Unsupervised Anomaly Detection for Traffic Surveillance Based on Background Modeling

Wei, Jiayi; Zhao, Jianfei; Zhao, Yanyun; Zhao, Zhicheng

doi:10.1109/cvprw.2018.00025

Cited by 32 publications

(14 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Target Reference Link OpenCV [190] in 2018 [191] in 2018 It is cross-platform C and C++ Library, it has more than 2500 conventional and state-of-the-art computer vision and machine learning algorithms. https://opencv.org/ Background Subtraction (BGS) [192] in 2013 [193]…”

Section: Librariesmentioning

confidence: 99%

Review on Real Time Background Extraction: Models, Applications, Environments, Challenges and Evaluation Approaches

Yasir

Ali

2021

Int. J. Onl. Eng.

View full text Add to dashboard Cite

In the computer vision, background extraction is a promising technique. It is characterized by being applied in many different real time applications in diverse environments and with variety of challenges. Background extraction is the most popular technique employed in the domain of detecting moving foreground objects taken by stationary surveillance cameras. Achieving high performance is required with many perspectives and demands. Choosing the suitable background extraction model plays the major role in affecting the performance matrices of time, memory, and accuracy.In this article we present an extensive review on background extraction in which we attempt to cover all the related topics. We list the four process stages of background extraction and we consider several well-known models starting with the conventional models and ending up with the state-of-the art models. This review also focuses on the model environments whether it is human activities, Nature or sport environments and illuminates on some of the real time applications where background extraction method is adopted. Many challenges are addressed in respect to environment, camera, foreground objects, background, and computation time. In addition, this article provides handy tables containing different common datasets and libraries used in the field of background extraction experiments. Eventually, we illustrate the performance evaluation with a table of the set performance metrics to measure the robustness of the background extraction model against other models in terms of time, accurate performance and required memory.

show abstract

Section: Librariesmentioning

confidence: 99%

Review on Real Time Background Extraction: Models, Applications, Environments, Challenges and Evaluation Approaches

Yasir

Ali

2021

Int. J. Onl. Eng.

View full text Add to dashboard Cite

show abstract

“…This section will discuss how the proposed system in this research, with the proposed system will complement the existing system and can also improve previous studies [22], so that this research becomes the latest research and can be the basis of research. In the future, the pictures and explanations can be seen below:…”

Section: Proposed Systemmentioning

confidence: 99%

“…The vehicles in this research are motorized vehicles that are used by motorists to drive on the highway, and commit violations on the highway, with a violation [21], motorized vehicles can be subject to a ticket sanction based on evidence obtained from CCTV. ∑ CCTV CCTV is a tool used to record images that will be used as evidence of a motorized vehicle making a mistake, with the presence of the image [22], the prohibitor cannot argue that he has committed a violation, CCTV is a tool that is very suitable for use on the highway because it can withstand all weather conditions , and and can produce maximum images to be used as proof of a ticket.…”

Section: Figure 2 Proposed Systemmentioning

confidence: 99%

Supervision and Law Enforcement on Intelligent Transportation Systems on the Highway

Dewi

2021

IJERSC

View full text Add to dashboard Cite

This research discusses the supervision and law enforcement on the transportation system, which will be applied to the smart transportation system. With this system, the police and local governments will be able to monitor the transportation system in a city, especially law enforcement on roads. The method used in this study is to use a literature review which is the basis for this research, by using a literature review it will be able to deepen a research, and be able to understand previous studies in order to create new research. The problem raised in this research is how to apply law enforcement on the highway to land transportation, both public vehicles and private vehicles that are on the highway every day, with strict law enforcement it will reduce crime on the road and can reduce accidents on the road Highway. This research will produce a proposed system, which can be used by the police and local governments in enforcing the law on public or private vehicles on the road.

show abstract

“…Inspired by the great success of deep learning in the object detection field, some researchers are beginning to attempt to introduce deep learning to vehicle detection field. Wei [27] et al tried to detect anomalous vehicles in traffic surveillance. They first employed background subtraction model to remove identified moving vehicles, and then utilized Faster R-CNN [10] to detect remaining anomalous vehicles.…”

Section: The Related Workmentioning

confidence: 99%

“…Hence, if we can utilize traditional algorithm MOG2 [19][20] to create robust scale-insensitive RoIs and exploit deep learning model H-SqueezeNet to finish detection, the advantages of both methods will be inherited and shortcomings of each method will be avoided. In our work, we didn't combine MOG2 with VGG, or imitate Wei [27] combine MOG2 with Faster R-CNN. Because we want to build a simple but powerful method.…”

Section: The Related Workmentioning

confidence: 99%

A Robust Vehicle Detection Scheme for Intelligent Traffic Surveillance Systems in Smart Cities

et al. 2020

View full text Add to dashboard Cite

Accurately obtaining road vehicle information is important in intelligent traffic surveillance systems for smart cities. Especially smart vehicle detection is recognized as the critical research issue of intelligent traffic surveillance systems. In this paper, a robust real-time vehicle detection method for the system is proposed. The method combines background subtraction model MOG2(Mixture of Gaussians) with a modified SqueezeNet model (H-SqueezeNet). The MOG2 model is utilized to create scale-insensitive Region of Interest (RoIs) from video frames. H-SqueezeNet is then proposed to accurately identify vehicle category. The effectiveness of the method was verified in CDnet2014 dataset, UA-DETRAC dataset and video data from a traffic intersection in Suzhou, China. The experiment results show that the method can achieves excellent detection accuracy in traffic surveillance systems, and achieve an average detection speed of 39.1 FPS.

show abstract

Unsupervised Anomaly Detection for Traffic Surveillance Based on Background Modeling

Cited by 32 publications

References 18 publications

Review on Real Time Background Extraction: Models, Applications, Environments, Challenges and Evaluation Approaches

Review on Real Time Background Extraction: Models, Applications, Environments, Challenges and Evaluation Approaches

Supervision and Law Enforcement on Intelligent Transportation Systems on the Highway

A Robust Vehicle Detection Scheme for Intelligent Traffic Surveillance Systems in Smart Cities

Contact Info

Product

Resources

About