Hybrid Method Approach

Texture-based Tracking with Object Extraction Process (Fig 5.1)

In this approach, we take object-based extraction as an bonus for feature isolation and picking.

First, we use a standard texture-based feature tracking algorithm we proposed, and then use the results to help extracting the feature object. In figure 5.1, after our texture-based tracking process done, we use a clustering algorithm to find groups of these texture feature samples.

Histogram statistics of the samples in the same groups are builded with samples data. With mean and standard deviation, we choose a data region to estimate the threshold of the region growing processes we need. Finally, the region growing process can help us extract the object liked features. This approach is for data which user have already had a thought of what they want, and with tracking the movement and object extracting process, user can isolate the feature for observations.

Figure 5.1: Hybrid method which texture-based tracking result as an object extraction process input.

5.2 Future Work 35

Object-based Extraction with Texture-based Correspondence Test (Fig 5.2)

In the previous object-based feature extraction and tracking algorithm, the features for each timestep are extracted separately and then the system will try to associate them through time.

Many of the original algorithms correspond feature based on whether or not their regions over-lap in adjacent timesteps [28] [29]. For breaking the limits of features overover-lapping, we can use texture-based comparison to help finding the correspondences. The texture properties are cal-culated after object extracting processes in each timestep, and the texture comparison process can use to measure the object’s similarity. For each timestep, every feature object will contain several texture samples. Several samples distribution properties can be considered, such as most of the samples must find correspondences in one feature object to ensure this feature object is the correct tracking result. This approach is for object like dataset, and several object-based feature extraction techniques and applications for tracking result can be used.

Figure 5.2: Hybrid method which object-based extraction with texture-based correspondence test.

5.2 Future Work 36

Texture-based Tracking with Motion Pattern Recognition (Fig 5.3)

Since the tracking process of each texture samples hierarchy is independent in our works, the samples’ motion information can be extracted. First, every texture samples in the coarse reso-lution are tracked by our method, then the displacement information can help us tracking the feature by observing the samples relations. This method do not need the user input and the extraction and tracking process can be done in pre-processing time.

Figure 5.3: Hybrid method which texture-based tracking with motion pattern recognition.

Bibliography

[1] S. Belongie, C. Carson, H. Greenspan, and J. Malik. Color- and texture-based image segmentation using em and its application to content-based image retrieval. In ICCV ’98:

Proceedings of the Sixth International Conference on Computer Vision, pages 675–682, Washington, DC, USA, 1998. IEEE Computer Society.

[2] J. Bigun. Speed, frequency, and orientation tuned 3-d gabor filter banks and their design.

ICPR ’94: Proceedings of the International Conference on Pattern Recognition, c:184–

187, Oct 1994.

[3] I. Boada, I. Navazo, and R. Scopigno. Multi-resolution volume visualization with a texture-based octree. The Visual Computer, 17(3):185–197, 2001.

[4] R. Botchen, M. Chen, D. Weiskopf, and T. Ertl. Gpu-assisted multi-field video volume visualization. In IWVG’06: Proceedings of the Fifth International Workshop on Volume Graphics ’06, pages 47–54, Boston Park Plaza, Boston, Massachusetts, USA, July 2006.

[5] J. Caban, A. Joshi, and P. Rheingans. Texture-based feature tracking for effective time-varying data visualization. Visualization and Computer Graphics, IEEE Transactions on, 13(6):1472–1479, 2007.

[6] M. Fernandez, A. Mavilio, and M. Tejera. Texture segmentation of a 3d seismic section with wavelet transform and gabor filters. In ICPR ’00: Proceedings of the International

37

Bibliography 38

Conference on Pattern Recognition, page 3358, Washington, DC, USA, 2000. IEEE Com-puter Society.

[7] D. Gabor. Theory of communication. In Proceeding of the Institute of Electrical Engi-neers, volume 93, pages 429–457, 1946.

[8] B. Galvin, B. McCane, and K. Novins. Robust feature tracking. In DICTA ’99: Proceed-ings of the Fifth International Conference on Digital Image Computing, Techniques, and Applications ’99, Perth, Australia, December 1999.

[9] X. Guan, G. Pan, and Z. Wu. Automatic categorization of traditional chinese painting images with statistical gabor feature and color feature. In In Lectures in Computer Science, pages 743–750. Springer Berlin/Heidelberg, 2005.

[10] B. Guo. Interval set: A volume rendering technique generalizing isosurface extraction. In VIS ’95: Proceedings of the 6th conference on Visualization ’95, page 3, Washington, DC, USA, 1995. IEEE Computer Society.

[11] S. Guthe, M. Wand, J. Gonser, and W. Straßer. Interactive rendering of large volume data sets. In VIS ’02: Proceedings of the conference on Visualization ’02, pages 53–60, Washington, DC, USA, 2002. IEEE Computer Society.

[12] G. Heidemann and H. Ritter. A neural 3-d object recognition architecture using optimized gabor filters. ICPR ’96: Proceedings of the International Conference on Pattern Recogni-tion, 4:70, 1996.

[13] R. Huang and K. Ma. Rgvis: Region growing based techniques for volume visualiza-tion. In PG ’03: Proceedings of the 11th Pacific Conference on Computer Graphics and Applications, page 355, Washington, DC, USA, 2003. IEEE Computer Society.

[14] F. V. Hundelshausen and R. Rojas. Tracking regions and edges by shrinking and growing.

In Proceedings of the RoboCup ’03 International Symposium, Padova, Italy, 2003.

Bibliography 39

[15] G. Ji, H. Shen, and R. Wenger. Volume tracking using higher dimensional isosurfacing.

