Temporal Unknown Incremental Clustering Model for Analysis of Traffic Surveillance Videos

@article{Santhosh2019TemporalUI,
  title={Temporal Unknown Incremental Clustering Model for Analysis of Traffic Surveillance Videos},
  author={Kelathodi Kumaran Santhosh and Debi Prosad Dogra and Partha Pratim Roy},
  journal={IEEE Transactions on Intelligent Transportation Systems},
  year={2019},
  volume={20},
  pages={1762-1773}
}
Optimized scene representation is an important characteristic of a framework for detecting abnormalities on live videos. One of the challenges for detecting abnormalities in live videos is real-time detection of objects in a non-parametric way. Another challenge is to efficiently represent the state of objects temporally across frames. In this paper, a Gibbs sampling-based heuristic model referred to as temporal unknown incremental clustering has been proposed to cluster pixels with motion… 

Trajectory-Based Scene Understanding Using Dirichlet Process Mixture Model

TLDR
Experimental validation reveals that the proposed unsupervised and nonparametric method can learn a scene quickly without prior knowledge about the number of paths, and the advantages of the proposed method over the existing techniques popularly used for designing traffic monitoring applications are highlighted.

Dynamic State Model for Analysis of Traffic States using Dirichlet Process Mixture Model

TLDR
An unsupervised and nonparametric method to learn frequently used paths from the tracks of moving objects in time, that can be used for administrative decision making to control traffic at junctions or crowded places and is extended to represent notable traffic dynamics of a scene.

Video trajectory analysis using unsupervised clustering and multi-criteria ranking

TLDR
This paper proposes an unsupervised trajectory clustering method referred to as t-Cluster, which is able to place abnormal patterns on the top of the list and has obtained higher clustering accuracies on public datasets with significantly lesser computation overhead.

Topic-based Video Analysis

TLDR
The scope, variations, and applications of topic modelling, particularly focusing on surveillance video analysis, are discussed, with a methodological survey on existing topic models, their features, underlying representations, characterization, andApplications in visual surveillance’s perspective.

Anomaly Detection in Road Traffic Using Visual Surveillance

TLDR
This study aims to investigate the recent visual surveillance–related research on anomaly detection in public places, particularly on road, and analyzes various vision-guided anomaly detection techniques using a generic framework such that the key technical components can be easily understood.

Spatial-Temporal Map Vehicle Trajectory Detection Using Dynamic Mode Decomposition and Res-UNet+ Neural Networks

TLDR
This paper presents a machine-learning-enhanced longitudinal scanline method to extract vehicle trajectories from high-angle traffic cameras and fundamentally addressed many quality issues found in NGSIM trajectory data.

Intelligent Video Analytic for Suspicious Object Detection : A Systematic Review

  • HanaviF. Hidayat
  • Computer Science
    2020 International Conference on ICT for Smart Society (ICISS)
  • 2020
TLDR
This paper will comprehensively and systematically review the literature on applying machine learning for object detection and video surveillance systems published between 2010 and 2020 to describe the scope of research to detect suspicious objects using intelligent video analytics, frameworks, methods, datasets and identifying suspicious characteristics.

References

SHOWING 1-10 OF 37 REFERENCES

Scene understanding by statistical modeling of motion patterns

TLDR
A novel method for the discovery and statistical representation of motion patterns in a scene observed by a static camera, and an algorithm for learning these patterns from dense optical flow in a hierarchical, unsupervised fashion.

The Dependent Dirichlet Process Mixture of Objects for Detection-free Tracking and Object Modeling

TLDR
A model is presented that localizes objects via unsupervised tracking while learning a representation of each object, avoiding the need for pre-built detectors and requires only spatial and color video data that can be efficiently extracted via frame differencing.

Activity Recognition Using a Mixture of Vector Fields

TLDR
This paper considers pedestrian trajectories and proposes modeling them through a small set of motion/vector fields together with a space-varying switching mechanism, and presents an expectation-maximization algorithm to learn all the parameters of the model, and applies it to trajectory classification tasks.

Trajectory Classification Using Switched Dynamical Hidden Markov Models

TLDR
The ability of the approach to properly describe trajectories with sudden changes is shown, with real data from two different scenarios: a shopping center and a university campus, as well as a set of human activities in both scenarios is successfully recognized.

Trajectory-Based Anomalous Event Detection

TLDR
The proposed work addresses anomaly detection by means of trajectory analysis, an approach with several application fields, most notably video surveillance and traffic monitoring, based on single-class support vector machine (SVM) clustering, where the novelty detection SVM capabilities are used for the identification of anomalous trajectories.

Trajectory Learning for Activity Understanding: Unsupervised, Multilevel, and Long-Term Adaptive Approach

  • B. MorrisM. Trivedi
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2011
TLDR
A framework for live video analysis in which the behaviors of surveillance subjects are described using a vocabulary learned from recurrent motion patterns, for real-time characterization and prediction of future activities, as well as the detection of abnormalities.

Online Nonparametric Bayesian Activity Mining and Analysis From Surveillance Video

TLDR
Experimental results on real surveillance video data are provided to show the performance of the proposed algorithm in different tasks of trajectory clustering, classification, and abnormality detection.

An Incremental DPMM-Based Method for Trajectory Clustering, Modeling, and Retrieval

TLDR
This paper proposes an incremental version of a DPMM-based clustering algorithm and applies it to cluster trajectories, and a trajectory-based video retrieval model is developed.

Temporal Analysis of Motif Mixtures Using Dirichlet Processes

TLDR
The model is designed to handle the difficult case of multivariate time series obtained from a mixture of activities, that is, the authors' observations are caused by the superposition of multiple phenomena occurring concurrently and with no synchronization.