: Agenda: Welcome Remarks, Joint Science and Technology, Doing Business with USSOCOM, Reducing th... more : Agenda: Welcome Remarks, Joint Science and Technology, Doing Business with USSOCOM, Reducing the Threat of Nuclear and Radiological Terrorism, Avon M53 Protective Mask for USSOCOM, Chemical Homeland Security Suite (C-HoSS), Radiological Emergency Response, Use of Recombinant Butyrylcholinesterase in Responding to Chemical Weapon Attack, Reliable Discrimination of High Explosive/Chem/Bio/Artillery Using Acoustic IGS, Real-Time First Bite Detection, Polymer Technology for the Lock-Down/Removal of Radiological Contamination, Modeling Tool for Prediction and Mitigation of CBRNE Events, Terrorist Motivations to Employ CBRN Weapons, USAF Counter-Biological Warfare Effort, Keynote Presentation, Question and Answer Session, Responding to Multiple Ebola Attacks: The Need for Coordinated Preparedness, Capture, Contain, Treat and Dispose of Decontamination Runoff on Site, National Guard CBRN Response: Achieving Unity of Effort Between Local/State/Federal, CBRN Detectors for Early Warning of ...
2012 15th International Conference on Information Fusion, 2012
This paper proposes an approach to the fusion of multi-modal sensor data for the purpose of perso... more This paper proposes an approach to the fusion of multi-modal sensor data for the purpose of personnel intrusion detection. The focus is on using low cost non-imaging sensors for applications such as border crossings where issues of rapid deployment and power consumption are prevalent. The main challenge of fusing data from such sensors lies in the wide variation of granularity of classification that they may provide. While some sensors may provide detailed characteristics of the motion in a scene and therefore a very fine classification, others may only provide simple alerts and little detail. In order to fuse data from a wide range of sensors that are often designed for disparate applications, an approach based on the Dempster-Shafer theory of evidence is used. The implicit handling of uncertainty and ambiguous propositions leads to a convenient hierarchical approach that can represent data from numerous sensor modalities.
: Tracking moving objects, especially human objects in surveillance systems has attracted conside... more : Tracking moving objects, especially human objects in surveillance systems has attracted considerable research attention. This study proposes a novel joint Electro-Optical (EO) and Infrared (IR) cameras tracking approach by employing particle filter. A centroid-based detection technique is used to discover potentially moving objects and obtain the coordinate data. Once moving targets are detected, both EO and IR features are combined to extract object templates for sampling particles. Statistic information of a blob centered at current particle and likelihood of each pixels in terms of foreground, background and occlusion components are obtained, to determine and update importance of each particle and handle temporary occlusion. Hence, particles which can provide accurate prediction are assigned with higher weights. Simulations have been conducted to validate the proposed method.
In this paper several methods and models for improving small arms localization are investigated. ... more In this paper several methods and models for improving small arms localization are investigated. Each acoustic sensor is placed at a disparate location and it is assumed that each system may or may not return an estimated range and/or azimuth shooter. Various simple geometric based data fusion methods are proposed and their performance evaluated. Models of localization errors are also proposed and these models are used herein to develop a maximum likelihood approach to data fusion. The parameters of these statistical distributions are estimated from real world data. Comparing/contrasting the results of both methods side by side, it can be shown that while the maximum likelihood based approach performs the best, decent results can be achieved with the simpler geometric based approach.
Abstract Time synchronization has proven to be critical in sensor fusion applications where the t... more Abstract Time synchronization has proven to be critical in sensor fusion applications where the time of arrival is utilized as a decision variable. Herein, the application of pulse-coupled synchronization to an acoustic event detection system based on a wireless sensor network is presented. The aim of the system is to locate the source of acoustic events utilizing time of arrival measurements for different formations of the sensor network. A distributed localization algorithm is introduced that solves the problem locally using only a subset of the time of arrival measurements and then fuses the local guesses using averaging consensus techniques. It is shown that the pulse-coupled strategy provides the system with the proper level of synchronization needed to enable accurate localization, even when there exists drift between the internal clocks and the formation is not perfectly maintained. Moreover, the distributed nature of pulse-coupled synchronization allows coordinated synchronization and distributed localization over an infrastructure-free ad-hoc network.
