Abstract
Reports of traffic accidents show that a considerable percentage of the accidents are caused by human factors. Human-centric driver assistance systems, with integrated sensing, processing and networking, aim to find solutions to this problem and other relevant issues. The key technology in such systems is the capability to automatically understand and characterize driver behaviors. In this paper, we propose a novel, efficient feature extraction approach for driving postures from a video camera, which consists of Homomorphic filter, skin-like regions segmentation, canny edge detection, connected regions detection, small connected regions deletion and spatial scale ratio calculation. With features extracted from a driving posture dataset we created at Southeast University (SEU), holdout and cross-validation experiments on driving posture classification are then conducted using Bayes classifier. Compared with a number of commonly used classification methods including naive Bayes classifier, subspace classifier, linear perception classifier and Parzen classifier, the holdout and cross-validation experiments show that the Bayes classifier offers better classification performance than the other four classifiers. Among the four predefined classes, i.e., grasping the steering wheel, operating the shift gear, eating a cake and talking on a cellular phone, the class of talking on a cellular phone is the most difficult to classify. With Bayes classifier, the classification accuracies of talking on a cellular phone are over 90 % in holdout and cross-validation experiments, which shows the effectiveness of the proposed feature extraction method and the importance of Bayes classifier in automatically understanding and characterizing driver behaviors towards human-centric driver assistance systems.
Similar content being viewed by others
References
Nadeau, C.L., Maag, U., Bellavance, F., et al.: Wireless telephones and the risk of road crashes. Accid. Anal. Prev. 35, 649–660 (2003)
Oliver, N., Pentland, A.P.: Graphical models for driver behavior recognition in a smart car. In: IEEE Intell. Vehicle Symp., pp. 7–12 (2002)
Liu, X., Zhu, Y.D., Fujimura, K.: Real-time pose classification for driver monitoring. In: IEEE Intell. Transp. Syst., pp. 174–178 (2003)
Eren, H., Celik, U., Poyraz, M.: Stereo vision and statistical based behavior prediction of driver. In: IEEE Intell. Vehicle Symp., pp. 657–662 (2007)
Sekizawa, S., Inagaki, S., Suzuki, T., et al.: Modeling and recognition of driving behavior based on stochastic switched ARX model. IEEE Trans. Intell. Transp. Syst. 8(4), 593–606 (2007)
Watta, P., Lakshmanan, S., Hou, Y.L.: Nonparametric approaches for estimating driver pose. IEEE Trans. Veh. Technol. 56(4), 2028–2041 (2007)
Kato, T., Fujii, T., Tanimoto, M.: Detection of driver’s posture in the car by using far infrared camera. In: IEEE Intell. Vehicle Symp., pp. 339–344 (2004)
Cheng, S.Y., Park, S., Trivedi, M.M.: Multi-spectral and multi-perspective video arrays for driver body tracking and activity analysis. Comput. Vis. Image Underst. 106(2–3), 245–257 (2007)
Demirdjian, D., Varri, C.: Driver poses estimation with 3D time-of-flight sensor. IEEE CIVVS, pp. 16–22 (2009)
Cheng, S.Y., Trivedi, M.M.: Turn-intent analysis using body pose for intelligent driver assistance. IEEE Perv. Comp. 5(4), 28–37 (2006)
Yang, C.M., Wu, C.C., Chou, C.M., et al.: Vehicle driver’s ECG and sitting posture monitoring system. In: 9th Conf. Inform. Tech. App. Bio., pp. 1–4 (2009)
Cheng, S.Y., Trivedi, M.M.: Vision-based infotainment user determination by hand recognition for driver assistance. IEEE Trans. Intell. Transp. Syst. 11(3), 759–764 (2010)
Harini, V., Stefan, A., Nathaniel, B., et al.: Driver activity monitoring through supervised and unsupervised learning. In: IEEE Conf. Intell. Transp. Syst., pp. 895–900 (2005)
Veeraraghavan, H., Bird, N., Atev, S., et al.: Classifiers for driver activity monitoring. Transp. Res. Part C 15(1), 51–67 (2007)
Heusch, G., Cardinaux, F., Marcel, S.: Lighting Normalization Algorithms for Face Verification. Tech. Rep., IDIAP (2005)
Heath, M., Sarkar, S., Sanocki, T., et al.: Comparison of edge detectors: a methodology and initial study. Comput. Vis. Image Underst. 69(1), 38–54 (1998)
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley, New York (2001)
Zhang, B.L., Zhang, Y.C., Begg, R.K.: Gait classification in children with cerebral palsy by Bayesian approach. Pattern Recogn. 42(4), 581–586 (2009)
Wong, T.T., Chang, L.H.: Individual attribute prior setting methods for naive Bayesian classifiers. Pattern Recogn. 44(5), 1041–1047 (2011)
Sohn, S.Y., Shin, H.W.: Experimental study for the comparison of classifier combination methods. Pattern Recogn. 40(1), 33–40 (2007)
Collins, M.: Discriminative training methods for hidden markov models: theory and experiments with perceptron algorithms. In: Proc. of Conf. on Empirical Methods in Natural Language Processing, Philadelphia, vol. 10, pp. 1–8 (2002)
Kraaijveld, M.A.: A Parzen classifier with an improved robustness against deviations between training and test data. Pattern Recogn. Lett. 17(7), 679–689 (1996)
Zhang, B.L., Zhang, Y.C.: Classification of cerebral palsy gait by Kernel Fisher discriminant analysis. Int. J. Hybrid Intell. Syst. 5(4), 209–218 (2008)
Author information
Authors and Affiliations
Corresponding author
Additional information
The project is supported by National Natural Science Foundation of China (No. 51078087).
Rights and permissions
About this article
Cite this article
Zhao, C., Zhang, B. & He, J. Vision-based Classification of Driving Postures by Efficient Feature Extraction and Bayesian Approach. J Intell Robot Syst 72, 483–495 (2013). https://doi.org/10.1007/s10846-012-9797-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10846-012-9797-z