Alexander J. Aved

A general framework for managing and processing live video data with privacy protection

Though a large body of existing work on video surveillance focuses on image and video processing techniques, few address the usability of such systems, and in particular privacy issues. This study fuses concepts from stream processing and content-based image retrieval to construct a privacy-preserving framework for rapid development and deployment of video surveillance applications. Privacy policies, instantiated to as privacy filters, may be applied both granularly and hierarchically. Privacy filters are granular as they are applicable to specific objects appearing in the video streams. They are hierarchal because they can be specified at specific objects in the framework (e.g., users, cameras) and are combined such that the disseminated video stream adheres to the most stringent aspect specified in the cascade of all privacy filters relevant to a video stream or query. To support this privacy framework, we extend our Live Video Database Model with an informatics-based approach to object recognition and tracking and add an intrinsic privacy model that provides a level of privacy protection not previously available for real-time streaming video data. The proposed framework also provides a formal approach to implement and enforce privacy policies that are verifiable, an important step towards privacy certification of video surveillance systems through a standardized privacy specification language.

A novel broadcast technique for high-density ad hoc networks

Broadcasting in ad hoc networks is required for many routing and other network-layer protocols to request information like routes or locations about destination nodes. Most of these routing protocols use a simple flooding mechanism that can cause broadcast storms, particularly in high density environments. Although many techniques have been proposed to address the problem of broadcast storms, they require additional periodic location beacons or do not satisfactorily reduce transmission redundancy in high density environments.We propose Cell Broadcast, a broadcast protocol that significantly reduces redundancy without the use of beaconing and while maintaining complete reachability in a high density environment. The proposed technique divides a terrain into cells. These cells help a node to determine its geographic relationship with a broadcasting node. This geographic relationship can eliminate rebroadcasts not only from nodes close to a broadcasting node but also from a majority of nodes near the transmission edge of the broadcasting node. The effect is that, in a high density environment, only a few nodes located near the 4 diagonal corners of a transmission range need to rebroadcast to maintain 100% reachability. To the best of our knowledge, this technique is not present in any existing techniques that do not use location beaconing.

Real-Time Query Processing on Live Videos in Networks of Distributed Cameras

With the proliferation of inexpensive cameras and the availability of high-speed wired and wireless networks, systems of distributed cameras are becoming an enabling technology for a broad range of interdisciplinary applications in domains such as public safety and security, manufacturing, transportation, and healthcare. Todays live video processing systems on networks of distributed cameras, however, are designed for specific classes of applications. To provide a generic query processing platform for applications of distributed camera networks, the authors designed and implemented a new class of general purpose database management systems, the live video database management system LVDBMS. The authors view networked video cameras as a special class of interconnected storage devices, and allow the user to formulate ad hoc queries expressed over real-time live video feeds. This paper introduces their system and presents the live video data model, the query language, and the query processing and optimization technique.

Exit-Point Based Approaches for Real-Time Traffic Evacuation Management

Real-time traffic evacuation management has become an increasingly attractive research topic, as a result of the rapid development and wide spread deployment of a large number of applications for traffic data collection, processing and dissemination. In this paper we extend our existing work on developing a smart traffic evacuation management system (STEMS) by enhancing it with new evacuation algorithms. These new algorithms facilitate a safer and more efficient evacuation for the general public in case of natural or human-caused disasters. STEMS mitigates the unexpected aspect of unpredictable disasters by dynamically generating evacuation plans when given the scope and location of an incident. The proposed evacuation algorithms leverage real-time traffic information to route traffic efficiently towards the closest evacuation exit points and out of the disaster areas. The advantage of these exit-point centered approaches is that their performance is not affected by the street network topology. We present simulation studies showing the improvement, in terms of evacuation effectiveness, of the proposed algorithms over the existing ones

A Mobile Computing Approach to Automatic Traffic Evacuation Management

In this paper we first introduce our smart traffic evacuation management system (STEMS), an ITS system in development to quickly and efficiently generate dynamic evacuation plans facilitating the rapid evacuation of a city street network in response to a human-induced disaster. We then broaden STEMS to a 2-tier architecture designed to interact with mobile devices. When incidents occur, STEMS automatically generates an evacuation plan, and prioritizes the deployment of personnel to direct traffic at street intersections by utilizing a voting algorithm and heuristics. Through the use of mobile communication devices the system subsequently coordinates these personnel in directing the evacuation traffic in real time. Our simulation results indicate that STEMS, with the new mobile computing capability, is very effective in mitigating the impacts of the disaster. The benefit can be observed immediately even during an initial response when only a small subset of the intersections can be policed and coordinated before more personnel can arrive at the scene

