BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系 - ECPv6.16.0//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://ece.hku.hk
X-WR-CALDESC:Events for Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:20220101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;VALUE=DATE:20231122
DTEND;VALUE=DATE:20231123
DTSTAMP:20260513T083038
CREATED:20231121T062836Z
LAST-MODIFIED:20250114T080513Z
UID:17850-1700611200-1700697599@ece.hku.hk
SUMMARY:RPG Seminar – Toward Domain Generalization in Stereo Matching Networks
DESCRIPTION:Estimating depth from images is a fundamental problem in many computer vision applications such as autonomous driving and robot navigation. Stereo matching is a solution to this task\, which finds the matching correspondences between stereo image pairs and recovers the depth through triangulation. However\, despite recent stereo matching networks achieving impressive performance given sufficient training data\, they suffer from domain shifts and generalize poorly to unseen domains. In this seminar\, we will review representative works and show some possible improvement directions on domain-generalized stereo matching network. \nZoom Link :\nhttps://hku.zoom.us/j/99189328899?pwd=U291c092a2FrWG03VnB2dGduSkNqUT09 \nBiography of the speaker:\n\nZezheng Zhang received his Bachelor’s from Nankai University in 2020. He is currently pursuing his Ph.D. degree in the Department of Electrical and Electronic Engineering of HKU\, under the supervision of Prof. Kenneth K. Y. Wong. His research interest mainly focus on computer vision and computational imaging. \nAll are welcome.
URL:https://ece.hku.hk/events/rpg-seminar-toward-domain-generalization-in-stereo-matching-networks/
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/11/rpg-seminar.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;VALUE=DATE:20231122
DTEND;VALUE=DATE:20231123
DTSTAMP:20260513T083038
CREATED:20231121T063620Z
LAST-MODIFIED:20250114T080539Z
UID:17851-1700611200-1700697599@ece.hku.hk
SUMMARY:RPG Seminar – A Novel Algorithm For TDOA-BASED SOURCE LOCALIZATION with None Line of Sight Error using Robust Least M-estimation
DESCRIPTION:This work presents a novel algorithm for source localization based on Time Difference of Arrival (TDoA) measurements. We proposed a robust variant of the classic least-squares solution that improves the precision and robustness of the localization technique in the presence of heavily noisy measurements\, including those with non-line-of-sight (NLOS) errors\, which could be caused by reverb and reflections. Specifically\, we employ a robust regression algorithm\, namely the Robust Linear Model (RLM)\, to estimate the TDoA values that are used in the least-squares optimization problem. Our proposed RLM-based algorithm is evaluated using both simulations with NLOS error and real-recorded data sets\, and compared with existing methods including conventional least squares(LS) and Regularized Least Squares (RLS) . Simulation results show that our proposed algorithm outperforms existing methods in terms of accuracy and robustness\, especially in highly noisy environments with NLOS error. The use of real-recorded data further demonstrates the effectiveness and practicality of our proposed algorithm. The proposed algorithm has potential applications in acoustic tracking\, speech recognition\, and surveillance\, among others. \nBiography of the speaker:\n\nXiling Sheng completed his Bachelor’s at Commucation University of\nChina\, specializing in Sound Recording Engineering and his MPhil in Technology Leadership and Entreprenurship at HKUST. Currently\, Xiling is a Ph.D. student in the Departmental of Electrical and Electronic Engineering at the University of Hong Kong under the supervision of Prof. Shing Chow Chan. His primary research interest lies in the acoustics\, array signal processing for applications such as tracking\, source seperation and MIMO distribution systems. \nAll are welcome.
URL:https://ece.hku.hk/events/rpg-seminar-a-novel-algorithm-for-tdoa-based-source-localization-with-none-line-of-sight-error-using-robust-least-m-estimation/
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/02/Seminar-s-banner.jpg
END:VEVENT
END:VCALENDAR