Currently, the detection of moving objects is being mandatory in most of the security systems. Moving objects are crucial in the areas of image searching, automatic annotation and for the understanding of scenes. Although the detection is a challenging task therefore, the detection of moving objects is essential to describe the accurate position and unique features of an object. The tracking of moving objects used in most of the computer vision applications. The detection and identification of objects form a moving scene or a video is called tracking. Some of the major challenges are occurred because of the position of moving cameras are not stable hence. The visibility of pictures is affected and the shadow area also considered as a challenge for the detection. In the previous research, Decision tree (J48), MLPNN (Multi-Layer Perceptron Neural Network) and KNN (K- Nearest Neighbor) used for the detection of moving objects but all these approaches are supervised that are not applicable to easily classify the data. The accuracy decreased and the false error rates increased. To sort out the previous work challenges, the current approaches are considered as namely as Optimized-MLPNN that easily stables the position and fix the location of objects.. For the classification, filters are trained that performed well and used the basic three operators as selection, crossover and mutation for the classification of moving objects. In proposed work, improve the accuracy rate, specificity, precision and reduce the FAR, FPR and FRR rate using simulation Tool MATLAB 2016a.

Moving Object Detection (MOD), Tracking and Classifciation, OMLPNN (Optimized Multi Perceptron Neuron Network), Artifical Intellgience (AI) and GMM (Gassuian Mixture Model)

[1] Neff, Michael G., Shirley N. Cheng, and Ted L. Johnson. "Moving object detection." U.S. Patent 7,999,849, issued August 16, 2011.
[2] Dhar, P. K., Khan, M. I., Gupta, A. K. S., Hasan, D. M. H., & Kim, J. M. (2012). An efficient real time moving object detection method for video surveillance system. International journal of Signal processing, Image processing and Pattern Recognition, 5(3), 93-110.
[3] Brouard, O., Delannay, F., Ricordel, V., &Barba, D. (2008, October). Spatio-temporal segmentation and regions tracking of high definition video sequences based on a Markov Random Field model. In Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on (pp. 1552-1555). IEEE.
[4] Kalirajan, K., &Sudha, M. (2015). Moving object detection for video surveillance. The Scientific World Journal, 2015.
[5] Kulchandani, J. S., &Dangarwala, K. J. (2015, January). Moving object detection: Review of recent research trends. In Pervasive Computing (ICPC), 2015 International Conference on (pp. 1-5). IEEE.
[6] Mahamuni, P. D., Patil, R. P., &Thakar, H. S. (2014). Moving object detection using background subtraction algorithm using Simulink. International Journal of Research in Engineering and Technology (IJRET), 3(6), 594-598.
[7] Sangale, K., and Kadu, N. B. Real-time foreground segmentation and boundary matting for live videos using SVM technique. International journal of advanced research in computer engineering and technology (IJARCET), volume 4 issue 11.
[8] Gong, M. (2011, June). Foreground segmentation of live videos using locally competing 1SVMs. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on (pp. 2105-2112). IEEE.
[9] Cheng, J., Yang, J., Zhou, Y., and Cui, Y. (2006). Flexible background mixture models for foreground segmentation. Image and Vision Computing, 24(5), 473-482.
[10] Mohan, Anaswara S., and R. Resmi. "Video image processing for moving object detection and segmentation using background subtraction." In Computational Systems and Communtions (ICCSC), 2014 First International Conference on, pp. 288-292. IEEE, 2014.
[11] Jadhav, Ms Jyoti J., and J. Jyoti. "Moving Object Detection and Tracking for Video Survelliance." International Journal of Engineering Research and General Science 2, no. 4 (2014): 372-378.
[12] Fablet, Ronan, P. Bouyhemy, and Marc Gelgon. "Moving object detection in color image sequences using region-level graph labeling." In Image Processing, 1999. ICIP 99. Proceedings. 1999 International Conference on, vol. 2, pp. 939-943. IEEE, 1999.
[13] Jadav, K., M. Lokhandwala, and A. Gharge. "Vision based moving object detection and tracking." In National Conference on Recent Trends in Engineering & Technology, pp. 13-14. 2011.
[14] Cohen, Isaac, and Gerard Medioni. "Detecting and tracking moving objects for video surveillance." In Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on., vol. 2, pp. 319-325. IEEE, 1999.
[15] Ergezer, Hamza, and Kemal Leblebicioglu. "Visual detection and tracking of moving objects." In Signal Processing and Communications Applications, 2007. SIU 2007. IEEE 15th, pp. 1-4. IEEE, 2007.