Feature extraction methods based on the statistical analysis of the change in event pressure leve... more Feature extraction methods based on the statistical analysis of the change in event pressure levels over a period and the level of ambient pressure excitation facilitate the development of a robust classification algorithm. The features reliably discriminates mortar and artillery variants via acoustic signals produced during the launch events. Utilizing acoustic sensors to exploit the sound waveform generated from the
Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security and Homeland Defense V, 2006
Feature extraction methods based on the discrete wavelet transform and multiresolution analysis f... more Feature extraction methods based on the discrete wavelet transform and multiresolution analysis facilitate the development of a robust classification algorithm that reliably discriminates between launch and impact mortar events via acoustic signals produced during these events. Distinct characteristics arise within the different explosive events because impact events emphasize concussive and shrapnel effects, while launch events result from blasts that expel
Unmanned/Unattended Sensors and Sensor Networks VI, 2009
ABSTRACT Detection and tracking of a varying number of people is very essential in surveillance s... more ABSTRACT Detection and tracking of a varying number of people is very essential in surveillance sensor systems. In the real applications, due to various human appearance and confusors, as well as various environmental conditions, multiple targets detection and tracking become even more challenging. In this paper, we proposed a new framework integrating a Multiple-Stage Histogram of Oriented Gradients (HOG) based human detector and the Particle Filter Gaussian Process Dynamical Model (PFGPDM) for multiple targets detection and tracking. The Multiple-Stage HOG human detector takes advantage from both the HOG feature set and the human motion cues. The detector enables the framework detecting new targets entering the scene as well as providing potential hypotheses for particle sampling in the PFGPDM. After processing the detection results, the motion of each new target is calculated and projected to the low dimensional latent space of the GPDM to find the most similar trained motion trajectory. In addition, the particle propagation of existing targets integrates both the motion trajectory prediction in the latent space of GPDM and the hypotheses detected by the HOG human detector. Experimental tests are conducted on the IDIAP data set. The test results demonstrate that the proposed approach can robustly detect and track a varying number of targets with reasonable run-time overhead and performance.
Presented here is a novel clustering method for Hidden Markov Models (HMMs) and its application i... more Presented here is a novel clustering method for Hidden Markov Models (HMMs) and its application in acoustic scene analysis. In this method, HMMs are clustered based on a similarity measure for stochastic models defined as the generalized probability product kernel (GPPK), which can be efficiently evaluated according to a fast algorithm introduced by Chen and Man (2005) [1]. Acoustic signals
Unmanned/Unattended Sensors and Sensor Networks IV, 2007
Integrating a sensor suite with ability to discriminate potential Chemical/Biological (CB) events... more Integrating a sensor suite with ability to discriminate potential Chemical/Biological (CB) events from high-explosive (HE) events employing a standalone acoustic sensor with a Time Difference of Arrival (TDOA) algorithm we developed a cueing mechanism for more power intensive and range limited sensing techniques. Enabling the event detection algorithm to locate to a blast event using TDOA we then provide further information of the event as either Launch/Impact and if CB/HE. The added information is provided to a range limited chemical sensing system that exploits spectroscopy to determine the contents of the chemical event. The main innovation within this sensor suite is the system will provide this information on the move while the chemical sensor will have adequate time to determine the contents of the event from a safe stand-off distance. The CB/HE discrimination algorithm exploits acoustic sensors to provide early detection and identification of CB attacks. Distinct characteristics arise within the different airburst signatures because HE warheads emphasize concussive and shrapnel effects, while CB warheads are designed to disperse their contents over large areas, therefore employing a slower burning, less intense explosive to mix and spread their contents. Differences characterized by variations in the corresponding peak pressure and rise time of the blast, differences in the ratio of positive pressure amplitude to the negative amplitude, and variations in the overall duration of the resulting waveform. The discrete wavelet transform (DWT) is used to extract the predominant components of these characteristics from air burst signatures at ranges exceeding 3km. Highly reliable discrimination is achieved with a feed-forward neural network classifier trained on a feature space derived from the distribution of wavelet coefficients and higher frequency details found within different levels of the multiresolution decomposition. The development of an adaptive noise floor to provide early event detection assists in minimizing the false alarm rate and increasing the confidence whether the event is blast event or back ground noise. The integration of these algorithms with the TDOA algorithm provides a complex suite of algorithms that can give early warning detection and highly reliable look direction from a great stand-off distance for a moving vehicle to determine if a candidate blast event is CB and if CB what is the composition of the resulting cloud.
