Dynamic Object Segmentation Approach For Videos

International Journal of Computer Science and Engineering

© 2020 by SSRG - IJCSE Journal

Volume 7 Issue 9

Year of Publication : 2020

Authors : Mr. Vivaram Veera Raghavulu, Prof. Dr. Ande. Prasad

10.14445/23488387/IJCSE-V7I9P104

How to Cite?

Mr. Vivaram Veera Raghavulu, Prof. Dr. Ande. Prasad, "Dynamic Object Segmentation Approach For Videos," SSRG International Journal of Computer Science and Engineering , vol. 7,  no. 9, pp. 18-24, 2020. Crossref, https://doi.org/10.14445/23488387/IJCSE-V7I9P104

Abstract:

Video analytics are analyzing video streams in real time and provide timely actionable information to make surveillance systems more predictable, accurate and efficient. Enhancing the quality of video, detecting events related to people, vehicles and enabling easy searching for video of interest. In this video analytics, image segmentation has become an indispensable task in many image and video applications.This work develops an image segmentation method based on, unsupervised dynamic object segmentation of moving and static objects occurring in a video. Objects are spatially cohesive and characterized by locally smooth motion trajectories, so they occupy regions within each frame. And, the shape and location of these regions vary slowly from frame to frame. So the existing methods don’t give the fairly good segmentation performance results within a least time. The proposed method is demonstrated to take the least computational time for achieving fairly good segmentation performance results in various image types. Thus, DOS can be formulating as tracking regions across the frames, such that the resulting tracks are locally smooth. Most prior work focuses on simplified formulation of DOS- that of motion segmentation. Typically, these methods require that the number of moving objects or layers is pre-specified.

Keywords:

surveillance, unsupervised, segmentation, cohesive, trajectories, region-growing, filters, stream, predictable, indispensable, frame, DOS.

References:

[1] F. Meyer and S. Beucher, Morphological segmentation, J. Vis. Commun. Image Rep., vol. 1, no. 1, pp. 21–46, Sept.1990.
[2] “Morphological area openings and closings for gray-scale images,” inNATO Advanced Research Workshop on “Shape in Picture:Mathematical Description of Shape in Grey- Level Images, Driebergen, The Netherlands, 1992, pp. 197– 208.
[3] K. K. Singh, A. Singh,“A Study of Image Segmentation Algorithms for Different Types of Images”, International Journal of Computer Science Issues, Vol. 7, Issue 5, 2010.
[4] H. Zhang, J. E. Fritts, S. A. Goldman,“Image Segmentation Evaluation: A Survey of unsupervised methods”, computer vision and image understanding, pp. 260-280, 2008.
[5] P.Correia and F.Pereira.Therole of analysis in content-based video coding and indexing. Signal Processing, 66:125{142, 1998.
[6] D. Wang. Unsupervised video segmentation based on watershedsandtemporaltracking.IEEETransactionsonCircuitsandSystemsfor VideoTechnology, 8(5):539{547, Sept.1998.
[7] Rafael C. Gonzalez, Richard E. Woods, ―Digital Image Processing, Second Edition, Pearson Education.
[8] Deeplai Kelkar and Surendra Gupta, Improved Quadtree Method for Split Merge Image Segmentation, Emerging Trends in Engineering and Technology, 2008
[9] Umakant Bhaskar rao Gohatre, Dr. C. Ram Singla, “The Inverted Flight Optimization of the Genetic Algorithm to Hyper boost Vehicle Trajectory” SSRG International Journal of Electrical and Electronics Engineering 6.10(2019): 1-8. ICETET.