This paper introduces an artificial neural network(ANN) based machine learning technique for on-road vehicle recognition and tracking that falls under the machine learning community. The feature extraction technique employed in this recognition and tracking system is multilevel Haar Wavelet transform which mainly focuses in separating low frequency components from high frequency components present in the image. This highlighted feature of Haar transform enables to increase the transmission speed of images and considerably aids in reducing the noise level. The neural network is trained by the images from database which has been subjected to feature extraction. The robust on-road vehicle recognition system is then integrated with a Kalman filter, which is extended to multiple vehicle tracking system to build complete vehicle recognition and tracking system and it has been evaluated on public domain vehicle images. This study reveals that this system yields high recalling rate, appreciable precision, and better localization effects on the recognized and tracked images.

1. T. Gandhi M. M. Trivedi, " Computer vision and machine learning for enhancing pedestrian safety, " in Computational Intelligence in Automotive Applications. Berlin , Germany : Springer-Verlag, May 2008,pp. 59-77.
2. C. Wang and J. -J. J. Lien, " Automatic vehicle detection using local features – A statistical approach, " IEEE Trans. Intell. Transp. Syst. , Vol. 9, no. 1,pp. 83-96, Mar . 2008.
3. M. M. Trivedi, T. Gandhi, and J. McCall, " Looking-in and looking-out of a vehicle: Computer-vision-based enhanced vehicle safety," IEEE Trans. Intell. Transp. Syst. , Vol. 8, no. 1,pp. 108-120,Mar. 2007.
4. M. M. Trivedi and S. Cheng, " Holistic sensing and active displays for intelligent driver supports," Computer, Vol. 40,no. 5,pp. 60-68,May 2007.
5. T. Gandhi and M. M. Trivedi, "Vehicle surround capture: Survey of techniques and a novel Omni video based approach for dynamic panoramic surround maps, " IEEE Trans. Intell. Transp. Syst. , vol. 7,no. 3,pp. 293-308,Sep. 2006.
6. J. McCall and M. M. Trivedi, " Video-based lane estimation and tracking for driver assistance: Survey, system, ans evaluation," IEEE Trans. Intell. Transo. Syst. , Vol. 7,no. 1,pp. 20-37,Mar. 2006
7. E. B. Koller-Meier and F. Ade," Tracking multiple objects using the condensation algorithm,"Robot. Auton. Syst. ,vol. 34,no. 2/3, pp. 93-105,Feb. 2001.
8. M. V. Shirvaikar and M. M Trivedi, " A neural network filter to detect small targets in high clutter backgrounds," IEEE Trans. Neural Netw. , vol. 6, no. 1,pp. 252-257,Jan. 1995.
9. World Health Org. ," World Report on Road Traffic Injury Prevention,"[online]. Available:http://www. who. int/violence_ injury_prevention/publications/road_traffic/ world_report/factsheets/en/index. html.
10. S. Rajasekaran and G. A. Vijayalakshmi Pai," Neural networks. Fuzzy logic and Genetic Algorithms Synthesis and Applications," 2003.
11. Sanyanan Sivaraman and Mohan Manubhai Trivedi," General Active-Learning framework for on-road vehicle recognition and tracking " IEEE Trans. Intell. Transp. Syst. ,Jun. 2010

Machine Learning Feature Extraction Ann