Abstract
This paper presents a method for classifying the direction of movement and for segmenting objects simultaneously using features of space-time patches. Our approach uses vector quantization to classify the direction of movement of an object and to estimate its centroid by referring to a codebook of the space-time patch feature, which is generated from multiple learning samples. We segmented the objects’ regions based on the probability calculated from the mask images of the learning samples by using the estimated centroid of the object. Even though occlusions occur when multiple objects overlap in different directions of movement, our method detects objects individually because their direction of movement is classified. Experimental results show that object detection is more accurate with our method than with the conventional method, which is only based on appearance features.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Fujiyoshi, H., Komura, T., Yairi, I.E., Kayama, K.: Road Observation and Information Providing System for Supporting Mobility of Pedestrian. In: IEEE International Conference on Computer Vision Systems, pp. 37–44. IEEE Computer Society Press, Los Alamitos (2006)
Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)
Shechtman, E., Irani, M.: Space-Time Behavior Based Correlation. Computer Vision and Pattern Recognition 1, 405–412 (2005)
Niebles, J.C., Wang, H., Fei-Fe, L.: i: Unsupervised learning of human action categories using spatial-temporal words. In: British Machine Vision Conference, vol. 3, pp. 1249–1258 (2006)
Agarwal, S., Roth, D.: Learning a Sparse Representation for Object Detection. In: European Conference on Computer Vision, pp. 113–130 (2002)
Leibe, B., Leonardis, A., Schiele, B.: Interleaved Object Categorization and Segmentation. In: British Machine Vision Conference, Norwich, pp. 759–768 (2003)
Leibe, B., Leonardis, A., Schiele, B.: Combined Object Categorization and Segmentation with an Implicit Shape Model. In: European Conference on Computer Vision, Prague, pp. 496–510 (2004)
Opelt, A., Pinz, A., Zisserman, A.: Incremental learning of object detectors using a visual shape alphabet. Computer Vision and Pattern Recognition 1, 3–10 (2006)
Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. IEEE Computer Vision and Pattern Recognition, 886–893 (2005)
Viola, P., Jones, M.: Rapid Object Detection using a Boosted Cascade of Simple Features. Computer Vision and Pattern Recognition 1, 511–519 (2001)
Linde, Y., Buzo, A., Gray, R.M.: An Algorithm for Vector Quantizer Design. IEEE Trans. on Communications 28(1), 84–95 (1980)
Comaniciu, D., Meer, P.: Mean Shift Analysis and Applications. International Conference on Computer Vision 2, 1197–1203 (1999)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Murai, Y., Fujiyoshi, H., Kanade, T. (2007). Combined Object Detection and Segmentation by Using Space-Time Patches. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds) Computer Vision – ACCV 2007. ACCV 2007. Lecture Notes in Computer Science, vol 4843. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76386-4_87
Download citation
DOI: https://doi.org/10.1007/978-3-540-76386-4_87
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76385-7
Online ISBN: 978-3-540-76386-4
eBook Packages: Computer ScienceComputer Science (R0)