Multiple Anomalous Activity Detection in Videos

视频中的多重异常活动检测

Procedia Computer Science, Volume 125, 2018, Pages 336-345

Sarita Chaudhary, Mohd Aamir Khan, Charul Bhatnagar

摘要：Due to exponential increase in crime rate, surveillance systems are being put up in malls, stations, schools, airports etc. With the videos being captured 24x7 from these cameras, it is difficult to manually monitor them to detect suspicious activities. So, there is a great demand for intelligent surveillance system. The proposed work automatically detects multiple anomalous activities in videos. The proposed framework includes three main steps: moving object detection, object tracking and behavior understanding for activity recognition. By using feature extraction process key features (speed, direction, centroid and dimensions) are identified. These features helps to track object in video frames. Problem domain knowledge rules helps to distinguish activities and dominant behavior of activities shows whether particular activity belongs to normal activity class or anomalous class. It has been experimentally proven that the proposed framework is capable of detecting multiple anomalous activities successfully with detection accuracy upto 90%.

Abnormal event detection based on analysis of movement information of video sequence

基于视频序列运动信息分析的异常事件探测

Optik - International Journal for Light and Electron Optics, Volume 152, January 2018, Pages 50-60

Tian Wang, Meina Qiao, Yingjun Deng, Yi Zhou, Hichem Snoussi

摘要：Abnormal event detection is a challenging problem in video surveillance which is essential to the early-warning security and protection system. We propose an algorithm to solve this problem efficiently based on an image descriptor which encodes the movement information and the classification method. The new abnormality indicator is derived from the hidden Markov model which learns the histograms of optical flow orientations of the observed video frames. This indicator measures the similarity between the observed video frame and existing normal frames. The proposed method is evaluated and validated on several video surveillance datasets.

Intelligent video surveillance beyond robust background modeling

优于鲁棒性背景建模的智能视频监控

Expert Systems with Applications, Volume 91, January 2018, Pages 138-149

Eduardo Cermeño, Ana Pérez, Juan Alberto Sigüenza

摘要：The increasing number of video surveillance cameras is challenging video control systems. Monitoring centers require tools to guide the process of supervision. Different video analysis methods have effectively met the main requirements from the industry of perimeter protection. High accuracy detection systems are able to process real time video on affordable hardware. However some problematic environments cause a massive number of false alerts. Many approaches in the literature do not consider this kind of environments while others use metrics that dilute their impact on results. An intelligent video solution for perimeter protection must select and show the cameras which are more likely witnessing a relevant event but systems based only on background modeling tend to give importance to problematic situations no matter if an intrusion is taking place or not. We propose to add a module based on machine learning and global features, bringing adaptability to the video surveillance solution, so that problematic situations can be recognized and given the right priority. Tests with thousands of hours of video show how good an intruder detector can perform but also how a simple fault in a camera can flood a monitoring center with alerts. The new proposal is able to learn and recognize events such that alerts from problematic environments can be properly handled.

Shadow traffic: A unified model for abnormal traffic behavior simulation

阴影交通：异常交通行为模拟统一模型

Computers & Graphics, Volume 70, February 2018, Pages 235-241

Hua Wang, Mingliang Xu, Fubao Zhu, Zhigang Deng, Bing Zhou

摘要：Abnormal traffic behaviors are common traffic phenomena. Existing traffic simulators focus on showing how traffic flow develops after an anomaly occurs; however, they cannot depict the anomaly itself. In this paper, we introduce the concept of shadow traffic for modeling traffic anomalies in a unified way in traffic simulations. We transform the properties of anomalies to the properties of shadow vehicles and then describe how these shadow vehicles participate in traffic simulations. Our model can be incorporated into most existing traffic simulators with little computational overhead. Moreover, experimental results demonstrate that our model is capable of simulating a variety of abnormal traffic behaviors realistically and efficiently.