Open Access Open Access  Restricted Access Subscription or Fee Access

A Comparative Study Of RCNN, YOLO V3-Tiny and YOLO V5 Object Classification Architectures for Accurate Object Classification in Military Domain

Arvind walia

Abstract


Late advances in object distinguishing proof computations consolidate speedy and faster RCNN which
made the ID times also low with high accuracy. In this paper, we demonstrate the reliability of a
suggested computation that employs RPN (Region Suggestion Associations) and Fast RCNN (Regionbased
Convolutional Neural Networks) for the distinguishing proof. The RPN gives region suggestions
from that we give the ROI (Regions of Interest) as commitment to the RCNN association, it will in
general be also merged into a singular association by sharing their convolutional components to
perceive a specific thing in a given picture. Because we work in a tightly knit group, there is no
compelling reason to seek ROI from a third party, making this cycle free of charge. We arranged
VGGnet with two particular enlightening assortments PASCAL VOC 2012 and MS COCO on a
negligible cost GPU and affirmed the exactnesses while differentiating the outcomes and extending
number of region proposals. As we extended the amount of suggestions, we saw a tremendous
development in the mAP (Mean Average Precision) regard till 2000 proposals from where it showed
up at submersion. Our results are differentiated and the state of the workmanship computation with an
augmentation of 1.2% to the extent MAP for 1800 proposals


Full Text:

PDF

References


Aguilar, W.G.; Luna, M.A.; Moya, J.F.; Abad, V.; Parra, H.; Ruiz, H. Pedestrian detection for UAVs using cascade classifiers with meanshift. In Proceedings of the, San Diego, CA, USA, IEEE, 30 Jan.-1 Feb. 2017

Alex, K.; Ilya, S.; Geoffrey, E.H. ImageNet Classification with Deep Convolutional Neural Networks. Imagenet Compet. 2012, 25, Pp1097–1105.

Alzubaidi, L.; Zhang, J.; Humaidi, A.J.; Al-Dujaili, A.; Duan, Y.; Al-Shamma, O.; Santamaría, J.; Fadhel, M.A.; Al-Amidie, M.; Farhan, L. Review of deep learning: Concepts, CNN architecture, challenges, applications, future directions. J. Big Data 2021, 8, Pp1–74.

Asifullah, K.; Anabia, S.; Umme, Z.; Aqsa, S.Q. A survey of the Recent Architectures of Deep Convolutional Neural Networks. Artif. Intell. Rev. 2020, 53, Pp5455–5516.

Bai, S.; Kolter, J.Z.; Koltun, V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv 2018.

A Comparative Study Of RCNN, YOLO V3-Tiny and YOLO V5 Walia and Mulimani

© JournalsPub 2021. All Rights Reserved 36

Bayot, R.; Gonalves, T. A Survey on Object Classfication Using Convolutional Neural Networks. 2015. Available online: https://core.ac.uk/download/pdf/62473376.pdf (accessed on 1 April 2021).

Christian, S.; Wei, L.; Yangqing, J.; Pierre, S.; Scott, R.; Dragomir, A.; Dumitru, E.; Vincent, V.; Andrew, R. Going Deeper with Convolutions. arXiv 2015, arXiv:1409.4842.

Connor, S.; Taghi, K.M. A survey on Image Data Augmentation of Deep Learning. J. Big Data 2019, 6, Pp1–48.

Fabrice, R.N. Machine Learning and a Small Autonomous Aerial Vehicle Part 1: Navigation and Supervised Deep Learning. Tech. Rep. 2018.

Gageik, N.; Benz, P.; Montenegro, S. Obstacle detection and collision avoidance for a uav with complementary low-cost sensors. IEEE Access 2015, 3, Pp599–609.

Gao, H.; Zhuang, L.; van der Laurens, M.; Kilian, Q.W. Densely Connected Convolutional Networks. arXiv 2016, arXiv:1608.06993.

Geoffrey, E.H.; Nitish, S.; Alex, K.; Ilya, S.; Ruslan, R.S. Improving neural networks by preventing co-adaptation of feature detectors. arXiv 2012, arXiv:1207.0580

He, K.; Zhang, X.; Ren, S.; Sun, J. Deep Residual Learning for Image Recognition. Computer Vision and Pattern Recognition. arXiv 2015, arXiv:1512.03385.

Hugo, L.; Yoshua, B.; Jerome, L.; Pascal, L. Exploring Strategies for Training Deep Neural Networks. J. Mach. Learn. Res. 2009.

Ivana, S.; Eva, T.; Nebojsa, B.; Miodrag, Z.; Marko, B.; Milan, T. Designing Convolutional Neural Network Architecture by the Firefly Algorithm. Int. Young Eng. Forum 2019.

Jefferson, S.; Gustavo, P.; Fernando, O.; Denis, W. Vision-Based Autonomous Navigation Using Supervised Learning Techniques. In Proceedings of the 12th Engineering Applications of Neural Networks and 7th Artificial Intelligence Applications and Innovations, Corfu, Greece, 15–18 September 2011.

