hofmann, M., Kaiser, M., Aliakbarpour, H., & Rigoll, G. (2011). Fusion of multi-modal sensors in a voxel occupancy grid for tracking and behaviour analysis. In: Proceedings of International Workshop on Image Analysis for Multimedia Interactive Services.Google Scholar
  21. Hogenboom, M. (2013). Secret of Usain Bolt’s speed unveiled. Accessed 06 Nov 2014.
  22. Huerta, I., Ferrer, G., Herrero, F., Prati, A., & Sanfeliu, A. (2014). Multimodal feedback fusion of laser, image and temporal information. In: Proceedings of International Conference on Distributed Smart Cameras (pp. 25:1–25:6). ACM, New York, USA.Google Scholar
  23. Kassir, A., & Peynot, T. (2010). Reliable automatic camera-laser calibration. In: Proceedings of the Australasian Conference on Robotics & Automation (p. 10).Google Scholar
  24. Liu, Z., & von Wichert, G. (2014). Extracting semantic indoor maps from occupancy grids. Robotics and Autonomous Systems, 62(5), 663–674.CrossRefGoogle Scholar
  25. MacKenzie, D. I., Nichols, J. D., Hines, J. E., Knutson, M. G., & Franklin, A. B. (2003). Estimating site occupancy, colonization, and local extinction when a species is detected imperfectly. Ecology, 84(8), 2200–2207.Google Scholar
  26. Monteiro, G., Premebida, C., Peixoto, P., & Nunes, U. (2006). Tracking and classification of dynamic obstacles using laser range finder and vision. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems.Google Scholar
  27. Ngako Pangop, L., Chausse, F., Chapuis, R., & Cornou, S. (2008). Asynchronous Bayesian algorithm for object classification: Application to pedestrian detection in urban areas. In: Proceedings of International Conference on Information Fusion (pp. 1–7).Google Scholar
  28. Nüchter, A., & Hertzberg, J. (2008). Towards semantic maps for mobile robots. Journal of Robotics and Autonomous Systems, 56(11), 915–926.CrossRefGoogle Scholar
  29. Oliveira, L., Nunes, U., Peixoto, P., Silva, M., & Moita, F. (2010). Semantic fusion of laser and vision in pedestrian detection. Pattern Recognition, 43, 3648–3659.CrossRefzbMATHGoogle Scholar
  30. Papoulis, A., & Pillai, S. U. (2002). Probability, random variables, and stochastic processes (4th ed.). New York: Mc-Graw Hill.Google Scholar
  31. Pereira, F. G., Vassallo, R. F., & Salles, E. O. T. (2013). Human-robot interaction and cooperation through people detection and gesture recognition. Journal of Control, Automation and Electrical Systems, 24(3), 187–198.CrossRefGoogle Scholar
  32. Premebida, C., Carreira, J., Batista, J., & Nunes, U. (2014). Pedestrian detection combining RGB and dense LIDAR data. In: Proceedings of International Conference on Intelligent Robots and Systems (pp. 4112–4117).Google Scholar
  33. Premebida, C., Ludwig, O., & Nunes, U. (2009). Lidar and vision-based pedestrian detection system. Journal of Field Robotics, 26(9), 696–711.CrossRefGoogle Scholar
  34. SICK. (2006). Technical description for the lms200/211/221/291 laser measurement systems. Tech. rep., SICK AG Waldkirch, Germany.Google Scholar
  35. Spinello, L., & Siegwart, R. (2008). Human detection using multimodal and multidimensional features. In: Proceedings of the IEEE International Conference on Robotics and Automation (pp. 3264–3269).Google Scholar
  36. Stein, G., Mano, O., & Shashua, A. (2003). Vision-based acc with a single camera: bounds on range and range rate accuracy. In: Proceedings of IEEE Intelligent Vehicles Symposium (pp. 120–125).Google Scholar
  37. Thrun, S., Burgard, W., & Fox, D. (2005). Probabilistic robotics. Cambridge, MA: The MIT Press.zbMATHGoogle Scholar
  38. Utasi, A., & Benedek, C. (2013). A Bayesian approach on people localization in multicamera systems. IEEE Transactions on Circuits and Systems for Video Technology, 23(1), 105–115.CrossRefGoogle Scholar
  39. Varga, R., Vesa, A., Jeong, P., & Nedevschi, S. (2014). Real-time pedestrian detection in urban scenarios. In: Proceedings of IEEE International Conference on Intelligent Computer Communication and Processing (pp. 113–118).Google Scholar
  40. Varvadoukas, T., Giotis, I., & Konstantopoulos, S. (2012). Detecting human patterns in laser range data. In: Proceedings of the European Conference on Artificial Intelligence, vol 242 (pp. 804–809).Google Scholar
  41. Wu, B., Liang, J., Ye, Q., Han, Z., & Jiao, J. (2011). Fast pedestrian detection with laser and image data fusion. In: Proceedings of the International Conference on Image and Graphics (pp. 605–608).Google Scholar
  42. Yguel, M., Aycard, O., & Laugier, C. (2006). Efficient gpu-based construction of occupancy girds using several laser range-finders. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 105–110).Google Scholar
  43. Yoder, J.D., Perrollaz, M., Paromtchik, I., Mao, Y., & Laugier, C. (2010). Experiments in vision-laser fusion using the bayesian occupancy filter. In: Proceedings of International Symposium on Experimental Robotics, Delhi, India.Google Scholar

Copyright information

© Brazilian Society for Automatics--SBA 2015

Authors and Affiliations

  1. 1.Federal University of Itajubá - UNIFEIItabiraBrazil
  2. 2.Federal University of Minas Gerais - UFMGBelo HorizonteBrazil

Personalised recommendations