Data Mining - Concepts and Techniques.

Allowing computation to be performed at the edge of a network, edge computing has been recognized as a promising approach to address some challenges in the cloud computing paradigm, particularly to the delay-sensitive and mission-critical applications like real-time surveillance. Prevalence of networked cameras and smart mobile devices enable video analytics at the network edge. However, human objects detection and tracking are still conducted at cloud centers, as real-time, online tracking is computationally expensive. In this paper, we investigated the feasibility of processing surveillance video streaming at the network edge for real-time, uninterrupted moving human objects tracking. Moving human detection based on Histogram of Oriented Gradients (HOG) and linear Support Vector Machine (SVM) is illustrated for features extraction, and an efficient multi-object tracking algorithm based on Kernelized Correlation Filters (KCF) is proposed. Implemented and tested on Raspberry Pi 3, our experimental results are very encouraging, which validated the feasibility of the proposed approach toward a real-time surveillance solution at the edge of networks.

Real-Time Human Objects Tracking for Smart Surveillance at the Edge

Thanks to rapid technological advances in the Internet of Things (IoT), a smart public safety (SPS) system has become feasible by integrating heterogeneous computing devices to collaboratively provide public protection services. While service-oriented architecture (SOA) has been adopted by IoT and cyber-physical systems (CPS), it is difficult for a monolithic architecture to provide scalable and extensible services for a distributed IoT based SPS system. Furthermore, traditional security solutions rely on a centralized authority, which can be a performance bottleneck or single point failure. Inspired by microservices architecture and blockchain technology, this paper proposes a BLockchain-ENabled Decentralized Microservices Architecture for Smart public safety (BlendMAS). Within a permissioned blockchain network, a microservices based security mechanism is introduced to secure data access control in an SPS system. The functionality of security services is decoupled into separate containerized microservices that are built using a smart contract and deployed on edge and fog computing nodes. An extensive experimental study verified that the proposed BlendMAS is able to offer a decentralized, scalable and secured data sharing and access control to distributed IoT based SPS system.

BlendMAS: A Blockchain-Enabled Decentralized Microservices Architecture for Smart Public Safety

Edge computing efficiently extends the realm of information technology beyond the boundary defined by cloud computing paradigm. Performing computation near the source and destination, edge computing is promising to address the challenges in many delay-sensitive applications, like real-time human surveillance. Leveraging the ubiquitously connected cameras and smart mobile devices, it enables video analytics at the edge. In recent years, many smart video surveillance approaches are proposed for object detection and tracking by using Artificial Intelligence (AI) and Machine Learning (ML) algorithms. This work explores the feasibility of two popular human-objects detection schemes, Harr-Cascade and HOG feature extraction and SVM classifier, at the edge and introduces a lightweight Convolutional Neural Network (L-CNN) leveraging the depthwise separable convolution for less computation, for human detection. Single Board computers (SBC) are used as edge devices for tests and algorithms are validated using real-world campus surveillance video streams and open data sets. The experimental results are promising that the final algorithm is able to track humans with a decent accuracy at a resource consumption affordable by edge devices in real-time manner.

Smart Surveillance as an Edge Network Service: From Harr-Cascade, SVM to a Lightweight CNN

Information from surveillance video is essential for situational awareness (SAW). Nowadays, a prohibitively large amount of surveillance data is being generated continuously by ubiquitously distributed video sensors. It is very challenging to immediately identify the objects of interest or zoom in suspicious actions from thousands of video frames. Making the big data indexable is critical to tackle this problem. It is ideal to generate pattern indexes in a real-time, on-site manner on the video streaming instead of depending on the batch processing at the cloud centers. The modern edge-fog-cloud computing paradigm allows implementation of time sensitive tasks at the edge of the network. The on-site edge devices collect the information sensed in format of frames and extracts useful features. The near-site fog nodes conduct the contextualization and classification of the features. The remote cloud center is in charge of more data intensive and computing intensive tasks. However, exchanging the index information among devices in different layers raises security concerns where an adversary can capture or tamper with features to mislead the surveillance system. In this paper, a blockchain enabled scheme is proposed to protect the index data through an encrypted secure channel between the edge and fog nodes. It reduces the chance of attacks on the small edge and fog devices. The feasibility of the proposal is validated through intensive experimental analysis.