In VIS ’03: Proceedings of the 14th IEEE Visualization ’03, page 28, Washington, DC, USA, 2003. IEEE Computer Society.

[16] C. Ko, H. Liao, T. Wang, K. Fu, C. Lin, and J. Chuang. Visualization of large time-varying volume data using multi-resolution technique with video based compression. In Computer Graphics Workshop ’07, 2007.

[17] E. LaMar, B. Hamann, and K. Joy. Multiresolution techniques for interactive texture-based volume visualization. In VIS ’99: Proceedings of the conference on Visualization

’99, pages 355–361, Los Alamitos, CA, USA, 1999. IEEE Computer Society Press.

[18] P. Ljung, C. Lundstrom, A. Ynnerman, and K. Museth. Transfer function based adaptive decompression for volume rendering of large medical data sets. In VV ’04: Proceed-ings of the 2004 IEEE Symposium on Volume Visualization and Graphics, pages 25–32, Washington, DC, USA, 2004. IEEE Computer Society.

[19] A. Madabhushi, M. Feldman, D. Metaxas, D. Chute, and J. Tomaszewski. A novel stochas-tic combination of 3d texture features for automated segmentation of prostastochas-tic adenocar-cinoma from high resolution mri. Medical Image Computing and Computer-Assisted In-tervention, 2:581–591, 2003.

[20] D. Pinskiy, E. Brugger, H. Childs, and B. Hamann. An octree-based multi-resolution approach supporting interactive rendering of very large volume data sets. In Proceedings of the International Conference on Imaging Science, Systems, and Technology, pages 16–

22, 2001.

[21] J. Plate, M. Tirtasana, R. Carmona, and B. Fr¨ohlich. Octreemizer: a hierarchical approach for interactive roaming through very large volumes. In VISSYM ’02: Proceedings of the symposium on Data Visualisation ’02, pages 53–ff, Aire-la-Ville, Switzerland, Switzer-land, 2002. Eurographics Association.

Bibliography 40

[22] F. Post, B. Vrolijk, H. Hauser, R. Laramee, and H. Doleisch. The state of the art in flow visualization: Feature extraction and tracking. Eurographics, 22(4):775–792, 2003.

[23] Z. Qian, D. Metaxas, and L. Axel. Extraction and tracking of mri tagging sheets using a 3d gabor filter bank. Engineering in Medicine and Biology Society, 2006. EMBS ’06. 28th Annual International Conference of the IEEE, pages 711–714, 2006.

[24] F. Reinders, F. Post, and H. Spoelder. Attribute-based feature tracking. In Data Visualiza-tion 99, pages 63–72. Springer Verlag, 1999.

[25] R. Samtaney, D. Silver, N. Zabusky, and J. Cao. Visualizing features and tracking their evolution. Computer, 27(7):20–27, 1994.

[26] H. Shen, L. Chiang, and K. Ma. A fast volume rendering algorithm for time-varying fields using a time-space partitioning (tsp) tree. In VIS ’99: Proceedings of the conference on Visualization ’99, pages 371–377, Los Alamitos, CA, USA, 1999. IEEE Computer Society Press.

[27] D. Silver. Object-oriented visualization. IEEE Comput. Graph. Appl., 15(3):54–62, 1995.

[28] D. Silver and X. Wang. Volume tracking. In VIS ’96: Proceedings of the 7th conference on Visualization ’96, pages 157–ff, Los Alamitos, CA, USA, 1996. IEEE Computer Society Press.

[29] D. Silver and X. Wang. Tracking scalar features in unstructured datasets. In VIS ’98:

Proceedings of the conference on Visualization ’98, pages 79–86, Los Alamitos, CA, USA, 1998. IEEE Computer Society Press.

[30] S. Smith and J. Brady. Asset-2: real-time motion segmentation and shape tracking. Trans-actions of the IEEE on Pattern Matching and Machine Intelligence, 17(8):814–820, Jun 1995.

Bibliography 41

[31] F. Tzeng and K. Ma. Intelligent feature extraction and tracking for visualizing large-scale 4d flow simulations. In SC ’05: Proceedings of the 2005 ACM/IEEE conference on Supercomputing, page 6, Washington, DC, USA, 2005. IEEE Computer Society.

[32] C. Wang and H. Shen. A framework for rendering large time-varying data using wavelet-based time-space partitioning(wtsp) tree. Technical Repost OSU-CISRC-1/04-TR05, Jan-uary 2004.

[33] C. Wang and H. Shen. Lod map - a visual interface for navigating multiresolution volume visualization. IEEE Transactions on Visualization and Computer Graphics, 12(5):1029–

1036, 2006.

[34] C. Wang, A. Garcia, and H. Shen. Interactive level-of-detail selection using image-based quality metric for large volume visualization. IEEE Transactions on Visualization and Computer Graphics, 13(1):122–134, 2007.

[35] J. Wang, T. Xu, H. Shum, and M. Cohen. Video tooing. In Proceedings of ACM SIG-GRAPH ’04, pages 574–583, 2004.

[36] M. Weiler, R. Westermann, C. Hansen, K. Zimmermann, and T. Ertl. Level-of-detail volume rendering via 3d textures. In VVS ’00: Proceedings of the 2000 IEEE symposium on Volume visualization, pages 7–13, New York, NY, USA, 2000. ACM.

[37] T. P. Weldon and W. E. Higgins. An algorithm for designing multiple gabor filters for segmenting multi-textured images. In In Proc. IEEE Intl. Conf. Image Proc, pages 4–7, 1998.

[38] T. Xu, M. Sonka, G. McLennan, J. Guo, and E. Hoffman. Mdct-based 3-d texture clas-sification of emphysema and early smoking related lung pathologies. MedImg, 25(4):

464–475, April 2006.