Feature extraction methods based on the discrete wavelet transform and multiresolution analysis f... more Feature extraction methods based on the discrete wavelet transform and multiresolution analysis facilitate the development of a robust classification algorithm that reliably discriminates mortar and artillery variants via acoustic signals produced during the launch/impact events. Utilizing acoustic sensors to exploit the sound waveform generated from the blast for the identification of mortar and artillery variants. Distinct characteristics arise within the
Unmanned/Unattended Sensors and Sensor Networks IV, 2007
Proposed are techniques toward using collaborative robots for infrastructure security application... more Proposed are techniques toward using collaborative robots for infrastructure security applications by utilizing them for mobile sensor suites. A vast number of critical facilities/technologies must be protected against unauthorized intruders. Employing a team of mobile robots working cooperatively can alleviate valuable human resources. Addressed are the technical challenges for multi-robot teams in security applications and the implementation of multi-robot motion
Unattended Ground, Sea, and Air Sensor Technologies and Applications X, 2008
In this paper we discuss a random walk model to characterize the pulse discharge battery process.... more In this paper we discuss a random walk model to characterize the pulse discharge battery process. Several theoretical results are derived including the mean and variance of an unattended battery-driven sensor lifetime. Some numerical results are presented.
An acoustic array, integrated with an algorithm to discriminate potential Launch (LA) or Impact (... more An acoustic array, integrated with an algorithm to discriminate potential Launch (LA) or Impact (IM) events, was augmented by employing the Launch Impact Discrimination (LID) algorithm for mortar events. We develop an added situational awareness capability to determine whether the localized event is a mortar launch or mortar impact at safe standoff distances. The algorithm utilizes a discrete wavelet transform
: Agenda: Welcome Remarks, Joint Science and Technology, Doing Business with USSOCOM, Reducing th... more : Agenda: Welcome Remarks, Joint Science and Technology, Doing Business with USSOCOM, Reducing the Threat of Nuclear and Radiological Terrorism, Avon M53 Protective Mask for USSOCOM, Chemical Homeland Security Suite (C-HoSS), Radiological Emergency Response, Use of Recombinant Butyrylcholinesterase in Responding to Chemical Weapon Attack, Reliable Discrimination of High Explosive/Chem/Bio/Artillery Using Acoustic IGS, Real-Time First Bite Detection, Polymer Technology for the Lock-Down/Removal of Radiological Contamination, Modeling Tool for Prediction and Mitigation of CBRNE Events, Terrorist Motivations to Employ CBRN Weapons, USAF Counter-Biological Warfare Effort, Keynote Presentation, Question and Answer Session, Responding to Multiple Ebola Attacks: The Need for Coordinated Preparedness, Capture, Contain, Treat and Dispose of Decontamination Runoff on Site, National Guard CBRN Response: Achieving Unity of Effort Between Local/State/Federal, CBRN Detectors for Early Warning of ...
2012 15th International Conference on Information Fusion, 2012
This paper proposes an approach to the fusion of multi-modal sensor data for the purpose of perso... more This paper proposes an approach to the fusion of multi-modal sensor data for the purpose of personnel intrusion detection. The focus is on using low cost non-imaging sensors for applications such as border crossings where issues of rapid deployment and power consumption are prevalent. The main challenge of fusing data from such sensors lies in the wide variation of granularity of classification that they may provide. While some sensors may provide detailed characteristics of the motion in a scene and therefore a very fine classification, others may only provide simple alerts and little detail. In order to fuse data from a wide range of sensors that are often designed for disparate applications, an approach based on the Dempster-Shafer theory of evidence is used. The implicit handling of uncertainty and ambiguous propositions leads to a convenient hierarchical approach that can represent data from numerous sensor modalities.
