Marci Meingast

CITRIC: A low-bandwidth wireless camera network platform

In this paper, we propose and demonstrate a novel wireless camera network system, called CITRIC. The core component of this system is a new hardware platform that integrates a camera, a frequency-scalable (up to 624 MHz) CPU, 16MB FLASH, and 64MB RAM onto a single device. The device then connects with a standard sensor network mote to form a camera mote. The design enables in-network processing of images to reduce communication requirements, which has traditionally been high in existing camera networks with centralized processing. We also propose a back-end client/server architecture to provide a user interface to the system and support further centralized processing for higher-level applications. Our camera mote enables a wider variety of distributed pattern recognition applications than traditional platforms because it provides more computing power and tighter integration of physical components while still consuming relatively little power. Furthermore, the mote easily integrates with existing low-bandwidth sensor networks because it can communicate over the IEEE 802.15.4 protocol with other sensor network platforms. We demonstrate our system on three applications: image compression, target tracking, and camera localization.

Security and Privacy Issues with Health Care Information Technology

The face of health care is changing as new technologies are being incorporated into the existing infrastructure. Electronic patient records and sensor networks for in-home patient monitoring are at the current forefront of new technologies. Paper-based patient records are being put in electronic format enabling patients to access their records via the Internet. Remote patient monitoring is becoming more feasible as specialized sensors can be placed inside homes. The combination of these technologies will improve the quality of health care by making it more personalized and reducing costs and medical errors. While there are benefits to technologies, associated privacy and security issues need to be analyzed to make these systems socially acceptable. In this paper we explore the privacy and security implications of these next-generation health care technologies. We describe existing methods for handling issues as well as discussing which issues need further consideration

Respectful cameras: detecting visual markers in real-time to address privacy concerns

To address privacy concerns with digital video surveillance cameras, we propose a practical, real-time approach that preserves the ability to observe actions while obscuring individual identities. In our proposed respectful cameras system, people who wish to remain anonymous agree to wear colored markers such as a hat or vest. The system automatically tracks these markers using statistical learning and classification to infer the location and size of each face and then inserts elliptical overlays. Our objective is to obscure the face of each individual wearing a marker, while minimizing the overlay area in order to maximize the remaining observable region of the scene. Our approach incorporates a visual color-tracker based on a 9 dimensional color-space by using a probabilistic AdaBoost classifier with axis-aligned hyperplanes as weak-learners. We then use particle filtering to incorporate interframe temporal information. We present experiments illustrating the performance of our system in both indoor and outdoor settings, where occlusions, multiple crossing targets, and lighting changes occur. Results suggest that the respectful camera system can reduce false negative rates to acceptable levels (under 2%).

Vision based terrain recovery for landing unmanned aerial vehicles

We propose a system for landing unmanned aerial vehicles (UAV), specifically an autonomous rotorcraft, in uncontrolled, arbitrary, terrains. We present plans for and progress on a vision-based system for the recovery of the geometry and material properties of local terrain from a mounted stereo rig for the purposes of finding an optimal landing site. A system is developed which integrates motion estimation from tracked features, and an algorithm for approximate estimation of a dense elevation map in a world coordinate system.

Transactional Confidentiality in Sensor Networks

In a sensor network environment, elements such as message rate, message size, mote frequency, and message routing can reveal transactional data - that is, information about the sensors deployed, frequency of events monitored, network topology, parties deploying the network, and location of subjects and objects moving through the networked space. Whereas the confidentiality of network communications content is secured through encryption and authentication techniques, the ability of network outsiders and insiders to observe transactional data can also compromise network confidentiality. Four types of transactional data are typically observable in sensor networks. Measures to limit the availability and utility of transactional data are essential to preserving confidentiality in sensor networks.

Automatic Camera Network Localization using Object Image Tracks

Camera networks are being used in more applications as different types of sensor networks are used to instrument large spaces. Here we show a method for localizing the cameras in a camera network to recover the orientation and position up to scale of each camera, even when cameras are wide-baseline or have different photometric properties. Using moving objects in the scene, we use an intra-camera step and an inter-camera step in order to localize. The intra-camera step compares frames from a single camera to build the tracks of the objects in the image plane of the camera. The inter-camera step uses these object image tracks from each camera as features for correspondence between cameras. We demonstrate this idea on both simulated and real data.

Distributed Reputation System for Tracking Applications in Sensor Networks

Ad-hoc sensor networks are becoming more common, yet security of these networks is still an issue, node misbehavior due to malicious attacks can impair the overall functioning of the system. Existing approaches mainly rely on cryptography to ensure data authentication and integrity. These approaches only address part of the problem of security in sensor networks. However, cryptography is not sufficient to prevent the attacks in which some of the nodes are overtaken and compromised by a malicious user. Recently, the use of reputation systems has shown positive results as a self-policing mechanism in ad-hoc networks. This scheme can aid in decreasing vulnerabilities which are not solved by cryptography, We look at how a distributed reputation scheme can benefit the object tracking application in sensor networks. Tracking multiple objects is one of the most important applications of the sensor network. In our setup, nodes detect misbehavior locally from observations, and assign a reputation to each of their neighbors. These reputations are used to weight node readings appropriately when performing object tracking. Over time, data from malicious nodes will not be included in the track formation process. We evaluate the reputation system experimentally and demonstrate how it improves object tracking in the presence of malicious nodes

Fusion-based localization for a Heterogeneous camera network

Heterogeneous sensor networks (HSNs) are becoming more commonly used for purposes such as monitoring and surveillance, as they offer richer sources of data for situational awareness. An important aspect of HSNs is localization. In this paper, we describe a novel method for localizing a network of cameras equipped with wireless radios. Our method fuses both the image data and radio interferometry data in order to determine the position of the sensors and the orientation of each camerapsilas field of view. While existing methods that rely solely on image data alone are often limited in that they can only recover position up to scale factors, by fusing the image data and radio interferometry data, we are able to recover the position and orientation with no scale factor ambiguity. In contrast, localization of sensor nodes using radio alone only recovers the position of the sensors and often relies on computationally expensive methods. The method discussed in this paper exploits both the image and radio data for a more computationally efficient process of localization. We discuss both a linear and nonlinear approach to fusing the data which depend on different constraints on the network. We demonstrate our approach on a real network of camera and radio nodes.

The Recursive Multi-Frame Planar Parallax Algorithm

This paper presents a method for obtaining accurate dense elevation and appearance models of terrain using a single camera on-board an aerial platform. Applications of this method include geographical information systems, robot path planning, immersion and visualization, and surveying for scientific purposes such as watershed analysis. When given geo-registered images, the method can compute terrain maps on-line in real time. This algorithm, called the recursive multi-frame planar parallax algorithm, is a recursive extension of Irani et al.s multi-frame planar parallax framework and in theory, with perfectly registered imagery, it will produce range data with error expected to increase between linearly and with the square root of the range, depending on image properties and whether other constants such as framerate and vehicle velocity are held constant. This is an improvement over stereo systems whose expected errors are proportional to the square of the range. We show experimental evidence on synthetic imagery and on a real video sequence taken in an experiment for autonomous helicopter landing.