Proceedings ArticleDOI
SEVA: A Salient Event Detection Framework from Video Shots Using Support Vector Data Description
Chiranjoy Chattopadhyay,Sukhendu Das +1 more
- pp 273-278
TLDR
This paper proposes SEVA (Salient Events for Video Analytics), a framework for accurate detection and localization of salient events from a given video shot based on statistical learning theory and models salient event detection as a one-class classification problem.Abstract:
In this paper we propose SEVA (Salient Events for Video Analytics), a framework for accurate detection and localization of salient events from a given video shot. Our proposed method is based on statistical learning theory and models salient event detection as a one-class classification problem. Video frames are split into blocks for extracting both the spatial and temporal features. Given a video shots we first track the moving foreground blob. Features are extracted using only the foreground pixels to avoid influence of the background. Using Support Vector Data Description (SVDD) in kernel feature space for each block in a given video frame, the decision boundary for the normal activity class is modeled. For a test video sequence, feature vectors are computed from the video frames and the learnt model is utilized to classify each block as normal or salient. Finally, we have adapted a spatio-temporal smoothing approach to remove the false positives. We have reported both qualitative and quantitative results of our experiments on two real-world benchmarked video datasets. Performance of SEVA is compared with five recent works on video event detection to validate its effectiveness.read more
References
More filters
Journal Article
A Novelty Detection Approach for Foreground Region Detection in Videos with Quasi-stationary Backgrounds
TL;DR: In this paper, a novel approach based on support vector data description is presented, which detects foreground regions in videos with quasi-stationary backgrounds, which automatically segments video frames into background/foreground regions.
Proceedings ArticleDOI
Anomaly detection in surveillance video using motion direction statistics
TL;DR: Experiments demonstrate the effectiveness of proposed algorithm in detecting abnormal events in surveillance video, while keeping a low false alarm rate.
Book ChapterDOI
A novelty detection approach for foreground region detection in videos with quasi-stationary backgrounds
TL;DR: A novel approach based on support vector data description is presented, which detects foreground regions in videos with quasi-stationary backgrounds, which automatically segments video frames into background/foreground regions.
Journal ArticleDOI
Spatiotemporal Features for Action Recognition and Salient Event Detection
TL;DR: A novel method to compute visual saliency from video sequences by counting in the actual spatiotemporal nature of the video by extending existing visual feature models to a volumetric representation and formulating constraints in accordance with perceptual principles is proposed.
Proceedings ArticleDOI
A novel statistical learning-based framework for automatic anomaly detection and localization in crowds
TL;DR: Qualitative experiments on real-life surveillance videos, the recently published UCSD anomaly detection datasets, validate the effectiveness of the proposed approach.