Comparing Segmentation Quality of Real-Time Image Segmentation Techniques Using Metrics
Keywords:
Image segmentation, foreground segmentation, Precision, Recall, F1-score, AccuracyAbstract
The roles of real-time image segmentation and matching are of utmost importance, requiring the utilisation of efficient algorithms to promptly and precisely analyze images. The main goal of this research is to explore the procedure of obtaining real-time images from video footage using a camera, followed by the selection of a random image frame for the purpose of segmentation. Nevertheless, a notable obstacle arises when calculating metrics like Precision, Recall, F1 score, Accuracy, and SSIM by utilizing the segmented image and the Ground Truth image. To address these problems, a range of segmentation approaches are assessed in terms of their efficacy in computing the metrics described above. The segmentation technique employed in this study is the proposed method, which yields segmented images that exhibit successful outcomes. The paper presents a suggested methodology to augment the metrics of Precision, Recall, F1 score, Accuracy, and SSIM.
Downloads
References
Piccardi M 2004 Background subtraction techniques: a review. IEEE IntConfSyst Man Cybern 4:3099–3104
Benezeth Y, Jodoin Pierre-Marc, Emile Bruno, Laurent Helene and Rosenberger Christophe 2012 Comparative study of background subtraction algorithms. J Electron Imaging 19(3):12
Ahmed Sumaya H, El-SayedKhaled M and ElhabianShireen Y 2008 Moving object detection in spatialdomain using background removal techniques-state-of-art. Recent Pat ComputSci 1(1):32–54
Bouwmans Thierry 2014 Traditional and recent approaches in background modeling for foreground detection: an overview. ComputSci Rev 11(12):31–66
Sen-ching SC and Chandrika K 2004 Robust techniques for background subtraction in urban traffic video. Proceedings of the SPIE 5308: 881-892
Li L, Huang W, Irene YH Gu and Qi Tian 2003, November Foreground object detection from videos containing complex background. ACM International Conference on Multimedia, pp: 2–10
Wahyono A and Filonenko Jo KH 2016 Unattended object identification for intelligent surveillance systems using sequence of dual background difference. IEEE Trans IndInf 12(6):2247–2255
Wang K, Liu Y, Gou C and Wang FY 2016 A multi-view learning approach to foreground detection for traffic surveillance applications. IEEE Trans VehTechnol 65(6):4144–4158
Cheng FC, Huang SC and Ruan SJ 2011 Illumination-sensitive background modeling approach for accurate moving object detection. IEEE Trans Broadcast 57(4):794–801
Barnich O and Van Droogenbroeck M 2011 ViBe: a universal background subtraction algorithm for video sequences. IEEE Trans Image Process 20(6):1709–1724
Manzanera A and Richefeu JC 2004, December a robust and computationally efficient motion detection algorithm based on background estimation. Indian Conference on Computer Vision, Graphics and Image Processing, pp: 46–51
Lou J, Yang H, Hu W and Tan T 2002, January An illumination invariant change detection algorithm. Asian Conference on Computer Vision, pp: 13–18
Holtzhausen PJ, Crnojevic V and Herbst BM 2015 An illumination invariant framework for real-time foreground detection. J Real Time Image Process 10(2):423–433
Elharrouss O, AbbadA,Moujahid D and Tairi H 2018 Moving object detection zone using a block-based background model. IET Comput Vision 12(1):86–94
Kim W and Kim Y 2016 Background subtraction using illumination-invariant structural complexity. IEEE Signal Process Letters 23(5):634–638
Mahmoudpour S and Robust M Kim 2016 Foreground detection in sudden illumination change, Electron. Letters, vol.52, no.6, pp : 441–443
Cheng FC, Huang SC and Ruan SJ 2011 Illumination-sensitive background modeling approach for accurate moving object detection, IEEE Trans. Broadcasting, 57(4):794–801
Jin Ran, Han Xiaozhen and Yu Tongrui 2021 A Real-Time Image Semantic Segmentation Method Based on Multilabel Classification Hindawi Mathematical Problems in Engineering vol 2021, 13 pages .
Zhou Tianfei , Porikli Fatih , Crandall David , Gool Luc Van and Wang Wenguan 2022 A Survey on Deep Learning Technique for Video Segmentation IEEE Transactions On Pattern Analysis and Machine Intelligence Volume: 45, pp: 7099 – 7122
Robinson Andreas, JäremoLawin Felix, Danelljan Martin, Khan FahadShahbaz and Felsberg Michael 2020 Learning Fast and Robust Target Models for Video Object Segmentation IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Kim Hyungjoon, Lee Jae Ho and Lee Suan 2023 A Hybrid Image Segmentation Method for Accurate Measurement of Urban Environments Electronics, 12(8), 1845.
Karthikeyan Panjappagounder Rajamanickam and Periyasamy Sakthivel 2019 Entropy Based Illumination-Invariant Foreground Detection IEICE TRANS. INF. & SYST., VOL.E102–D, NO.7 pp:1437-1437
Holtzhausen P J , Crnojevic V and Herbst B M, 2015 An illumination invariant framework for real-time foreground detection Journal of Real-Time Image Processing volume 10, pp: 423–433
Karthikeyan P R, Sakthivel P and Karthik T S, 2018 Comparative study of illumination-invariant foreground detection The Journal of Supercomputing volume 76, pp:2289–2301
Hu Yuan-Ting, Huang Jia-Bin, and Schwing Alexander G. 2018 VideoMatch: Matching based Video Object Segmentation Computer Vision ECCV , pp: 56–73
Wang Kunfeng, Liu Yuqiang, Gou Chao, and Wang Fei-Yue 2016 A Multi-View Learning Approach to Foreground Detection for Traffic Surveillance Applications IEEE Transactions on Vehicular Technology 65(6) :4144 – 4158
Chen Haiyan, Zhang Huaqing and Zhen Xiajun 2022 A hybrid active contour image segmentation model with robust to initial contour position Multimedia Tools and Applications, 82, 10833
Wenjuan Ma and Feng Xu Retraction 2021 Underwater image segmentation based on computer vision and research on recognition algorithm Arabian Journal of Geosciences, 14:1-11
Cigaroudy Ladan Sharafyan and Aghazadeh Nasser 2016 A multiphase segmentation method based on binary segmentation method for Gaussian noisy image Signal, Image and Video Processing, 11, pp:825–831
Downloads
Published
How to Cite
Issue
Section
License
![Creative Commons License](http://i.creativecommons.org/l/by-sa/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.