ADAPTIVE THRESHOLD BACKGROUND SUBTRACTION FOR DETECTING MOVING OBJECT ON CONVEYOR BELT

  • D.P. Tripathy 2Dept. Of Mining Engineering, NIT, Rourkela.
  • K.Guru Raghavendra Reddy 2Dept. Of Mining Engineering, NIT, Rourkela.
Keywords: Motion segmentation, Moving objects, Background subtraction, Adaptive Threshold, Conveyor.

Abstract

Moving object detection is an important task in many computer vision classifications applications. The goal of this study is to identify a moving object detection method that provides a reliable and accurate identification of objects on the conveyor belt. In this paper, a study of the moving object detection methods is presented. Firstly, moving object detection pixel by pixel was performed using background subtraction, frame difference method. The threshold value in both background subtraction and frame difference is a fixed value, which determines the accuracy of object identification. The adaptive threshold values were calculated for both the methods to improve the accuracy. The performance of these methods was compared with the ground truth image.

References

[1] J. Tao, and C. Yu. Real-time detection and tracking of moving object. Second International Symposium on Intelligent Information Technology Application, IEEE, 2008, Vol. 2, Pg.860-863.

[2] S. Suresh, P. Deepak, and K. Chitra, 2014; An efficient low cost background subtraction method to extract foreground object during human tracking. International Conference on Circuit, Power and Computing Technologies, IEEE, 2014, Pg. 1432-1436.

[3] Y. Zhang, X. Wang, and B. Qu; Three-frame difference algorithm research based on mathematical morphology. Procedia Engineering, 2012, Vol. 29, Pg. 2705-2709.

[4] N. Prabhakar, V. Vaithiyanathan, A.P. Sharma, A. Singh, and P. Singhal. 2012; Object tracking using frame differencing and template matching. Research Journal of Applied Sciences, Engineering and Technology, 2012, Vol. 4, No. 24, Pg. 5497-5501.

[5] M. Li, J. Fan, Y. Zhang, R. Zhang, W. Xu, and D. Hou. 2013; A moving object detection algorithm based on multiple judgments. Indonesian Journal of Electrical Engineering and Computer Science, 2013, Vol. 11, No. 10, Pg. 5539-5544.

[6] A.M. McIvor; Background subtraction techniques. Proc. of Image and Vision Computing, 2000, Vol. 4, Pg. 3099-3104.

[7] N. Singla; Motion detection based on frame difference method. International Journal of Information & Computation Technology, 2014, Vol. 4, No. 15, Pg. 1559-1565.

[8] H. Liu, J. Dai, R. Wang, H. Zheng, and B. Zheng; Combining background subtraction and three-frame difference to detect moving object from underwater video. In OCEANS, 2016-Shanghai, IEEE.2016, Pg. 1-5.

[9] L. Zhang, and Y. Liang; Motion human detection based on background subtraction. Second International Workshop on Education Technology and Computer Science, IEEE, 2010, Vol. 1, Pg. 284-287.

[10] N. Otsu; A threshold selection method from gray-level histograms. Automatica,1975, Vol. 11, Pg. 23-27.

[11] W. Jun-Qin. 2012; An adaptive frame difference method for human tracking. Advances in information sciences & services sciences, 2012, Vol. 4, No. 1, Pg. 381-387.
Published
2017-01-25
Section
Articles