In this paper, we consider the problem of finding correspondences between distributed cameras that have partially overlapping field of views. When multiple cameras with adaptable orientations and zooms are deployed, as in many wide area surveillance applications, identifying correspondence between different activities becomes a fundamental issue. We propose a correspondence method based upon activity features that, unlike photometric features, have certain geometry independence properties. The proposed method is robust to pose, illumination and geometric effects, unsupervised (does not require any calibration objects). In addition, these features are amenable to low communication bandwidth and distributed network applications. We present quantitative and qualitative results with synthetic and real life examples, and compare the proposed method with scale invariant feature transform (SIFT) based method. We show that our method significantly outperforms the SIFT method when cameras have significantly different orientations. We then describe extensions of our method in a number of directions including topology reconstruction, camera calibration, and distributed anomaly detection.

A crucial task for a network of cognitive radios is to detect occupied frequency bands, to protect transmissions of primary users, and to identify spectrum holes to maximize the utilization of wasted resources. This paper is motivated by the need to account for challenging constraints that naturally arise in such applications such as channel model uncertainties and demanding sensitivity constraints of the sensing devices. We propose false discovery rate (FDR) based cooperative strategies to sense the occupancy of the spectrum. The strategies we propose could either be used to maximize bandwidth utilization or to provide guarantees on incurred interference levels. The proposed strategies are robust to significant uncertainties such as lack of CSI, fading and shadowing effects. The key idea of the paper is that the twin objectives of bandwidth utilization and interference control can significantly benefit from group testing across all channels in contrast to conventionally employed channel-by-channel detection strategy. Furthermore, it is shown that the cooperative sensing strategy significantly reduces sensitivity requirements. We quantify the effect of channel occupancy rate on the required cooperation degree for achieving a guaranteed level of primary user protection.

We consider a change detection problem in video surveillance applications and propose busy-idle rates, meaningful and easy to compute features, to characterize the behavior profile of a given pixel. We describe the geometry independence property of these features, and use them to model the typical behavior that is observed in training sequences. Using a small number of samples for each pixel we generate behavior clusters, wherein pixels with similar behavior profiles fall into the same cluster. We then generate probabilistic models corresponding to behavior clusters, and use these models to perform abnormal behavior detection.

We consider a multi-target detection problem over a sensor network (SNET) with limited range sensors and communication constraints, which complements the decentralized detection problem where all sensors observe the same target. We consider sensing models where the signal power from targets undergoes a power-law decay. The task is to determine the locations of the targets while minimizing false alarms and communication between sensors. We extend the well-known FDR framework to solve the multi-target detection problem.

The design and deployment of sensor networks (SNET) for decision making pose fundamental challenges due to energy constraints and uncertain environments. In this paper we focus on one such problem where minimization of communication costs due to information exchange is required subject to end to end information quality constraints. Specifically, we develop solutions for detection of distributed events, sources, or abnormalities that are localized, i.e., only a small number of sensors in the vicinity of the phenomena are in the field of observation. This problem complements the standard decentralized detection problem, where noisy information about a global event is measured by the entire network. The global phenomena by itself can be one of several different discrete possibilities and researchers have investigated several architectures within this context. Our objective in this paper is to characterize the fundamental tradeoffs between global performance (false alarms and miss rate) and communication cost. We develop a framework to minimize the communication cost subject to worst-case misclassification constraints by making use of the false discovery rate (FDR) concept along with an optimal local measure transformation at each sensor node. The preliminary results show that the FDR concept applied in a sensor network context leads to significant reduction in the communication cost of the system.

Sensor networks (SNETs) for monitoring spatial phenomena has emerged as an area of significant practical interest. We focus on the important problem of detection of distributed events, sources, or abnormalities that are localized, i.e., only a small number of sensors in the vicinity of the phenomena are in the field of observation. This problem complements the standard decentralized detection problem, where noisy information about an event is measured by the entire network. For localized phenomena the main difficulty arises from the coupling of: a) noisy sensor observations that lead to local false positives/negatives; and b) limited energy, which constrains communication among sensor nodes. Together these difficulties call for reaching a decentralized statistical ordering based on limited collaboration. We are then led to the following fundamental problem: determine the most probable event locations while minimizing communication cost. Our objective in this paper is to characterize the fundamental trade offs between global performance (false alarms and miss rate) and communication cost. We develop a framework to minimize the communication cost subject to worst-case misclassification constraints by making use of the false discovery rate (FDR) concept along with an optimal local measure transformation at each sensor node. The preliminary results show that the FDR concept applied in a sensor networks context leads to significant reduction in the communication cost of the system. A very interesting implication of this work is that the detection performance of a wireless sensor network is comparable to that of a wired network of sensors.