Multi-object Detection and Tracking (MODT) Machine Learning Model for Real-Time Video Surveillance Systems

被引：0
作者：
M. Elhoseny
机构：
[1] Mansoura University,Faculty of Computers and Information
来源：
Circuits, Systems, and Signal Processing | 2020年 / 39卷
关键词：
Video surveillance; Multi objection detection and tracking (MODT); Machine learning; Kalman filtering; Region growing;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Recently, video surveillance has garnered considerable attention in various real-time applications. Due to advances in the field of machine learning, numerous techniques have been developed for multi-object detection and tracking (MODT). This paper introduces a new MODT methodology. The proposed method uses an optimal Kalman filtering technique to track the moving objects in video frames. The video clips were converted based on the number of frames into morphological operations using the region growing model. After distinguishing the objects, Kalman filtering was applied for parameter optimization using the probability-based grasshopper algorithm. Using the optimal parameters, the selected objects were tracked in each frame by a similarity measure. Finally, the proposed MODT framework was executed, and the results were assessed. The experiments showed that the MODT framework achieved maximum detection and tracking accuracies of 76.23% and 86.78%, respectively. The results achieved with Kalman filtering in the MODT process are compared with the results of previous studies.
引用
收藏
页码：611 / 630
页数：19
相关论文
共 72 条
  • [11] Lu P(2018)A robust single and multiple moving object detection, tracking and classification Applied Comput. Inf. 4 8116-8120
  • [12] Woo WL(2015)Techniques and methods for detection and tracking of moving object in a video J. Innov. Res. Comput. Commun. Eng. 102 1-39
  • [13] Yang Y(2018)An adaptive spatio-temporal Gaussian filter for processing cardiac optical mapping data Comput. Biol. Med. 7 1-8
  • [14] Fan Y(2018)A fast valley-based segmentation for detection of slowly moving objects Signal Image Video Process. 13 8171-8181
  • [15] Qiu X(2016)Object detection and movement tracking in H. 264 compressed video based on optimal particle filtering technique J. Comput. Theor. Nanosci. 1 147-150
  • [16] Gu L(2011)Automatic breast DCE-MRI segmentation using compound morphological operations Fourth IEEE Int. Conf. BMEI 13 1-10
  • [17] Hasan SMA(2017)Multi-task learning for object keypoints detection and classification Pattern Recognit. Lett. 127 613-619
  • [18] Ko K(2016)Object tracking based on Kalman particle filter with LSSVR Optik Int. J. Light Electron Opt. 68 76-87
  • [19] Hamuda E(2017)Moving object detection and segmentation in urban environments from a moving platform Image Vis. Comput. undefined undefined-undefined
  • [20] Mc Ginley B(undefined)undefined undefined undefined undefined-undefined
12345678