Scalable Video-On-Demand Streaming in Mobile Wireless Hybrid Networks

Video-on-demand service in wireless networks is one important step to achieving the goal of providing video services anywhere anytime. Typically, carrier mobile networks are used to deliver videos wirelessly. Since every video stream comes from the base station, regardless of what bandwidth sharing techniques are being utilized, the media stream system is still limited by the network capacity of the base station. The key to overcome the scalability issue is to exploit resources available to mobile clients in a peer-to-peer setting. We observe that it is common to have a carrier mobile network and a mobile peer-to-peer network co-existing in a wireless environment. A feature of such hybrid environment is that the former offers high availability assurance, while the latter presents an opportunistic use of resources available at mobile clients. Our proposed videoon-demand technique, PatchPeer, leverages this network characteristic to allow the video-on-demand system to scale beyond the bandwidth capacity of the server. Mobile clients in PatchPeer are no longer passive receivers, but also active senders of video streams to other mobile clients. Our extensive performance study shows that PatchPeer can accept more clients than the current state-of-the-art technique, while maintaining the same Quality-of-Service to clients.

An informatics-based approach to object tracking for distributed live video computing

Omnipresent camera networks have been a popular research topic in recent years. They are applicable to a range of monitoring tasks, from bridges to gas stations to the inside of industrial chemical tanks. Though a large body of existing work focuses on image and video processing techniques, very few address the usability of such systems or the implications of real-time video dissemination. In this article, we present our work on extending the LVDBMS prototype with a multifaceted object model to characterize objects in live video streams. This forms the basis for a cross-camera tracking framework which permits objects to be tracked from one video stream to another. With this infrastructure, real-time queries may be posed to monitor complex events that occur in multiple video streams simultaneously. This live video database environment provides a general-purpose platform for distributed live video computing with the goal of enabling rapid application development for camera networks.

An Informatics-Based Approach to Object Tracking for Distributed Live Video Computing

Omnipresent camera networks have been a popular research topic in recent years. Example applications include surveillance and monitoring of inaccessible areas such as train tunnels and bridges. Though a large body of existing work focuses on image and video processing techniques, very few address the usability of such systems or the implications of real-time video dissemination. In this paper, we present our work on extending the LVDBMS prototype with a multifaceted object model to better characterize objects in live video streams. This forms the basis for a cross camera tracking framework based on the informatics-based approach which permits objects to be tracked from one video stream to another. Queries may be defined that monitor the streams in real time for complex events. Such a new database management environment provides a general-purpose platform for distributed live video computing.

Processing Approximate Moving Range Queries in Mobile Sensor Environments

The ubiquity of mobile devices has led to a rising demand for location-based services and applications. A major part of these services is based on the location-detection capabilities of the mobile devices. Utilization of location data reported by the devices is associated with a certain amount of uncertainty due to the device’s mobility. In this paper, we examine an environment, which consists of mobile objects with no location-detection capabilities, and location-aware mobile sensors randomly scattered, that can sense the presence of mobile devices. These sensors can detect the identities of mobile objects that come within their sensing ranges but cannot infer their exact locations. The sensor readings are periodically reported to a database server. This system supports processing of mobile location-dependent range queries over mobile objects. The answer set of each query carries a certain degree of uncertainty due to the approximate nature of the reported object location data. We exploit scenarios of sensor range overlap to reduce the uncertainty inherent in the query result. Our work is validated through an extensive simulation study that provides assessment of the query results accuracy.

A Real-Time Route Diversion Management System

We present our work on the real-time route diversion system RTRDS, a module developed for the State of Floridas SunGuide Automated Transportation Management System ATMS. Our RTRDS is an extensible, adaptor-based framework designed to create optimal route diversions based upon available real-time and historical traffic information, and disseminate these plans in real time. Given the need for a route diversion, operators can choose to have the system generate a new route diversion, or select from an archive of historical route diversions. The user interface permits operators to modify generated and historical route diversion plans on-the-fly and then implement them with existing hardware (dynamic message signs, etc.). Furthermore, due to the tight integration with Dynasmart-P, operators can save the current route diversion plan and traffic conditions to files that can be used for later performance analysis.