eprintid: 4785
rev_number: 13
eprint_status: archive
userid: 378
dir: disk0/00/00/47/85
datestamp: 2023-02-10 07:29:21
lastmod: 2023-02-10 07:29:21
status_changed: 2023-02-10 07:29:21
type: conference_item
metadata_visibility: show
creators_name: Nguyễn, Hồng Thịnh
creators_name: Bùi, Sơn Tùng
creators_name: Phùng, Thế Ngọc
creators_name: Đỗ, Duy Thanh
creators_id: hongthinh.nguyen@vnu.edu.vn
title: AI-based video analysis for traffic monitoring
ispublished: pub
subjects: ECE
divisions: fac_fet
abstract: Video data from these surveillance cameras is ex- tremely huge. When it requires extracting information about an object or event from the surveillance camera without knowing the exact time, it is very challenging to immediately identify it from billions of video frames. Thus, how to effectively extract information from video surveillance has a strategically important role in practical applications. In this paper, we introduce a system to manage and retrieve surveillance videos based on the indexing of moving objects. The system contains object detection and features extraction, video indexing, retrieval processing mechanism, and fast previewing. Specifically, this system uses information from moving objects to index video content. As a result, in the retrieval phase, the system allows both text- based query and image-based query mechanisms. The system performance are evaluated on traffic surveillance videos and got promising results.
date_type: completed
full_text_status: public
pres_type: paper
event_title: 2022 APSIPA Annual Summit and Conference
event_location: Chiang Mai, Thailand
event_dates: 7-10 November 2022
event_type: conference
refereed: TRUE
citation:   Nguyễn, Hồng Thịnh and Bùi, Sơn Tùng and Phùng, Thế Ngọc and Đỗ, Duy Thanh   AI-based video analysis for traffic monitoring.  In: 2022 APSIPA Annual Summit and Conference, 7-10 November 2022, Chiang Mai, Thailand.     
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/4785/1/2022190413.pdf