A novel framework of video condensation and video retrieval process using hybrid meta-heuristic development with YOLO-based anomaly detection

被引：0

作者：

Suhandas ^{[1
]}

Kumar, G. Santhosh ^{[2
]}

机构：

[1] Department of Electronics and Communication Engineering, A J Institute of Engineering and Technology, NH-66, Kottara Chowki, Karnataka, Mangaluru

[2] Department of Electronics and Communication Engineering, East West College of Engineering Bengaluru, CA Site-13, Major Akshay Girish Kumar Rd., Sector A, Yelahanka Satellite Town, Yelahanka New Town, Karnataka, Bengaluru

来源：

International Journal of Intelligent Systems Technologies and Applications | 2024年 / 22卷 / 03期

关键词：

anomaly detection; DenseNet; equilibrium optimiser assisted hybrid leader optimisation; gated recurrent unit; MSF; multi-similarity function; video condensation; video retrieval; YOLOv5; model;

D O I：

10.1504/IJISTA.2024.140950

中图分类号：

学科分类号：

摘要：

Visual surveillance systems have presently got the attention of various researchers. Anomaly detection is considered as a challenging issue that reduces the accuracy rate in the video retrieval system with the video surveillance data. To resolve this, a novel method is proposed for the video condensation and retrieval model. The extracted frames are given as input to the YoloV5 model, where the anomalies objects are detected. Here, the condensed video is retrieved using anomaly aware EOHLO-DGRU-MSF (AA-EOHLO-DGRU-MSF). Then, the parameters in DenseNet and GRU are optimised by using equilibrium optimiser-assisted hybrid leader optimisation (EOHLO) algorithm for attaining optimal results. Finally, the multi-similarity function (MSF) between the features in the database and query video is considered. Finally, the performance is evaluated and measured with diverse metrics. Contrary to other approaches, the proposed work outperforms the detection of video and retrieval of video. © 2024 Inderscience Enterprises Ltd.

引用

页码：281 / 312

页数：31

共 32 条

[1] Anuradha K., Anand V., Raajan N.R., An effective technique for the creation of a video synopsis, Journal of Ambient Intelligence and Humanized Computing, (2020)
[2] Cao C., Lu Y., Zhang Y., Context recovery and knowledge retrieval: a novel two-stream framework for video anomaly detection, Computer Vision and Pattern Recognition, (2022)
[3] Chen D., Yue L., Chang X., Xu M., Jia T., NM-GAN: Noise-modulated generative adversarial network for video anomaly detection, Pattern Recognition, 116, (2021)
[4] Cheng K-W., Chen Y-T., Fang W-H., An efficient subsequence search for video anomaly detection and localization, Multimedia Tools and Applications, 75, pp. 15101-115122, (2016)
[5] Chiang C-C., Yang H-F., Quick browsing and retrieval for surveillance videos, Multimedia Tools and Applications, 74, pp. 2861-2877, (2015)
[6] Cui X., Xiao J., Cao Y., Zhu J., Multi-grained encoding and joint embedding space fusion for video and text cross-modal retrieval, Multimedia Tools and Applications, 81, pp. 34367-34386, (2022)
[7] Cui Y., Liu W., Dong S., A time-slice optimization based weak feature association algorithm for video condensation, Multimedia Tools and Applications, 75, pp. 17515-17530, (2016)
[8] Darby J., Sanchez M.B., Bew S., Loram I., Butler P., The development of a video retrieval system using a clinician-led approach, Expert Systems with Applications, 142, (2020)
[9] Deepak K., Srivathsan G., Roshan S., Chandrakala S., Deep multi-view representation learning for video anomaly detection using spatiotemporal autoencoders, Circuits, Systems, and Signal Processing, 40, pp. 1333-1349, (2021)
[10] Dehghani M., Trojovsky P., Hybrid leader based optimization: a new stochastic optimization algorithm for solving optimization applications, Scientific Reports, 12, 1, (2022)

← 1 2 3 4 →