A neural network-based image processing system for detection of vandal acts in unmanned railway environments

Sacchi, Claudio; Regazzoni, Carlo S.; Vernazza, G.

doi:10.1109/iciap.2001.957064

Cited by 14 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They extract new implicit information, hidden in the raw data provided by the cameras and sensors. Some deductive techniques use Neural Networks [51,52] or Clustering Algorithms [53] to classify behaviors and contexts but they are normally resource-greedy and data processing is slow.…”

Section: Monitoring and Control Systemmentioning

confidence: 99%

An Intelligent Surveillance Platform for Large Metropolitan Areas with Dense Sensor Deployment

Fernández

Calavia

Baladrón

et al. 2013

Sensors

View full text Add to dashboard Cite

This paper presents an intelligent surveillance platform based on the usage of large numbers of inexpensive sensors designed and developed inside the European Eureka Celtic project HuSIMS. With the aim of maximizing the number of deployable units while keeping monetary and resource/bandwidth costs at a minimum, the surveillance platform is based on the usage of inexpensive visual sensors which apply efficient motion detection and tracking algorithms to transform the video signal in a set of motion parameters. In order to automate the analysis of the myriad of data streams generated by the visual sensors, the platform's control center includes an alarm detection engine which comprises three components applying three different Artificial Intelligence strategies in parallel. These strategies are generic, domain-independent approaches which are able to operate in several domains (traffic surveillance, vandalism prevention, perimeter security, etc.). The architecture is completed with a versatile communication network which facilitates data collection from the visual sensors and alarm and video stream distribution towards the emergency teams. The resulting surveillance system is extremely suitable for its deployment in metropolitan areas, smart cities, and large facilities, mainly because cheap visual sensors and autonomous alarm detection facilitate dense sensor network deployments for wide and detailed coverage.

show abstract

Section: Monitoring and Control Systemmentioning

confidence: 99%

An Intelligent Surveillance Platform for Large Metropolitan Areas with Dense Sensor Deployment

Fernández

Calavia

Baladrón

et al. 2013

Sensors

View full text Add to dashboard Cite

show abstract

“…Only qualitative results given, no quantitative empirical analysis [180] Features are generated by motion Only qualitative results given, no quantitative empirical analysis [181] Motion, blob's area, perimeter, centroid, and speed About 84% TP, 9% FP [183] Eigenfeatures Accuracy ranges from 78% to 93.7%, depending on event. Misclassification rates are given [196] Motion history, blobs, compactness, density…”

Section: Evaluation Frameworkmentioning

confidence: 99%

Evaluation of Smart Video for Transit Event Detection

Goldgof¹

2009

View full text Add to dashboard Cite

Transit agencies are increasingly using video cameras to fight crime and terrorism. As the volume of video data increases, the existing digital video surveillance systems provide the infrastructure only to capture, store and distribute video, while leaving the task of threat detection exclusively to human operators. The objective of this research project was to study and develop an evaluation framework for commercial video analytics systems. A state-of-the-art research literature survey was conducted. Identified strengths, weaknesses, future directions of research and state-of-the-art commercial video analytics products were surveyed. Product capabilities were identified by working together with vendors and analyzing the available literature offered by the providers. Use of analytic technology in transit agencies in Florida was analyzed. A technology survey among the largest agencies in the state indicates very low use of video analytics, significant skepticism, and poor general knowledge of the technology and its capabilities. Based on existing general evaluation frameworks, an evaluation framework for video analytics technology was developed, including annotation guidelines, scoring metrics, and implementation of the scoring metrics in the scoring software.

show abstract

“…The method in [3] defines a semiautomatic system to aid an operator in the detection of vandal acts. The actual detection is done by feeding geometric and kinematic features to a neural network classifier which is trained to recognize suspicious variations in those features some of which include the coordinates of the minimum bounding box and center of gravity of tracked objects along with their areas and perimeters.…”

Section: Introductionmentioning

confidence: 99%

Real-time automatic detection of vandalism behavior in video sequences

Ghazal

Vázquez

Amer

2007

2007 IEEE International Conference on Systems, Man and Cybernetics

View full text Add to dashboard Cite

This paper proposes a method for the realtime detection of vandalism in video sequences. The proposed method detects vandalism through the robust extraction of a sequence of high-level events leading to it without resorting to object recognition and using a single camera. Vandalism is declared when an object enters the scene and causes an unauthorized change inside a predefined vandalisable area in the scene such as a pay phone or a sign. The proposed method was tested offline and on-line and our results show that it is robust in detecting vandalism or graffiti in surveillance video sequences.

show abstract

A neural network-based image processing system for detection of vandal acts in unmanned railway environments

Abstract: Abstract

Cited by 14 publications

References 10 publications

An Intelligent Surveillance Platform for Large Metropolitan Areas with Dense Sensor Deployment

An Intelligent Surveillance Platform for Large Metropolitan Areas with Dense Sensor Deployment

Evaluation of Smart Video for Transit Event Detection

Real-time automatic detection of vandalism behavior in video sequences

Contact Info

Product

Resources

About