Abstract
In this paper we present a vision-based approach to detect multiple persons with occlusion handling from a mobile robot in real-world scenarios under two lighting conditions, good illumination (lighted) and poor illumination (dark). We use depth and thermal information that are fused for occlusion handling. First, a classifier is trained using thermal images of the human upper-body. This classifier is used to obtain the bounding box coordinates of human. The depth image is later fused with the region of interest obtained from the thermal image. Using the initial bounding box, occlusion handling is performed to determine the final position of human in the image. The proposed method significantly improves human detection even in crowded scene and poor illumination.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Xia, L., Chen, C., Aggarwal, J.K.: Human detection using depth information by kinect. In: Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2011 IEEE, pp. 15–22 (2011)
Eng, H., Wang, J., Kam, A.H., Yau, W.A.: Bayesian framework for robust human detection and occlusion handling using human shape model. In: Proceedings of the 17th International Conference on ICPR 2004, vol. 2, pp. 257–260 (2004)
Kamijo, S., Matsushita, Y., Ikeuchi, K., Sakauchi, M.: Occlusion robust tracking utilizing spatio-temporal Markov random field model. In: Proceedings of 15th International Conference on Pattern Recognition ICPR-2000 [Internet], vol. 1, pp. 140–144. IEEE Computer Society (200). http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=905292
Otsuka, K., Mukawa, N.: Multiview occlusion analysis for tracking densely populated objects based on 2-D visual angles. In: Proceedings of 2004 IEEE Computer Society Conference on Computer Vision Pattern Recognition, 2004 CVPR 2004 [Internet], vol. 1, pp. 90–97. IEEE (2004). http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=1315018
Ikemura, S., Fujiyoshi, H.: Real-time human detection using relational depth similarity features. Computer Vision—ACCV 2010. Lecture Notes in Computer Science, vol. 6495, pp. 25–38 (2011)
Camps, O., Sznaier, M.: Segmentation for robust tracking in the presence of severe occlusion. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001 CVPR 2001. pp. 483–489 (2001)
Almerfors, A.: Infrared Camera [Internet] (2009). http://www.applegate.co.uk/b2b-news-articles/more-detail-regarding-infrared-camera-0020792.htm?view=NEWS_105027
Zhang, H., Reardon, C., Parker, L.E.: Real-time multiple human perception with color-depth cameras on a mobile robot. IEEE Trans Cybern. 43(5), 1429–41 (2013)
Varshney, P.K.: Multisensor data fusion. Electron Commun. Eng. J. 245–253 (1997)
Hadi, H.S., Rosbi, M., Sheikh, U.U.: A review of infrared spectrum in human detection for surveillance systems. Int. J. Interact Digit Med. 1(3), 13–20 (2013)
Ding, J., Kuo, C., Hong, W.: An efficient image segmentation technique by Graduate Institute of Communication Engineering, National Taiwan University. In: The 21th IPPR Conference on Computer Vision, Graphics and Image Processing (2009). http://djj.ee.ntu.edu.tw/FastS
Alonso, I.P., Llorca, D.F., Sotelo, M.Á., Bergasa, L.M., Member, A., De, Toro P.R., et al.: Combination of feature extraction methods for SVM pedestrian detection. IEEE Trans. Intell. Transp. Syst. 8(2), 292–307 (2007)
Wu, S., Yu, S., Chen, W.: An attempt to pedestrian detection. In: Third Chinese Conference on Intelligent Visual Surveillance (IVS), pp. 9–12 (2011)
Zhang, S., Liu, J.: A self-occlusion detection approach based on range image of vision object 2041–2046 (2011)
Zhang, S., Liu, J.: A self-occlusion detection approach based on depth image using SVM. Int. J. Adv. Robot Syst. 9, 230 (2012). http://www.intechopen.com/journals/international_journal_of_advanced_robotic_systems/a-self-occlusion-detection-approach-based-on-depth-image-using-svm
Mallat, S.G.: A theory for multiresolution signal decomposition? The wavelet representation. IEEE Trans. Pattern Anal. Mach. Intell. II(7), 674–693 (1989)
