Abstract
We address the problem of event classification for intelligent vehicle navigation system from video sequences acquired by a front mounted camera in complex urban scenes. Although in normal driving condition, large variety of events could be found and be preferably attached to an alerting system in a vehicle, there have been relatively narrow research activities on driving scene analysis, for example, finding local information such as lanes, pedestrians, traffic signs or light detections. Yet, the above-mentioned methods only provide limited performance due to many challenges in normal urban driving conditions, i.e. complex background, inhomogeneous illumination, occlusion, etc. In this paper, we tackle the problem of classification of various events by learning regional optical flows to detect some important events (very frequent occurring and involving riskiness on driving) using low cost front mounted camera equipment. We approached the problem as follows: First, we present an optical flow-based event detection method by regional significance analysis with the introduction of a novel significance map based on regional histograms of flow vectors; Second, we present a global and a local method to robustly detect ego-motion-based events and target-motion-based events. In our experiments, we achieved classification accuracy about 91% on average tested with two classifiers (Bayesian and SVM). We also show the performance of the method in terms of computational complexity achieving about 14.3 fps on a laptop computer with Intel Pentium 1.2 Ghz.
Similar content being viewed by others
References
Loy, C.C., Xiang, T., Gong, S.: From local temporal correlation to global anomaly detection. In: Proceedings of Workshop on ICCV (2008)
Georg, M., Pless, R.: Fitting parametric road models to spatio-temporal derivatives. In: Proceedings of Workshop on ICCV, pp. 421–427 (2009)
Saleemi, I., Hartung, L., Shah, M.: Scene understanding by statistical modeling of motion patterns. In: Proceedings of CVPR (2010) 2069–2076
Gandhi, T., Trivedi, M.M.: Pedestrian protection system: issue, survey, and challenges. In: IEEE Transaction on Intelligent Transportation System, pp. 413–430 (2007)
Gavrila, D.M., Munder, S.: Multi-cue pedestrian detection and tracking from a moving vehicle. Int. J. Comput. Vis. 73 (2006)
Escalera, S., Pujol, O., Radeva, P.: Traffic sign recognition system with β-correction. Vis. Appl. (2010)
Ruta, A., Li, Y., Liu, X.: Towards real-time traffic sign recognition by class-specific fiscriminative features. In: Proceedings of BMVC (2007)
Gavrila, D.: Pedestrian detection from a moving vehicle. In: Proceedings of ECCV, pp. 37–49 (2000)
Danescu, R., Nedevschi, S.: Probabilistic lane tracking in difficult road scenarios using stereovision. In: Proceedings of Intelligent Vehicles Symp. (2009)
Kruger, W., Enkelmann, W., Rossle, S.: Real-time estimation and tracking of optical flow vector for obstacle detection. In: Proceedings of Intelligent Vehicles Symp., pp. 729–734 (1995)
Gern, A., Moebus, R., Franke, U.: Vision-based lane recognition under adverse weather condition using optical flow. In: Proceedings of Intelligent Vehicles Symp., pp. 652–657 (2002)
Roberts, R., Potthast, C., Dellaert, F.: Learning general optical flow subspaces for egomotion estimation and detection of motion anomalies. In: Proceedings of CVPR (2009)
Geiger, A., Kitt, B.: Objectflow: a descriptor for classifying traffic motion. In: Proceedings of Intelligent Vehicles Symp (2010)
Ess, A., Muller, T., Grabner, H., Van Gool, L.J: Segmentation-based urban traffic scene understanding. In: Proceedings of BMVC (2009)
Roth, S., Black, M.J.: On the spatial statistics of optical flow. Int. J. Comput. Vis. 74(1) (2007)
Roth, S., Black, M.J.: Fields of expert: a framework for learning image priors. In: Proceedings of CVPR (2005)
Wall, M.E., Rechtsteiner, A., Rocha, L.M.: Singular value decomposision and principal component anlaysis. In: A Practical Approach to Microarray Data Analysis, pp. 91–109 (2003)
Horn, B., Schunck, B.: Determining optical flow. In: Proceedings of Artificial Intelligence, pp. 185–203 (1981)
Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vistion. In: Proceedings of Artificial Intelligence, pp. 674–679 (1981)
Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Proceedings of ECCV, pp. 25–36 (2004)
Black, M.J., Anandan, P.: The robust estimation of multiple motion: parametric and piecewise-smooth flow fields. In: CVIU, pp. 972–986 (1996)
Wedel, A., Pock, T., Cremers, D.: Structure- and motion-adaptive regularization for tv-l1 optic flow. In: Proceedings of ICCV (2009)
Bruhn, A., Weickert, W., Schnorr, C.: Lucas/kanade meets horn/schunck: combining local and global optical flow methods. Int. J. Comput. Vis. 211–231 (2005)
Sun, D., Roth, S., Black, M.J.: Secretes of optical flow estimation and their principles. In: Proceedings of CVPR (2010)
Lei, C., Yang, Y.H.: Optical flow estimation on coarse-to-fine region-trees using discrete optimization. In: Proceedings of ICCV (2009)
Baker, S., Scharstein, D., Lewis, J.P., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. In: Proceedings of ICCV (2007)
Barron J.L., Fleet D.J., Beauchemin S.S.: Performance of optical flow techniques. Int. J. Comput. Vis. 12, 43–77 (1994)
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley-Interscience. ISBN 0471056693 (2000)
Cortes, C., Vapnik, V.: Support-vector networks. In: Machine Learning, pp. 273–297 (1995)
Chang, C.C., Lin, C.J.: Software available at http://www.scie.ntu.edu.tw/~cjlin/libsvm (2001)
Werlberger, M., Trobin, W., Pock, T., Wedel, A., Cremers, D., Bischof, H.: Anisotropic huber-l1 optical flow. In: Proceedings of BMVC (2009)
Author information
Authors and Affiliations
Corresponding author
Electronic Supplementary Material
The Below is the Electronic Supplementary Material.
ESM 1 (AVI 7282 kb)
Rights and permissions
About this article
Cite this article
Choi, MK., Park, J. & Lee, SC. Event classification for vehicle navigation system by regional optical flow analysis. Machine Vision and Applications 25, 547–559 (2014). https://doi.org/10.1007/s00138-011-0384-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-011-0384-2