Hybrid Texture and Gradient Modeling for Dynamic Background Subtraction Identification System in Tobacco Plant Using 5G Data Service

M.T. Thirthe Gowda; J. Chandrika

doi:10.24423/cames.455

M.T. Thirthe Gowda Government Engineering College Hassan / Malnad College of Engineering Hassan
J. Chandrika Malanad College of Engineering, Hassan

DOI: http://dx.doi.org/10.24423/cames.455

Abstract

Background: Detecting the plants as objects of interest in any vision-based input sequence is highly complex due to nonlinear background objects such as rocks, shadows, etc. Therefore, it is a difficult task and an emerging one with the development of precision agriculture systems. The nonlinear variations of pixel intensity with illumination and other causes such as blurs and poor video quality also make the object detection task challenging. To detect the object of interest, background subtraction (BS) is widely used in many plant disease identification systems, and its detection rate largely depends on the number of features used to suppress and isolate the foreground region and its sensitivity toward image nonlinearity.
Methodology: A hybrid invariant texture and color gradient-based approach is proposed to model the background for dynamic BS, and its performance is validated by various real-time video captures covering different kinds of complex backgrounds and various illumination changes. Based on the experimental results, a simple multimodal feature attribute, which includes several invariant texture measures and color attributes, yields finite precision accuracy compared with other state-of-art detection methods. Experimental evaluation of two datasets shows that the new model achieves superior performance over existing results in spectral-domain disease identification model.
5G assistance: After successful identification of tobacco plant and its analysis, the final results are stored in a cloud-assisted server as a database that allows all kinds of 5G services such as IoT and edge computing terminals for data access with valid authentication for detailed analysis and references.

Keywords

background subtraction, local binary pattern, tobacco plant, texture, Gaussian mixture model, illumination changes, plant disease identification system,

References

1. N. Friedman, S. Russell, Image segmentation in video sequences: A probabilistic approach, [in:] UAI’97: Proceedings of the Thirteenth conference on Uncertainty in artificial intelligence, pp. 175–181, 1997.
2. A. Elgammal, D. Harwood, L.S. Davis, Non-parametric model for background subtraction, [in:] D. Vernon [Ed.], Computer Vision – ECCV 2000. Lecture Notes in Computer Science, Vol. 1843, pp. 751–767, Springer, Berlin, Heidelberg, 2000, doi: 10.1007/3-540-45053-X_48.
3. W. Wang, J. Yang, W. Gao, Modeling background and segmenting moving objects from compressed video, IEEE Transactions on Circuits and Systems for Video Technology, 18(5): 670–681, 2008, doi: 10.1109/TCSVT.2008.918800.
4. T. Wang, Z. Zhu, Real time moving vehicle detection and reconstruction for improving classification, [in:] 2012 IEEE Workshop on the Applications of Computer Vision (WACV), 2012, pp. 497–502, doi: 10.1109/WACV.2012.6163039.
5. Z. Guo, L. Zhang, D. Zhang, A completed modeling of local binary pattern operator for texture classification, IEEE Transactions on Image Processing, 19(6): 1657–1663, 2010, doi: 10.1109/TIP.2010.2044957.
6. D.Y. Lee, J.K. Ahn, C.C. Kim, Fast background subtraction algorithm using two-level sampling and silhouette detection, [in:] 2009 16th IEEE International Conference on Image Processing, pp. 3177–3180, 2009, doi: 10.1109/icip.2009.5414397.
7. W. Zhou, Y. Liu, W. Zhang, L. Zhuang, N. Yu, Dynamic background subtraction using spatial-color binary patterns, [in:] 2011 Sixth International Conference on Image and Graphics, pp. 314–319, 2011, doi: 10.1109/icig.2011.76.
8. J. Hu, T. Su, S. Jeng, Robust background subtraction with shadow and highlight removal for indoor surveillance, [in:] 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4545–4550, 2006, doi: 10.1109/IROS.2006.282156.
9. S. Liao, G. Zhao, V. Kellokumpu, M. Pietikäinen, S.Z. Li, Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes, [in:] 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1301–1306, 2010, doi: 10.1109/cvpr.2010.5539817.
10. A.D. Andrushia, A.T. Patricia, Artificial bee colony optimization (ABC) for grape leaves disease detection, Evolving Systems, 11(1): 105–117, 2020, doi: 10.1007/s12530-019-09289-2.
11. S.K. Pravin Kumar, M. G. Sumithra, N. Saranya, Artificial bee colony-based fuzzy c means (ABC-FCM) segmentation algorithm and dimensionality reduction for leaf disease detection in bioinformatics, The Journal of Supercomputing, 75(12): 8293–8311, 2019, doi: 10.1007/s11227-019-02999-z.
12. Q. Gu et al., Early detection of tomato spotted wilt virus infection in tobacco using the hyperspectral imaging technique and machine learning algorithms, Computers and Electronics in Agriculture, 167: 105066, 2019, doi: 10.1016/j.compag.2019.105066.
13. S.-Y. Chiu, C.-C. Chiu, S.S.-D. Xu, A background subtraction algorithm in complex environments based on category entropy analysis, MDPI Applied Sciences, 8(6): Article ID 885, 2018, doi: 10.3390/app8060885.
14. X. Li, G. Li, Q. Jiang, Dynamic background subtraction method based on spatio-temporal classification, IET Computer Vision, 12(4): 492–501, 2018, doi: 10.1049/iet-cvi.2017.0339.
15. Y. Yang, Q. Zhang, P. Wang, X. Hu, N. Wu, Moving object detection for dynamic background scenes based on spatiotemporal model, Hindawi Advances in Multimedia, 2017: Article ID 5179013, 2017, doi: 10.1155/2017/5179013.
16. D. Sirohi, N. Kumar, P.S. Rana, Convolutional neural networks for 5G-enabled intelligent transportation system: A systematic review, Computer Communications, 153: 459–498, 2020, doi: 10.1016/j.comcom.2020.01.058.
17. G.Y. Kim, R. Kim, S. Kim, K.D. Nam, S.U. Rha, J.H. Yoon, DNN inference offloading for object detection in 5G multi-access edge computing, [in:] 2021 International Conference on Information and Communication Technology Convergence, pp. 389–392, 2021, doi: 10.1109/ictc52510.2021.9620821.
18. H. Li et al., Human detection via image denoising for 5G-enabled intelligent applications, Hindawi Wireless Communications and Mobile Computing, 2021: Article ID 5344890, 2021, doi: 10.1155/2021/5344890.
19. L. Nkenyereye, J. Kwon, Y.-H. Choi, Secure and lightweight cloud-assisted video reporting protocol over 5G-enabled vehicular networks, MDPI Sensors, 17(10): 2191, 2017, doi: 10.3390/s17102191.
20. C. Kim, J. Lee, T. Han, Y.M. Kim, A hybrid framework combining background subtraction and deep neural networks for rapid person detection, Journal of Big Data, 5(1): 1–24, 2018, doi: 10.1186/s40537-018-0131-x.