An Efficient Scheme to Obtain Background Image in Video for YOLO-based Static Object Recognition

Authors

  • Hyeong-Jin Kim Division of Computer Engineering, Hoseo University, Republic of Korea
  • Min-Cheol Shin Division of Computer Engineering, Hoseo University, Republic of Korea
  • Man-Wook Han Division of Computer Engineering, Hoseo University, Republic of Korea
  • Chung-pyo Hong Division of Computer Engineering, Hoseo University, Republic of Korea
  • Ho-Woong Lee Division of Computer Engineering, Hoseo University, Republic of Korea

DOI:

https://doi.org/10.13052/jwe1540-9589.21513

Keywords:

Background obtainment, histogram, object detection, YOLO

Abstract

Detecting backgrounds in videos is an important technology that can be used for many applications such as management of major facilities and military surveillance depending on the purpose. It is difficult to accurately find and identify important objects in the background if there are obstacles such as pedestrian or car in the video. In order to overcome this problem, the following method is used to detect the background. First, a pixel area histogram is generated to determine the amount of change in pixel units of an image over time. Based on the histogram, we propose an algorithm that estimates the background by selecting the case with the smallest rate of change. In addition, in order to strongly respond to changes in the surrounding environment, even when a change in brightness occurs, this is solved through frame overlap. Finally, the desired object is identified by applying YOLO v3 as a model for object detection in the obtained background. Through the above process, this study proposes a method for effectively identifying static objects in the background by precisely estimated background of the video. Experimental results show that the non-detection and false detection rate for the background object is enhanced by 60.2% and 11.2%, respectively, in comparison with when the proposed method was not applied.

Downloads

Download data is not yet available.

Author Biographies

Hyeong-Jin Kim, Division of Computer Engineering, Hoseo University, Republic of Korea

Hyeong-Jin Kim received BS degree in computer science from Hoseo University in 2021. He is currently an MS of Computer Engineering at Hoseo University, Asan, Korea. His research interests include machine learning, Healthcare AI, and data science.

Min-Cheol Shin, Division of Computer Engineering, Hoseo University, Republic of Korea

Min-Cheol Shin received BS degree in computer science from Kongju University in 2022. He is currently an MS of Computer Engineering at Hoseo University, Asan, Korea. His research interests include AI, Computer Vision, Deep Learning.

Man-Wook Han, Division of Computer Engineering, Hoseo University, Republic of Korea

Man-Wook Han entered the Department of Computer Science at Hoseo University in 2018. He is currently a BA in Computer Science, Hoseo University, Asan. His research interests are AI, backend servers, and deep learning.

Chung-pyo Hong, Division of Computer Engineering, Hoseo University, Republic of Korea

Chung-Pyo Hong received BS and MS degrees in computer science from Yonsei University, Seoul, Korea, in 2004 and 2006, respectively. In 2012, he received a PhD in computer science from Yonsei University, Seoul, Korea. He is currently an associate professor of Computer Engineering at Hoseo University, Asan, Korea. His research interests include machine learning, explainable AI, and data science.

Ho-Woong Lee, Division of Computer Engineering, Hoseo University, Republic of Korea

Ho-Woong Lee completed a PhD in computer science from Dankook University, Gyenggi-do, Korea. From 2000 to 2020, he served as CTO of AhnLab, Inc. and adjunct professor at Seoul Women’s University and Dankook University. He is currently an associate professor in the Department of Computer Science and Engineering, Hoseo University, Asan. His research interests are machine learning, computer security, digital healthcare and blockchain.

References

A. Darwich, P. A. Hébert, A. Bigand, Y. Mohanna, ‘Background subtraction based on a new fuzzy mixture of Gaussians for moving object detection’, Journal of Imaging, pp. 92, July, 2018.

N. O’Mahony, S. Campbell, A. Carvalho, S. Harapanahalli, G. V. Hernandez, L. Krpalkova, D. Riordan, J. Walsh, ‘Deep learning vs. traditional computer vision’, In Science and information conference, pp. 128–144, April, 2019.

A. Sofwan, M. S. Hariyanto, A. Hidayatno, E. Handoyo, M. Arfan, M. Somantri, ‘Design of Smart Open Parking Using Background Subtraction in the IoT Architecture’, In 2018 2nd International Conference on Electrical Engineering and Informatics (ICon EEI), pp. 7–11, October, 2018.

C. Naimeng, Y. Wanjun, W. Xiaoyu, ‘Smoke detection for early forest fire in aerial photography based on GMM background and wavelet energy’, In 2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA), pp. 763–765, January, 2021.

J. Han, C. Liu, Y. Liu, Z. Luo, X. Zhang, Q. Niu, ‘Infrared small target detection utilizing the enhanced closest-mean background estimation’, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, pp. 645–662, November, 2020.

T. Mahalingam, M. Subramoniam, ‘A robust single and multiple moving object detection, tracking and classification’, Applied Computing and Informatics. July, 2020.

T. Germer, T. Uelwer, S. Conrad, S. Harmeling, ‘Fast multi-level foreground estimation’, In 2020 25th International Conference on Pattern Recognition (ICPR), pp. 1104–1111, January, 2021.

Z. Zeng, J. Jia, D. Yu, Y. Chen, Z. Zhu, ‘Pixel modeling using histograms based on fuzzy partitions for dynamic background subtraction’, IEEE Transactions on Fuzzy Systems, pp. 584–593, June, 2017.

H. Yang, S. Qu, ‘Real-time vehicle detection and counting in complex traffic scenes using background subtraction model with low-rank decomposition’, IET Intelligent Transport Systems, pp. 75–85, January, 2018.

S. H. Jeevith, S. Lakshmikanth, ‘Detection and tracking of moving object using modified background subtraction and Kalman filter’, International Journal of Electrical and Computer Engineering, pp. 217–223, February, 2021.

S. B. Song, J. H. Kim, ‘SFMOG: Super Fast MOG Based Background Subtraction Algorithm’, Journal of IKEEE, pp. 1415–1422, December, 2019.

Y. Liu, G. Tang, W. Zou, ‘Video monitoring of Landslide based on background subtraction with Gaussian mixture model algorithm’, In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, pp. 8432–8435. July, 2021.

M. Babaee, D. T. Dinh, G. Rigoll, ‘A deep convolutional neural network for background subtraction’, arXiv preprint arXiv:1702.01731. February, 2017.

M. Vijayan, P. Raguraman, R. Mohan, ‘A Fully Residual Convolutional Neural Network for Background Subtraction’, Pattern Recognition Letters, pp. 63–69, June, 2021.

T. Bouwmans, S. Javed, M. Sultana, S. K. Jung, ‘Deep neural network concepts for background subtraction: A systematic review and comparative evaluation’, Neural Networks, pp. 8–66. September, 2019.

D. Zeng, M. Zhu, A. Kuijper, ‘Combining background subtraction algorithms with convolutional neural network’, Journal of Electronic Imaging, January, 2019.

W. He, K. Yong, W. Kim, H. L. Ko, J. Wu, W. Li, B. Tu, ‘Local compact binary count based nonparametric background modeling for foreground detection in dynamic scenes’, IEEE Access, pp. 92329–92340, 2019.

J. Redmon, A. Farhadi, ‘Yolov3: An incremental improvement’, arXiv preprint arXiv:1804.02767. April, 2018.

Published

2022-08-27

Issue

Section

SPECIAL ISSUE ON Future Multimedia Contents and Technology on Web in the 5G Era