Jurgen, S. Deep learning in neural networks: An overview. Neural Netw. 2015, 61, Pp85–117.

Karen, S.; Andrew, Z. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv 2015

Keiron, O.; Ryan, N. An Introduction to Convolutional Neural Networks. Neural and Evolutionary Computing. arXiv 2015

Liu, D.; Cui, Y.; Chen, Y.; Zhang, J.; Fan, B. Video object detection for autonomous driving: Motion-aid feature calibration. Neurocomputing 2020, 409, Pp1–11.

Louati, H.; Bechikh, S.; Louati, A.; Hung, C.C.; Said, L.B. Deep convolutional neural network architecture design as a bi-level optimization problem. Neurocomputing 2021, 439, Pp44–62.

Naghavi, S.H.; Avaznia, C.; Talebi, H. Integrated real-time object detection for self-driving vehicles. In Proceedings of the 10th Iranian Conference on Machine Vision and Image Processing, Isfahan, Iran, 22–23 November 2017.

Neha, S.; Vibhor, J.; Anju, M. An Analysis Of Convolutional Neural Networks For Image Classification. Procedia Comput. Sci. 2018, 132, Pp377–384.

Nielsen, M. Neural Networks and Deep Learning. Free Online Book, Michael Nielsen, 2019; Chapter 5. Available online: http://neuralnetworksanddeeplearning.com/about.html (accessed on 1 April 2021).

Niu, H.; Gonzalez-Prelcic, N.; Heath, R.W. A uav-based traffic monitoring system-invited paper. In Proceedings of the IEEE 87th Vehicular Technology Conference, Porto, Portugal, 3–6 June 2018.

Richard, L.; Roberto, F. Space Object Classification Using Deep Convolutional Neural Networks. In Proceedings of the 19th International Conference on Information Fusion, Big Sky, MT, USA, 3–10 March 2018.

Rikiya, Y.; Mizuho, N.; Richard, K.G.D.; Kaori, T. Convolutional neural networks: An overview and application in radiology. Insights Imaging 2018, 9, Pp611–629.

Saloni, W. The Role of Autonomous Unmanned Ground Vehicle Technologies in Defense Applications. Aerospace & Defense Technology Magazine. 2020. Available online: https://www.aerodefensetech.com/component/content/article/adt/features/ articles/37888

International Journal of Broadband Cellular Communication

Volume 7, Issue 1

ISSN: 2455-8532

© JournalsPub 2021. All Rights Reserved 37

(accessed on 1 April 2021).

Sarthak, B.; Sujit, P. UAV Target Tracking in Urban Environments Using Deep Reinforcement Learning. arXiv 2020. arXiv:2007.10934.

Soumya, J.; Dhirendra, K.V.; Gaurav, S.; Amit, P. Issues in Training a Convolutional Neural Network Model for Image Classification. Adv. Comput. Data Sci. 2019, doi10.1007/978-981-13-9942-8_27.

Stephan, Z.; Yang S.; Thomas, L.; Ian G. Improving the Robustness of Deep Neural Networks via Stability Training. arXiv 2016

Tamás, O.; Anton, R.; Ants, K.; Pedro, A.; David, P.; Jan, K.; Pavel, K. Robust Design Optimization and Emerging Technologies for Electrical Machines: Challenges and Open Problems. Appl. Sci. 2020, 10, 6653.

Thumu, K.; Gurrala, N.R.; Srinivasan, N. Object Classification and Detection using Deep Convolution Neural Network Architecture. Int. J. Recent Technol. Eng. 2020.

Wang, D.; Chen, J. Supervised Speech Separation Based on Deep Learning: An Overview. Available online: https://arxiv.org/ pdf/1708.07524.pdf (accessed on 1 April 2021).

Wang, Y.; Liu, D.; Jeon, H.; Chu, Z.; Matson, E. End-to-end learning approach for autonomous driving: A convolutional neural network model. In Proceedings of the International Conference on Agents and Artificial Intelligence 2019, Prague, Czech Republic, 19–21 February 2019.

Xavier, G.; Yoshua, B. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of Machine Learning Research, Sardinia, Italy, 13–15 May 2010.

Yang, X.; Kwitt, R.; Niethammer, M. Fast predictive image registration. In Deep Learning and Data Labeling for Medical Applications; Springer: Cham, Switzerland, 2016; Pp 48–57.

Yann, L.; Yoshua, B.; Geoffrey, H. Deep learning. Nature 2015, 521, Pp 436–444.

Zhang, W.J.; Yang, G.; Lin, Y.; Gupta, M.M.; Ji, C. On the definition of deep learning. In Proceedings of the 2018 World Automation Congress (WAC), Stevenson, WA, USA, 3–6 June 2018.

Zhen, J.; Balasuriya, A.; Subhash, C. Autonomous vehicles navigation with visual target tracking: Technical approaches. Algorithms 2008, 1, Pp153–182.


Refbacks

  • There are currently no refbacks.