Improvement of Vehicle detection and classification performance with Region of Interest

Trần Minh Đức; Nguyễn Thị Hương

doi:10.24235/itej.v8i1.116

Trần Minh Đức Hanoi University of Science and Technology
Nguyễn Thị Hương Hanoi University of Science and Technology

DOI: https://doi.org/10.24235/itej.v8i1.116

Keywords: ROI, Detection, Tracking

Abstract

This Abstract-Paper presents an innovative approach to improve the performance of vehicle detection and classification in the context of computer vision. This study proposes the use of Region of Interest (ROI) to identify and process vehicle information in traffic images. The proposed method is based on a combination of deep learning-based object detection algorithms with a more focused ROI-based approach. First, we use state-of-the-art convolution neural networks to perform object detection in traffic images, which involves a visual recognition process to identify vehicle locations. Then, using ROI, we reorder and reduce the dimensions of irrelevant data to remove background areas and increase attention to vehicle objects. This aims to reduce the computational load and speed up the detection and classification processes. We evaluate the proposed approach on a wide traffic dataset and compare the results with conventional object detection approaches without using ROI. The experimental results show that the proposed method outperforms the conventional approach in terms of vehicle detection speed and accuracy. In conclusion, this study succeeded in improving the performance of vehicle detection and classification by leveraging Region of Interest, which allows better focus on relevant regions and reduces computational complexity. These results can make an important contribution to the development of a more efficient and reliable traffic control and transportation system.

Downloads

Download data is not yet available.

References

Saluky, “Development of Enterprise Architecture Model for Smart City,” ITEJ (Information Technol. Eng. Journals), vol. 02, no. 02, 2017.

P. Girardi and A. Temporelli, “Smartainability: A Methodology for Assessing the Sustainability of the Smart City,” Energy Procedia, vol. 111, no. September 2016, pp. 810–816, 2017, doi: 10.1016/j.egypro.2017.03.243.

S. Saluky, “Abandoned Object Detection Method Using Convolutional Neural Network,” 2007.

S. S. Yoni Marine, “Penerapan IoT untuk Kota Cerdas,” ITEJ (Information Technol. Eng. Journals), vol. 03, no. 01, 2018.

Z. Chen and T. Ellis, “Semi-automatic annotation samples for vehicle type classification in urban environments,” vol. 9, no. August 2013, pp. 240–249, 2015, doi: 10.1049/iet-its.2013.0150.

D. Der Ingenieurwissenschaften, “Background Subtraction for the Detection of Moving and Static Objects in Video Surveillance.”

M. Hörhan and H. Eidenberger, “An Efficient DCT template-based Object Detection Method using Phase Correlation,” 2016 50th Asilomar Conf. Signals, Syst. Comput., pp. 444–448, 2016, doi: 10.1109/ACSSC.2016.7869078.

K. Xiao, J. Zhao, Y. He, C. Li, and W. Cheng, “Abnormal behavior detection scheme of uav using recurrent neural networks,” IEEE Access, vol. 7, pp. 110293–110305, 2019, doi: 10.1109/ACCESS.2019.2934188.

J. Bao, W. Chen, Z. Xiang, Y. Chen, and Y. Shui, “Effect Analysis of Early Warning for Abandoned Object on Highway Based on Internet-of-Vehicles CA Model,” Discret. Dyn. Nat. Soc., vol. 2018, no. 1, 2018.

H. Im, B. Hong, S. Jeon, and J. Hong, “Bigdata analytics on CCTV Images for Collecting Traffic Information,” pp. 525–528, 2016.

C. S. Rao and P. Darwin, “Frame Difference And Kalman Filter Techniques For Detection Of Moving Vehicles In Video Surveillance,” vol. 2, no. 6, pp. 1168–1170, 2012.

H. K. . Vigneshwar.K, “Detection and Counting of Pothole using Image Processing Techniques,” 2016 IEEE Int. Conf. Comput. Intell. Comput. Res., pp. 8–11, 2016, doi: 10.1109/ICCIC.2016.7919622.

K. Lin, S. Chen, C. Chen, D. Lin, and Y. Hung, “Left-Luggage Detection from Finite-State-Machine Analysis in Static-Camera Videos,” 2014 22nd Int. Conf. Pattern Recognit., pp. 4600–4605, 2014, doi: 10.1109/ICPR.2014.787.

W. Pedrycz and S. Chen, Deep Learning : Algorithms and Applications. .

A. H. Pratomo, W. Kaswidjanti, and S. Mu’arifah, “Implementasi Algoritma Region Of Interest (ROI) Untuk Meningkatkan Performa Algoritma Deteksi Dan Klasifikasi Kendaraan Implementation of Region Of Interest (ROI) Algorithm To Improve Car Detection And Classification Algorithm,” J. Teknol. Inf. dan Ilmu Komput., vol. 7, no. 1, pp. 155–162, 2020, doi: 10.25126/jtiik.202071718.

A. J. Lipton, C. H. Heartwell, N. Haering, and D. Madden, “Automated video protection, monitoring & detection,” IEEE Aerosp. Electron. Syst. Mag., vol. 18, no. 5, pp. 3–18, 2003, doi: 10.1109/MAES.2003.1201453.

I. Baek, A. Davies, G. Yan, and R. R. Rajkumar, “Real-time Detection, Tracking, and Classification of Moving and Stationary Objects using Multiple Fisheye Images,” IEEE Intell. Veh. Symp. Proc., vol. 2018-June, pp. 447–452, 2018, doi: 10.1109/IVS.2018.8500455.

R. K. Tripathi, “A Framework for Abandoned Object Detection from Video Surveillance,” 2013 Fourth Natl. Conf. Comput. Vision, Pattern Recognition, Image Process. Graph., pp. 1–4, 2013.

S. Ma, W. Zhu, and L. Zhang, “Region of Interest Extraction Based on Unsupervised Cross-Domain Adaptation for Remote Sensing Images,” Int. Geosci. Remote Sens. Symp., vol. 2021-July, pp. 1169–1172, 2021, doi: 10.1109/IGARSS47720.2021.9553642.