| published |
| DOI
http://dx.doi.org/10.25098/4.1.23 |
Multi Moving Object detection system using Modified K-means and Deep Learning Algorithms algorithm
azhee Wria Muhamad1, Luqman Mohammed Mustafa2, Ari Sabir Arif3
1,2,3 Computer Science Department, College of Basic Education, University of Slemani, Slemani, Iraq
E-mail :[email protected]1, [email protected]2, [email protected]3
Received : 5-7-2019 Revised:10-9-2019
Accepted : 20-9-2019 Published :30-6-2020
Abstract:
We present a multi moving object detection system for surveillance systems that detect multiple moving objects in varying lighting conditions. This work proposes a modified k-means algorithm and deep neural networks for feature extraction and recognizing and tracking of the objects. Traditional k-means algorithm is time-consuming, so we modify the k-means algorithm for speed and optimized feature extraction. The simulations performed as a part of the study indicates better accuracy precision and the F1 score (F-score or F-measure an amount of a test’s accuracy. It accounts both the precision p and the recall (r) of the test to compute the score: (p) is the number of correct positive product divided by the number of all positive results come back by the classifier, and ( r ) is the number of true positive results separated by the number of all relevant sample) scores for the proposed method. The performance of the present approach was compared to that of the other works, and the results indicate that the proposed system offered in this paper can be considered a suitable in terms of quality, accuracy, and speed.
Keywords: Deep learning, Object Detection, K-means, Video surveillance
References:
[1] Hakan Bilen, Marco Pedersoli and Tinne Tuytelaars. “Weakly Supervised Object Detection with Convex Clustering.” The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015: 1081-1089.
[2] Barnich, Olivier; Van Droogenbroeck, Marc (2009). “ViBe: A powerful random technique to estimate the background in video sequences”. 2009 IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 945–948.
[3] P. Viola; M. Jones, Rapid object detection using a boosted cascade of simple features, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.
[5] Karthikeyan PANJAPPAGOUNDER RAJAMANICKAM and Sakthivel PERIYASAMY, “Entropy Based Illumination-Invariant Foreground Detection.” IEICE TRANS. INF. & SYST VOL.E102–D, NO.7 (JULY 2019): pp. 1436.
[6] Niranjil Kumar, Sureshkumar, “Background Subtraction Based on Threshold Detection using Modified K_Means Algorithm,” Proceedings of the 2013 International Conference on Pattern Recognition, Information and Mobile Engineering, p. 381, 21 February 2013.
[7] J. Li, X. Liang, S. Shen, T. Xu and S. Yan, “Scale-aware fast R_CNN for Pedestrian Detection,” CORR, vol. abs/ 1510.08160, p. 25, June 2016.
[8] SouYoung Jin, Aruni Roy-Chowdhury, Huaizu Jiang, AshishSingh, Aditya Prasad, Deep Chakraborty, and Erik Learned-Miller, “Unsupervised Hard Example Mining from Video for Improved Object Detection,” European Conference on Computer Vision (ECCV), 2018.
[9] P. K. Abhishek Kumar Chauhan, “Moving Object Tracking using Gaussian Mixture Model and Optical Flow,” International Journal of Advanced Research in Computer Science and Software Engineering, vol. 3, no. 4, April 2013.
[10] L. Zhang, L. Lin, X. Liang, and K. He, “Is Faster R-CNN Ding Well for Pedestrian Detection?” IEEE International Conference on Computer Vision, Vols. abs/ 1607.07032,27, 27 Jul 2016.
[11] Zhao, L., Thorpe, C.E., “Stereo- and neural network-based pedestrian detection,” IEEE Transaction on Intelligent Transportation Systems 1, vol. 2, Sep 2000.
[12] Yang C. Li B. and Xu G., “Particle filter based multi-pedestrian tracking by HOG and HOF,” IEEE Int. Conf. Inform. Sci. and Tech., 2014.
[13] W. Lan, J. Dang, Y. Wang, and S. Wang, “Pedestrian Detection Based on YOLO network model,” IEEE Int. Conf. Mechatronics and Automation, 2018.
[14] R. Girshick, “Fast-RCNN,” Proceeding of the 2015 IEEE International Conference on Computer Vision, pp. 1440-1448, December 2015.
