A review of state-of-the-art techniques for abnormal human activity recognition

人群异常行为识别新技术综述

Engineering Applications of Artificial Intelligence, Volume 77, January 2019, Pages 21-45

Chhavi Dhiman, Dinesh Kumar Vishwakarma

摘要：The concept of intelligent visual identification of abnormal human activity has raised the standards of surveillance systems, situation cognizance, homeland safety and smart environments. However, abnormal human activity is highly diverse in itself due to the aspects such as (a) the fundamental definition of anomaly (b) feature representation of an anomaly, (c) its application, and henceforth (d) the dataset. This paper aims to summarize various existing abnormal human activity recognition (AbHAR) handcrafted and deep approaches with the variation of the type of information available such as two-dimensional or three-dimensional data. Features play a vital role in an excellent performance of an AbHAR system. The proposed literature provides feature designs of abnormal human activity recognition in a video with respect to the context or application such as fall detection, Ambient Assistive Living (AAL), homeland security, surveillance or crowd analysis using RGB, depth and skeletal evidence. The key contributions and limitations of every feature design technique, under each category: 2D and 3D AbHAR, in respective contexts are tabulated that will provide insight of various abnormal action detection approaches. Finally, the paper outlines newly added datasets for AbHAR by the researchers with added complexities for method validations.

ArchCam: Real time expert system for suspicious behaviour detection in ATM site

ArchCam： ATM场所可疑行为检测实时专家系统

Expert Systems with Applications, Volume 109, 1 November 2018, Pages 12-24

摘要：Automated Teller Machine (ATM) offers great convenience to many people by allowing quick bank transactions and cash withdrawal. However, ATM machines are also vulnerable to attacks when they are unattended during non-office hours and public holidays. Recently, many ATM machines were reported being removed from the premises or damaged using various methods in order to steal the cash inside. Due to this reason, many ATM sites are actually equipped with video surveillance systems to monitor the environment for crime prevention. However, it is difficult for security personnel to pin-point the crime scene in real time when the number of surveillance cameras increases. In this paper, a real time security expert video surveillance system was proposed to detect the suspicious behaviour by utilizing image processing techniques. The proposed expert system, hereafter referred to as ArchCam, is capable in detecting suspicious behaviours that attempt to remove or attack the ATM machines and provide early warning to the centralized video surveillance system. The suspicious behaviour that ArchCam detects include squatting/climbing (attempt to remove security alarm system or place a bomb) and carrying “belt shape” object (attempt to remove the ATM). The squatting/climbing activity is detected through novel technique to estimate the height of the moving object(s) in front of ATM. On the other hand, the “belt shape” object is detected through estimation of object width by using region splitting and merging technique. With the intelligence of detecting suspicious behaviour, the proposed expert system can effectively alert the security personnel to take proactive actions before the cash is being robbed from the ATM machines. This greatly reduces the effort for security personnel as they only need to observe the camera videos with suspicious behaviour, which on the other hand help to improve the possibility of detecting actual crime scene in real time. ArchCam was implemented in an embedded system with GPU platform and has been verified in a simulated ATM setup with good detection accuracy and fast computational timing performance.

Video surveillance systems-current status and future trends  

视频监控系统：目前现状与未来趋势

Computers & Electrical Engineering, Volume 70, August 2018, Pages 736-753

Vassilios Tsakanikas, Tasos Dagiuklas

摘要：Within this survey an attempt is made to document the present status of video surveillance systems. The main components of a surveillance system are presented and studied thoroughly. Algorithms for image enhancement, object detection, object tracking, object recognition and item re-identification are presented. The most common modalities utilized by surveillance systems are discussed, putting emphasis on video, in terms of available resolutions and new imaging approaches, like High Dynamic Range video. The most important features and analytics are presented, along with the most common approaches for image / video quality enhancement. Distributed computational infrastructures are discussed (Cloud, Fog and Edge Computing), describing the advantages and disadvantages of each approach. The most important deep learning algorithms are presented, along with the smart analytics that they utilize. Augmented reality and the role it can play to a surveillance system is reported, just before discussing the challenges and the future trends of surveillance.

Multiple Anomalous Activity Detection in Videos  

视频中的多重异常行为检测

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%.