Real-time automatic detection of vandalism behavior in video sequences

Ghazal, Mohammed; Vázquez, Carlos; Amer, A.

doi:10.1109/icsmc.2007.4414038

Cited by 18 publications

(13 citation statements)

References 5 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…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%

See 1 more Smart Citation

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

Section: Evaluation Frameworkmentioning

confidence: 99%

“…VandalismVandalism is defined in Fuentes and Velastin[141] as irregular centroid motion of a blob, combined with detected changes in the background. This definition is also implemented in Ghazal et al[180] when a blob enters a scene and causes changes in the background or predefined "vandalisable" areas. In Sacchi et al[181 ], vandalism is…”

mentioning

confidence: 99%

Evaluation of Smart Video for Transit Event Detection

Goldgof¹

2009

View full text Add to dashboard Cite

show abstract

“…Significant amount of work has already been reported in the field of vandalism, with each system employing its own unique technique. A series of studies was performed by Ghazal et.al [1,2] to detect vandalism. In his first experimentation on detecting vandalism [1], a simple methodology is adopted without involving object recognition task.…”

Section: Introductionmentioning

confidence: 99%

“…A series of studies was performed by Ghazal et.al [1,2] to detect vandalism. In his first experimentation on detecting vandalism [1], a simple methodology is adopted without involving object recognition task. Vandalism act is declared when an object enters the scene and causes an illicit change inside an area prone to vandalism.…”

Section: Introductionmentioning

confidence: 99%

Versatile Defacement Detection by Monitoring Video Sequences Using Deep Learning

R¹,

Arivazhagan²

2019

EJERS

View full text Add to dashboard Cite

The main objective of this paper is to detect vandal and vandalism by monitoring recorded video sequences. Vandalism is one of the most commonly occurring crimes in the society that indirectly affects the economy of the country. The proposed algorithm takes in the input from the video extracted from surveillance camera which prevails in public places. Further, it is converted into frames and subtracted with the background to detect the foreground object. The background subtracted image contains both human and non-human moving objects. In order to differentiate human pixels and other moving objects in the video sequence, discriminative features are extracted using deep architecture and classified using SVM classifier. Deep features proved to be highly discriminative when compared with the handcrafted Histogram of Oriented Gradients features. By analyzing the dwell time of the person in the restricted scene and his motion pattern with time and significant change in background vandalism act is declared and the person is considered as vandal. The proposed method was evaluated on the videos collected from You Tube with the contents taken during night time, multiple vandals, car vandals etc.

show abstract

“…Penelitian hampir serupa juga dilakukan oleh Ghazal, Vazquez, dan Amer yang mengusulkan sebuah metode untuk mendeteksi aksi perusakan (vandalisme) pada video pengawasan secara real time [9]. Deteksi vandalisme dilakukan dengan mengekstraksi kejadian tanpa perlu pengenalan obyek.Penelitian tersebut menguji metode yang diusulkan secara online dan offline dan hasil penelitiannya menunjukkan bahwa metode tersebut dapat mendeteksi vandalisme dan membedakan antara tindakan yang normal dengan tindakan yang bersifat merusak (vandalisme).…”

unclassified