Abstract
Stream processing is currently an active research direction in computer vision. This is due to the existence of many computer vision algorithms that can be expressed as a pipeline of operations, and the increasing demand for online systems that process image and video streams. Recently, a formal stream algebra has been proposed as an abstract framework that mathematically describes computer vision pipelines. The algebra defines a set of concurrent operators that can describe a pipeline of vision tasks, with image and video streams as operands. In this paper, we extend this algebra framework by developing a formal and abstract description of feedback control in computer vision pipelines. Feedback control allows vision pipelines to perform adaptive parameter selection, iterative optimization and performance tuning. We show how our extension can describe feedback control in the vision pipelines of two state-of-the-art techniques.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Flickr: https://www.flickr.com/ (last accessed on 7 September 2014).
- 2.
ImageNet: http://www.image-net.org/ (last accessed on 7 September 2014).
References
Zhao, B., Fei-Fei, L., Xing, E.: Online detection of unusual events in videos via dynamic sparse coding. In: CVPR, Colorado Springs, pp. 3313–3320 (2011)
Helala, M., Pu, K., Qureshi, F.: Road boundary detection in challenging scenarios. In: AVSS, pp. 428–433 (2012)
Meghdadi, A., Irani, P.: Interactive exploration of surveillance video through action shot summarization and trajectory visualization. IEEE Trans. Vis. Comput. Graph. 19, 2119–2128 (2013)
Yenikaya, S., Yenikaya, G., Düven, E.: Keeping the vehicle on the road: A survey on on-road lane detection systems. ACM Comput. Surv. 46, 1–2 (2013)
Ozcanli, O., Dong, Y., Mundy, J., Webb, H., Hammoud, R., Victor, T.: Automatic geo-location correction of satellite imagery. In: IEEE CVPR Workshops (2014)
Wischounig-Strucl, D., Quartisch, M., Rinner, B.: Prioritized data transmission in airborne camera networks for wide area surveillance and image mosaicking. In: IEEE CVPR Workshops, pp. 17–24 (2011)
Yuping, L., Medioni, G.: Map-enhanced uav image sequence registration and synchronization of multiple image sequences. In: IEEE CVPR, Minneapolis, Minnesota, USA, pp. 1–7 (2007)
Ryoo, M.S.: Human activity prediction: Early recognition of ongoing activities from streaming videos. In: ICCV, Barcelona, Spain, pp. 1036–1043 (2011)
Lu, C., Shi, J., Jia, J.: Online robust dictionary learning. In: IEEE CVPR, pp. 415–422 (2013)
Xu, C., Xiong, C., Corso, J.J.: Streaming hierarchical video segmentation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VI. LNCS, vol. 7577, pp. 626–639. Springer, Heidelberg (2012)
Loy, C., Hospedales, T., Xiang, T., Gong, S.: Stream-based joint exploration-exploitation active learning. In: CVPR, pp. 1560–1567 (2012)
Al Harbi, N., Gotoh, Y.: Spatio-temporal human body segmentation from video stream. In: Wilson, R., Hancock, E., Bors, A., Smith, W. (eds.) CAIP 2013, Part I. LNCS, vol. 8047, pp. 78–85. Springer, Heidelberg (2013)
Yang, J., Luo, J., Yu, J., Huang, T.: Photo stream alignment and summarization for collaborative photo collection and sharing. IEEE Trans. Multimedia 14, 1642–1651 (2012)
Kim, G., Xing, E.: Jointly aligning and segmenting multiple web photo streams for the inference of collective photo storylines. In: CVPR, pp. 620–627 (2013)
Chkodrov, G., Ringseth, P., Tarnavski, T., Shen, A., Barga, R., Goldstein, J.: Implementation of stream algebra over class instances, Google patents (2013)
Broy, M., Stefanescu, G.: The algebra of stream processing functions. Theoret. Comput. Sci. 258, 99–129 (2001)
Carlson, J., Lisper, B.: An event detection algebra for reactive systems. In: Proceedings of the 4th ACM International Conference on Embedded Software, pp. 147–154 (2004)
Demers, A., Gehrke, J., Hong, M., Riedewald, M., White, W.: A general algebra and implementation for monitoring event streams. Cornell University, Technical report (2005)
Shen, C., Little, J., Fels, S.: Towards OpenVL: Improving real-time performance of computer vision applications. In: Kisačanin, B., Bhattacharyya, S.S., Chai, S. (eds.) Embedded Computer Vision. Advances in Pattern Recognition, pp. 195–216. Springer, London (2009)
GStreamer. http://gstreamer.freedesktop.org (2014). Accessed: 26 January 2014
Helala, M.A., Pu, K.Q., Qureshi, F.Z.: A stream algebra for computer vision pipelines. In: IEEE CVPR Workshops (2014)
Kisilev, P., Freedman, D.: Parameter tuning by pairwise preferences. In: BMVC (2010)
Sherrah, J.: Learning to adapt: a method for automatic tuning of algorithm parameters. In: Blanc-Talon, J., Bone, D., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2010, Part I. LNCS, vol. 6474, pp. 414–425. Springer, Heidelberg (2010)
Chau, D., Badie, J., Bremond, F., Thonnat, M.: Online tracking parameter adaptation based on evaluation. In: IEEE International Conference on AVSS, pp. 189–194 (2013)
III, J.S., Ramanan, D.: Self-paced learning for long-term tracking. In: CVPR, Washington, DC, USA, pp. 2379–2386 (2013)
Chau, D., Bremond, F., Thonnat, M.: A multi-feature tracking algorithm enabling adaptation to context variations. In: ICDP 2011, pp. 1–6 (2011)
Corvee, E., Bremond, F.: Body parts detection for people tracking using trees of histogram of oriented gradient descriptors. In: IEEE International Conference on AVSS, pp. 469–475 (2010)
Kim, G., Xing, E.: On multiple foreground cosegmentation. In: IEEE CVPR, pp. 837–844 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Helala, M.A., Pu, K.Q., Qureshi, F.Z. (2015). Towards Efficient Feedback Control in Streaming Computer Vision Pipelines. In: Jawahar, C., Shan, S. (eds) Computer Vision - ACCV 2014 Workshops. ACCV 2014. Lecture Notes in Computer Science(), vol 9009. Springer, Cham. https://doi.org/10.1007/978-3-319-16631-5_24
Download citation
DOI: https://doi.org/10.1007/978-3-319-16631-5_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16630-8
Online ISBN: 978-3-319-16631-5
eBook Packages: Computer ScienceComputer Science (R0)