John M. Irvine

Fusing face and ECG for personal identification

Single modality biometric identification systems exhibit performance that may not be adequate for many security applications. Face and fingerprint modalities dominate the biometric verification/identification field. However, both face and fingerprint can be compromised using counterfeit credentials. Previous research has demonstrated the use of the electrocardiogram (ECG) as a novel biometric. This paper explores the fusion of a traditional face recognition technique with ECG. System performance with multimodality fusion can be superior to reliance on a single biometric, but performance depends heavily on the fusion technique. In addition, a fusion-based system is more difficult to defeat, since an imposter must provide counterfeit credentials for both face and cardiovascular function.

A sequential procedure for individual identity verification using ECG

The electrocardiogram (ECG) is an emerging novel biometric for human identification. One challenge for the practical use of ECG as a biometric is minimizing the time needed to acquire user data. We present a methodology for identity verification that quantifies the minimum number of heartbeats required to authenticate an enrolled individual. The approach rests on the statistical theory of sequential procedures. The procedure extracts fiducial features from each heartbeat to compute the test statistics. Sampling of heartbeats continues until a decision is reached—either verifying that the acquired ECG matches the stored credentials of the individual or that the ECG clearly does not match the stored credentials for the declared identity. We present the mathematical formulation of the sequential procedure and illustrate the performance with measured data. The initial test was performed on a limited population, twenty-nine individuals. The sequential procedure arrives at the correct decision in fifteen heartbeats or fewer in all but one instance and in most cases the decision is reached with half as many heartbeats. Analysis of an additional 75 subjects measured under different conditions indicates similar performance. Issues of generalizing beyond the laboratory setting are discussed and several avenues for future investigation are identified.

Image quality and performance modeling for automated target detection

Several methods have been developed for quantifying the information potential of imagery exploited by a human observer. The National Imagery Interpretability Ratings Scale (NIIRS) has proven to be a useful standard for intelligence, surveillance, and reconnaissance (ISR) applications. A comparable standard for automated information extraction would be useful for a variety of applications, including tasking and collection management. This paper examines the applicability of NIIRS to automated exploitation methods. In particular, we compare image-based estimates of the NIIRS to observed performance of an automated target detection (ATD) algorithm. In addition, we examine other image metrics and their relationship to ATD performance. The findings indicate that NIIRS is not a good predictor of ATD performance, but methods that quantify the complexity of the clutter hold promise.

Robust human identification using ecg: eigenpulse revisited

Biometrics, such as fingerprint, iris scan, and face recognition, offer methods for identifying individuals based on a unique physiological measurement. Recent studies indicate that a persons electrocardiogram (ECG) may also provide a unique biometric signature. Several methods for processing ECG data have appeared in the literature and most approaches rest on an initial detection and segmentation of the heartbeats. Various sources of noise, such as sensor noise, poor sensor placement, or muscle movements, can degrade the ECG signal and introduce errors into the heartbeat segmentation. This paper presents a screening technique for assessing the quality of each segmented heartbeat. Using this technique, a higher quality signal can be extracted to support the identification task. We demonstrate the benefits of this quality screening using a principal component technique known as eigenpulse. The analysis demonstrated the improvement in performance attributable to the quality screening.

A model-based approach to human identification using ECG

Biometrics, such as fingerprint, iris scan, and face recognition, offer methods for identifying individuals based on a unique physiological measurement. Recent studies indicate that a persons electrocardiogram (ECG) may also provide a unique biometric signature. Current techniques for identification using ECG rely on empirical methods for extracting features from the ECG signal. This paper presents an alternative approach based on a time-domain model of the ECG trace. Because Auto-Regressive Integrated Moving Average (ARIMA) models form a rich class of descriptors for representing the structure of periodic time series data, they are well-suited to characterizing the ECG signal. We present a method for modeling the ECG, extracting features from the model representation, and identifying individuals using these features.

Real-time video image quality estimation supports enhanced tracker performance

Numerous methods exist for quantifying the information potential of imagery exploited by a human observer. The National Imagery Interpretability Ratings Scale (NIIRS) is a useful standard for intelligence, surveillance, and reconnaissance (ISR) applications. Extensions of this approach to motion imagery provide an understanding of the factors affecting interpretability of video data. More recent investigations have shown, however, that human observers and automated processing methods are sensitive to different aspects of image quality. This paper extends earlier research to present a model for quantifying the quality of motion imagery in the context of automated exploitation. In particular, we present a method for predicting the tracker performance and demonstrate the results on a range of video clips. Automated methods for assessing video quality can provide valuable feedback for collection management and guide the exploitation and analysis of the imagery.

