Author:
Bekeneva Ya A,Petukhov V D,Frantsisko O Yu
Abstract
Abstract
In this paper an approach to local image processing in distributed monitoring systems is considered. The proposed approach makes possible to optimize traffic transmitted from monitoring devices generating images or video streams. Image processing, object recognition and identification are performed locally. Based on information received from all monitoring devices, including images, event logs are generated locally for their further transmission to the central data collection, processing and analysis unit. The method of local image processing was tested on the example of face recognition of people who took part in the experiment. Under various experimental conditions, it was found that the proposed method has a sufficiently high accuracy.
Subject
General Physics and Astronomy
Reference12 articles.
1. An Approach to the Distributed Generation of Event Logs Based on Data from Heterogeneous Monitoring Devices;Bekeneva,2020
2. Human detection from images and videos: A survey;Nguyen;Pattern Recognition,2016
3. AnimalFinder: A semi-automated system for animal detection in time-lapse camera trap images;Tack;Ecological Informatics,2016
4. Vehicle detection and counting using haar feature-based classifier;Choudhury,2017
5. Real time traffic sign detection using color and shape-based features;Le,2010
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献