Abstract
Robustness and real-time usually are the main challenges when designing image understanding approach for practical application. To achieve robustness, integrating multiple algorithms to make a special hybrid approach are becoming a popular way and there have been a lot of successful hybrid approaches. But this aggravates the difficulties in achieving real-time because of heavy computational workload of multiple algorithms. To design a hybrid approach with real-time constraint more easily, some theoretical researches about multiple algorithm integration are very necessary. This paper presents a common multiple algorithm integration model and architecture for typical image understanding applications. To achieve robustness and real-time in a hybrid approach, the strategies for increasing robustness and speed up are analyzed. Finally a robust hybrid approach for rear vehicle and motorcycle detection and tracking is introduced as a sample.
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.
Similar content being viewed by others
References
Sun, Z., Bebis, G., Miller, R.: On-road vehicle detection using optical sensors a review. In: IEEE International Conference on Intelligent Transportation Systems, pp. 585–590. IEEE Press, New York (2004)
Heidemann, G., Kummert, F., Ritter, H., Sagerer, G.: A Hybrid Object Recognition Architecture. In: Vorbrüggen, J.C., von Seelen, W., Sendhoff, B. (eds.) ICANN 1996. LNCS, vol. 1112, pp. 305–310. Springer, Heidelberg (1996)
Tay, Y.H., Khalid, M., Yusof, R., Viard-Gaudin, C.: Offline Cursive Handwriting Recognition System base on Hybrid Markov Pattern and Neural Networks. In: IEEE International Symposium on Computational Intelligence in Robotics and Automation, vol. 3, pp. 1190–1195. IEEE Press, New York (2003)
Leibe, B., Mikolajczyk, K., Schiele, B.: Segmentation based multi-cue integration for object detection. In: 17th British Machine Vision Conference, vol. 3, p. 1169. BMVA Press (2006)
Spengler, M., Schiele, B.: Towards Robust Multi-Cue Integration fot Visual Tracking. International Journal of Machine Vision and Applications 14, 50–58 (2003)
Cao, X., Balakrishnan, R.: Evaluation of an On-line Adaptive Gesture Interface with Command Prediction. In: Graphics Interface Conference, pp. 187–194. Canadian Human-Computer Communications Society (2005)
Teng, L., Jin, L.W.: Hybrid Recognition for One Stroke Style Cursive Handwriting Characters. In: 8th International Conference on Document Analysis and Recognition, pp. 232–236. IEEE Computer Press, Los Alamitos (2005)
Koerich, A.L., Leydier, Y., Sabourin, R., Suen, C.Y.: A Hybrid Large Vocabulary Handwritten Word Recognition System using Neural Networks with Hidden Markov Patterns. In: 8th International Workshop on Frontiers in Handwriting Recognition, p. 99. IEEE Press, New York (2002)
Hall, D.L.: Mathematical Techniques in Multisensor Data Fusion. Artech House, Boston (2002)
Scheunert, U., Lindner, P., Richter, E., Tatschke, T., Schestauber, D., Fuchs, E.: Early and Multi Level Fusion for Reliable Automotive Safety Systems. In: IEEE Intelligent Vehicles Symposium, pp. 196–201. IEEE Press, New York (2007)
Duan, B., Liu, W., Fu, P., Yang, C., Wen, X., Yuan, H.: Real-Time On-Road Vehicle and Motorcycle Detection Using a Single Camera. In: IEEE International Conference on Industrial Technology, pp. 1–6. IEEE Press, New York (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Duan, B., Yang, C., Liu, W., Yuan, H. (2009). Architecture of Multiple Algorithm Integration for Real-Time Image Understanding Application. In: Deng, H., Wang, L., Wang, F.L., Lei, J. (eds) Artificial Intelligence and Computational Intelligence. AICI 2009. Lecture Notes in Computer Science(), vol 5855. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-05253-8_74
Download citation
DOI: https://doi.org/10.1007/978-3-642-05253-8_74
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-05252-1
Online ISBN: 978-3-642-05253-8
eBook Packages: Computer ScienceComputer Science (R0)