Abstract
This article presents a method for classifying color points for automotive applications in the Hue Saturation Intensity (HSI) Space based on the distances between their projections onto the SI plane. Firstly the HSI Space is analyzed in detail. Secondly the projection of image points from a typical automotive scene onto the SI plane is shown. The minimal classes relevant for driver assistance applications are derived. The requirements for the classification of the points into those classes are obtained. Several weighting functions are proposed and a fast form of an euclidean metric is investigated in detail. In order to improve the sensitivity of the weighting function, dynamic coefficients are introduced. It is shown how to compute them automatically in order to get optimal results for the classification. Finally some results of applying the metric to the sample images are shown and the conclusions are drawn.
Similar content being viewed by others
Notes
This is the same as saying that they either belong to chromatic elements or are very dark.
The metric term is used here in a relaxed notation, without giving both points as function parameters. The set for all metrics is the integer SI plane, i.e. 2-tuples of S and I values where both S and I take integer values between 0 and 255. If the weighting function has the mathematical properties of a metric or semimetric, then it is called so. If not, then it will be simply called “weighting function”.
References
Adams, R., Bischof, L.: Seeded region growing. IEEE Trans. Pattern Anal. Mach. Intell. pp. 641–647 (1994)
Brodley, C., Utgoff, P.: Multivariate decision trees. Mach. Learn. 19, 45–77 (1995)
Brown, T., Koplowitz, J.: The weighted nearest neighbor rule for class dependent sample sizes. IEEE Trans. Inf. Theory 25, 617–619 (1979)
Chen, T., Lu, Y.: Color image segmentation-an innovative approach. In: Proceedings of the IEEE ICPR Conference, pp. 395–405 (2001)
Cheng, H.D., Jiang, X.H., Sun, Y., Wang, J.: Color image segmentation: advances and prospects. Pattern Recognit. 34, 2259–2281 (2001)
Comaniciu, D., Meer, P.: Robust analysis of feature spaces: color image segmentation. In: Proceedings of 1997 IEEE Conference on Computer Vision and Pattern Recognition, pp. 750–755 (1997)
Deshmukh, K., Shinde, G.: An adaptive color image segmentation. Electron. Lett. Comput. Vis. Image. Anal. 5, 12–23 (2005)
Funka-Lea, G., Bajcsy, R.: Combining color and geometry for the active, visual recognition of shadow. Fifth International Conference on Computer Vision, Cambridge, MA, USA, pp. 203–209 (1995)
Hanbury, A., Serra, J.: A 3d-polar coordinate colour representation well adapted to image analysis. Lecture Notes in Computer Science, pp. 804–811 (2003)
Haykin, S.: Neural networks a comprehensive foundation (1999)
Jain, R., Kasturi, R., Schunck, B.: Recovery of egomotion using region alignment. Machine vision. McGrawHill, NY (1995)
Ji, S., Park, H.: Image segmentation of color image based on region coherency. International Conference on Image Processing, pp. 80–83 (1998)
Jie, X., Fei, S.P.: Natural color image segmentation. Proc. Int. Conf. Image Process. 1, 973–976 (2003)
Kato, Z., Pong, T.C., Lee, J.C.M.: Color image segmentation and parameter estimation in a markovian framework. Pattern Recognit. Lett. 22, 309–321 (2001)
Kurugollu, F., Sankur, B., Harmani, A.: Color image segmentation using histogram multithresholding and fusion. Image Vis. Comput. 19, 915–928 (2001)
Li, N., Li, Y.: Feature encoding for unsupervised segmentation of color images. IEEE Trans. Syst. Man. Cybern. 33, 438–446 (2003)
Meyer, F., Beucher, S.: Morphological segmentation. J. Vis. Commun. Image Represent. 1, 21–46 (1990)
Nagao, M., Matsuyama, T., Ikeda, Y.: Region extraction and shape analysis in aerial images. Comput. Graph. Image Process. 10, 195–223 (1979)
Navon, E., Miller, O., Averabuch, A.: Color image segmentation based on adaptive local thresholds. Image vis. comput. 23, 69–85 (2005)
Rotaru, C., Schmidt, R.: Color based segmentation in automotive image processing using hsi metrics. 11th World Congress on ITS, Japan (2004)
Rotaru, C., Schipritt, J., Graf, T., Zhang, J., Buchwald, W.P.: High accuracy object detection and following in color images for automotive applications. IEEE International Conference on Information Acquisition (2005)
Sahoo, P.K., Soltani, S., Wong, A.K.C., Chen, Y.C.: A survey on thresholding techniques. Comput. Vis. Graph. Image Process. 41, 233–260 (1988)
Silk, E.: Human detection and recognition for an hors d’oeuvres serving robot. Data structures and network algorithms (1983)
Soto, A., Saptharishi, M., Ollennu, A.T., Dolan, J., Khosla, P.: Cyber-atvs: dynamic and distributed reconnaissance and surveillance using all terrain ugv. In: Proceedings of the International Conference on Field and Service Robotics, pp. 329–334 (1999)
Wang, C., Hunag, L., Rosenfeld, A.: Detecting clouds and cloud shadows on aerial photograps. Pattern Recognit. Lett. 12, 55–64 (1991)
Weszka, J.: A survey of threshold selection techniques. Comput. Graph. Image Process. 7, 259–265 (1978)
Yining Deng, B.M.: Unsupervised segmentation of color texture region in images and video. IEEE Trans. Pattern Anal. Mach. Intell. pp. 1–25 (2001)
Zhang, C., P.Wang: A new method of color image segmentation based on intensity and hue clustering. International Conference on Pattern Recognition (ICPR), pp. 613–616 (2000)
Acknowledgments
This work was supported by Volkswagen AG.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rotaru, C., Graf, T. & Zhang, J. Color image segmentation in HSI space for automotive applications. J Real-Time Image Proc 3, 311–322 (2008). https://doi.org/10.1007/s11554-008-0078-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-008-0078-9