Performance Evaluation on Real-time object detection using DL techniques

Authors

  • B Sai Jyothi Dept. of Information Technology, Vasireddy Venkatadri Institute of Technology, Guntur, AP, India
  • Chavali Saathvika Durga Abhinaya Dept. of Information Technology, Vasireddy Venkatadri Institute of Technology, Guntur, AP, India
  • Bellamkonda Lahari Dept. of Information Technology, Vasireddy Venkatadri Institute of Technology, Guntur, AP, India
  • Chinta Devika Priya Dept. of Information Technology, Vasireddy Venkatadri Institute of Technology, Guntur, AP, India
  • Devarapalli Anjali Dept. of Information Technology, Vasireddy Venkatadri Institute of Technology, Guntur, AP, India
  • Bathula Sri Navya Dept. of Information Technology, Vasireddy Venkatadri Institute of Technology, Guntur, AP, India

DOI:

https://doi.org/10.26438/ijcse/v12i4.7580

Keywords:

YOLOV8(You only look once), F, Faster region convolutional neural network (faster R-CNN),, object detection, deep learning, deep neural networks,, and convolutional neural networks

Abstract

Objects are located by drawing a bounding box around the detected object. One of computer vision`s specialties is object detection, which finds things in an image or video. Techniques for object detection are the foundation of the area of artificial intelligence. Typically, object detection uses deep learning and machine learning to yield accurate and significant findings. It is essentially made up of localization and classification. The state-of-the-art techniques utilized for real-time object detection have advanced recently. This study paper compares state-of-the-art techniques, such as faster region convolutional neural networks (Faster R-CNN) and you only look once V8 (YOLOV8). These algorithms are deep neural network representations, or neural networks with numerous hidden layers. Although each of these algorithms is notable for its own distinctiveness, they are compared to see which is superior. This study focuses on determining which of these algorithms is more practical to employ despite sharing a common core, namely CNNs.

References

[1] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.” arXiv, Jan. 06, 2016. Accessed: Jun. 17, 2023. [Online]. Available: http://arxiv.org/abs/1506.01497.

[2] S. J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement.” arXiv, apr. 08, 2018. Accessed: Sep. 25, 2022. [Online]. Available: http://arxiv.org/abs/1804.0276.

[3] A.M.A.ghani Abdulghani and G.G. Menekse Dalveren, “Moving Object Detection in Video with Algorithms YOLO and Faster R-CNN in Different Conditions,” European Journal of Science and Technology, Jan. 2022, DOI: 10.31590/ejosat.1013049.

[4] H. Jiang and E. Learned-Miller, Face Detection with the Faster R-CNN.” arXiv, Jun. 10, 2016. Accessed: Sep. 25, 2022. [Online].Available: http://arxiv.org/abs/1606.03473.

[5] Chandana, R. K., & Ramachandra, A. C. Real time object detection system with YOLO and CNN 740 models: A review. arXiv preprint arXiv:2208.00773, 2022.

[6] JiayiFan; JangHyeon, Lee; InSuJung; YongKeunLee, “Improvement of Object Detection Based on Faster R-CNN and YOLO”, International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) June, pp.27-30 2021. DOI: 10.1109/ITC-CSCC52171.2021.9501480.

[7] J. Kim, J.-Y. Sung, and S. Park, “Comparison of Faster-RCNN, YOLO, and SSD for Real-Time Vehicle Type Recognition,” in 2020 IEEE International Conference on Consumer Electronics - Asia (ICCE-Asia), Seoul, Korea (South): IEEE, Nov. pp.1–4, 2020.

DOI: 10.1109/ICCE-Asia49877.2020.9277040.

[8] F. Miao, Y. Tian, and L. Jin, “Vehicle Direction Detection Based on YOLOv3,” in 2019 11th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), Hangzhou, China: IEEE, Aug., pp.268–271, 2019.

DOI: 10.1109/IHMSC.2019.10157.

[9] Rohan, A., Rabah, M., & Kim, S. H. Convolutional neural network-based real-time object detection and tracking for parrot AR drone 2. IEEE access, 7, pp.69575- 69584, 2019.

[10] Younis, A., Shixin, L., Jn, S., & Hai, Z. (January). Real-time object detection using pre- trained deep learning models MobileNet-SSD. In Proceedings of 2020 6th International Conference on Computing and Data Engineering, pp.44-48, 2020.

[11] Nguyen, N. D., Do, T., Ngo, T. D., & Le, D. D. An evaluation of deep learning methods for small object detection. Journal of electrical and computer engineering, 2020, pp.1-18, 2020.

[12] Hossain, S., & Lee, D. J. Deep learning-based real- time multiple-object detection and tracking from aerial imagery via a flying robot with GPU-based embedded devices. Sensors, Vol.19, Issue.15, pp.33-71, 2019.

[13] Pal, S. K., Pramanik, A., Maiti, J., & Mitra, P. Deep learning in multi-object detection and tracking: state of the art. Applied Intelligence, 51, pp.6400-6429, 2021.

[14] J. Du, Understanding of Object Detection Based on CNN Family and YOLO,” J. Phys.: Conf. Ser., Apr., Vol.1004, pp.12-29, 2018. DOI: 10.1088/1742-6596/1004/1/012029.

[15] S. Ren, K. He, R. Girshick, and J. Sun, Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Trans. Pattern Anal. Mach. Intell., Jun., Vol.39, No.6, pp.1137–1149, 2017, DOI: 10.1109/TPAMI.2016.2577031.

Downloads

Published

2024-04-30
CITATION
DOI: 10.26438/ijcse/v12i4.7580
Published: 2024-04-30

How to Cite

[1]
B. Sai Jyothi, C. Saathvika Durga Abhinaya, B. Lahari, C. Devika Priya, D. Anjali, and B. Sri Navya, “Performance Evaluation on Real-time object detection using DL techniques”, Int. J. Comp. Sci. Eng., vol. 12, no. 4, pp. 75–80, Apr. 2024.

Issue

Vol. 12 No. 4 (2024): IJCSE April Edition

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.