Oren, M., Papageorgiou, C., Sinha, P., Osuna, E., Poggio, T.: Pedestrian detection using wavelet templates. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 193–199. IEEE Computer Society (1997)
Shimizu, H., Poggio, T.: Direction estimation of pedestrian from multiple §\({}\) tidl images 596–600 (2004)
Koenig, N.: Toward real-time human detection and tracking in diverse environments. In: 2007 ICDL 2007 IEEE 6th International Conference on Development and Learning, pp. 94–98 (2007)
Dalal, N., Triggs, B., Schmid, C.: Human detection using oriented histograms of flow and appearance. In: European Conference on Computer Vision, pp. 428–441 (2006)
Chang, T.-H., Gong, S., Ong, E.-J.: Tracking multiple people under occlusion using multiple cameras. In: Proceedings of 11th British Machine Vision Conference (2000)
Dockstader, S.L., Tekalp, A.M.: Multiple camera fusion for multi-object tracking. In: Proceedings of IEEE Workshop on Multi-Object Tracking. IEEE Computer Society, pp. 95–102 (2001)
Dockstader, S.L., Tekalp, A.M.: Multiple camera tracking of interacting and occluded human motion. Proc. IEEE 89(10), 1441–1455 (2001)
Cucchiara, R., Grana, C., Tardini, G., Vezzani, R., Emilia, R.: Probabilistic people tracking for occlusion handling. In: Proceedings of the 17th International Conference on ICPR 2004, pp. 132–135 (2004)
Wu, Y., Yu, T., Hua, G.: Tracking appearances with occlusions. In: 2003 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. I-789–I-795. IEEE Computer Society (2003)
Siebel, N.T., Maybank, S.: Fusion of multiple tracking algorithms for robust people tracking. In: 7th European Conference on Computer Vision, Denmark, vol. IV, pp. 373–387 (2002)
Senior, A., Hampapur, A., Tian, Y.-L., Brown, L., Pankanti, S., Bolle, R.: Appearance models for occlusion handling. Image Vis. Comput. 24(11), 1233–1243 (2006)
Nguyen, H.T., Smeulders, A.W.M.: Fast occluded object tracking by a robust appearance filter. IEEE Trans. Pattern Anal. Mach. Intell. 26(8), 1099–1104 (2004)
Tao, H., Sawhney, H.S., Kumar, R., Rd, W.: Dynamic layer representation with applications to tracking (2000)
Wloka, M,M., Anderson, B.G.: Resolving occlusion in augmented reality. In: Proceedings of the 1995 Symposium on Interactive 3D Graphics, pp. 5–12 (1995)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of 2001 IEEE Computer Society Conference on Computer Vision Pattern Recognition CVPR 2001, vol. 1, pp. I-511–I-518. IEEE Computer Society (2001)
Shoelson, B.: Cascade trainer: specify ground truth, train a detector [Internet] (2013). http://www.mathworks.com/matlabcentral/fileexchange/39627-cascade-trainer--specify-ground-truth--train-a-detector
Hadi, H.S., Rosbi, M., Sheikh, U.U., Amin, S.H.M.: Improved occlusion handling for human detection from mobile robot. In: Science and Information Conference (SAI), IEEE, pp. 694–698 (2015)
Chai, T., Draxler, R.R.: Root mean square error (RMSE) or mean absolute error (MAE)? Arguments against avoiding RMSE in the literature. Geosci. Model Dev. 7(3), 1247–1250 (2014)
Acknowledgments
The authors would like to thank Faculty of Electrical Engineering of Universiti Teknologi Malaysia for providing technical support for this research work. The authors are also grateful to the financial aid from Centre for Artificial Intelligence and Robotics (CAIRO) and Computer Vision, Video and Image Processing Research Lab (CvviP) of Universiti Teknologi Malaysia.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Hasim, S.H., Mamat, R., Sheikh, U.U., Amin, S.H.M. (2016). Depth and Thermal Image Fusion for Human Detection with Occlusion Handling Under Poor Illumination from Mobile Robot. In: Chen, L., Kapoor, S., Bhatia, R. (eds) Emerging Trends and Advanced Technologies for Computational Intelligence. Studies in Computational Intelligence, vol 647. Springer, Cham. https://doi.org/10.1007/978-3-319-33353-3_19
Download citation
DOI: https://doi.org/10.1007/978-3-319-33353-3_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-33351-9
Online ISBN: 978-3-319-33353-3
eBook Packages: EngineeringEngineering (R0)