: Tracking moving objects, especially human objects in surveillance systems has attracted conside... more : Tracking moving objects, especially human objects in surveillance systems has attracted considerable research attention. This study proposes a novel joint Electro-Optical (EO) and Infrared (IR) cameras tracking approach by employing particle filter. A centroid-based detection technique is used to discover potentially moving objects and obtain the coordinate data. Once moving targets are detected, both EO and IR features are combined to extract object templates for sampling particles. Statistic information of a blob centered at current particle and likelihood of each pixels in terms of foreground, background and occlusion components are obtained, to determine and update importance of each particle and handle temporary occlusion. Hence, particles which can provide accurate prediction are assigned with higher weights. Simulations have been conducted to validate the proposed method.
In this paper several methods and models for improving small arms localization are investigated. ... more In this paper several methods and models for improving small arms localization are investigated. Each acoustic sensor is placed at a disparate location and it is assumed that each system may or may not return an estimated range and/or azimuth shooter. Various simple geometric based data fusion methods are proposed and their performance evaluated. Models of localization errors are also proposed and these models are used herein to develop a maximum likelihood approach to data fusion. The parameters of these statistical distributions are estimated from real world data. Comparing/contrasting the results of both methods side by side, it can be shown that while the maximum likelihood based approach performs the best, decent results can be achieved with the simpler geometric based approach.
Abstract Time synchronization has proven to be critical in sensor fusion applications where the t... more Abstract Time synchronization has proven to be critical in sensor fusion applications where the time of arrival is utilized as a decision variable. Herein, the application of pulse-coupled synchronization to an acoustic event detection system based on a wireless sensor network is presented. The aim of the system is to locate the source of acoustic events utilizing time of arrival measurements for different formations of the sensor network. A distributed localization algorithm is introduced that solves the problem locally using only a subset of the time of arrival measurements and then fuses the local guesses using averaging consensus techniques. It is shown that the pulse-coupled strategy provides the system with the proper level of synchronization needed to enable accurate localization, even when there exists drift between the internal clocks and the formation is not perfectly maintained. Moreover, the distributed nature of pulse-coupled synchronization allows coordinated synchronization and distributed localization over an infrastructure-free ad-hoc network.
Feature extraction methods based on the statistical analysis of the change in event pressure leve... more Feature extraction methods based on the statistical analysis of the change in event pressure levels over a period and the level of ambient pressure excitation facilitate the development of a robust classification algorithm. The features reliably discriminates mortar and artillery variants via acoustic signals produced during the launch events. Utilizing acoustic sensors to exploit the sound waveform generated from the
Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security and Homeland Defense V, 2006
Feature extraction methods based on the discrete wavelet transform and multiresolution analysis f... more Feature extraction methods based on the discrete wavelet transform and multiresolution analysis facilitate the development of a robust classification algorithm that reliably discriminates between launch and impact mortar events via acoustic signals produced during these events. Distinct characteristics arise within the different explosive events because impact events emphasize concussive and shrapnel effects, while launch events result from blasts that expel
Unmanned/Unattended Sensors and Sensor Networks VI, 2009
ABSTRACT Detection and tracking of a varying number of people is very essential in surveillance s... more ABSTRACT Detection and tracking of a varying number of people is very essential in surveillance sensor systems. In the real applications, due to various human appearance and confusors, as well as various environmental conditions, multiple targets detection and tracking become even more challenging. In this paper, we proposed a new framework integrating a Multiple-Stage Histogram of Oriented Gradients (HOG) based human detector and the Particle Filter Gaussian Process Dynamical Model (PFGPDM) for multiple targets detection and tracking. The Multiple-Stage HOG human detector takes advantage from both the HOG feature set and the human motion cues. The detector enables the framework detecting new targets entering the scene as well as providing potential hypotheses for particle sampling in the PFGPDM. After processing the detection results, the motion of each new target is calculated and projected to the low dimensional latent space of the GPDM to find the most similar trained motion trajectory. In addition, the particle propagation of existing targets integrates both the motion trajectory prediction in the latent space of GPDM and the hypotheses detected by the HOG human detector. Experimental tests are conducted on the IDIAP data set. The test results demonstrate that the proposed approach can robustly detect and track a varying number of targets with reasonable run-time overhead and performance.
