Visible to the public Intelligent monitoring of indoor surveillance video based on deep learning

TitleIntelligent monitoring of indoor surveillance video based on deep learning
Publication TypeConference Paper
Year of Publication2019
AuthorsLiu, Y., Yang, Y., Shi, A., Jigang, P., Haowei, L.
Conference Name2019 21st International Conference on Advanced Communication Technology (ICACT)
KeywordsCameras, convolutional neural nets, Deep Learning, deep learning methods, deep video, fine-tuning network, high-quality segmentation mask, image retrieval, image segmentation, indoor surveillance video, information technology, Instance Segmentation, intelligent monitoring, intelligent video analytics technology, learning (artificial intelligence), Mask R-CNN, Metrics, object detection, pose estimation, protection system, pubcrawl, recurrent neural nets, Resiliency, Scalability, Semantics, smart monitoring system, storage management, Streaming media, surveillance, surveillance cameras, Surveillance video, Training, video image, video signal processing, video surveillance, video surveillance system

With the rapid development of information technology, video surveillance system has become a key part in the security and protection system of modern cities. Especially in prisons, surveillance cameras could be found almost everywhere. However, with the continuous expansion of the surveillance network, surveillance cameras not only bring convenience, but also produce a massive amount of monitoring data, which poses huge challenges to storage, analytics and retrieval. The smart monitoring system equipped with intelligent video analytics technology can monitor as well as pre-alarm abnormal events or behaviours, which is a hot research direction in the field of surveillance. This paper combines deep learning methods, using the state-of-the-art framework for instance segmentation, called Mask R-CNN, to train the fine-tuning network on our datasets, which can efficiently detect objects in a video image while simultaneously generating a high-quality segmentation mask for each instance. The experiment show that our network is simple to train and easy to generalize to other datasets, and the mask average precision is nearly up to 98.5% on our own datasets.

Citation Keyliu_intelligent_2019