Walk This Way: Improving Pedestrian Agent-Based Models through Scene Activity Analysis

Pedestrian movement is woven into the fabric of urban regions. With more people living in cities than ever before, there is an increased need to understand and model how pedestrians utilize and move through space for a variety of applications, ranging from urban planning and architecture to security. Pedestrian modeling has been traditionally faced with the challenge of collecting data to calibrate and validate such models of pedestrian movement. With the increased availability of mobility datasets from video surveillance and enhanced geolocation capabilities in consumer mobile devices we are now presented with the opportunity to change the way we build pedestrian models. Within this paper we explore the potential that such information offers for the improvement of agent-based pedestrian models. We introduce a Scene- and Activity-Aware Agent-Based Model (SA2-ABM), a method for harvesting scene activity information in the form of spatiotemporal trajectories, and incorporate this information into our models. In order to assess and evaluate the improvement offered by such information, we carry out a range of experiments using real-world datasets. We demonstrate that the use of real scene information allows us to better inform our model and enhance its predictive capabilities.

Predicting the effectiveness of SAR imagery for target detection

We present an image quality metric and prediction model for SAR imagery that addresses automated information extraction and exploitation by imagery analysts. This effort drarws on our teams direct experience with the development of the Radar National Imagery Interpretability Ratings Scale (Radar NIIRS), the General Image Quality Equations (GIQE) for other modalities, and extensive expertise in ATR characterization and performance modeling. In this study, we produced two separate GIQEs: one to predict Radar NIIRS and one to predict Automated Target Detection (ATD) performance. The Radar NIIRS GIQE is most significantly influenced by resolution, depression angle, and depression angle squared. The inclusion of several image metrics was shown to improve performance. Our development of an ATD GIQE showed that resolution and clutter characteristics (e.g., clear, forested, urban) are the dominant explanatory variables. As was the case with NIIRS GIQE, inclusion of image metrics again increased performance, but the improvement was significantly more pronounced. Analysis also showed that a strong relationship exists between ATD and Radar NIIRS, as indicated by a correlation coefficient of 0.69; however, this correlation is not strong enough that we would recommend a single GIQE be used for both ATD and NIIRS prediction.

Video image quality analysis for enhancing tracker performance

Object tracking in video data is fundamental to many practical applications, including gesture recognition, activity analysis, physical security, and surveillance. A fundamental assumption is that the quality of the video stream is adequate to support the analysis. In practice, however, the video quality can vary widely due to lighting and weather, camera placement, and data compression. These factors affect the performance of object tracking algorithms. We present a method for automated analysis of the video quality which can be used to adjust the object tracker appropriately. This paper extends earlier research, presenting a model for quantifying the quality of motion imagery in the context of automated exploitation. We present a method for predicting the tracker performance and demonstrate the results on a range of video clips. The model rests on a suite of image metrics computed in real-time from the video. We will describe the metrics and the formulation of the quality estimation model. Results from a recent experiment will quantify the empirical performance of the model. We conclude with a discussion of methods for enhancing tracker performance based on the real-time video quality analysis.

Deriving economic and social indicators from imagery

The application of remote sensing to the social sciences is an emerging research area. Peoples behavior and values shape the environment in which they live. Similarly, values and behaviors are influenced by the environment. This study explores the relationship between features observable in overhead imagery and direct measurements of attitudes obtained through surveys. We focus on three topic areas: (1) Income and Economic Development (2) Centrality and Decision Authority (3) Social Capital Using commercial satellite imagery data from rural Afghanistan, we present an exploration of the direct and indirect indicators derived from the imagery. We demonstrate a methodology for extracting relevant measures from the imagery, using a combination of human-guided and automated methods. These imagery observables indicate characteristics of the villages which will be compared to survey data in future modeling work. Preliminary survey modeling, based on data from sub-Saharan Africa, suggests that modeling of the Afghan data will also demonstrate a relationship between remote sensing data and survey-based measures of economic and social phenomena. We conclude with a discussion of the next steps, which include extensions to new regions of the world.