Enhanced Salient Object Detection Using GrabCut Segmentation and SuperPoint Feature Integration
Keywords:
Salient Object Detection; GrabCut Segmentation; SuperPoint Features; Graph Cuts; Image SegmentationAbstract
In this work, we propose an advanced model for salient object detection and segmentation by integrating the GrabCut algorithm with SuperPoint feature detection. The GrabCut algorithm is known for its robust interactive foreground extraction using iterative graph cuts, while SuperPoint offers a state-of-the-art self-supervised approach for detecting and describing keypoints. Our approach begins with preprocessing the input image and applying the SuperPoint model to extract keypoints and descriptors. These keypoints are then used to generate an initial segmentation mask, marking regions based on salient object detection. The initial mask serves as the input for the GrabCut algorithm, which refines the segmentation boundary through iterative optimization. The proposed model combines the strengths of feature detection and graph-based segmentation, aiming to enhance accuracy and robustness in various scenarios. Experimental results on standard datasets demonstrate the effectiveness of our approach, showing significant improvements in metrics such as Intersection over Union (IoU), Precision, Recall, and F-measure compared to traditional methods. This model provides a robust solution for salient object detection and segmentation, suitable for applications in computer vision and image analysis.
Downloads
References
Jianfang Dou and Jianxun Li, "Moving object detection based on improved VIBE and graph cut optimization," Optik, vol. 124, no. 23, pp. 6081-6088, 2013
C. Rother, V. Kolmogorov, and A. Blake, "GrabCut: Interactive Foreground Extraction using Iterated Graph Cuts," ACM Trans. Graphics, vol. 23, no. 3, pp. 309-314, Aug. 2004.
Ning Xu and Narendra Ahuja and Ravi Bansal, "Object segmentation using graph cuts based active contours," Computer Vision and Image Understanding, vol. 107, no. 3, pp. 210-224, 2007.
S. Vicente and V. Kolmogorov and C. Rother, " Graph cut based image segmentation with connectivity priors," in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA, 2008, pp. 1-8.
S. Alpert and M. Galun and R. Basri and A. Brandt, "Image segmentation by probabilistic bottom-up aggregation and cue integration," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2009, pp. 1-8.
J. Xue and N. Zheng and X. Zhong, "Sequential stratified sampling belief propagation for multiple targets tracking," Science in China Series F, 2007, vol. 49, pp. 48-62, 2006.
Thomas Brox and Jitendra Malik, "Object segmentation by long term analysis of point trajectories," in Proc Computer Vision – ECCV, 2010, pp. 282295.
P. Kohli and P. H. S. Torr, "Efficiently solving dynamic Markov random fields using graph cuts," in Proceedings Tenth IEEE International Conference on Computer Vision (ICCV'05), Beijing, China, 2005, pp. 922-929.
M. Tang and L. Gorelick and O. Veksler and Y. Boykov, "GrabCut in one cut," in Proceedings IEEE International Conference on Computer Vision, Sydney, NSW, Australia, 2013, pp. 1769-1776.
I. S. Dhillon and Y. Guan and B. Kulis, " Weighted Graph Cuts without Eigenvectors A Multilevel Approach," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 11, pp. 1944-1957, Nov. 2007.
F. Questier and R. Put and D. Coomans and B. Walczak and Y. Vander Heyden, " The use of CART and multivariate regression trees for supervised and unsupervised feature selection," Chemometrics and Intelligent Laboratory Systems, vol. 76, no. 1, pp. 45-54, 2005.
A. Golovinskiy and T. Funkhouser, " Min-cut based segmentation of point clouds," in Proc. IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, Kyoto, Japan, 2009, pp. 39-46.
John S. H. Baxter and Martin Rajchl and A. Jonathan McLeod and Jing Yuan and Terry M. Peters,"Directed Acyclic Graph Continuous Max-Flow Image Segmentation for Unconstrained Label Orderings," International Journal of Computer Vision, vol. 123, pp. 415-434, 2017.
Haiying Wang and Kaihuai Qin, " Construction of panoramic image mosaics based on affine transform and graph cut," in Proc. International Conference on Image Processing and Pattern Recognition in Industrial Engineering, 78202T, 2010.
Long, Jianwu, Xin Feng, Xiaofei Zhu, Jianxun Zhang, and Guanglei Gou., " Efficient Superpixel-Guided Interactive Image Segmentation Based on Graph Theory," Symmetry, vol. 10, no. 5, pp. 415-434, 2018.
D. DeTone, T. Malisiewicz, and A. Rabinovich, "SuperPoint: Self-Supervised Interest Point Detection and Description," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
P.-E. Sarlin, D. DeTone, T. Malisiewicz, and A. Rabinovich, "SuperGlue: Learning Feature Matching with Graph Neural Networks," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
Li, Zhaoyang, Jie Cao, Qun Hao, Xue Zhao, Yaqian Ning, and Dongxing Li, " DAN-SuperPoint: Self-Supervised Feature Point Detection Algorithm with Dual Attention Network," Sensors, vol. 22, no. 5, 2022.
Anam Zaman, Fan Yangyu, Muhammad Irfan, Muhammad Saad Ayub, Lv Guoyun and Liu Shiya, " LifelongGlue: Keypoint matching for 3D reconstruction with continual neural networks," Expert Systems with Applications, vol. 195, 2022.
S. Deng, Q. Dong, B. Liu and Z. Hu, " Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Clouds," in Proceedings of International Conference on Robotics and Automation (ICRA), Philadelphia, PA, USA, 2022, pp. 9214-9220.
Aritra Bhowmik, Stefan Gumhold, Carsten Rother and Eric Brachmann, " Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
Y. Tian, V. Balntas, T. Ng, A. Barroso-Laguna, Y. Demiris, K. Mikolajczyk, " D2D: Keypoint Extraction with Describe to Detect Approach," in Proceedings of the Asian Conference on Computer Vision (ACCV), 2021.
B. Talbot, S. Garg and M. Milford, "OpenSeqSLAM2.0: An Open-Source Toolbox for Visual Place Recognition Under Changing Conditions," in Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018, pp. 7758-7765.
X. Kong et al., " Semantic Graph Based Place Recognition for 3D Point Clouds," in Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA, 2020, pp. 8216-8223.
Lorenzo Bertoni, Sven Kreiss and Alexandre Alahi, " MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation," in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 6861-6871.
Yingyan Yang, Yuxiao Han, Shuai Li, Yuanda Yang, Man Zhang, Han Li, " Vision based fruit recognition and positioning technology for harvesting robots," Computers and Electronics in Agriculture, vol. 213, 2023, pp. 108-258.
Cao, Mingwei, Wei Jia, Zhihan Lv, Liping Zheng, and Xiaoping Liu, " Superpixel-Based Feature Tracking for Structure from Motion," Applied Sciences, vol. 9, no. 15, pp. 29-61.
H. Saleem, R. Malekian and H. Munir, " Neural Network-Based Recent Research Developments in SLAM for Autonomous Ground Vehicles: A Review," IEEE Sensors Journal, vol. 23, no. 13, pp. 13829-13858, 2023.
Y. Cao, G. Beltrame, " VIR-SLAM: visual, inertial, and ranging SLAM for single and multi-robot systems," Autonomous Robots, vol. 45, pp. 905-917, 2021.
Han, X., Tao, Y., Li, Z., Cen, R., & Xue, F. (2020). SuperPointVO: A Lightweight Visual Odometry based on CNN Feature Extraction. 2020 5th International Conference on Automation, Control and Robotics Engineering (CACRE), 685-691.
Downloads
Published
How to Cite
Issue
Section
License
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.