Presented here is a novel clustering method for Hidden Markov Models (HMMs) and its application i... more Presented here is a novel clustering method for Hidden Markov Models (HMMs) and its application in acoustic scene analysis. In this method, HMMs are clustered based on a similarity measure for stochastic models defined as the generalized probability product kernel (GPPK), which can be efficiently evaluated according to a fast algorithm introduced by Chen and Man (2005) [1]. Acoustic signals
Unmanned/Unattended Sensors and Sensor Networks IV, 2007
Integrating a sensor suite with ability to discriminate potential Chemical/Biological (CB) events... more Integrating a sensor suite with ability to discriminate potential Chemical/Biological (CB) events from high-explosive (HE) events employing a standalone acoustic sensor with a Time Difference of Arrival (TDOA) algorithm we developed a cueing mechanism for more power intensive and range limited sensing techniques. Enabling the event detection algorithm to locate to a blast event using TDOA we then provide further information of the event as either Launch/Impact and if CB/HE. The added information is provided to a range limited chemical sensing system that exploits spectroscopy to determine the contents of the chemical event. The main innovation within this sensor suite is the system will provide this information on the move while the chemical sensor will have adequate time to determine the contents of the event from a safe stand-off distance. The CB/HE discrimination algorithm exploits acoustic sensors to provide early detection and identification of CB attacks. Distinct characteristics arise within the different airburst signatures because HE warheads emphasize concussive and shrapnel effects, while CB warheads are designed to disperse their contents over large areas, therefore employing a slower burning, less intense explosive to mix and spread their contents. Differences characterized by variations in the corresponding peak pressure and rise time of the blast, differences in the ratio of positive pressure amplitude to the negative amplitude, and variations in the overall duration of the resulting waveform. The discrete wavelet transform (DWT) is used to extract the predominant components of these characteristics from air burst signatures at ranges exceeding 3km. Highly reliable discrimination is achieved with a feed-forward neural network classifier trained on a feature space derived from the distribution of wavelet coefficients and higher frequency details found within different levels of the multiresolution decomposition. The development of an adaptive noise floor to provide early event detection assists in minimizing the false alarm rate and increasing the confidence whether the event is blast event or back ground noise. The integration of these algorithms with the TDOA algorithm provides a complex suite of algorithms that can give early warning detection and highly reliable look direction from a great stand-off distance for a moving vehicle to determine if a candidate blast event is CB and if CB what is the composition of the resulting cloud.
Feature extraction methods based on the discrete wavelet transform and multiresolution analysis f... more Feature extraction methods based on the discrete wavelet transform and multiresolution analysis facilitate the development of a robust classification algorithm that reliably discriminates mortar and artillery variants via acoustic signals produced during the launch/impact events. Utilizing acoustic sensors to exploit the sound waveform generated from the blast for the identification of mortar and artillery variants. Distinct characteristics arise within the
Unmanned/Unattended Sensors and Sensor Networks IV, 2007
Proposed are techniques toward using collaborative robots for infrastructure security application... more Proposed are techniques toward using collaborative robots for infrastructure security applications by utilizing them for mobile sensor suites. A vast number of critical facilities/technologies must be protected against unauthorized intruders. Employing a team of mobile robots working cooperatively can alleviate valuable human resources. Addressed are the technical challenges for multi-robot teams in security applications and the implementation of multi-robot motion
Unattended Ground, Sea, and Air Sensor Technologies and Applications X, 2008
In this paper we discuss a random walk model to characterize the pulse discharge battery process.... more In this paper we discuss a random walk model to characterize the pulse discharge battery process. Several theoretical results are derived including the mean and variance of an unattended battery-driven sensor lifetime. Some numerical results are presented.
An acoustic array, integrated with an algorithm to discriminate potential Launch (LA) or Impact (... more An acoustic array, integrated with an algorithm to discriminate potential Launch (LA) or Impact (IM) events, was augmented by employing the Launch Impact Discrimination (LID) algorithm for mortar events. We develop an added situational awareness capability to determine whether the localized event is a mortar launch or mortar impact at safe standoff distances. The algorithm utilizes a discrete wavelet transform
Uploads
Papers by Sachi Desai