Real-Time Object Detection and Classification Using Sparse Persistence Image-Based Color Directional Pattern (SPICDP) For Indoor Scenes
Keywords:
Object, detection, Segmentation, persistent, featureAbstract
For the visual perception of mobile robots, object detection technique used in unseen real-world contexts is still a difficult task. Therefore, object recognition and localization, which are frequently referred to as detection, are crucial components of robot visual perception. The effectiveness of object detectors has significantly increased because of the quick development of deep learning networks. Topologically persistent characteristics, which rely on knowledge of an object's shape, are used in the suggested approach. Particularly, sparse persistence image (PI) feature types are retrieved in the proposed approach. Then, a Convolutional Neural Network (CNN) is trained to recognize objects using these properties. To do this, the system is first fed with the labelled training data. In contrast to prior object identification systems, the suggested approach takes input from videos or photos and classifies the objects using novel Sparse Persistence Image-Based Color Directional Pattern (SPICDP). The proposed approach achieves high accuracy than the other state-of-the-art methods.
Downloads
References
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 779–788.
S. Thys, W. Van Ranst, and T. Goedem´e, “Fooling automated surveillance cameras: adversarial patches to attack person detection,” in IEEE Conf. Comput. Vis. Pattern Recognit. Workshop, 2019, pp. 0–0.
C. Eriksen, A. Nicolai, and W. Smart, “Learning object classifiers with limited human supervision on a physical robot,” in IEEE Int. Conf. Robotic Comput., 2018, pp. 282–287.
Y. Chen, W. Li, C. Sakaridis, D. Dai, and L. Van Gool, “Domain Adaptive Faster R-CNN for object detection in the wild,” in IEEE Conf. Comput. Vis. Pattern Recognit., 2018, pp. 3339–3348.
K. Saito, Y. Ushiku, T. Harada, and K. Saenko, “Strong-weak distribution alignment for adaptive object detection,” in IEEE Conf. Comput. Vis. Pattern Recognit., 2019, pp. 6956–6965.
J. Reininghaus, S. Huber, U. Bauer, and R. Kwitt, “A stable multi-scale kernel for topological machine learning,” in IEEE Conf. Comput. Vis. Pattern Recognit., 2015, pp. 4741–4748.
E.U.Samani, X.Yang, A.G.Banerjee, “UW Indoor Scenes (UW-IS) Dataset”, Mendeley Data, V2, 2021,doi: 10.17632/dxzf29ttyh.2
Ranadev, M. B. ., V. R. . Sheelavant, and R. L. . Chakrasali. “Predetermination of Performance Parameters of 3-Phase Induction Motor Using Numerical Technique Tools”. International Journal on Recent and Innovation Trends in Computing and Communication, vol. 10, no. 6, June 2022, pp. 63-69, doi:10.17762/ijritcc.v10i6.5628.
K. He, X. Zhang, S. Ren and J. Sun, “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778.
E.U.Samani, X.Yang , A.G.Banerjee, “Visual object recognition in indoor environments using topologically persistent features,” IEEE Robotics and Automation Letters. 2021 Jul 26;6(4):7509-16.
S.Lazebnik, C.Schmid. J.Ponce, “Beyond Bags of Features: Spatial Pyramid Matching for Recognize Natural Scene Categories”, in IEEE Conference on Computer Vision and Pattern Recognition, pp. 2169–2178. IEEE Press,2006 New York.
T.Ojala, M.Pietikainen, T.Maenpaa, “Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns”, in IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(7),2002,pp. 971–987.
Gupta, D. J. . (2022). A Study on Various Cloud Computing Technologies, Implementation Process, Categories and Application Use in Organisation. International Journal on Future Revolution in Computer Science &Amp; Communication Engineering, 8(1), 09–12. https://doi.org/10.17762/ijfrcsce.v8i1.2064
Z.Yang ,L. Jin , D.Tao , “A comparative study of several feature extraction methods for person re-identification”,In Chinese Conference on Biometric Recognition 2012 Dec 4 (pp. 268-277). Springer, Berlin, Heidelberg.
A.KNsaif, S.H.Ali , K.N.Jassim , A.K.Nseaf, R.Sulaiman , A.Al-Qaraghuli , O.Wahdan , N.A.Nayan , “FRCNN-GNB: Cascade faster R-CNN with gabor filters and naïve Bayes for enhanced eye detection”, IEEE Access. 2021 Jan 19; 9:15708-19.
N.Jiang, J.Fang, Q.Yang, “Global-local domain adaptive object detection based on single shot multibox detector”, Journal of Computer Applications. 2021 Feb 10;41(2):517.
Andrie Dazlee, N. M. A., Abdul Khalil, S., Abdul-Rahman, S., & Mutalib, S. (2022). Object Detection for Autonomous Vehicles with Sensor-based Technology Using YOLO. International Journal of Intelligent Systems and Applications in Engineering, 10(1), 129–134. https://doi.org/10.18201/ijisae.2022.276
G. Tauzin, U. Lupo, L. Tunstall, J. B. P´erez, M. Caorsi, A. MedinaMardones, A. Dassatti, and K. Hess, “giotto-tda: A topological data analysis toolkit for machine learning and data exploration,” arXiv preprint arXiv:2004.02551, 2020.
B.Baheti, S.Innani, S.Gajre, S.Talbar, “Semantic scene segmentation in unstructured environment with modified DeepLabV3+”, Pattern Recognition Letters. 2020 Oct 1; 138:223-9.
Linda R. Musser. (2020). Older Engineering Books are Open Educational Resources. Journal of Online Engineering Education, 11(2), 08–10. Retrieved from http://onlineengineeringeducation.com/index.php/joee/article/view/41
A.S.Alphonse, D.Dharma, “A novel Monogenic Directional Pattern (MDP) and pseudo-Voigt kernel for facilitating the identification of facial emotion”, Journal of Visual Communication and Image Representation. 2017 Nov 1;49:459-70.
A.S.Alphonse, M.S.Starvin, “A novel maximum and minimum response-based Gabor (MMRG) feature extraction method for facial expression recognition”, Multimedia tools and applications. 2019 Aug;78(16):23369-97.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 A.Sherly Alphonse, S. Abinaya, S. Abirami, G.Geo Jenefer, T. Benil
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.