Real-Time Index Authentication for Event-Oriented Surveillance Video Query using Blockchain

Recently, various conferences and journals have published articles related to Video Surveillance Systems, indicating researchers' attention. The goal of this review is to examine the latest works were published in journals, propose a new classification framework of video surveillance systems and investigate each aspect of this classification framework. This paper provides a comprehensive and systematic literature review of video surveillance systems from 2010-2011, extracted from six online digital libraries using article's title and keyword. The proposed classification framework is expanded on the basis of architecture of video surveillance systems, which is composed of six layers: Concept and Foundation Layer, Network Infrastructure Layer, Processing Layer, Communication Layer, Application Layer, and User Interaction Layer. This review shows, although many publication and research focus on real-time aspect of the challenge, only few researches have investigated the deployment of extracted and retrieved information for forensic video surveillance.

/pdf/systematic-review-and-classification-on-video-surveillance-4ulpohcjgd.pdf

Systematic Review and Classification on Video Surveillance Systems

The exponential growth in the number of surveillance videos makes the search and retrieval of their contents an extensive, time-consuming, and tedious task. Video abstraction is a general solution to alleviate this problem by generating a short and concise version of the original video. The existing abstraction approaches have commonly relied on global characteristics of visual content and neglected the local details of video frames. This paper presents an enhanced video abstraction approach called Density-based Surveillance video abstraction (DbSva) to generate a static short-length video. The novelty of DbSva is (a) to integrate the advantages of both the global and local features of video contents by fusion and (b) to employ the DENsity-based CLUstEring algorithm (DENCLUE) to significantly improve the quality of abstract videos. Utilizing fusion and the DENCLUE algorithm resulted in the extraction of more informative parts of the videos and increased the robustness of the proposed approach to handle large-scale and noisy videos with no further tuning of the input parameters. A number of qualitative and quantitative experiments support the effectiveness of the proposed approach in generating higher-quality abstract videos compared to the other approaches.

Video abstraction using density-based clustering algorithm

The manual search through the surveillance video archives for a specific object or event is very time-consuming and tedious task due to the large volume of video data captured by many installed surveillance cameras. Therefore, the solution to accelerate and facilitate this process is to design an automatic video surveillance with the efficient and effective video indexing, video data model, query formulation and language, as well as visualization interface. There are many challenges, for developing a powerful query processing module, formulating complex queries and selecting suitable similarity matching strategy to detect any abnormality based on semantic content of the video using various query types. This study presents a novel video surveillance indexing and retrieval framework to cope with the above challenges. The proposed framework consists of three main modules i.e., pre-processing, query processing and retrieval processing. Moreover, it supports an efficient search and actively refines the retrieval result by formulating various query types including: query-by-text, query-by-example and query-by-region.

A Framework for Automatic Video Surveillance Indexing and Retrieval

The goal of surveillance video abstraction is to generate a video abstract that includes important events and object by eliminating the redundant frames, lacking from activity in original video. Although many research and progresses have been done in video abstraction, the developed approaches either fail to accurately and effectively cover the overall visual content of video or they are computationally expensive in term of time or process. In this paper, firstly we critically review the applicable video abstraction techniques in surveillance domain based on our hierarchical classification, and then briefly introduce a new approach for generating a static surveillance video abstraction, which mitigate the drawbacks of reviewed approaches.

/pdf/a-study-on-surveillance-video-abstraction-techniques-4kn0ad51lw.pdf

A study on surveillance video abstraction techniques

The rapid growth of technological advances and availability of mobile devices has raised the opportunity to innovate feasible context-aware applications with the ability to access information anywhere and anytime. Therefore, this paper intends to review the recent developed mobile context-aware application. The reviewed articles are selected based on their application domains which cover the following six categories: smart space, healthcare, advertising, mobile guide, memory aid and disaster alerting applications. The selected applications are discussed based on their designed techniques, simulations and areas to show their impact on human computer interaction.

Fereshteh Falah Chamasemani

Papers

Systematic Review and Classification on Video Surveillance Systems

Video abstraction using density-based clustering algorithm

A Framework for Automatic Video Surveillance Indexing and Retrieval

A study on surveillance video abstraction techniques

Impact of mobile context-aware applications on human computer interaction