I
Iman Gholampour
Researcher at Sharif University of Technology
Publications - 38
Citations - 259
Iman Gholampour is an academic researcher from Sharif University of Technology. The author has contributed to research in topics: Topic model & Optical flow. The author has an hindex of 7, co-authored 36 publications receiving 200 citations.
Papers
More filters
Journal ArticleDOI
Accurate Detection and Recognition of Dirty Vehicle Plate Numbers for High-Speed Applications
Rahim Panahi,Iman Gholampour +1 more
TL;DR: An online highly accurate system for automatic number plate recognition (ANPR) that can be used as a basis for many real-world ITS applications and is not language dependent, as well as tested on available English plates data set and achieved 97% overall accuracy.
Journal ArticleDOI
Abnormal event detection and localisation in traffic videos based on group sparse topical coding
TL;DR: An unsupervised method is proposed to automatically discover abnormal events occurring in traffic videos by applying a group sparse topical coding framework and an improved version of it to optical flow features extracted from video clips.
Proceedings ArticleDOI
Incorporating fully sparse topic models for abnormality detection in traffic videos
TL;DR: This paper addresses the problem of abnormality detection based on an unsupervised learning approach with Fully Sparse Topic Models (FSTM), which uses a set of visual features and automatically discovers the activity patterns occurring in complicated scenes.
Proceedings ArticleDOI
Persian text classification based on topic models
TL;DR: The main goal in this paper is to investigate the possibility of applying the topic models for Persian text classification and compare between the feature processing techniques of BOW and the topic model based approaches.
Proceedings ArticleDOI
Automatic accident detection using topic models
TL;DR: A new framework for automated traffic accident recognition using topic models is proposed, which uses a set of visual features and automatically discovers the motion patterns in traffic scenes and detects accidents by using these learned motion patterns.