S
Synh Viet-Uyen Ha
Researcher at Vietnam National University, Ho Chi Minh City
Publications - 37
Citations - 240
Synh Viet-Uyen Ha is an academic researcher from Vietnam National University, Ho Chi Minh City. The author has contributed to research in topics: Computer science & Background subtraction. The author has an hindex of 6, co-authored 31 publications receiving 168 citations. Previous affiliations of Synh Viet-Uyen Ha include Sungkyunkwan University & International University, Cambodia.
Papers
More filters
Book ChapterDOI
Adaptive guided image filtering for sharpness enhancement and noise reduction
TL;DR: Experiments showed the results produced from the proposed adaptive guided image filtering (AGF) are superior to those produced from unsharp masking-based techniques and comparable to ABF filtered output.
Journal ArticleDOI
Change Detection by Training a Triplet Network for Motion Feature Extraction
TL;DR: A novel data-driven approach that combines the sample-based background model with a feature extractor obtained by training a triplet network that outperforms the other state-of-the-art methods on CDNet 2014 and other benchmarks.
Proceedings ArticleDOI
Tiny-PIRATE: A Tiny model with Parallelized Intelligence for Real-time Analysis as a Traffic countEr
TL;DR: In this article, the authors proposed a framework of vehicle counting designed specifically for IoT edge computers which follows the detection-tracking-counting (DTC) model, which aims at addressing the multimodality of contextual dynamics in traffic scenes with a small detector model, a robust tracker and a counting process that accurately estimate both a vehicle's motion of interest and its exit time from observation areas.
Journal ArticleDOI
High variation removal for background subtraction in traffic surveillance systems
TL;DR: A new method is proposed that incorporates entropy estimation and a removal framework into the Gaussian mixture model to improve the performance of background subtraction.
Proceedings ArticleDOI
Occlusion vehicle detection algorithm in crowded scene for Traffic Surveillance System
TL;DR: A vision-based approach in which undefined blobs of occluded vehicles are examined to extract the vehicles individually based on the geometric and the ellipticity characteristic of objects' shapes to improve the occlusion vehicle detection from static surveillance cameras.