Browse > Article
http://dx.doi.org/10.9717/kmms.2022.25.3.546

Research on Intelligent Anomaly Detection System Based on Real-Time Unstructured Object Recognition Technique  

Lee, Seok Chang (Power Wireless Communication Project Team, Electric Power Research Institute, Korea Electric Power Corporation)
Kim, Young Hyun (Power Wireless Communication Project Team, Electric Power Research Institute, Korea Electric Power Corporation)
Kang, Soo Kyung (Power Wireless Communication Project Team, Electric Power Research Institute, Korea Electric Power Corporation)
Park, Myung Hye (Power Wireless Communication Project Team, Electric Power Research Institute, Korea Electric Power Corporation)
Publication Information
Journal of Korea Multimedia Society / v.25, no.3, 2022 , pp. 546-557 More about this Journal
Abstract
Recently, the demand to interpret image data with artificial intelligence in various fields is rapidly increasing. Object recognition and detection techniques using deep learning are mainly used, and video integration analysis to determine unstructured object recognition is a particularly important problem. In the case of natural disasters or social disasters, there is a limit to the object recognition structure alone because it has an unstructured shape. In this paper, we propose intelligent video integration analysis system that can recognize unstructured objects based on video turning point and object detection. We also introduce a method to apply and evaluate object recognition using virtual augmented images from 2D to 3D through GAN.
Keywords
Object Detection; Anomaly Detection; Class Activation Map; Unstructured Object Recognition; Gan; Transfer Learning; Self-Learning;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Anomaly Detection, http://docs.iris.tools/manual/IRIS-Usecase/AnomalyDetection/AnomalyDetection_202009_v01.html (accessed October 1, 2021).
2 Computer vision technology, http://www.aitimes.kr/news/articleView.html?idxno=12087 (accessed July 24, 2021).
3 Axis, https://www.axis.com/ko-kr/learning/web-articles/perfect-pixel-count/pixel-density (accessed June 20, 2021).
4 S.-C. Lim and J.-C. Kim, "Bottleneck-based Siam-CNN Algorithm for Object Tracking," Journal of Korea Multimedia Society, Vol. 5, No. 1, pp. 72-81, 2022.
5 M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, "MobileNetV2: Inverted Residuals and Linear Bottlenecks," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510-4520, 2018.
6 A. Krizhevsky, I. Sutskever, and G.E. Hinton, "ImageNet Classification with Deep Convolutional Neural Network," NIPS, pp. 1097-1105, 2012.
7 I.J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, and D. Warde-Farley, Generative Adversarial Networks, arXiv Preprint, arXiv: 1406.2661, 2014.
8 NIPA, Understanding and Utilization of Visual Intelligence, Issue Report 2019-09, p. 2, 2019.
9 S.-Y. Ok, "Real-Time Large-Capacity/ LargeScale Video Data Distributed Agent- Based for Analysis to Develop a High- Performance Object Tracking Platform," A Study on Korea (Research), pp. 3-7, 2017.
10 B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba, "Learning Deep Features for Discriminative Localization," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921-2929, 2016.
11 GAN review, https://airsbigdata.tistory.com/217 (accessed July 24, 2021).
12 Pyscenedetect, https://pyscenedetect.readthedocs.io/en/latest/other/literature/ (accessed July 24, 2021).
13 H.S. Parekh, D. Thakore, and U.K. Jaliya, "A Survey on Object Detection and Tracking Methods," IJIRCCE, Vol. 2, pp. 2970-2978, 2014.
14 M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, and S. Hochreiter, GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium, NIPS, Vol. 30, pp. 6629-6640, 2018.
15 Yolov5, https://github.com/ultralytics/yolov5, 202 (accessed April 15, 2021).
16 C. Szegedy, et al. "Going Deeper with Convolutions," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-9, 2015.
17 Fire dataset, https://www.kaggle.com/phylake1337/fire-dataset (accessed September 12, 2021).